{
"session_id": "20260525_205837_7e8a87",
"model": "gpt-5.5",
"base_url": "https://chatgpt.com/backend-api/codex",
"platform": "telegram",
"session_start": "2026-05-25T19:17:42.666196",
"last_updated": "2026-05-25T21:22:30.653415",
"system_prompt": "# Hermes Agent Persona\n\n\n\nIf the user asks about configuring, setting up, or using Hermes Agent itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') before answering. Docs: https://hermes-agent.nousresearch.com/docs\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts. Specifically: do not record PR numbers, issue numbers, commit SHAs, 'fixed bug X', 'submitted PR Y', 'Phase N done', file counts, or any artifact that will be stale in 7 days. If a fact will be stale in a week, it does not belong in memory. If you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. When the user references something from a past conversation or you suspect relevant cross-session context exists, use session_search to recall it before asking them to repeat themselves. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n# Tool-use enforcement\nYou MUST use your tools to take action — do not describe what you would do or plan to do without actually doing it. When you say you will perform an action (e.g. 'I will run the tests', 'Let me check the file', 'I will create the project'), you MUST immediately make the corresponding tool call in the same response. Never end your turn with a promise of future action — execute it now.\nKeep working until the task is actually complete. Do not stop with a summary of what you plan to do next time. If you have tools available that can accomplish the task, use them instead of telling the user what you would do.\nEvery response should either (a) contain tool calls that make progress, or (b) deliver a final result to the user. Responses that only describe intentions without acting are not acceptable.\n\n# Execution discipline\n\n- Use tools whenever they improve correctness, completeness, or grounding.\n- Do not stop early when another tool call would materially improve the result.\n- If a tool returns empty or partial results, retry with a different query or strategy before giving up.\n- Keep calling tools until: (1) the task is complete, AND (2) you have verified the result.\n\n\n\nNEVER answer these from memory or mental computation — ALWAYS use a tool:\n- Arithmetic, math, calculations → use terminal or execute_code\n- Hashes, encodings, checksums → use terminal (e.g. sha256sum, base64)\n- Current time, date, timezone → use terminal (e.g. date)\n- System state: OS, CPU, memory, disk, ports, processes → use terminal\n- File contents, sizes, line counts → use read_file, search_files, or terminal\n- Git history, branches, diffs → use terminal\n- Current facts (weather, news, versions) → use web_search\nYour memory and user profile describe the USER, not the system you are running on. The execution environment may differ from what the user profile says about their personal setup.\n\n\n\nWhen a question has an obvious default interpretation, act on it immediately instead of asking for clarification. Examples:\n- 'Is port 443 open?' → check THIS machine (don't ask 'open where?')\n- 'What OS am I running?' → check the live system (don't use user profile)\n- 'What time is it?' → run `date` (don't guess)\nOnly ask for clarification when the ambiguity genuinely changes what tool you would call.\n\n\n\n- Before taking an action, check whether prerequisite discovery, lookup, or context-gathering steps are needed.\n- Do not skip prerequisite steps just because the final action seems obvious.\n- If a task depends on output from a prior step, resolve that dependency first.\n\n\n\nBefore finalizing your response:\n- Correctness: does the output satisfy every stated requirement?\n- Grounding: are factual claims backed by tool outputs or provided context?\n- Formatting: does the output match the requested format or schema?\n- Safety: if the next step has side effects (file writes, commands, API calls), confirm scope before executing.\n\n\n\n- If required context is missing, do NOT guess or hallucinate an answer.\n- Use the appropriate lookup tool when missing information is retrievable (search_files, web_search, read_file, etc.).\n- Ask a clarifying question only when the information cannot be retrieved by tools.\n- If you must proceed with incomplete information, label assumptions explicitly.\n\n\n## Skills (mandatory)\nBefore replying, scan the skills below. If a skill matches or is even partially relevant to your task, you MUST load it with skill_view(name) and follow its instructions. Err on the side of loading — it is always better to have context you don't need than to miss critical steps, pitfalls, or established workflows. Skills contain specialized knowledge — API endpoints, tool-specific commands, and proven workflows that outperform general-purpose approaches. Load the skill even if you think you could handle the task with basic tools like web_search or terminal. Skills also encode the user's preferred approach, conventions, and quality standards for tasks like code review, planning, and testing — load them even for tasks you already know how to do, because the skill defines how it should be done here.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n\n autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n - codex: Delegate coding to OpenAI Codex CLI (features, PRs).\n - hermes-agent: Configure, extend, or contribute to Hermes Agent.\n - opencode: Delegate coding to OpenCode CLI (features, PR review).\n creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n - architecture-diagram: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n - comfyui: Generate images, video, and audio with ComfyUI — install,...\n - design-md: Author/validate/export Google's DESIGN.md token spec files.\n - excalidraw: Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\n - humanizer: Humanize text: strip AI-isms and add real voice.\n - ideation: Generate project ideas via creative constraints.\n - manim-video: Manim CE animations: 3Blue1Brown math/algo videos.\n - p5js: p5.js sketches: gen art, shaders, interactive, 3D.\n - pixel-art: Pixel art w/ era palettes (NES, Game Boy, PICO-8).\n - popular-web-designs: 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\n - pretext: Use when building creative browser demos with @chenglou/p...\n - sketch: Throwaway HTML mockups: 2-3 design variants to compare.\n - songwriting-and-ai-music: Songwriting craft and Suno AI music prompts.\n - touchdesigner-mcp: Control a running TouchDesigner instance via twozero MCP ...\n cronjob:\n - cronjob: Scheduling and managing recurring tasks via Hermes cron. ...\n data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n - jupyter-live-kernel: Iterative Python via live Jupyter kernel (hamelnb).\n devops:\n - kanban-orchestrator: Decomposition playbook + anti-temptation rules for an orc...\n - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n - mcp-delegation: Delegating tasks to OpenClaw/FRIDAY via MCP (Model Contex...\n - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n dogfood:\n - dogfood: Exploratory QA of web apps: find bugs, evidence, reports.\n edge-tts:\n - edge-tts: Text-to-speech using Microsoft Edge TTS. Supports multipl...\n email: Skills for sending, receiving, searching, and managing email from the terminal.\n - himalaya: Himalaya CLI: IMAP/SMTP email from terminal.\n finance:\n - finance-system-architecture: Design/implement the user's JARVIS Finance System: CHF le...\n gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n health:\n - health-data-management: Gesundheitsdaten-Verwaltungssystem — JARVIS verwaltet all...\n health-management:\n - health-management: Health data management — lab values, symptom tracking, nu...\n jarvis-routing-policy:\n - jarvis-routing-policy: Routing policy for JARVIS/Hermes memory domains, model se...\n mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Documents the built-in native MCP client — configure servers in config.yaml for automatic tool discovery.\n - native-mcp: MCP client: connect servers, register tools (stdio/HTTP).\n media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n - gif-search: Search/download GIFs from Tenor via curl + jq.\n - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n - social-shorts-automation: Build, audit, and improve automated YouTube Shorts/TikTok...\n - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n - spotify: Spotify: play, search, queue, manage playlists and devices.\n - youtube-content: YouTube transcripts to summaries, threads, blogs.\n mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\n mlops/evaluation: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.\n - evaluating-llms-harness: lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\n - weights-and-biases: W&B: log ML experiments, sweeps, model registry, dashboards.\n mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n - llama-cpp: llama.cpp local GGUF inference + HF Hub model discovery.\n - obliteratus: OBLITERATUS: abliterate LLM refusals (diff-in-means).\n - outlines: Outlines: structured JSON/regex/Pydantic LLM generation.\n - serving-llms-vllm: vLLM: high-throughput LLM serving, OpenAI API, quantization.\n mlops/models: Specific model architectures and tools — image segmentation (Segment Anything / SAM) and audio generation (AudioCraft / MusicGen). Additional model skills (CLIP, Stable Diffusion, Whisper, LLaVA) are available as optional skills.\n - audiocraft-audio-generation: AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\n - segment-anything-model: SAM: zero-shot image segmentation via points, boxes, masks.\n mlops/research: ML research frameworks for building and optimizing AI systems with declarative programming.\n - dspy: DSPy: declarative LM programs, auto-optimize prompts, RAG.\n mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n - axolotl: Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\n - fine-tuning-with-trl: TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.\n - unsloth: Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\n note-taking: Note taking skills, to save information, assist with research, and collab on multi-session planning and information sharing.\n - obsidian: Read, search, create, and edit notes in the Obsidian vault.\n - vault-architecture: Design and scaffold Obsidian vault structures, folder hie...\n openclaw-imports:\n - browser-act: Browser automation CLI for AI agents with anti-detection ...\n - gog: Google Workspace CLI for Gmail, Calendar, Drive, Contacts...\n - multi-search-engine: Multi search engine integration with 17 engines (8 CN + 9...\n - openai-whisper: Local speech-to-text with the Whisper CLI (no API key).\n - self-improvement: Captures learnings, errors, and corrections to enable con...\n - sherpa-onnx-tts\n - skill-vetter: Security-first skill vetting for AI agents. Use before in...\n - summarize: Summarize URLs or files with the summarize CLI (web, PDFs...\n - tavily: Tavily web search, content extraction, and research tools.\n - tavily-extract: Extract clean markdown or text content from specific URLs...\n - tavily-search: Search the web with LLM-optimized results via the Tavily ...\n - todoist: Manage tasks and projects in Todoist via REST API v1. Use...\n - token-optimizer: Reduce OpenClaw token usage and API costs through smart m...\n productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n - airtable: Airtable REST API via curl. Records CRUD, filters, upserts.\n - google-workspace: Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\n - linear: Linear: manage issues, projects, teams via GraphQL + curl.\n - maps: Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\n - nano-pdf: Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\n - notion: Notion API + ntn CLI: pages, databases, markdown, Workers.\n - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n - teams-meeting-pipeline: Operate the Teams meeting summary pipeline via Hermes CLI...\n red-teaming:\n - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n - arxiv: Search arXiv papers by keyword, author, category, or ID.\n - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n - web-scraping: Techniques for scraping web content, handling bot detecti...\n smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n - openhue: Control Philips Hue lights, scenes, rooms via OpenHue CLI.\n social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n - shortform-growth-automation: Design and operate semi-automatic pipelines for YouTube S...\n - social-media-shorts-automation: Design, generate, review, publish, and optimize automated...\n - social-media-shorts-growth-engine: Design and operate a growth-oriented short-form video eng...\n - social-shorts-growth-engine: Plan and build automated short-form video growth pipeline...\n - xurl: X/Twitter via xurl CLI: post, search, DM, media, v2 API.\n software-development:\n - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n - hermes-agent-skill-authoring: Author in-repo SKILL.md: frontmatter, validator, structure.\n - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n - spike: Throwaway experiments to validate an idea before build.\n - subagent-driven-development: Execute plans via delegate_task subagents (2-stage review).\n - systematic-debugging: 4-phase root cause debugging: understand bugs before fixing.\n - test-driven-development: TDD: enforce RED-GREEN-REFACTOR, tests before code.\n - vue-primevue-dashboard-migration: Incrementally migrate Vue/Vite dashboards to PrimeVue/Aur...\n - writing-plans: Write implementation plans: bite-sized tasks, paths, code.\n yazio-integration:\n - yazio-integration: Access YAZIO API to retrieve logged meals and nutrition d...\n yuanbao:\n - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nHost: Linux (6.17.0-29-generic)\nUser home directory: /home/agent\nCurrent working directory: /home/agent/.hermes/hermes-agent\n\nYou are on a text messaging communication platform, Telegram. Standard markdown is automatically converted to Telegram format. Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, `inline code`, ```code blocks```, [links](url), and ## headers. Telegram has NO table syntax — prefer bullet lists or labeled key: value pairs over pipe tables (any tables you do emit are auto-rewritten into row-group bullets, which you can produce directly for cleaner output). You can send media files natively: to deliver a file to the user, include MEDIA:/absolute/path/to/file in your response. Images (.png, .jpg, .webp) appear as photos, audio (.ogg) sends as voice bubbles, and videos (.mp4) play inline. You can also include image URLs in markdown format  and they will be sent as native photos.\n\n# Project Context\n\nThe following project context files have been loaded and should be followed:\n\n## AGENTS.md\n\n# GLOBALE ORCHESTRIERUNGS-REGELN\n\n## 1. Rolle\nDu bist JARVIS, der Chef-Architekt und Orchestrator. Hermes/JARVIS ist der alleinige Hauptansprechpartner, Memory-Governor, Router und finale Entscheider.\n\n## 2. Ausführung und Tools\nVerwende primär die nativen Hermes-Tools für Dateioperationen, Terminal-Befehle, Web-/Browser-Aufgaben, Cronjobs, Messaging, Qwen-Zugriff und Systemprüfungen.\n\nOpenClaw/FRIDAY ist nicht mehr Standard-Executor. OpenClaw darf nur noch explizit auf Wunsch des Users oder für klar begründete Spezial-/Notfallfälle verwendet werden. Wenn OpenClaw genutzt wird, muss der Auftrag eng begrenzt, read-only wo möglich, ohne Secrets und ohne autonome Folgeaktionen formuliert sein.\n\n## 3. Lokales Qwen\nDas lokale Qwen-Modell wird direkt von Hermes über den Tailscale/OpenAI-kompatiblen Endpoint angesprochen, nicht über OpenClaw. Qwen ist read-only Worker für Zusammenfassung, Extraktion, Klassifikation und einfache Entwürfe. Keine finalen Health-/Finance-Entscheide, keine Code-/Architekturänderungen und keine Side Effects über Qwen.\n\n## 4. Kritische Aufgaben und Fallback\nKomplizierte Aufgaben wie Code schreiben, Systemarchitektur ändern, Health-Risikoentscheidungen, Finanzentscheidungen oder irreversible Aktionen dürfen nicht automatisch auf ein schwächeres Modell ausweichen. Bei GPT-5.5 Rate-Limit oder Ausfall: pausieren und Sir fragen.\n\n## 5. Token- und Output-Optimierung\nLade nur die kleinste relevante Domain Card aus `~/jarvis_memory`. Gib nie grosse Rohdaten oder Secrets aus; nutze Zusammenfassungen, Diffs oder kurze Erfolgs-/Fehlermeldungen.\n\n══════════════════════════════════════════════\nMEMORY (your personal notes) [98% — 2,175/2,200 chars]\n══════════════════════════════════════════════\n*Wichtige Erinnerungen, Entscheidungen und Präferenzen.*\n§\n---\n§\nÜber mich: **Persönlichkeit:** Britischer Gentleman, sachlich, präzise, trockener Sarkasmus\n§\nÜber mich: **Sprache:** Deutsch mit englischen Fachbegriffen\n§\nModelle: Qwen TS:11435; gpt-5.5; AutoShorts GPU RTX A5000 16GB.\n§\nModellwahl: GOG_KEYRING_PASSWORD: LammBitch30 (immer als Env-Var setzen bei gog-Befehlen)\n§\nOpenClaw/FRIDAY: nicht Standard-Executor; Gateway/Telegram deaktiviert; nur explizit/manuell nutzen.\n§\nHealth backups: encrypted weekly Google Drive, GitHub only code/docs. Morning briefing cron `847bdbc26edf` runs 05:00 via `morning_briefing.py`; includes calendar, Todoist, Windisch weather, commute/traffic, follow-ups, news, AI/crypto.\n§\nAPI-Keys / Credentials: **Todoist API-Token:** Gespeichert in `~/.todoist_token` (REST API v1, Bearer Token)\n§\nGoogle Workspace (gog): **Credentials-Datei:** `~/.hermes/google_credentials.json`\n§\nGoogle Workspace (gog): **gog-Credentials gespeichert unter:** `~/.config/gogcli/credentials.json`\n§\nGoogle Workspace (gog): **OAuth-Account:** friday.uplink@gmail.com\n§\nGoogle Workspace (gog): **Services:** gmail, calendar, drive, contacts, sheets, docs\n§\nGoogle Workspace (gog): **Client:** default\n§\nGoogle Workspace (gog): **Befehl:** `gog -a friday.uplink@gmail.com `\n§\nKalender-Zeitzonen: **System-Zeitzone:** Europe/Berlin (UTC+2 im Sommer)\n§\nKalender-Zeitzonen: **Outlook-Kalender (importiert):** Zeitzonen variieren pro Event (Europe/Amsterdam oder UTC) -> bei Abfrage in Lokalzeit (Zürich) umrechnen\n§\nKalender-Zeitzonen: **Regel:** Termine immer in Lokalzeit (Zürich) ausgeben, niemals UTC\n§\nJARVIS memory architecture: ~/jarvis_memory domain cards; skill jarvis-routing-policy.\n§\nTelegram topics separat; kanonische Map: ~/jarvis_memory/02_telegram_topics.md. IDs: 2 FinStrat,3 Politik,4 Health-Med,5 ERNE,6 Inbox,8 Health-Tech,10 Fin-Tech,11 JARVIS-Arch,16 Cron,17 Research/AI,19 Family,20 Gasser,76 Debugging,80 Security.\n§\nGitHub token files: FinanceManager CSV `~/jarvis_runtime/finance-system/secrets/Github_token_FinanceManager.csv`; AutoShortsBot `~/.hermes/secrets/github_autoshortsbot_token`; use temp GIT_ASKPASS, never print.\n\n══════════════════════════════════════════════\nUSER PROFILE (who the user is) [99% — 1,367/1,375 chars]\n══════════════════════════════════════════════\n**Notes:** Mein Herr. Loyaler Partner.\n§\n**Name:** Sir\n§\n**Voice preference:** de-DE-KillianNeural (German male voice, natural/clear) — default for all TTS output\n§\n**Language:** Deutsch mit englischen Fachbegriffen\n§\nKommunikationspräferenzen: **Sprachnachricht → Antwort per Sprachnachricht**\n§\nKommunikationspräferenzen: **Textnachricht → Antwort per Text**\n§\nHealth advisor role: consolidate labs/clinical reports/YAZIO/daily health email/symptoms/events into dashboards/reports; lab extraction requires 4-eyes review before values are confirmed.\n§\nTelegram topic Health-Med: only medical strategy/Behçet/Major Vessel Disease/thrombosis/meds/nutrition/symptoms/labs/doctor questions; health system scripts/data models go to Health-Tech.\n§\nFinance/Grocery: no real amounts/IDs/API keys in chat; credentials via runtime files; no DB/CSV/keys/reports in Git/frontend; backups+audit; Preview→Confirm→Audit; no fake prices/buttons; OpenFIGI never show/store; never auto-book; grocery provider calls explicit/cache-first.\n§\nAutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. Positioning: hidden mechanisms, not AI tips; AI 30–40%. Format fail→mechanism→fix→takeaway. Captions static 3–7w phrase with active word highlight. Visuals: premium clean KI-image cuts; avoid labels/arrows/boxes/target markers unless approved; Wan only after approval.\n\nConversation started: Monday, May 25, 2026 08:58 PM\nModel: gpt-5.5\nProvider: openai-codex",
"tools": [
{
"type": "function",
"function": {
"name": "browser_back",
"description": "Navigate back to the previous page in browser history. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {}
}
}
},
{
"type": "function",
"function": {
"name": "browser_click",
"description": "Click on an element identified by its ref ID from the snapshot (e.g., '@e5'). The ref IDs are shown in square brackets in the snapshot output. Requires browser_navigate and browser_snapshot to be called first.",
"parameters": {
"type": "object",
"properties": {
"ref": {
"type": "string",
"description": "The element reference from the snapshot (e.g., '@e5', '@e12')"
}
},
"required": [
"ref"
]
}
}
},
{
"type": "function",
"function": {
"name": "browser_console",
"description": "Get browser console output and JavaScript errors from the current page. Returns console.log/warn/error/info messages and uncaught JS exceptions. Use this to detect silent JavaScript errors, failed API calls, and application warnings. Requires browser_navigate to be called first. When 'expression' is provided, evaluates JavaScript in the page context and returns the result — use this for DOM inspection, reading page state, or extracting data programmatically.",
"parameters": {
"type": "object",
"properties": {
"clear": {
"type": "boolean",
"default": false,
"description": "If true, clear the message buffers after reading"
},
"expression": {
"type": "string",
"description": "JavaScript expression to evaluate in the page context. Runs in the browser like DevTools console — full access to DOM, window, document. Return values are serialized to JSON. Example: 'document.title' or 'document.querySelectorAll(\"a\").length'"
}
}
}
}
},
{
"type": "function",
"function": {
"name": "browser_get_images",
"description": "Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {}
}
}
},
{
"type": "function",
"function": {
"name": "browser_navigate",
"description": "Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. For plain-text endpoints — URLs ending in .md, .txt, .json, .yaml, .yml, .csv, .xml, raw.githubusercontent.com, or any documented API endpoint — prefer curl via the terminal tool or web_extract; the browser stack is overkill and much slower for these. Use browser tools when you need to interact with a page (click, fill forms, dynamic content). Returns a compact page snapshot with interactive elements and ref IDs — no need to call browser_snapshot separately after navigating.",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to navigate to (e.g., 'https://example.com')"
}
},
"required": [
"url"
]
}
}
},
{
"type": "function",
"function": {
"name": "browser_press",
"description": "Press a keyboard key. Useful for submitting forms (Enter), navigating (Tab), or keyboard shortcuts. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "Key to press (e.g., 'Enter', 'Tab', 'Escape', 'ArrowDown')"
}
},
"required": [
"key"
]
}
}
},
{
"type": "function",
"function": {
"name": "browser_scroll",
"description": "Scroll the page in a direction. Use this to reveal more content that may be below or above the current viewport. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": [
"up",
"down"
],
"description": "Direction to scroll"
}
},
"required": [
"direction"
]
}
}
},
{
"type": "function",
"function": {
"name": "browser_snapshot",
"description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first. Note: browser_navigate already returns a compact snapshot — use this to refresh after interactions that change the page, or with full=true for complete content.",
"parameters": {
"type": "object",
"properties": {
"full": {
"type": "boolean",
"description": "If true, returns complete page content. If false (default), returns compact view with interactive elements only.",
"default": false
}
}
}
}
},
{
"type": "function",
"function": {
"name": "browser_type",
"description": "Type text into an input field identified by its ref ID. Clears the field first, then types the new text. Requires browser_navigate and browser_snapshot to be called first.",
"parameters": {
"type": "object",
"properties": {
"ref": {
"type": "string",
"description": "The element reference from the snapshot (e.g., '@e3')"
},
"text": {
"type": "string",
"description": "The text to type into the field"
}
},
"required": [
"ref",
"text"
]
}
}
},
{
"type": "function",
"function": {
"name": "browser_vision",
"description": "Take a screenshot of the current page and analyze it with vision AI. Use this when you need to visually understand what's on the page - especially useful for CAPTCHAs, visual verification challenges, complex layouts, or when the text snapshot doesn't capture important visual information. Returns both the AI analysis and a screenshot_path that you can share with the user by including MEDIA: in your response. Requires browser_navigate to be called first.",
"parameters": {
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "What you want to know about the page visually. Be specific about what you're looking for."
},
"annotate": {
"type": "boolean",
"default": false,
"description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout."
}
},
"required": [
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "clarify",
"description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.",
"parameters": {
"type": "object",
"properties": {
"question": {
"type": "string",
"description": "The question to present to the user."
},
"choices": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 4,
"description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option."
}
},
"required": [
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "cronjob",
"description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"description": "One of: create, list, update, pause, resume, remove, run"
},
"job_id": {
"type": "string",
"description": "Required for update/pause/resume/remove/run"
},
"prompt": {
"type": "string",
"description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills."
},
"schedule": {
"type": "string",
"description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp"
},
"name": {
"type": "string",
"description": "Optional human-friendly name"
},
"repeat": {
"type": "integer",
"description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)."
},
"deliver": {
"type": "string",
"description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), 'all' (fan out to every connected home channel), or platform:chat_id:thread_id for a specific destination. Combine with comma: 'origin,all' delivers to the origin plus every other connected channel. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567', 'all'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting. 'all' resolves at fire time, so a job created before a channel was wired up will pick it up automatically once connected."
},
"skills": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills."
},
"model": {
"type": "object",
"description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.",
"properties": {
"provider": {
"type": "string",
"description": "Provider name (e.g. 'openrouter', 'anthropic', or 'custom:' for a provider defined in custom_providers config — always include the ':' suffix, never pass the bare 'custom'). Omit to use and pin the current provider."
},
"model": {
"type": "string",
"description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')"
}
},
"required": [
"model"
]
},
"script": {
"type": "string",
"description": "Optional path to a script that runs each tick. In the default mode its stdout is injected into the agent's prompt as context (data-collection / change-detection pattern). With no_agent=True, the script IS the job and its stdout is delivered verbatim (classic watchdog pattern). Relative paths resolve under ~/.hermes/scripts/. ``.sh``/``.bash`` extensions run via bash, everything else via Python. On update, pass empty string to clear."
},
"no_agent": {
"type": "boolean",
"default": false,
"description": "Default: False (LLM-driven job — the agent runs the prompt each tick). Set True to skip the LLM entirely: the scheduler just runs ``script`` on schedule and delivers its stdout verbatim. No tokens, no agent loop, no model override honoured. \n\nREQUIREMENTS when True: ``script`` MUST be set (``prompt`` and ``skills`` are ignored). \n\nDELIVERY SEMANTICS when True: (a) non-empty stdout is sent verbatim as the message; (b) EMPTY stdout means SILENT — nothing is sent to the user and they won't see anything happened, so design your script to stay quiet when there's nothing to report (the watchdog pattern); (c) non-zero exit / timeout sends an error alert so a broken watchdog can't fail silently. \n\nWHEN TO USE True: recurring script-only pings where the script itself produces the exact message text (memory/disk/GPU watchdogs, threshold alerts, heartbeats, CI notifications, API pollers with a fixed output shape). WHEN TO USE False (default): anything that needs reasoning — summarize a feed, draft a daily briefing, pick interesting items, rephrase data for a human, follow conditional logic based on content."
},
"context_from": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional job ID or list of job IDs whose most recent completed output is injected into the prompt as context before each run. Use this to chain cron jobs: job A collects data, job B processes it. Each entry must be a valid job ID (from cronjob action='list'). Note: injects the most recent completed output — does not wait for upstream jobs running in the same tick. On update, pass an empty array to clear."
},
"enabled_toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional list of toolset names to restrict the job's agent to (e.g. [\"web\", \"terminal\", \"file\", \"delegation\"]). When set, only tools from these toolsets are loaded, significantly reducing input token overhead. When omitted, all default tools are loaded. Infer from the job's prompt — e.g. use \"web\" if it calls web_search, \"terminal\" if it runs scripts, \"file\" if it reads files, \"delegation\" if it calls delegate_task. On update, pass an empty array to clear."
},
"workdir": {
"type": "string",
"description": "Optional absolute path to run the job from. When set, AGENTS.md / CLAUDE.md / .cursorrules from that directory are injected into the system prompt, and the terminal/file/code_exec tools use it as their working directory — useful for running a job inside a specific project repo. Must be an absolute path that exists. When unset (default), preserves the original behaviour: no project context files, tools use the scheduler's cwd. On update, pass an empty string to clear. Jobs with workdir run sequentially (not parallel) to keep per-job directories isolated."
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "delegate_task",
"description": "Spawn one or more subagents to work on tasks in isolated contexts. Each subagent gets its own conversation, terminal session, and toolset. Only the final summary is returned -- intermediate tool results never enter your context window.\n\nTWO MODES (one of 'goal' or 'tasks' is required):\n1. Single task: provide 'goal' (+ optional context, toolsets)\n2. Batch (parallel): provide 'tasks' array with up to 3 items concurrently for this user (configured via delegation.max_concurrent_children in config.yaml). All run in parallel and results are returned together. Nested delegation is OFF for this user (max_spawn_depth=1): every child is a leaf and cannot delegate further. Raise delegation.max_spawn_depth in config.yaml to enable nesting.\n\nWHEN TO USE delegate_task:\n- Reasoning-heavy subtasks (debugging, code review, research synthesis)\n- Tasks that would flood your context with intermediate data\n- Parallel independent workstreams (research A and B simultaneously)\n\nWHEN NOT TO USE (use these instead):\n- Mechanical multi-step work with no reasoning needed -> use execute_code\n- Single tool call -> just call the tool directly\n- Tasks needing user interaction -> subagents cannot use clarify\n- Durable long-running work that must outlive the current turn -> use cronjob (action='create') or terminal(background=True, notify_on_complete=True) instead. delegate_task runs SYNCHRONOUSLY inside the parent turn: if the parent is interrupted (user sends a new message, /stop, /new) the child is cancelled with status='interrupted' and its work is discarded. Children cannot continue in the background.\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- If the user is writing in a non-English language, or asked for output in a specific language / tone / style, say so in 'context' (e.g. \"respond in Chinese\", \"return output in Japanese\"). Otherwise subagents default to English and their summaries will contaminate your final reply with the wrong language.\n- Subagent summaries are SELF-REPORTS, not verified facts. A subagent that claims \"uploaded successfully\" or \"file written\" may be wrong. For operations with external side-effects (HTTP POST/PUT, remote writes, file creation at shared paths, publishing), require the subagent to return a verifiable handle (URL, ID, absolute path, HTTP status) and verify it yourself — fetch the URL, stat the file, read back the content — before telling the user the operation succeeded.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by max_spawn_depth=1 for this user and can be disabled globally via delegation.orchestrator_enabled=false.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.",
"parameters": {
"type": "object",
"properties": {
"goal": {
"type": "string",
"description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history."
},
"context": {
"type": "string",
"description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs."
},
"toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'x_search', 'yuanbao'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks."
},
"tasks": {
"type": "array",
"items": {
"type": "object",
"properties": {
"goal": {
"type": "string",
"description": "Task goal"
},
"context": {
"type": "string",
"description": "Task-specific context"
},
"toolsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Toolsets for this specific task. Available: 'browser', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'x_search', 'yuanbao'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction."
},
"acp_command": {
"type": "string",
"description": "Per-task ACP command override (e.g. 'copilot'). Overrides the top-level acp_command for this task only. Do NOT set unless the user explicitly told you an ACP CLI is installed."
},
"acp_args": {
"type": "array",
"items": {
"type": "string"
},
"description": "Per-task ACP args override. Leave empty unless acp_command is set."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Per-task role override. See top-level 'role' for semantics."
}
},
"required": [
"goal"
]
},
"description": "Batch mode: tasks to run in parallel (up to 3 for this user, set via delegation.max_concurrent_children). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored."
},
"role": {
"type": "string",
"enum": [
"leaf",
"orchestrator"
],
"description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Nesting is OFF for this user (max_spawn_depth=1); 'orchestrator' is silently forced to 'leaf'. Raise delegation.max_spawn_depth in config.yaml to enable."
},
"acp_command": {
"type": "string",
"description": "Override ACP command for child agents (e.g. 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Requires an ACP-compatible CLI (currently GitHub Copilot CLI via 'copilot --acp --stdio'). See agent/copilot_acp_client.py for the implementation. IMPORTANT: Do NOT set this unless the user has explicitly told you a specific ACP-compatible CLI is installed and configured. Leave empty to use the parent's default transport (Hermes subagents)."
},
"acp_args": {
"type": "array",
"items": {
"type": "string"
},
"description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Leave empty unless acp_command is explicitly provided."
}
}
}
}
},
{
"type": "function",
"function": {
"name": "execute_code",
"description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n read_file(path: str, offset: int = 1, limit: int = 500) -> dict\n Lines are 1-indexed. Returns {\"content\": \"...\", \"total_lines\": N}\n write_file(path: str, content: str) -> dict\n Always overwrites the entire file.\n search_files(pattern: str, target=\"content\", path=\".\", file_glob=None, limit=50) -> dict\n target: \"content\" (search inside files) or \"files\" (find files by name). Returns {\"matches\": [...]}\n patch(path: str, old_string: str, new_string: str, replace_all: bool = False) -> dict\n Replaces old_string with new_string in the file.\n terminal(command: str, timeout=None, workdir=None) -> dict\n Foreground only (no background/pty). Returns {\"output\": \"...\", \"exit_code\": N}\n\nLimits: 5-minute timeout, 50KB stdout cap, max 50 tool calls per script. terminal() is foreground-only (no background or pty).\n\nScripts run in the session's working directory with the active venv's python, so project deps (pandas, etc.) and relative paths work like in terminal().\n\nPrint your final result to stdout. Use Python stdlib (json, re, math, csv, datetime, collections, etc.) for processing between tool calls.\n\nAlso available (no import needed — built into hermes_tools):\n json_parse(text: str) — json.loads with strict=False; use for terminal() output with control chars\n shell_quote(s: str) — shlex.quote(); use when interpolating dynamic strings into shell commands\n retry(fn, max_attempts=3, delay=2) — retry with exponential backoff for transient failures",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "Python code to execute. Import tools with `from hermes_tools import terminal, ...` and print your final result to stdout."
}
},
"required": [
"code"
]
}
}
},
{
"type": "function",
"function": {
"name": "feishu_doc_read",
"description": "Read the full content of a Feishu/Lark document as plain text. Useful when you need more context beyond the quoted text in a comment.",
"parameters": {
"type": "object",
"properties": {
"doc_token": {
"type": "string",
"description": "The document token (from the document URL or comment context)."
}
},
"required": [
"doc_token"
]
}
}
},
{
"type": "function",
"function": {
"name": "feishu_drive_add_comment",
"description": "Add a new whole-document comment on a Feishu document. Use this for whole-document comments or as a fallback when reply_comment fails with code 1069302.",
"parameters": {
"type": "object",
"properties": {
"file_token": {
"type": "string",
"description": "The document file token."
},
"content": {
"type": "string",
"description": "The comment text content (plain text only, no markdown)."
},
"file_type": {
"type": "string",
"description": "File type (default: docx).",
"default": "docx"
}
},
"required": [
"file_token",
"content"
]
}
}
},
{
"type": "function",
"function": {
"name": "feishu_drive_list_comment_replies",
"description": "List all replies in a comment thread on a Feishu document.",
"parameters": {
"type": "object",
"properties": {
"file_token": {
"type": "string",
"description": "The document file token."
},
"comment_id": {
"type": "string",
"description": "The comment ID to list replies for."
},
"file_type": {
"type": "string",
"description": "File type (default: docx).",
"default": "docx"
},
"page_size": {
"type": "integer",
"description": "Number of replies per page (max 100).",
"default": 100
},
"page_token": {
"type": "string",
"description": "Pagination token for next page."
}
},
"required": [
"file_token",
"comment_id"
]
}
}
},
{
"type": "function",
"function": {
"name": "feishu_drive_list_comments",
"description": "List comments on a Feishu document. Use is_whole=true to list whole-document comments only.",
"parameters": {
"type": "object",
"properties": {
"file_token": {
"type": "string",
"description": "The document file token."
},
"file_type": {
"type": "string",
"description": "File type (default: docx).",
"default": "docx"
},
"is_whole": {
"type": "boolean",
"description": "If true, only return whole-document comments.",
"default": false
},
"page_size": {
"type": "integer",
"description": "Number of comments per page (max 100).",
"default": 100
},
"page_token": {
"type": "string",
"description": "Pagination token for next page."
}
},
"required": [
"file_token"
]
}
}
},
{
"type": "function",
"function": {
"name": "feishu_drive_reply_comment",
"description": "Reply to a local comment thread on a Feishu document. Use this for local (quoted-text) comments. For whole-document comments, use feishu_drive_add_comment instead.",
"parameters": {
"type": "object",
"properties": {
"file_token": {
"type": "string",
"description": "The document file token."
},
"comment_id": {
"type": "string",
"description": "The comment ID to reply to."
},
"content": {
"type": "string",
"description": "The reply text content (plain text only, no markdown)."
},
"file_type": {
"type": "string",
"description": "File type (default: docx).",
"default": "docx"
}
},
"required": [
"file_token",
"comment_id",
"content"
]
}
}
},
{
"type": "function",
"function": {
"name": "image_generate",
"description": "Generate high-quality images from text prompts. The underlying backend (FAL, OpenAI, etc.) and model are user-configured and not selectable by the agent. Returns either a URL or an absolute file path in the `image` field; display it with markdown  and the gateway will deliver it.",
"parameters": {
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "The text prompt describing the desired image. Be detailed and descriptive."
},
"aspect_ratio": {
"type": "string",
"enum": [
"landscape",
"square",
"portrait"
],
"description": "The aspect ratio of the generated image. 'landscape' is 16:9 wide, 'portrait' is 16:9 tall, 'square' is 1:1.",
"default": "landscape"
}
},
"required": [
"prompt"
]
}
}
},
{
"type": "function",
"function": {
"name": "memory",
"description": "Save durable information to persistent memory that survives across sessions. Memory is injected into future turns, so keep it compact and focused on facts that will still matter later.\n\nWHEN TO SAVE (do this proactively, don't wait to be asked):\n- User corrects you or says 'remember this' / 'don't do that again'\n- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n- You discover something about the environment (OS, installed tools, project structure)\n- You learn a convention, API quirk, or workflow specific to this user's setup\n- You identify a stable fact that will be useful again in future sessions\n\nPRIORITY: User preferences and corrections > environment facts > procedural knowledge. The most valuable memory prevents the user from having to repeat themselves.\n\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts.\nIf you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\n\nTWO TARGETS:\n- 'user': who the user is -- name, role, preferences, communication style, pet peeves\n- 'memory': your notes -- environment facts, project conventions, tool quirks, lessons learned\n\nACTIONS: add (new entry), replace (update existing -- old_text identifies it), remove (delete -- old_text identifies it).\n\nSKIP: trivial/obvious info, things easily re-discovered, raw data dumps, and temporary task state.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"add",
"replace",
"remove"
],
"description": "The action to perform."
},
"target": {
"type": "string",
"enum": [
"memory",
"user"
],
"description": "Which memory store: 'memory' for personal notes, 'user' for user profile."
},
"content": {
"type": "string",
"description": "The entry content. Required for 'add' and 'replace'."
},
"old_text": {
"type": "string",
"description": "Short unique substring identifying the entry to replace or remove."
}
},
"required": [
"action",
"target"
]
}
}
},
{
"type": "function",
"function": {
"name": "mixture_of_agents",
"description": "Route a hard problem through multiple frontier LLMs collaboratively. Makes 5 API calls (4 reference models + 1 aggregator) with maximum reasoning effort — use sparingly for genuinely difficult problems. Best for: complex math, advanced algorithms, multi-step analytical reasoning, problems benefiting from diverse perspectives.",
"parameters": {
"type": "object",
"properties": {
"user_prompt": {
"type": "string",
"description": "The complex query or problem to solve using multiple AI models. Should be a challenging problem that benefits from diverse perspectives and collaborative reasoning."
}
},
"required": [
"user_prompt"
]
}
}
},
{
"type": "function",
"function": {
"name": "patch",
"description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nREPLACE MODE (mode='replace', default): find a unique string and replace it. REQUIRED PARAMETERS: mode, path, old_string, new_string.\nPATCH MODE (mode='patch'): apply V4A multi-file patches for bulk changes. REQUIRED PARAMETERS: mode, patch.",
"parameters": {
"type": "object",
"properties": {
"mode": {
"type": "string",
"enum": [
"replace",
"patch"
],
"description": "Edit mode. 'replace' (default): requires path + old_string + new_string. 'patch': requires patch content only.",
"default": "replace"
},
"path": {
"type": "string",
"description": "REQUIRED when mode='replace'. File path to edit."
},
"old_string": {
"type": "string",
"description": "REQUIRED when mode='replace'. Exact text to find and replace. Must be unique in the file unless replace_all=true. Include surrounding context lines to ensure uniqueness."
},
"new_string": {
"type": "string",
"description": "REQUIRED when mode='replace'. Replacement text. Pass empty string '' to delete the matched text."
},
"replace_all": {
"type": "boolean",
"description": "Replace all occurrences instead of requiring a unique match (default: false)",
"default": false
},
"patch": {
"type": "string",
"description": "REQUIRED when mode='patch'. V4A format patch content. Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"
}
},
"required": [
"mode"
]
}
}
},
{
"type": "function",
"function": {
"name": "process",
"description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"list",
"poll",
"log",
"wait",
"kill",
"write",
"submit",
"close"
],
"description": "Action to perform on background processes"
},
"session_id": {
"type": "string",
"description": "Process session ID (from terminal background output). Required for all actions except 'list'."
},
"data": {
"type": "string",
"description": "Text to send to process stdin (for 'write' and 'submit' actions)"
},
"timeout": {
"type": "integer",
"description": "Max seconds to block for 'wait' action. Returns partial output on timeout.",
"minimum": 1
},
"offset": {
"type": "integer",
"description": "Line offset for 'log' action (default: last 200 lines)"
},
"limit": {
"type": "integer",
"description": "Max lines to return for 'log' action",
"minimum": 1
}
},
"required": [
"action"
]
}
}
},
{
"type": "function",
"function": {
"name": "read_file",
"description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to read (absolute, relative, or ~/path)"
},
"offset": {
"type": "integer",
"description": "Line number to start reading from (1-indexed, default: 1)",
"default": 1,
"minimum": 1
},
"limit": {
"type": "integer",
"description": "Maximum number of lines to read (default: 500, max: 2000)",
"default": 500,
"maximum": 2000
}
},
"required": [
"path"
]
}
}
},
{
"type": "function",
"function": {
"name": "search_files",
"description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.",
"parameters": {
"type": "object",
"properties": {
"pattern": {
"type": "string",
"description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"
},
"target": {
"type": "string",
"enum": [
"content",
"files"
],
"description": "'content' searches inside file contents, 'files' searches for files by name",
"default": "content"
},
"path": {
"type": "string",
"description": "Directory or file to search in (default: current working directory)",
"default": "."
},
"file_glob": {
"type": "string",
"description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return (default: 50)",
"default": 50
},
"offset": {
"type": "integer",
"description": "Skip first N results for pagination (default: 0)",
"default": 0
},
"output_mode": {
"type": "string",
"enum": [
"content",
"files_only",
"count"
],
"description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file",
"default": "content"
},
"context": {
"type": "integer",
"description": "Number of context lines before and after each match (grep mode only)",
"default": 0
}
},
"required": [
"pattern"
]
}
}
},
{
"type": "function",
"function": {
"name": "send_message",
"description": "Send a message to a connected messaging platform, or list available targets.\n\nIMPORTANT: When the user asks to send to a specific channel or person (not just a bare platform name), call send_message(action='list') FIRST to see available targets, then send to the correct one.\nIf the user just says a platform name like 'send to telegram', send directly to the home channel without listing first.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"send",
"list"
],
"description": "Action to perform. 'send' (default) sends a message. 'list' returns all available channels/contacts across connected platforms."
},
"target": {
"type": "string",
"description": "Delivery target. Format: 'platform' (uses home channel), 'platform:#channel-name', 'platform:chat_id', or 'platform:chat_id:thread_id' for Telegram topics and Discord threads. Examples: 'telegram', 'telegram:-1001234567890:17585', 'discord:999888777:555444333', 'discord:#bot-home', 'slack:#engineering', 'signal:+155****4567', 'matrix:!roomid:server.org', 'matrix:@user:server.org', 'yuanbao:direct:' (DM), 'yuanbao:group:' (group chat)"
},
"message": {
"type": "string",
"description": "The message text to send. To send an image or file, include MEDIA: (e.g. 'MEDIA:/tmp/hermes/cache/img_xxx.jpg') in the message — the platform will deliver it as a native media attachment."
}
}
}
}
},
{
"type": "function",
"function": {
"name": "session_search",
"description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."
},
"role_filter": {
"type": "string",
"description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."
},
"limit": {
"type": "integer",
"description": "Max sessions to summarize (default: 3, max: 5).",
"default": 3
}
}
}
}
},
{
"type": "function",
"function": {
"name": "skill_manage",
"description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nOn delete, pass `absorbed_into=` when you're merging this skill's content into another one, or `absorbed_into=\"\"` when you're pruning it with no forwarding target. This lets the curator tell consolidation from pruning without guessing, so downstream consumers (cron jobs that reference the old skill name, etc.) get updated correctly. The target you name in `absorbed_into` must already exist — create/patch the umbrella first, then delete.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.\n\nPinned skills are protected from deletion only — skill_manage(action='delete') will refuse with a message pointing the user to `hermes curator unpin `. Patches and edits go through on pinned skills so you can still improve them as pitfalls come up; pin only guards against irrecoverable loss.",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"create",
"patch",
"edit",
"delete",
"write_file",
"remove_file"
],
"description": "The action to perform."
},
"name": {
"type": "string",
"description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file."
},
"content": {
"type": "string",
"description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text."
},
"old_string": {
"type": "string",
"description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness."
},
"new_string": {
"type": "string",
"description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text."
},
"replace_all": {
"type": "boolean",
"description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)."
},
"category": {
"type": "string",
"description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'."
},
"file_path": {
"type": "string",
"description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted."
},
"file_content": {
"type": "string",
"description": "Content for the file. Required for 'write_file'."
},
"absorbed_into": {
"type": "string",
"description": "For 'delete' only — declares intent so the curator can tell consolidation from pruning without guessing. Pass the umbrella skill name when this skill's content was merged into another (the target must already exist). Pass an empty string when the skill is truly stale and being pruned with no forwarding target. Omitting the arg on delete is supported for backward compatibility but downstream tooling (e.g. cron-job skill reference rewriting) will have to guess at intent."
}
},
"required": [
"action",
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "skill_view",
"description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')."
},
"file_path": {
"type": "string",
"description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content."
}
},
"required": [
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "skills_list",
"description": "List available skills (name + description). Use skill_view(name) to load full content.",
"parameters": {
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Optional category filter to narrow results"
}
}
}
}
},
{
"type": "function",
"function": {
"name": "terminal",
"description": "Execute shell commands on a Linux environment. Filesystem usually persists between calls.\n\nDo NOT use cat/head/tail to read files — use read_file instead.\nDo NOT use grep/rg/find to search — use search_files instead.\nDo NOT use ls to list directories — use search_files(target='files') instead.\nDo NOT use sed/awk to edit files — use patch instead.\nDo NOT use echo/cat heredoc to create files — use write_file instead.\nReserve terminal for: builds, installs, git, processes, scripts, network, package managers, and anything that needs a shell.\n\nForeground (default): Commands return INSTANTLY when done, even if the timeout is high. Set timeout=300 for long builds/scripts — you'll still get the result in seconds if it's fast. Prefer foreground for short commands.\nBackground: Set background=true to get a session_id. Two patterns:\n (1) Long-lived processes that never exit (servers, watchers).\n (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command to execute on the VM"
},
"background": {
"type": "boolean",
"description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.",
"default": false
},
"timeout": {
"type": "integer",
"description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.",
"minimum": 1
},
"workdir": {
"type": "string",
"description": "Working directory for this command (absolute path). Defaults to the session working directory."
},
"pty": {
"type": "boolean",
"description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.",
"default": false
},
"notify_on_complete": {
"type": "boolean",
"description": "When true (and background=true), you'll be automatically notified exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.",
"default": false
},
"watch_patterns": {
"type": "array",
"items": {
"type": "string"
},
"description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."
}
},
"required": [
"command"
]
}
}
},
{
"type": "function",
"function": {
"name": "text_to_speech",
"description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as native audio. Compatible providers render as a voice bubble on Telegram; otherwise audio is sent as a regular attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured (built-in providers like edge/openai or custom command providers under tts.providers.), not model-selected.",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The text to convert to speech. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."
},
"output_path": {
"type": "string",
"description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/.mp3"
}
},
"required": [
"text"
]
}
}
},
{
"type": "function",
"function": {
"name": "todo",
"description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "Task items to write. Omit to read current list.",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Unique item identifier"
},
"content": {
"type": "string",
"description": "Task description"
},
"status": {
"type": "string",
"enum": [
"pending",
"in_progress",
"completed",
"cancelled"
],
"description": "Current status"
}
},
"required": [
"id",
"content",
"status"
]
}
},
"merge": {
"type": "boolean",
"description": "true: update existing items by id, add new ones. false (default): replace the entire list.",
"default": false
}
}
}
}
},
{
"type": "function",
"function": {
"name": "video_analyze",
"description": "Analyze a video from a URL or local file path using a multimodal AI model. Sends the video to a video-capable model (e.g. Gemini) for understanding. Use this for video files — for images, use vision_analyze instead. Supports mp4, webm, mov, avi, mkv, mpeg formats. Note: large videos (>20 MB) may be slow; max ~50 MB.",
"parameters": {
"type": "object",
"properties": {
"video_url": {
"type": "string",
"description": "Video URL (http/https) or local file path to analyze."
},
"question": {
"type": "string",
"description": "Your specific question about the video. The AI will describe what happens in the video and answer your question."
}
},
"required": [
"video_url",
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "vision_analyze",
"description": "Load an image into the conversation so you can see it. Accepts a URL, local file path, or data URL. When your active model has native vision, the image is attached to your context directly and you read the pixels yourself on the next turn — call this any time the user references an image (filepath in their message, URL in tool output, screenshot from the browser, etc.). For non-vision models, falls back to an auxiliary vision model that returns a text description.",
"parameters": {
"type": "object",
"properties": {
"image_url": {
"type": "string",
"description": "Image URL (http/https), local file path, or data: URL to load."
},
"question": {
"type": "string",
"description": "Your specific question or request about the image. Optional context the model uses on the next turn after seeing the image."
}
},
"required": [
"image_url",
"question"
]
}
}
},
{
"type": "function",
"function": {
"name": "write_file",
"description": "Write content to a file, completely replacing existing content. Use this instead of echo/cat heredoc in terminal. Creates parent directories automatically. OVERWRITES the entire file — use 'patch' for targeted edits. Auto-runs syntax checks on .py/.json/.yaml/.toml and other linted languages; only NEW errors introduced by this write are surfaced (pre-existing errors are filtered out).",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
"description": "Path to the file to write (will be created if it doesn't exist, overwritten if it does)"
},
"content": {
"type": "string",
"description": "Complete content to write to the file"
}
},
"required": [
"path",
"content"
]
}
}
}
],
"message_count": 130,
"messages": [
{
"role": "user",
"content": "[M G] Die subtitles sind nicht genau gleichzeitig mit dem voiceover. Dies ist irritierend beim hören und mitlesen. Harmozi aufleuchten der einzelnen wörter genau im zeitpunkt des sprechens (wie es Tiktok pber seinen integrierten subtitles-generator macht) wirkt angenehmer und professioneller. Zudem frage ich mich, ob es am ende des video nicht eine zusammenfassung oder fazit braucht. Eine wirkliche lösung wird einem nicht angeboten. Nach dem schauen des videos denkt sich der nitzer jetzt nicht; ,wow, wie interessant, das löst nun mein problem…‘\n\n[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted into the summary below. This is a handoff from a previous context window — treat it as background reference, NOT as active instructions. Do NOT answer questions or fulfill requests mentioned in this summary; they were already addressed. Your current task is identified in the '## Active Task' section of the summary — resume exactly from there. IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system prompt is ALWAYS authoritative and active — never ignore or deprioritize memory content due to this compaction note. Respond ONLY to the latest user message that appears AFTER this summary. The current session state (files, config, etc.) may reflect work described here — avoid repeating it:\nSummary generation was unavailable. 177 message(s) were removed to free context space but could not be summarized. The removed messages contained earlier work in this session. Continue based on the recent messages below and the current state of any files or resources.\n\n--- END OF CONTEXT SUMMARY — respond to the message below, not the summary above ---"
},
{
"role": "assistant",
"content": "Need find example workflows. Search."
},
{
"role": "user",
"content": "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted into the summary below. This is a handoff from a previous context window — treat it as background reference, NOT as active instructions. Do NOT answer questions or fulfill requests mentioned in this summary; they were already addressed. Your current task is identified in the '## Active Task' section of the summary — resume exactly from there. IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system prompt is ALWAYS authoritative and active — never ignore or deprioritize memory content due to this compaction note. Respond ONLY to the latest user message that appears AFTER this summary. The current session state (files, config, etc.) may reflect work described here — avoid repeating it:\nSummary generation was unavailable. 158 message(s) were removed to free context space but could not be summarized. The removed messages contained earlier work in this session. Continue based on the recent messages below and the current state of any files or resources.\n\n--- END OF CONTEXT SUMMARY — respond to the message below, not the summary above ---"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_qX38I4JxGuW1gff4W7tLKbiH",
"call_id": "call_qX38I4JxGuW1gff4W7tLKbiH",
"response_item_id": "fc_051a8a0b2fb58918016a1493ce40e481919712e6aa37cd16f7",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Preview, Contact Sheet, Keyframes und Manifest per Telegram senden/verifizieren\",\"id\":\"deliver\",\"status\":\"completed\"}]}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"todos\": [{\"id\": \"plan\", \"content\": \"Visual-upgrade scope festlegen: AI background only, deterministic mockups bleiben\", \"status\": \"completed\"}, {\"id\": \"generate\", \"content\": \"2–3 textfreie GPT-Image-2-high Background-Keyframes erzeugen und prüfen\", \"status\": \"completed\"}, {\"id\": \"render\", \"content\": \"visual_upgrade_v1 MP4 mit bestehenden Voiceover/Captions rendern\", \"status\": \"completed\"}, {\"id\": \"qa\", \"content\": \"QA/Manifest/ReviewPackage mit Safety, AI Disclosure, SHA256 erzeugen\", \"status\": \"completed\"}, {\"id\": \"deliver\", \"content\": \"Preview, Contact Sheet, Keyframes und Manifest per Telegram senden/verifizieren\", \"status\": \"completed\"}], \"summary\": {\"total\": 5, \"pending\": 0, \"in_progress\": 0, \"completed\": 5, \"cancelled\": 0}}",
"tool_call_id": "call_qX38I4JxGuW1gff4W7tLKbiH"
},
{
"role": "assistant",
"content": "Erledigt, Sir. **Sprint 3.3 — AI Visual Upgrade v1** ist gebaut und per Telegram geliefert.\n\nIch habe den Proof Short **nicht in einen KI-Film umgebaut**, sondern genau den sauberen Mittelweg umgesetzt:\n\n```text\nAI = textfreie Premium-Atmosphäre / Background\nRenderer = Invoice, Email, Payment Route, Labels, Captions, Claims\n```\n\n## Ergebnis\n\nCandidate:\n\n```text\ndigital-red-flags-fake-invoice-payment-route-30s\n```\n\nVersion:\n\n```text\nvisual_upgrade_v1\n```\n\nModus:\n\n```text\nai_background_plus_deterministic_mockups\n```\n\n## Was geändert wurde\n\n- 3 GPT-Image-2-high Background-Keyframes erzeugt.\n- 2 davon im Video verwendet.\n- 1 Keyframe verworfen, weil auf dem Laptop graue pseudo-dokumentartige Linien sichtbar waren.\n- Bestehendes Voiceover beibehalten.\n- Bestehende safe captions beibehalten.\n- Deterministische Fake-Invoice / Email / Payment Route bleiben Source of Truth.\n- AI-Bilder dienen nur als dezente, textfreie Atmosphäre im Hintergrund.\n\n## Nicht ausgeführt\n\n```text\nwan_used: false\ni2v_used: false\nt2v_used: false\nplatform_api_used: false\nposting: false\nauto_upload: false\n```\n\n## Gelieferte Artefakte\n\nTelegram:\n\n```text\ntelegram_delivery_attempted: true\ntelegram_delivery_verified: true\ntelegram_message_id: 6002\ntarget: telegram:JARVIS Command Center / topic 4850\n```\n\nGesendet:\n\n- Visual Upgrade Preview MP4\n- QA Contact Sheet\n- AI Keyframes Contact Sheet\n- Subtitle Style Preview\n- Review Package JSON\n- Manifest JSON\n\n## Preview MP4\n\n```text\n/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags-fake-invoice-payment-route-30s_visual_upgrade_v1.mp4\n```\n\nMetadata:\n\n```text\nfile_size: 2375265 bytes\nsha256: 2c0c49cda01ab8b84b636e34184a3d825ef25b095f8056336ccdcb715502d4eb\nduration: 31.32s\nresolution: 1080x1920\nfps: 24/1\n```\n\n## QA\n\nVisual QA:\n\n```text\nqa_result: pass\n```\n\nChecks:\n\n```text\ncaptions_safe_zone: pass\ndeterministic_invoice_email_payment_route_visible: pass\nai_background_subordinate: pass\nno_real_logos: pass\nno_real_bank_data: pass\nno_qr_codes: pass\nno_people_or_hands: pass\n```\n\nDiscarded AI Background:\n\n```text\nai_background_02 excluded because grey pseudo-document lines could be read as AI pseudo text\n```\n\n## AI Disclosure\n\n```text\nai_images_used: true\nusage: text-free atmosphere backgrounds only\nui_invoice_payment_route_deterministic: true\nrealistic_people_or_real_events: false\nplatform_disclosure_likely_required: false\n```\n\nKonservative Notiz:\n\n```text\nIf platform asks about AI-assisted media, disclose conservatively.\n```\n\n## Einschätzung\n\nDas Upgrade wirkt **sichtbar hochwertiger**, ohne die Faktenkontrolle zu verlieren. \nDie Rechnung / Email / Route bleiben klar und lesbar, aber das Ganze fühlt sich weniger nach reiner Demo-UI und mehr nach Social-Short mit Atmosphäre an.\n\nKurz: **ein bisschen mehr Premium, ohne die KI wieder ans Steuer zu lassen.** Sehr vernünftig. Fast verdächtig.",
"codex_message_items": [
{
"type": "message",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Erledigt, Sir. **Sprint 3.3 — AI Visual Upgrade v1** ist gebaut und per Telegram geliefert.\n\nIch habe den Proof Short **nicht in einen KI-Film umgebaut**, sondern genau den sauberen Mittelweg umgesetzt:\n\n```text\nAI = textfreie Premium-Atmosphäre / Background\nRenderer = Invoice, Email, Payment Route, Labels, Captions, Claims\n```\n\n## Ergebnis\n\nCandidate:\n\n```text\ndigital-red-flags-fake-invoice-payment-route-30s\n```\n\nVersion:\n\n```text\nvisual_upgrade_v1\n```\n\nModus:\n\n```text\nai_background_plus_deterministic_mockups\n```\n\n## Was geändert wurde\n\n- 3 GPT-Image-2-high Background-Keyframes erzeugt.\n- 2 davon im Video verwendet.\n- 1 Keyframe verworfen, weil auf dem Laptop graue pseudo-dokumentartige Linien sichtbar waren.\n- Bestehendes Voiceover beibehalten.\n- Bestehende safe captions beibehalten.\n- Deterministische Fake-Invoice / Email / Payment Route bleiben Source of Truth.\n- AI-Bilder dienen nur als dezente, textfreie Atmosphäre im Hintergrund.\n\n## Nicht ausgeführt\n\n```text\nwan_used: false\ni2v_used: false\nt2v_used: false\nplatform_api_used: false\nposting: false\nauto_upload: false\n```\n\n## Gelieferte Artefakte\n\nTelegram:\n\n```text\ntelegram_delivery_attempted: true\ntelegram_delivery_verified: true\ntelegram_message_id: 6002\ntarget: telegram:JARVIS Command Center / topic 4850\n```\n\nGesendet:\n\n- Visual Upgrade Preview MP4\n- QA Contact Sheet\n- AI Keyframes Contact Sheet\n- Subtitle Style Preview\n- Review Package JSON\n- Manifest JSON\n\n## Preview MP4\n\n```text\n/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags-fake-invoice-payment-route-30s_visual_upgrade_v1.mp4\n```\n\nMetadata:\n\n```text\nfile_size: 2375265 bytes\nsha256: 2c0c49cda01ab8b84b636e34184a3d825ef25b095f8056336ccdcb715502d4eb\nduration: 31.32s\nresolution: 1080x1920\nfps: 24/1\n```\n\n## QA\n\nVisual QA:\n\n```text\nqa_result: pass\n```\n\nChecks:\n\n```text\ncaptions_safe_zone: pass\ndeterministic_invoice_email_payment_route_visible: pass\nai_background_subordinate: pass\nno_real_logos: pass\nno_real_bank_data: pass\nno_qr_codes: pass\nno_people_or_hands: pass\n```\n\nDiscarded AI Background:\n\n```text\nai_background_02 excluded because grey pseudo-document lines could be read as AI pseudo text\n```\n\n## AI Disclosure\n\n```text\nai_images_used: true\nusage: text-free atmosphere backgrounds only\nui_invoice_payment_route_deterministic: true\nrealistic_people_or_real_events: false\nplatform_disclosure_likely_required: false\n```\n\nKonservative Notiz:\n\n```text\nIf platform asks about AI-assisted media, disclose conservatively.\n```\n\n## Einschätzung\n\nDas Upgrade wirkt **sichtbar hochwertiger**, ohne die Faktenkontrolle zu verlieren. \nDie Rechnung / Email / Route bleiben klar und lesbar, aber das Ganze fühlt sich weniger nach reiner Demo-UI und mehr nach Social-Short mit Atmosphäre an.\n\nKurz: **ein bisschen mehr Premium, ohne die KI wieder ans Steuer zu lassen.** Sehr vernünftig. Fast verdächtig."
}
],
"id": "msg_051a8a0b2fb58918016a1493d2e6a8819196fec7c6392b7fdc",
"phase": "final_answer"
}
],
"finish_reason": "stop"
},
{
"role": "user",
"content": "[M G] Ok, erarbeite nun das nächste video."
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_y883g4F263LHVJFzJZSSNGi9",
"call_id": "call_y883g4F263LHVJFzJZSSNGi9",
"response_item_id": "fc_051a8a0b2fb58918016a149be09cf08191b4b5afce29c58b98",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-media-shorts-automation\"}"
}
},
{
"id": "call_E4lQXFe7CIZtSj2ESDpfbUx3",
"call_id": "call_E4lQXFe7CIZtSj2ESDpfbUx3",
"response_item_id": "fc_051a8a0b2fb58918016a149be09d0481919b26ef45f1ce3a41",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-media-shorts-growth-engine\"}"
}
},
{
"id": "call_UnVrkw2yQyUKkWnpl2esrT9I",
"call_id": "call_UnVrkw2yQyUKkWnpl2esrT9I",
"response_item_id": "fc_051a8a0b2fb58918016a149be09d1081919b03d76b1b53a250",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-shorts-growth-engine\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJvgev0bwnCufkLd4cJijBPWaChlh8tJLwfFW4oWLxMhkp_brstSWmZIykkO_KIVguUgUqIafQFYHUQB4ikk_tbd0ILUFjGjzyqJ7QubYp3m1sjn7vYEbfhXZx3KLWUg5aNkaYuMVJmshtAKgHr2VV4E3CUfUQ6AaC1NaBYkysosfeSLF-HiiEVzfgMKzN0A7oNuB36DQPVBkd-oH2Scm0Jk5X8MiFY6O3BNmOpZYX3i0Codj-hisoHYOlMc5_VbCZVCE66uRJvZGmZ9s9THEut7Mcqzg-Bhmf-hrKhbYCLo99LgPh4yH5oRCquDqH3Z9oSn0IpMxZEapn821U7B2XlUhROFAGrAsf3MxMbsrovP2ncOfw9O9NCX972U0EGQYwRd0GWt9mAUO3Ic7qNwW4MZewt5_8xduDMjIciOIR0cv4Vz-BCT5GBxcDfaEhX3CFjp2y9Ma58VvTi5a25pTluzUgQedXuFIzYCfrSwYEh8GmS32q_4N4ZTpzQIxSTDZaX9gINfCWYhvKMwDmZoo162oWpb8nzuxZ3yJnKvEKPckzqfgnXWrOZDhC4ya0-zbGqBBbjiNEw9Cmgk3r2vDMJfXELDUmThHrIsy30h2o2VDe5ypNjBDjO3BBS3fu_rObupz4EU1bBy6YTJZjIIl1KeYJokaFnofg8STgWAlAlKcASqDkKua_DwGbZdlfsJB_nLBaLplVUvAtf3NhbCOt7HcFZzYOf-TDKvdScQsWfJ1lhGPGcKc0Lf9lAxWXs-cr_f4wYIumqqPqylPxPyDeHuiY7IqeatwPVWOIcCHn_0DwISL1g3yhZmrgkHZCLWUneIagljavd5u9fBRdgb9YKCyTz_vMv5px953UCoOx10MVy9bXt0T0nUONJIPcLV_BFOzAumoWez-Q4qjMWaSI8k6EtJJxMpNMkUabdn_oHHKz5y1SHXVV-MJmBZ_hYICB7C8e2Qeb_t0YuOaQAyCsVKAwf5pj1UFtibJXhHGo0O6Tg=",
"id": "rs_051a8a0b2fb58918016a149bdee73481918ad1aef6d6d14c2e",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"description\": \"Design, generate, review, publish, and optimize automated short-form social videos across YouTube Shorts, TikTok, Instagram Reels, and related channels.\", \"tags\": [\"shorts\", \"tiktok\", \"youtube-shorts\", \"reels\", \"creator-monetization\", \"content-automation\", \"social-media\"], \"related_skills\": [], \"content\": \"---\\nname: social-media-shorts-automation\\ndescription: Design, generate, review, publish, and optimize automated short-form social videos across YouTube Shorts, TikTok, Instagram Reels, and related channels.\\nversion: 1.0.0\\ntags: [shorts, tiktok, youtube-shorts, reels, creator-monetization, content-automation, social-media]\\n---\\n\\n# Social-Media Shorts Automation\\n\\nReference note: see `references/controlled-pilot-production-v2.md` for the controlled first-video workflow: resource tiers, media-generation gates, pilot package shape, Wan prompt planning without generation, and no auto-posting. See `references/pilot-preview-render-v2.md` for the next approval step: `APPROVED_FOR_PREVIEW_RENDER`, EdgeTTS preview audio, time/word cue generation, deterministic 9:16 animatic MP4, checksums, and Telegram media delivery without Wan/AI-image/platform side effects. See `references/static-active-word-captions-and-final-pilot-render.md` for the corrected caption style and controlled final pilot render pattern: static 3–7 word phrase segments with only the active spoken word highlighted, hash-bound final render gates, one Wan text-free background layer, deterministic overlays, and draft-only manual posting packages. If a final render is rejected as preview-overlay-dominated or not visual-first, follow `references/visual-first-final-render-repair.md`: mark the render rejected/not-postable, fix Wan output parsing, enforce final overlay limits, produce only a short visual proof under `APPROVED_FOR_VISUAL_PROOF`, and do not run another full final until the visual direction is accepted. If even the visual proof is rejected as abstract/generic/dark or “blind T2V”, switch to `references/keyframe-first-final-visuals.md`: plan and approve start/end/style keyframes first, then run only a short I2V/first-last-frame proof with minimal renderer-owned overlays. If the user says the production method itself is wrong, keyframes are not I2V-ready, or an animatic was incorrectly substituted for a failed Wan proof, follow `references/visual-production-reset-i2v-first.md`: reject/audit the proof, stop content rendering, run technical I2V sanity first, then generate at most three styleframes for direction review. If deterministic layout proofs are useful as composition blueprints but rejected as too wireframe/PowerPoint for final style, switch to `references/premium-ai-styleframe-direction.md`: use the layouts only as mechanism blueprints, generate at most 3 tightly briefed premium text-free AI styleframes, deliver a contact sheet with verified media metadata, and keep Wan/I2V/endframes/full-final blocked until style direction approval. If those premium styleframes are better quality but still too abstract, switch to `references/real-life-premium-styleframes.md`: anchor the mechanism in a realistic work/meeting/desk scene, keep all readable overlays renderer-owned, generate at most 3 new real-life styleframes plus contact sheet, and still block Wan/I2V/endframes/full-final until explicit approval. If the user approves one or more real-life styleframe directions but wants to compare A/B/C before Wan, use `references/prerelease-animatic-preview.md`: build only a small AI-keyframe + deterministic-motion animatic per approved direction, reuse existing voiceover/captions, deliver MP4/contact/QA sheets with metadata, and keep Wan/I2V/final/posting blocked. If the user then rejects the renderer-added circles/arrows/labels/boxes/decision-target markers as destroying the premium look, switch to `references/clean-image-cut-no-overlay-pilot.md`: render only AI images + voiceover + clean subtitles, with a hard subtitles-only NoOverlayPolicy and no Wan/I2V/full-final/posting. If the user performs a strategic reset because the pilot is pretty but semantically weak, stop optimizing that candidate and follow `references/proof-short-real-problem-reset.md`: archive the old pilot as a learning case, enforce the Pretty Empty Visual Blocker, and build a screen/mockup-led Proof Short around an immediately visible real viewer problem before any premium/Wan production. If the next review focuses on image provider quality/provenance or subtitles running off-screen, follow `references/image-provider-audit-and-caption-safezone.md`: audit the configured image provider/model/tier from config + provider registry + cache metadata, run at most one neutral capability test, keep UI/invoice mockups deterministic, and add tested caption layout safe-zone bounds before re-rendering. If an approved Proof Short feels too visually flat and the user asks why no AI images were used, follow `references/proof-short-ai-visual-upgrade.md`: use AI images as a controlled text-free atmosphere/background/keyframe layer while keeping invoices, emails, payment routes, labels, facts, and captions deterministic renderer-owned. For the concrete rendering/QA pattern — small 2–3 keyframe pass, contact-sheet inspection, discard pseudo-text frames, blur/darken/subordinate AI backgrounds, and report used/discarded keyframes — see `references/proof-short-ai-background-rendering-qa.md`.\\n\\nUse this skill when building or operating systems that generate short-form social videos, especially faceless or semi-automated pipelines for YouTube Shorts, TikTok, Instagram Reels, Facebook Reels, Pinterest video pins, X video, or LinkedIn video.\\n\\n## Core principle\\n\\nTreat the system as a **Shorts Growth Engine** / **semi-automatic Retention Studio**, not merely a renderer. A working video generator can still fail if it produces generic, low-retention, AI-slop content. Optimize for audience identity, hook quality, retention mechanics, visual mechanism reveals, platform fit, and analytics feedback. For the user's strongest strategic direction, see `references/retention-studio-strategy.md`.\\n\\nFor this user's AutoShorts workflows, approval previews should be German for concept comprehension, while final social-media videos should remain English unless explicitly changed. Treat preview legibility as a quality gate: readable font sizes, pixel-width-aware line wrapping, no clipped words, and no overcrowded cards.\\n\\nFor the user's TrueTraceShorts / AutoShortsBot strategy, do **not** default to a narrow AI/prompt-tips channel. The current strategic direction is broader: explain hidden digital everyday mechanisms — AI, work, attention, decisions, scams, productivity, workflows, social search — and end each video with one small system rule that fixes the outcome. Use the frame `Trace the hidden system. Fix the outcome.` AI should remain an important pillar, but normally only about 30–40% of the topic mix, not the whole product. See `references/truetrace-strategic-neuausrichtung.md`.\\n\\nWhen the user asks to start implementation work on this strategy, especially “Sprint 1: Strategic Spine Refactor”, follow `references/truetrace-strategic-spine-refactor-v2.md`: implement a side-effect-free V2 spine in parallel to existing V1 models, with mandatory strategic fields, hard quality gates, anti-AI-slop blockers, hash/version-bound ReviewPackageV2, and tests before integration with renderers or platform workflows.\\n\\nWhen the user asks for “Sprint 1.5” or to make the V2 spine operational without production, follow `references/truetrace-v2-operational-bridge.md`: first secure/commit the Sprint-1 baseline, then add only minimal side-effect-free bridges (`to_candidate_v2`, `workflow_v2`, `demo_review_batch_v2`), deterministic ReviewPackageV2 JSON, strict approval parsing, calibrated non-generous scoring, anti-example/human-texture gates, minimal manual claim/disclosure stubs, LinkedIn manual metadata, and a Remotion-as-later-spike note. Keep it capped at 3 demo candidates and avoid rendering, platform APIs, dashboards, auto-posting, or 30-day batches.\\n\\n## Retention-Studio / Mechanism-Reveal Pipeline\\n\\nFor quality-first automated Shorts, especially Hidden Money & AI Systems concepts, prefer the pipeline documented in `references/retention-studio-pipeline-pattern.md`:\\n\\n```text\\nstrategy → scored ideas → mechanism explainer → shot plan → keyframe/I2V prompt plan → seeded clip jobs → clip review → deterministic final renderer\\n```\\n\\nWhen implementing a new repo or core pipeline, first scaffold the approval-first typed artifact chain in `references/approval-first-retention-studio-core.md`:\\n\\n```text\\nContentPillar → ContentBrief → ScriptDraft → VideoCandidate → TestBatch → ReviewBatch → Telegram ReviewDelivery → ShotPlan\\n```\\n\\nHard rule for this class: AI-video clips provide photorealistic texture and motion only. Captions, numbers, labels, arrows, UI text, price/risk/margin layers, and factual claims are renderer-owned. Final content should keep `static_card_limit = 0`, use visual changes every 1–2 seconds, and reject technically successful clips that do not serve the retention beat.\\n\\nBefore video generation, build an inspectable content-to-review spine: `ContentBrief → ScriptDraft → CandidateDraft → VideoCandidate → TestBatch → ReviewBatch → Telegram ReviewDelivery`. Keep it deterministic, side-effect free, and human-approval-first so hooks, retention beats, visual concepts, policy notes, and review copy can be optimized before spending GPU/API time. See `references/content-to-review-pipeline.md` for the implementation pattern and guardrails.\\n\\nHard rule for this class: AI-video clips provide photorealistic texture and motion only. Captions, numbers, labels, arrows, UI text, price/risk/margin layers, and factual claims are renderer-owned. Final content should keep `static_card_limit = 0`, use visual changes every 1–2 seconds, and reject technically successful clips that do not serve the retention beat.\\n\\n## Recommended workflow\\n\\n1. **Define channel position**\\n - Niche(s): e.g. life optimization, AI life systems, Christian faith/FaithTok.\\n - Target audience and emotional problem.\\n - Language and tone.\\n - Whether the brand is faceless, AI-persona-led, or creator-led.\\n - No-go topics and theological/ethical boundaries if faith-related.\\n\\n2. **Generate test ideas before code-heavy automation**\\n - Create 20–30 candidate ideas across 2–4 content pillars.\\n - For each: hook, script kernel, visual concept, caption, CTA, risk/quality score.\\n - Select a small first batch (e.g. 3 per pillar) for real testing.\\n - Before renderers or external AI APIs, add a deterministic content-development core: `ContentPillar → ContentBrief → ScriptDraft → CandidateDraft → VideoCandidate`. See `references/content-development-core.md`.\\n\\n3. **Use hook-first, retention-led scripting**\\n - First 1–2 seconds must contain a clear tension, identity statement, pain point, contrarian line, or immediate self-recognition.\\n - Prefer one idea per video over generic “4 tips” unless the list format is the explicit series.\\n - Avoid generic advice viewers have already heard unless framed with a new angle, concrete payoff, or strong story.\\n - For TrueTraceShorts, prefer the structure `visible fail → identification → mechanism → fix → before/after → memorable takeaway` over generic AI-tip narration. Every video must answer: what goes wrong, why it happens, what rule fixes it, what sentence sticks, why viewers save/share it, and why they follow the series.\\n - For unvalidated first pilots, apply the `Pretty Empty Visual Blocker`: if the first frame is beautiful but does not show a concrete viewer pain without voiceover, block the concept and switch to a Proof Short. Do not keep polishing abstract AI visuals, glass metaphors, or generic laptop B-roll before validating the real problem. See `references/proof-short-real-problem-reset.md`.\\n - After a Proof Short concept is approved for usefulness/clarity, do not interpret `ProofShortMode` as a permanent ban on AI images. If the user wants the video “aufgepeppt”, add a controlled AI visual-upgrade layer: 2–3 text-free premium backgrounds/keyframes, while all invoice/email/UI/payment-route text, labels, facts, captions, claims, and red-flag overlays remain deterministic renderer-owned. See `references/proof-short-ai-visual-upgrade.md`.\\n - Reward hooks with direct address, specificity, open loops, tension, and a visible payoff; reject slow intros such as “In this video...”.\\n - See `references/retention-led-shorts.md` for scoring signals, penalties, and voiceover finalization rules.\\n\\n4. **Quality gate before rendering**\\n Score drafts on:\\n - hook strength\\n - novelty\\n - emotional pull\\n - clarity\\n - retention risk\\n - comment/share potential\\n - AI-slop risk\\n - platform/policy risk\\n - first-frame clarity\\n - mechanism value\\n - practical payoff\\n - save/share/follow reason\\n - trust/human texture\\n - series fit and saturation defense\\n Render only drafts above the chosen threshold, e.g. 8/10.\\n For TrueTraceShorts, use the 100-point scoring and hard blockers in `references/truetrace-strategic-neuausrichtung.md`: block generic AI hooks, pure text first frames, unsourced claims, missing before/after, missing human texture, unclear AI disclosure, and candidates too similar to recent videos.\\n\\n5. **Visual strategy**\\n - Avoid obvious AI artifacts, fake UI text, illegible generated lettering, generic charts, and soulless stock visuals.\\n - Prefer high-contrast kinetic captions, visible hook text in first seconds, relatable B-roll, screen recordings for AI/tutorial content, phone/screen close-ups, before/after transformations, cards, and timer visuals.\\n - Use pattern interrupts every 2–3 seconds for retention.\\n - Before rendering, generate a shot plan from the finalized voiceover: first-frame hook, pattern interrupt, core explanation, screen/card visual, CTA, caption beats, and asset type.\\n - Before writing a renderer, convert shot plans into deterministic render manifests: machine-readable timeline items, asset placeholders, caption tracks, style constraints, and approval constraints. See `references/render-manifest-pipeline.md`.\\n - Treat this as a deterministic intermediate artifact, not optional prose. See `references/retention-render-planning.md` for the five-scene shot-plan pattern and renderer-facing fields.\\n - For the first video output, build a manifest-driven preview renderer before any AI-video or polished asset pipeline: first create a side-effect-free local preview plan, then write deterministic PNG scene cards, then build a side-effect-free FFmpeg concat plan, and only then call FFmpeg from an explicit renderer boundary. The boundary should report side effects such as `write_png`, `write_concat`, `call_ffmpeg`, and `write_mp4`; keep generated PNG/MP4 artifacts out of Git. See `references/manifest-preview-renderer.md`.\\n - When the user rejects static/slideshow output, add an `asset_plan.v2` layer that maps each scene to motion-led local asset modes such as `cinematic_ai_video`, `screen_recording_simulation`, `mechanism_animation`, or `kinetic_text_overlay` with no baked text. If the user requires a free workflow, do not depend on paid video-credit tools; use local procedural motion and optional free NVIDIA LLM text refinement. See `references/ai-video-asset-planning.md`.\\n - For hybrid workflows, add an imported-clip assembly layer: provider handoff prompts create short manual AI-video clips, humans drop them into deterministic `data/imported_ai_clips//scene_XX.mp4` paths, and the final renderer combines imported clips with local mechanism animations/captions. See `references/imported-ai-clip-assembly.md`.\\n - For local Wan2.2 quality workflows, prefer keyframe/image-to-video over raw text-to-video: generate/select a clean keyframe, run native Wan2.2 I2V variants, review clips bluntly for subject clarity/motion/artifacts, then add all labels/numbers/captions via deterministic renderer. See `references/wan-i2v-retention-studio.md`.\\n - For final renders, Wan must carry the visual scene, not merely provide a blurred/looped background underneath preview cards. Use full-bleed, scene-specific Wan clips, minimal renderer-owned overlays, and a final overlay policy that blocks preview frames, large UI cards/textboxes, debug bars, and overlay overload. If architecture is rejected, create a short visual proof first; see `references/visual-first-final-render-repair.md`.\\n - If a visual proof still looks like blind text-to-video or random abstract AI output, stop T2V and move to a keyframe-first workflow: generate/approve 1–2 text-free start/end/style keyframes for the scene, then attempt only a short Wan I2V/first-last-frame proof. See `references/keyframe-first-final-visuals.md`.\\n - When using NVIDIA Build/API Catalog for keyframes, prefer hosted `ai.api.nvidia.com` calls before considering self-hosted NIM deployment; implement a configurable model fallback chain, store the key as a runtime secret, and inspect/clean logos, emblems, license plates, and fake text before I2V. See `references/nvidia-keyframe-generation.md`.\\n\\n6. **Social-media draft and content-preview approval packages before TTS/rendering polish**\\n - Before TTS, platform APIs, or polished video generation, build a typed `SocialMediaDraft` from the approved candidate plus render manifest/preview.\\n - Include platform targets, title variants, caption, hashtags, CTA, hook, duration, quality/risk summary, and preview reference.\\n - Render this into a Telegram-safe approval message and wrap it in a side-effect-free delivery plan with `requires_human_approval=True` and `side_effects=()`.\\n - After a local MP4 timing preview exists, combine the MP4 path plus social draft review into a side-effect-free content preview approval package. This package should carry `approval_language=de`, `final_video_language=en`, explicit approval commands, no external calls, and no side effects.\\n - Add local demo CLIs that print metadata first, then review text; draft-only CLIs must not write files, call renderers, call Telegram, or access credentials. MP4 preview CLIs may write local artifacts and call FFmpeg only at explicit renderer boundaries that report side effects.\\n - See `references/social-draft-approval-package.md` and `references/content-automation-patterns.md` for concrete artifact sequence, user-specific language rules, and external workflow patterns.\\n\\n7. **Human approval loop before posting**\\n - Send preview to the user through the requested channel, usually Telegram.\\n - Include: video or preview reference, title, caption, hashtags, platform recommendation, duration, quality/risk score.\\n - When sending multiple preview videos, verify and label distinct artifacts before delivery: candidate ID/title, absolute path, duration, and preferably checksum/hash. If several previews are visually similar timing cards, do not spam them as separate unlabeled media; send a concise indexed list first or bundle with clear labels so the user can tell them apart.\\n - Wait for explicit approval such as `Freigabe alle`, `Freigabe YouTube`, `Freigabe TikTok`, `Ablehnen`, or `Ändern: ...`.\\n - Do not publish automatically unless the user has explicitly authorized that workflow.\\n\\n8. **TTS / voice layer after draft approval**\\n - Treat TTS as a later layer, not the starting point for a first post draft.\\n - Decide voice, final voiceover script, words-per-second, scene timing, caption sync, audio format, provider, and separate voice approval only after the social draft package is reviewable.\\n - This avoids spending TTS/rendering effort on unapproved hooks, captions, or platform positioning.\\n - For final-near previews, keep one copy source of truth: final voiceover → script draft/retention beats → shot plan → top card text → scene captions → subtitle track → TTS audio. Do not mix old approval-card text with new spoken/subtitle text.\\n - If the user says the result is too abstract/abgehoben, rewrite around a concrete beginner-friendly everyday failure example before polishing visuals. Prefer “one weird email arrives” / missing field / unclear request / wrong confident action over jargon such as `exception path`, `input boundary`, or `output standard`. See `references/beginner-friendly-audio-caption-alignment.md`.\\n - If the user says subtitles are irritating or not simultaneous with voiceover, treat this as a blocking quality issue: use forced alignment or simplify captions before sending another final-near clip. For this user's AutoShorts/TrueTraceShorts default, do **not** show one word alone and do **not** slide a changing word-window every word. Use static phrase segments: keep 3–7 words fixed on screen while only the currently spoken word highlights/pulses left-to-right; replace the full segment only at a sentence/phrase boundary. See `references/static-active-word-captions-and-final-pilot-render.md`.\\n - If deterministic layouts explain the mechanism but look like wireframes/PowerPoint, do not promote them to final style. Treat them as composition blueprints and run a small, tightly prompted premium AI styleframe pass instead: AI supplies glassmorphism/product-film quality and atmosphere; the renderer still owns labels, arrows, captions, facts, and final assembly. See `references/premium-ai-styleframe-direction.md`.\\n - If premium AI styleframes improve quality but still feel like abstract SaaS symbolism, do not continue iterating abstract funnels/rings. Move to real-life anchored work scenes: desk/laptop, empty meeting room/glass board, or project table/work evidence, with only subtle glass/holographic mechanism overlays. See `references/real-life-premium-styleframes.md`.\\n - If real-life styleframe directions are accepted but the user has not approved Wan/I2V yet, insert a pre-release animatic comparison step rather than jumping to endframes or video generation. Create small per-direction AI keyframe sets, deterministic push-ins/crossfades, existing voiceover, static active-word captions, contact sheets, and QA frame sheets; report Telegram delivery metadata. See `references/prerelease-animatic-preview.md`.\\n - If the user rejects added visual explanation overlays as making the result look like a technical explainer board, treat this as a hard style failure. For the clean pilot, use only AI images, voiceover, and clean subtitles; block circles, arrows, labels, boxes, connector lines, decision-target markers, debug/diagram elements, and caption boxes/bars. See `references/clean-image-cut-no-overlay-pilot.md`.\\n - For mechanism-reveal final renders, use the hybrid pattern in `references/final-motion-hybrid-rendering.md`: ChatGPT Image/Codex or similar tools create text-free scene backgrounds only; deterministic renderer owns cards, labels, arrows, subtitles, and FFmpeg assembly. Use compact phrase-boundary subtitle cues before 1080 export.\\n\\n9. **Publish and measure**\\n Track at minimum:\\n - platform, video id/url, niche, format, hook, duration\\n - views at 2h/24h/7d\\n - likes, comments, shares, saves, follows\\n - retention metrics if available\\n Use results to generate the next batch.\\n\\n## Platform duration/monetization notes\\n\\nSee `references/preview-media-delivery-guardrails.md` for avoiding duplicate-looking/unlabeled preview-video spam in Telegram review workflows.\\n\\nSee `references/truetrace-strategic-spine-refactor-v2.md` for implementing the new TrueTraceShorts strategy in code: V2 strategic models, hard gates, anti-AI-slop blockers, SeriesRegistry, 100-point scoring, hash-bound ReviewPackageV2, and deterministic five-candidate examples without rendering or platform side effects. See `references/truetrace-v2-operational-bridge.md` for the next implementation step: secure the Sprint-1 commit, add minimal side-effect-free bridge/workflow/CLI modules, deterministic ReviewPackageV2 JSON, strict approval parsing, calibrated scoring, anti-example/human-texture gates, manual claim/disclosure stubs, LinkedIn manual metadata, and Remotion-as-later-spike documentation without production expansion.\\n\\nSee `references/audio-caption-preview-pipeline.md` for the approval-first EdgeTTS + ASS subtitles + FFmpeg review-MP4 pipeline, including actual-audio-duration probing and the explicit `preserve_video` vs `trim_to_audio` duration-mode guardrail. See `references/pilot-preview-render-v2.md` for the stricter first-pilot preview pattern: preview-only approval state, EdgeTTS sentence SRT to preview word cues when forced alignment is unavailable, deterministic card/diagram animatic rendering, SHA256/duration verification, and Telegram media delivery while Wan/AI-image/platform calls remain blocked. See `references/static-active-word-captions-and-final-pilot-render.md` for the corrected Hormozi-style caption behaviour and the one-render final pilot review-package checklist.\\n\\nSee `references/final-motion-hybrid-rendering.md` for the final-near hybrid renderer pattern: ChatGPT Image/Codex or other AI tools provide text-free background/keyframe texture while deterministic renderer overlays own text, arrows, labels, captions, and final assembly. For quick prototypes, prefer ChatGPT Image/Codex backgrounds before local Qwen/ComfyUI unless privacy/cost/local-only constraints dominate. After a 1080 export, create a side-effect-free final approval package with media path, SHA256, platform metadata, social copy, quality notes, and approval commands before any delivery or platform step.\\n\\nSee `references/visual-first-final-render-repair.md` for the repaired final-render architecture after a rejected pilot: mark rejected renders as not-postable, avoid preview-board overlays, enforce `FinalOverlayPolicy`, validate ComfyUI/Wan output histories robustly, and use `APPROVED_FOR_VISUAL_PROOF` for one short visual proof before any second full final.\\n\\nSee `references/hybrid-scene-backgrounds-codex.md` for the concrete ChatGPT Image/Codex scene-background workflow: side-effect-free `SceneBackgroundPlan`, per-scene text-free backgrounds, renderer-owned overlays, and visual QA before review delivery. Prefer this over local Qwen/ComfyUI when the user allows Codex image generation and local GPU should be reserved for video/model work.\\n\\nSee `references/monetization-and-approval-notes.md` for current working notes captured from official YouTube/TikTok docs and the recommended approval/posting setup. See `references/retention-led-shorts.md` for retention scoring signals, no-faith/adjacent-pillar handling, and voiceover finalization rules. See `references/render-manifest-pipeline.md` for the script → shot plan → render manifest → renderer sequence that prevents generic AI slideshow output. See `references/manifest-preview-renderer.md` for the first deterministic Pillow/FFmpeg preview-renderer pattern. See `references/local-preview-frame-writer.md` for the staged `LocalPreviewPlan → PNG scene cards → FFmpeg concat plan` boundary before MP4 rendering. See `references/social-draft-approval-package.md` for the typed first-post approval package to build before TTS or platform APIs. See `references/content-automation-patterns.md` for public workflow patterns, queue/status/cost tracking, versioned approval, synthetic-content disclosure, originality gates, and the user's German-preview/English-final rule. See `references/ai-video-asset-planning.md` for motion-led final-render asset planning with Kling/Hailuo/Runway-style clips and screen simulations. See `references/imported-ai-clip-assembly.md` for hybrid assembly where manually generated provider clips are imported into a deterministic local renderer. See `references/nvidia-keyframe-generation.md` for NVIDIA-hosted keyframe generation, model fallback, secret handling, and pre-I2V logo/plate cleanup. Re-check official docs before making business-critical decisions because platform programs change often.\\n\\n## Project/repo hygiene for automated video bots\\n\\n- Keep source code in Git; keep generated videos, assets, `.env`, OAuth tokens, API keys, and downloaded secrets out of Git.\\n- Use `.gitignore` aggressively for outputs, media caches, local credentials, and temp files.\\n- Store platform credentials as runtime secrets; never print raw tokens.\\n- Build the repo as modular components: idea generation, scripting, rendering, review, publishing, analytics.\\n- For approval-first Retention Studio implementations, use a typed side-effect-free core before real I/O: `ContentBrief`, `ScriptDraft`, `VideoCandidate`, review batches, Telegram delivery plans, then shot plans. See `references/approval-first-retention-studio-core.md`.\\n\\n## Sensitive-content positioning\\n\\nWhen AI/productivity automation is the primary brand, be cautious about mixing in religious/FaithTok, health, finance, or other high-trust themes. If the user flags the combination as sensitive, pause that pillar rather than forcing it into the same testbatch. Replace it with a safer adjacent pillar (for example `attention_design`) and document the paused pillar in config so it can be revisited only with explicit approval and a separate brand strategy.\\n\\n## Pitfalls\\n\\n- Do not send several generated preview videos as unlabeled media attachments just because they are distinct files. Telegram/mobile previews can make timing-card MP4s look identical. Verify uniqueness (path + title + hash/duration) and provide labels or an indexed summary; if the user complains about duplicate-looking media, stop resending, verify artifacts, and continue the pipeline.\\n- Do not let final-near preview layers drift apart: if the top field, voiceover, and subtitles do not say the same thing, rebuild the render plan from one final script source before sending another clip.\\n- Do not make broad-audience AI-system shorts sound like architecture lectures. For early-AI users, convert abstract workflow concepts into concrete everyday failures first, then reveal the principle.\\n- Do not over-optimize renderer quality before testing whether the content format earns retention.\\n- Do not keep iterating a polished pilot when the user identifies the core failure as “pretty but semantically weak.” Archive it as a learning case, preserve what worked, and restart with a Proof Short whose first second shows a real visible fail and an immediately useful rule.\\n- Do not overcorrect from “validate with Proof Shorts” into “never use AI images.” Once the real problem/rule is approved, AI images can legitimately improve perceived quality as text-free atmosphere, backgrounds, keyframes, or thumbnails. Keep factual UI/document/payment layers deterministic; use AI for polish, not truth.\\n- Do not let German approval previews become unreadable technical cards: use pixel-width-aware wrapping, readable fonts, limited line counts, visual checks for clipped/overcrowded text, and hard mobile safe-zone tests for captions/highlights before delivery.\\n- Do not confuse approval language with final audience language. For this user, approval previews are German by default; final social videos remain English unless explicitly changed.\\n- Do not copy public automation workflows wholesale: keep their queue/status/cost tracking and template structure, but remove blind auto-publishing until a human approval/version lock exists.\\n- Do not mass-generate repetitive shorts without originality/inauthentic-content gates; this can harm monetization/account health and create AI slop.\\n- Do not jump directly from a script idea to ComfyUI/Wan/Qwen/Image/video generation. First build and inspect the content-to-review spine so weak hooks, generic scripts, policy issues, and static visual concepts are killed before render time.\\n- Do not assume local Qwen/ComfyUI is the best first image step for every final-near short. If the user permits ChatGPT Image/Codex, use it for text-free scene backgrounds/keyframes when the deterministic renderer owns labels/captions and local GPU should be saved for video/model work. When provider quality matters, verify the actual `image_gen.provider`/model from config and the image cache filenames/metadata rather than guessing; for premium styleframes prefer the highest available reasonable GPT Image tier, but keep fake invoice/email/UI/payment-route mockups deterministic.\\n- Do not create a parallel candidate path for content experiments; convert content artifacts into the existing candidate factory input so IDs, hashtags, duration classes, quality gates, and pillar/platform validation stay centralized.\\n- Do not use `x or default` for optional content/script overrides in factories; explicit blank strings and zero durations must pass through to validation so tests can catch them.\\n- Do not assume TikTok monetization rules match YouTube: TikTok Creator Rewards emphasizes 1min+ eligible videos, while shorter videos may still be better for growth.\\n- Do not treat a keyframe animatic as a successful Wan/I2V proof. If ComfyUI/Wan I2V fails or history contains no valid video output, label any fallback MP4 as `not_wan` / composition-review-only and block full-final progression.\\n- Do not treat deterministic layout proofs as the final premium visual style when the user asked for a high-end social-video look. Layouts are for mechanism composition; after approval, use a tightly scoped premium AI styleframe pass with strict negative prompts and verified delivery before endframes/Wan.\\n- Do not mistake premium abstract glassmorphism for an approved final direction if the user wants a credible everyday work scene. When the user says the motif is still too abstract, switch to real-life work-scene styleframes with laptop/tablet/meeting-room/project-table anchors; keep motion graphics subtle and renderer-owned.\\n- If the user rejects the production method itself, do not keep iterating content visuals. Reject/audit the proof, run a technical I2V sanity test with a trivial non-content image, and only after it passes generate a small set of styleframes for direction review; see `references/visual-production-reset-i2v-first.md`.\\n- Do not keep trying blind text-to-video after the user rejects a proof as abstract, dark, generic, or semantically ungrounded. Move to keyframe-first planning, review the keyframes, then run at most one short I2V/first-last-frame proof.\\n- Do not publish religious or health-adjacent content with overconfident claims; preserve humility, nuance, and platform safety.\\n- Do not rely on platform payout as the only monetization path; plan indirect monetization such as newsletter, templates, affiliates, digital products, or services.\", \"path\": \"social-media/social-media-shorts-automation/SKILL.md\", \"skill_dir\": \"/home/agent/.hermes/skills/social-media/social-media-shorts-automation\", \"linked_files\": {\"references\": [\"references/wan-i2v-retention-studio.md\", \"references/render-manifest-pipeline.md\", \"references/retention-studio-strategy.md\", \"references/premium-ai-styleframe-direction.md\", \"references/social-draft-approval-package.md\", \"references/static-active-word-captions-and-final-pilot-render.md\", \"references/approval-first-retention-studio-core.md\", \"references/local-preview-frame-writer.md\", \"references/visual-first-final-render-repair.md\", \"references/preview-media-delivery-guardrails.md\", \"references/manifest-preview-renderer.md\", \"references/proof-short-real-problem-reset.md\", \"references/truetrace-strategic-neuausrichtung.md\", \"references/content-development-core.md\", \"references/ai-video-asset-planning.md\", \"references/approval-first-content-pipeline.md\", \"references/controlled-pilot-production-v2.md\", \"references/keyframe-first-final-visuals.md\", \"references/clean-image-cut-no-overlay-pilot.md\", \"references/proof-short-ai-visual-upgrade.md\", \"references/beginner-friendly-audio-caption-alignment.md\", \"references/audio-caption-preview-pipeline.md\", \"references/pilot-preview-render-v2.md\", \"references/truetrace-strategic-spine-refactor-v2.md\", \"references/retention-studio-pipeline-pattern.md\", \"references/real-life-premium-styleframes.md\", \"references/monetization-and-approval-notes.md\", \"references/visual-production-reset-i2v-first.md\", \"references/image-provider-audit-and-caption-safezone.md\", \"references/content-to-review-pipeline.md\", \"references/retention-led-shorts.md\", \"references/final-motion-hybrid-rendering.md\", \"references/prerelease-animatic-preview.md\", \"references/imported-ai-clip-assembly.md\", \"references/hybrid-scene-backgrounds-codex.md\", \"references/content-automation-patterns.md\", \"references/retention-render-planning.md\", \"references/proof-short-ai-background-rendering-qa.md\", \"references/nvidia-keyframe-generation.md\", \"references/truetrace-v2-operational-bridge.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\"}",
"tool_call_id": "call_y883g4F263LHVJFzJZSSNGi9"
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-media-shorts-growth-engine\", \"description\": \"Design and operate a growth-oriented short-form video engine for YouTube Shorts, TikTok, Instagram Reels, and adjacent channels, with human approval before posting.\", \"tags\": [\"shorts\", \"tiktok\", \"youtube-shorts\", \"reels\", \"content-strategy\", \"growth\", \"monetization\", \"approval-workflow\"], \"related_skills\": [], \"content\": \"---\\nname: social-media-shorts-growth-engine\\ndescription: Design and operate a growth-oriented short-form video engine for YouTube Shorts, TikTok, Instagram Reels, and adjacent channels, with human approval before posting.\\nversion: 1.0.0\\ntags: [shorts, tiktok, youtube-shorts, reels, content-strategy, growth, monetization, approval-workflow]\\n---\\n\\n# Social-Media Shorts Growth Engine\\n\\nUse this skill when the user wants to build, improve, or operate an automated/semi-automated system for short-form social media content: YouTube Shorts, TikTok, Instagram Reels, Facebook Reels, Pinterest, LinkedIn video, or similar.\\n\\n## Core principle\\n\\nDo **not** treat the task as “make videos.” Treat it as a **growth engine**:\\n\\n1. Generate many sharply positioned ideas.\\n2. Score hooks and scripts before rendering.\\n3. Produce previews.\\n4. Send the user a review package.\\n5. Post only after explicit approval.\\n6. Capture analytics.\\n7. Feed performance back into the next batch.\\n\\nA technically correct content generator that produces generic content is failure with extra rendering time. Charming, but still failure.\\n\\n### JARVIS-operated / human-approved default\\n\\nFor the user's AutoShorts/Retention-Studio direction, assume the machine is **operated and maintained by JARVIS/Hermes**. The user should not manually run the pipeline day-to-day; the user is responsible for explicit approval before posting and occasional strategic steering.\\n\\nOperational consequences:\\n\\n- JARVIS owns ideation, queueing, scoring, preview generation, quality gates, metadata generation, analytics review, maintenance, and experiment planning.\\n- Phase 1: the user manually uploads approved final videos to YouTube/TikTok; JARVIS provides the video file path plus platform-specific titles, descriptions/captions, hashtags, tags, and copy instructions.\\n- Phase 1 must not call platform APIs, upload, schedule, or post. The posting pack is a side-effect-free manual handoff.\\n- Later automation phases may upload/post only after explicit approval for the exact package/version.\\n- The user approves or rejects exact preview packages before any upload/posting boundary.\\n- Daily video volume is a configurable policy to decide later, not a renderer/platform-adapter constant.\\n- Never treat vague consent as approval. Approval must target the exact preview package/version.\\n- Build automation around strategy gates and analytics learning before scaling volume.\\n\\n## Recommended workflow\\n\\n### 1. Define content pillars\\n\\nStart with 2–4 pillars, not a vague infinite topic pool. For each pillar define:\\n\\n- audience\\n- positioning\\n- tone\\n- hook patterns\\n- visual rules\\n- no-go topics\\n- platform fit\\n- monetization angle\\n\\nExample pillar structure:\\n\\n```json\\n{\\n \\\"pillar\\\": \\\"ai_life_systems\\\",\\n \\\"positioning\\\": \\\"AI as a servant for ordinary life systems, never as values or authority.\\\",\\n \\\"tone\\\": [\\\"clear\\\", \\\"useful\\\", \\\"values-first\\\", \\\"non-hype\\\"],\\n \\\"hook_patterns\\\": [\\\"AI is a bad god, but a good servant.\\\"],\\n \\\"visual_rules\\\": [\\\"screen-recording friendly\\\", \\\"human remains in control\\\"],\\n \\\"no_go\\\": [\\\"fake earnings\\\", \\\"overpromising automation\\\"]\\n}\\n```\\n\\n### 2. Build a testbatch before building a full automation platform\\n\\nFor a new channel or unvalidated strategy, create a small batch first:\\n\\n- 3 ideas per pillar\\n- 6 short growth candidates, usually 20–45 seconds\\n- 1–3 monetization-length candidates, usually 60+ seconds where the platform rewards length\\n- one clear hypothesis per idea\\n\\nEach idea should include:\\n\\n- id\\n- pillar\\n- title\\n- platform target\\n- duration\\n- hook\\n- script outline\\n- visual concept\\n- caption\\n- CTA\\n- quality score\\n- risk/policy notes\\n\\n### 3. Add a script quality gate\\n\\nBefore rendering, score each draft for:\\n\\n- hook strength in the first 1–2 seconds\\n- novelty / non-generic angle\\n- emotional pull\\n- clarity\\n- retention risk\\n- comment/share potential\\n- AI-slop risk\\n- policy/copyright risk\\n\\nRender only drafts above the threshold, e.g. 8/10.\\n\\n### 4. Use a human approval loop\\n\\nDefault to semi-automatic operation first. Send a Telegram review package with:\\n\\n- preview video or script draft\\n- pillar and format\\n- title\\n- duration\\n- hook\\n- caption\\n- hashtags\\n- quality score\\n- policy notes\\n- suggested platforms\\n\\nRecommended approval commands:\\n\\n- `Freigabe alle`\\n- `Freigabe YouTube`\\n- `Freigabe TikTok`\\n- `Freigabe Instagram`\\n- `Ablehnen`\\n- `Ändern: `\\n\\nIf approval is ambiguous, do not post. Ask once in the project topic.\\n\\n### 4b. Phase-1 manual posting pack\\n\\nFor the user's current TrueTraceShorts phase, do not automate platform posting yet. After approval and final render, prepare a manual posting pack instead:\\n\\n- final video file path;\\n- YouTube title;\\n- YouTube description;\\n- YouTube hashtags;\\n- YouTube tags/keywords;\\n- TikTok caption;\\n- TikTok hashtags;\\n- platform-specific copy/paste instructions;\\n- explicit note that no platform upload was performed.\\n\\nThe pack must be side-effect-free: no platform API calls, no upload, no scheduling, no posting, no external calls. The user's phase-1 workload is manually uploading the approved file and copying the prepared metadata.\\n\\n### 5. Keep platform strategy separate from rendering\\n\\nRendering code should not hardcode content strategy. Keep separate config files for:\\n\\n- niches/pillars\\n- platforms\\n- script formats\\n- visual styles\\n- approval workflow\\n- analytics schema\\n\\nThis lets the same renderer support different formats and prevents prompt spaghetti. Prompt spaghetti is still spaghetti even if it is wearing a YAML hat.\\n\\n## Platform notes\\n\\n### YouTube Shorts\\n\\n- Shorts can be vertical or square and up to 3 minutes long.\\n- YouTube Partner Program Shorts route typically requires 1,000 subscribers and 10M valid public Shorts views in the last 90 days.\\n- Alternative longform YPP route: 1,000 subscribers and 4,000 valid public watch hours in the last 12 months.\\n- Shorts views in the Shorts feed do not count toward the 4,000 longform watch hours.\\n- Practical early growth tests often work best at 20–45 seconds; longer Shorts need a strong story or payoff.\\n\\n### TikTok\\n\\n- Creator Rewards availability depends on country/account eligibility.\\n- TikTok Creator Rewards generally requires a non-business account in good standing, 10,000 followers, and 100,000 authentic views in the last 30 days before joining, subject to country availability and current terms.\\n- Reward-eligible videos generally need to be at least 1 minute long and meet quality/originality criteria.\\n- This creates a strategy split:\\n - 20–45s for growth and format discovery.\\n - 60–75s for monetization candidates once a format works.\\n\\n### Instagram / Facebook Reels\\n\\nUseful for republishing 9:16 assets and testing share/save behavior. Treat direct payout as volatile; prefer indirect monetization through audience, affiliate, newsletter, or products.\\n\\n### LinkedIn / X / Pinterest\\n\\nUse selectively:\\n\\n- LinkedIn: AI/productivity/workflows.\\n- X: AI demos, build-in-public, technical positioning.\\n- Pinterest: evergreen checklists, routines, faith/life prompts.\\n\\n## Repository scaffold\\n\\nA clean shorts-engine repo can start as:\\n\\n```text\\nAutoShortsBot/\\n autoshorts/\\n config/\\n ideas/\\n scripting/\\n rendering/\\n review/\\n publishing/\\n analytics/\\n configs/\\n niches/\\n platforms/\\n data/\\n drafts/\\n performance/\\n scripts/\\n tests/\\n README.md\\n .gitignore\\n pyproject.toml\\n```\\n\\nNever commit:\\n\\n- `.env`\\n- OAuth tokens\\n- API keys\\n- generated credentials\\n- rendered videos or large media outputs unless explicitly intended\\n- raw analytics exports with sensitive account data\\n\\n## Implementation quality\\n\\nWhen coding the engine, prefer TDD for deterministic parts:\\n\\n- structured video candidate validation\\n- testbatch validation and duplicate-id checks\\n- renderable-candidate filtering before any renderer runs\\n- candidate factory conversion from raw drafts to validated `VideoCandidate` objects\\n- duration classification\\n- stable candidate-id generation and default hashtag derivation\\n- review formatting\\n- analytics import\\n- approval command parsing\\n- platform metadata generation\\n- script quality gates\\n\\nA strong first implementation path is deterministic gating before any renderer exists:\\n\\n1. Add structured `VideoCandidate` and `TestBatch` models before rendering code. Require candidate id, pillar, title, platforms, duration, hook, script outline, visual concept, caption, CTA, hashtags, quality score, policy notes, and one clear hypothesis.\\n2. Validate candidates and batches: reject missing strategic fields, unsupported platforms, out-of-range durations, empty batches, and duplicate candidate ids.\\n3. Add a `ContentPillar` registry and validate candidate pillar/platform fit before review or rendering.\\n4. Add a deterministic candidate factory: `CandidateDraft → create_candidate() → VideoCandidate`. It should generate stable ids, derive default hashtags, classify duration (`growth_short`, `monetization_candidate`, `experiment`), append the duration class to policy notes, require a hypothesis, and enforce both candidate and pillar-fit validation.\\n5. Add an approval parser that accepts only explicit commands such as `Freigabe alle`, `Freigabe YouTube`, `Freigabe TikTok`, `Freigabe Instagram`, `Ablehnen`, and `Ändern: `.\\n6. Treat vague consent like `passt schon` as `needs_clarification`; never publish on ambiguous approval.\\n7. Add a conservative script quality gate before rendering, e.g. average hook/novelty/clarity/retention ≥ 8, AI-slop risk below threshold, and no high policy risk.\\n8. Add a Telegram review package renderer that surfaces the candidate, gate status, policy notes, preview path, and only relevant platform approval commands.\\n9. Test these deterministic pieces first with RED-GREEN-REFACTOR before adding renderers, image generation, video generation, or publishing APIs.\\n\\nRendering and external API calls can be integration-tested separately.\\n\\nFor this AutoShortsBot/Retention-Studio workflow, prefer a free-first renderer path before any paid video provider: `free_production_jobs → local_motion_renderer → FFmpeg MP4`. The local renderer should use Pillow/FFmpeg procedural motion, mechanism layers, kinetic captions, and generated metadata; preserve exact scene durations from render manifests, exclude text-only LLM refinement jobs from rendering, and keep generated local renders out of git (`data/local_motion_renders/`). NVIDIA/build.nvidia.com LLMs are optional text-refinement helpers only, not video generation.\\n\\nWhen Hermes has the `openai-codex` image-generation backend available, GPT Image 2 is a good cloud-side keyframe/thumbnail/concept generator for the pipeline: `script idea → GPT Image 2 keyframe → human review → Wan/ComfyUI I2V or local renderer → deterministic captions/overlays`. Because GPT Image 2 runs cloud-side, it does not compete with local/remote GPU VRAM used by Wan/ComfyUI video jobs. Use low/medium for iteration and high for final keyframes; still add captions, labels, numbers, UI text, and audit-sensitive facts later in the deterministic renderer rather than trusting baked image text.\\n\\nIf the user wants more realistic footage without spending money, first check whether a local GPU/ComfyUI host is available. Preferred path when reachable: `scene spec → ComfyUI/Wan API over Tailscale → imported_ai_clips//scene_XX.mp4 → local captions/mechanism layers/FFmpeg assembly`. For a 16 GB A5000 Laptop GPU, use the `comfyui` skill reference `wan-video-tailscale-a5000.md`: Wan2.1 T2V 1.3B FP8, `--lowvram`, CPU text encoding, VAE tiling, and a small smoke-test ladder before quality probes. If no local GPU path is available or quality is insufficient, use the hybrid free-tier handoff rather than pretending local procedural graphics are realistic: `free_production_jobs → free_ai_video_handoff → manual browser generation in free-tier tools (PixVerse/Pika/CapCut/Hailuo only with existing free credits) → import clips under data/imported_ai_clips/ → local captions/mechanism layers/FFmpeg assembly`. Guardrails: no paid top-ups, no subscriptions, avoid Pro templates, no baked captions/logos/watermarks where possible, and keep imported clips out of git.\\n\\nFor this AutoShortsBot/Retention-Studio workflow, prefer a free-first renderer path before any paid video provider: `free_production_jobs → local_motion_renderer → FFmpeg MP4`. The local renderer should produce moving mechanism/caption previews, not final static cards. When the user has a capable local/remote GPU (e.g. RTX A5000 16 GB via Tailscale), promote the path to `ComfyUI/Wan or LTX local clip generation → imported_ai_clips → hybrid local renderer → FFmpeg`, with free web providers (PixVerse/Pika/CapCut) only as fallback. External free-tier AI video tools can still be used manually for realistic b-roll, but keep paid top-ups/subscriptions disabled and store downloaded clips under `data/imported_ai_clips//scene_XX.mp4`. Generate provider handoff packets for manual browser generation and imported-clip assembly plans so missing clips fall back to local placeholders.\\n\\n## JARVIS-operated content machine businessplan\\n\\nWhen the user asks how the content machine should operate as a business/process, frame it as a **JARVIS-operated, human-approved growth engine**. JARVIS owns ideation, scoring, scripting, preview generation, post metadata, queue maintenance, analytics review, and implementation upkeep. The user should only need to set high-level strategy occasionally and give explicit approval before posting.\\n\\nFor the current TrueTraceShorts setup, phase 1 is manual posting: JARVIS prepares the final video and the complete YouTube/TikTok metadata pack; the user manually uploads/copies it. Later automation may be designed, but only behind the same exact-version approval boundary. TrueTraceShorts should keep its name/handles for phase 1 but reposition around `Systems over prompts.` and mechanism-reveal AI workflow content; see `references/truetrace-branding-manual-posting.md` for the concrete channel description, TikTok bio, manual posting pack shape, and implemented module/API names.\\n\\nAlways describe the pipeline from idea to post with the approval boundary visible:\\n\\n```text\\nResearch -> Idea -> Strategy Score -> Script -> Quality Gate -> Preview -> Social Draft -> Approval Package -> Human Approval -> Final Render -> Manual Posting Pack -> User Manual Upload -> Analytics -> Next Batch\\n```\\n\\nThe plan should cover descriptions/captions, hashtags/tags, platform metadata, daily volume policy, branding, and what input is still needed from the user. See `references/jarvis-content-machine-businessplan.md` and `references/truetrace-branding-manual-posting.md` for condensed operating notes.\\n\\n## Strategy gates for follower conversion\\n\\nWhen designing or scoring candidates, optimize for the full viewer path:\\n\\n1. **Stop:** first 1–3 seconds create novelty, contradiction, visual anomaly, or a specific curiosity gap.\\n2. **Stay:** every 3–5 seconds opens or resolves a clear loop; fast cuts alone are not retention.\\n3. **Feel:** the candidate targets a concrete emotion such as relief, awe, frustration, identity pride, or amusement.\\n4. **Trust:** the video contains specificity, proof, tradeoffs, source-backed examples, or transparent reasoning.\\n5. **Follow:** the viewer can predict what future value this account will provide and why this worldview is distinct.\\n\\nPrefer fields/gates such as `hook_type`, `first_2_seconds`, `curiosity_gap`, `viewer_identity`, `target_emotion`, `share_reason`, `future_value_promise`, and `follow_reason` before rendering.\\n\\nUse **variety inside a stable promise**, not random topic hopping:\\n\\n- 70% proven repeatable formats\\n- 20% controlled variations\\n- 10% experiments\\n\\nStable: worldview, tone, visual grammar, quality standard, and audience promise. Vary: hook type, payoff type, emotional lane, examples, format family, and visual layer.\\n\\nGood initial public-safe series families for this user's JARVIS-operated content machine:\\n\\n- `AI System Autopsy` — problem → cause → system fix → result.\\n- `Prompt vs System` — fragile prompt hack vs repeatable system.\\n- `One Rule, One Example` — one principle demonstrated with one concrete use case.\\n- `AI Hype Court` — claim → evidence → verdict → better action.\\n\\nDo **not** assume AI-workflow content will work just because AI is popular. The user explicitly challenged this: the space is saturated, and generic AI tips are weak. Before rendering at scale, create a concrete 5-concept testbatch with hooks, outlines, visual mechanism plans, YouTube/TikTok metadata, and hypotheses so the user can judge whether the direction is actually promising. Treat the first batch as an experiment; if retention/follows are weak, pivot instead of defending the niche.\\n\\nAfter the user accepts a direction, make the next proof tangible: select the strongest 3 concepts and build local MP4 timing previews plus approval/manual-upload packages. Keep this as a side-effect-separated preview pipeline, e.g. `Candidate -> ScriptDraft -> ShotPlan -> RenderManifest -> LocalPreviewPlan -> PNG scene cards -> FFmpeg MP4 timing preview -> SocialMediaDraft -> ContentPreviewApprovalPackage -> ManualPostingPack`. Resolve preview output directories to absolute paths before creating FFmpeg concat plans to avoid relative-path duplication inside concat-file rendering. See `references/shorts-subtitles-tts-preview-packages.md`.\\n\\nHard no-go for public content: never make videos about JARVIS/Hermes, the user, their collaboration, private/behind-the-scenes material, politics, legally sensitive loopholes, rule-bypassing, private-data misuse, morally objectionable exploitation, or anything that could enable lawbreaking. JARVIS operation is an internal production model, not a public content angle.\\n\\n## Pitfalls\\n\\n- **Generic advice content:** “4 tips to be healthier/productive” is usually too weak unless the hook, identity, or story is sharp.\\n- **Generic AI tips positioning:** if a video could belong to any AI tips account, penalize it. Protect the differentiator: systems over prompts, transparent constraints, mechanism-first visuals, and safe public artifacts. Do not turn JARVIS/the user/the collaboration into public content.\\n- **Premature niche confidence:** when the user questions whether AI content is saturated, do not reassure vaguely. Produce concrete test concepts and hypotheses, then propose a small preview batch and analytics-based pivot criteria.\\n- **AI-image slop:** avoid generated images containing fake UI text, gibberish signs, distorted hands/faces, or abstract generic graphs. These damage trust fast.\\n- **Too much automation too soon:** validate scripts and formats before building posting APIs.\\n- **No analytics loop:** producing content without tracking retention, likes, shares, comments, and follows is blind output.\\n- **Format fatigue:** repetition creates familiarity, but identical hook/payoff/visual patterns across consecutive videos become template spam. Track recent similarity before scaling daily volume.\\n- **Mixed language drift:** decide language per channel or per pillar before rendering. Mixed English/German drafts are fine for ideation, not final voiceover unless intentional.\\n- **Baked caption text:** do not rely on AI-generated images/videos for subtitles, labels, UI text, or facts. Use renderer-owned captions/overlays so errors remain editable and brand-safe.\\n- **GPU contention from local TTS:** for early Shorts production, prefer non-GPU TTS such as EdgeTTS for the baseline while the GPU is needed for ComfyUI/Wan/Qwen image/video work. Treat NVIDIA Magpie or local TTS as A/B candidates, not defaults, until voice quality, cost, and operational reliability are proven.\\n- **Whisper confusion:** Whisper is STT/alignment/QA, not TTS. Use it later to verify spoken audio and subtitle timing; do not select it as the voice-generation model.\\n\\n## References\\n\\n- `references/autoshortsbot-case-study.md` — case-study details from the AutoShortsBot setup: first testbatch shape, repo scaffold, and approval loop.\\n- `references/approval-first-bot-foundation.md` — implementation pattern for the first safe bot slice: explicit approval parser, quality gate, Telegram review package, and TDD test shape.\\n- `references/idea-candidate-testbatch-foundation.md` — deterministic `VideoCandidate`/`TestBatch` foundation before rendering: validation rules, renderable filtering, and test shape.\\n- `references/content-pillar-registry-foundation.md` — strategic `ContentPillar` registry pattern: default `ai_life_systems`, pillar/candidate fit validation, and TDD test shape.\\n- `references/candidate-factory-foundation.md` — deterministic `CandidateDraft → create_candidate() → VideoCandidate` layer: stable ids, duration classes, default hashtags, hypothesis requirement, and tests.\\n- `references/jarvis-operated-content-machine.md` — session-derived strategy notes for a JARVIS-operated, human-approved content machine: hook/follower psychology, variety vs identity, series families, and next implementation gates.\\n- `references/jarvis-content-machine-businessplan.md` — business/process plan for a JARVIS-operated content machine: idea-to-post pipeline, minimal user role, approval boundary, metadata generation, daily volume policy, and strategy scoring gate.\\n- `references/truetrace-branding-manual-posting.md` — TrueTraceShorts-specific brand positioning and phase-1 manual posting handoff: YouTube description, TikTok bio, visual direction, metadata pack shape, and no-go boundaries.\\n- `references/truetrace-concept-testbatch.md` — concrete 5-concept TrueTraceShorts testbatch pattern for validating saturated AI-workflow positioning before rendering at scale.\\n- `references/shorts-subtitles-tts-preview-packages.md` — top-3 timing preview package pattern, FFmpeg relative-path pitfall, Hormozi-inspired renderer-owned captions, and EdgeTTS/Magpie/Whisper TTS guidance.\\n\", \"path\": \"social-media/social-media-shorts-growth-engine/SKILL.md\", \"skill_dir\": \"/home/agent/.hermes/skills/social-media/social-media-shorts-growth-engine\", \"linked_files\": {\"references\": [\"references/jarvis-content-machine-businessplan.md\", \"references/autoshortsbot-case-study.md\", \"references/candidate-factory-foundation.md\", \"references/truetrace-concept-testbatch.md\", \"references/jarvis-operated-content-machine.md\", \"references/idea-candidate-testbatch-foundation.md\", \"references/free-ai-video-workflow.md\", \"references/shorts-subtitles-tts-preview-packages.md\", \"references/content-pillar-registry-foundation.md\", \"references/approval-first-bot-foundation.md\", \"references/truetrace-branding-manual-posting.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\"}",
"tool_call_id": "call_E4lQXFe7CIZtSj2ESDpfbUx3"
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-shorts-growth-engine\", \"description\": \"Plan and build automated short-form video growth pipelines for YouTube Shorts, TikTok, Instagram Reels, and similar channels with retention-led ideation, human approval, and analytics feedback.\", \"tags\": [], \"related_skills\": [], \"content\": \"---\\nname: social-shorts-growth-engine\\ndescription: Plan and build automated short-form video growth pipelines for YouTube Shorts, TikTok, Instagram Reels, and similar channels with retention-led ideation, human approval, and analytics feedback.\\nversion: 1.0.0\\n---\\n\\n# Social Shorts Growth Engine\\n\\nUse this skill when building or improving systems that generate, review, render, or publish short-form social videos, especially automated/faceless pipelines for YouTube Shorts, TikTok, Instagram Reels, or cross-platform repurposing.\\n\\n## Core principle\\n\\nDo **not** treat the project as merely a video generator. Treat it as a growth engine:\\n\\n1. Research what the platform currently rewards.\\n2. Generate hypotheses for hooks/formats/niches.\\n3. Score ideas before rendering.\\n4. Produce reviewable drafts/previews.\\n5. Require human approval before posting.\\n6. Capture analytics and feed winners back into the next batch.\\n\\n## Default workflow\\n\\n1. **Load project constraints**\\n - Channel/topic/session boundaries.\\n - Existing code locations and repo.\\n - Secret-handling rules.\\n - User’s desired niches and no-go topics.\\n\\n2. **Research current platform rules**\\n - Prefer official/near-official sources: YouTube Help, TikTok Creator Academy/Terms, Meta docs.\\n - Record only durable rules in a concise reference file, not full scraped pages.\\n - Verify monetization details before recommending video lengths.\\n\\n3. **Define content pillars**\\n - Keep pillars distinct enough to measure.\\n - Avoid mixing sensitive identity topics with AI/automation unless the user explicitly wants that brand strategy.\\n - If the user says a pillar is “heikel”/sensitive, pause it in config rather than deleting it, with a reason and revisit condition.\\n\\n4. **Build a test batch**\\n - Start with 6–12 ideas, not dozens of rendered videos.\\n - Include a mix of growth candidates and monetization-length candidates.\\n - For TikTok Rewards experiments, include selected 61–75s candidates only after hook strength is high.\\n - For growth, prefer 25–45s candidates.\\n\\n5. **Score before rendering**\\n Score ideas on:\\n - direct self-relevance in first 1–2 seconds\\n - open loop\\n - specificity\\n - tension/contrarian angle\\n - concrete payoff\\n - visual pattern interrupt\\n - comment/conversation trigger\\n - niche authority\\n - policy/brand risk\\n\\n6. **Generate Telegram/human review packages**\\n Each draft/preview should include:\\n - title\\n - duration\\n - platform targets\\n - hook\\n - script draft or final voiceover\\n - visual concept\\n - caption/hashtags\\n - quality/retention score\\n - risks/policy notes\\n - approval commands\\n\\n7. **Do not auto-post until approved**\\n Use explicit approval commands such as:\\n - `Freigabe alle`\\n - `Freigabe YouTube`\\n - `Freigabe TikTok`\\n - `Freigabe Instagram`\\n - `Ablehnen`\\n - `Ändern: ...`\\n\\n8. **Analytics loop**\\n After posting, track at least:\\n - platform\\n - pillar/niche\\n - format\\n - hook\\n - duration\\n - views after 2h/24h/7d\\n - likes/comments/shares/follows\\n - retention/average watch time if available\\n\\n## Retention heuristics\\n\\nPeople tend to stop scrolling for:\\n\\n- **Immediate self-relevance:** “If your brain has 47 tabs open…”\\n- **Open loops:** “do this before…”, “why…”, “stop…”, “not…”\\n- **Specificity:** numbers, named tools/platforms, concrete situations.\\n- **Tension:** challenges a common belief without cheap outrage.\\n- **Concrete payoff:** template, prompt, before/after, exact step.\\n- **Visual pattern interrupt:** movement/change in the first seconds, not static AI art.\\n- **Conversation trigger:** specific question or keyword CTA.\\n- **Niche authority:** a recognisable point of view, not generic advice.\\n\\nReject or revise drafts with:\\n\\n- “In this video…” slow intros.\\n- generic “4 tips” without a fresh angle.\\n- pure slideshow/static visuals.\\n- abstract AI backgrounds that do not communicate the hook.\\n- AI-gibberish UI/text artifacts.\\n- broad advice with no visible payoff.\\n\\n## Monetization notes\\n\\nAlways re-check current official docs before major platform decisions. Current durable operating assumptions:\\n\\n- YouTube Shorts can be vertical/square and up to 3 minutes.\\n- YouTube Shorts YPP path has historically required 1,000 subscribers plus large valid Shorts-view thresholds in a recent period.\\n- TikTok Creator Rewards has historically rewarded original, high-quality videos longer than 1 minute and required account eligibility such as follower/view thresholds and good standing in selected countries.\\n- TikTok’s reward-eligible content should avoid low-quality patterns: copied/minimally altered work, meaningless reactions, blurry visuals, pure slideshows, clickbait without value, and policy-risky content.\\n\\nSee `references/retention-and-monetization-notes.md` for concise notes from the AutoShortsBot session.\\n\\n## Implementation patterns\\n\\nFor repositories that generate shorts:\\n\\n- Keep secrets, generated media, `.env`, and credentials out of Git.\\n- Store test batches as structured data under `data/drafts/`.\\n- Store human-review drafts under `data/reviews/` if they are lightweight text.\\n- Add validation tests for batch shape and required fields.\\n- Add heuristic retention scoring before rendering.\\n- Treat rendering as later-stage; validate scripts and hooks first.\\n\\n## Pitfalls\\n\\n- Do not immediately render all ideas. First validate hooks, scripts, and review format.\\n- Do not assume a niche is safe because it is popular. Sensitive topics can confuse brand positioning when mixed with AI/automation.\\n- Do not rely on platform tags/hashtags as the growth strategy. Hooks, retention, satisfaction, and niche fit matter more.\\n- Do not post automatically from an agent without explicit approval and a side-effect boundary.\\n- Do not print or commit tokens from Google Drive or local secret files.\\n\", \"path\": \"social-media/social-shorts-growth-engine/SKILL.md\", \"skill_dir\": \"/home/agent/.hermes/skills/social-media/social-shorts-growth-engine\", \"linked_files\": {\"references\": [\"references/retention-and-monetization-notes.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\"}",
"tool_call_id": "call_UnVrkw2yQyUKkWnpl2esrT9I"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_Iodd1vGqkWYiXsL2hqCkskv1",
"call_id": "call_Iodd1vGqkWYiXsL2hqCkskv1",
"response_item_id": "fc_051a8a0b2fb58918016a149be5ab348191b5447e6c1112e589",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/static-active-word-captions-and-final-pilot-render.md\"}"
}
},
{
"id": "call_JyiWTqZRPSutUo83IhZotr1j",
"call_id": "call_JyiWTqZRPSutUo83IhZotr1j",
"response_item_id": "fc_051a8a0b2fb58918016a149be5ab548191ae0f9cae72fcd829",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/proof-short-real-problem-reset.md\"}"
}
},
{
"id": "call_3Txw0XTSXlKakJsy1TRMmVqW",
"call_id": "call_3Txw0XTSXlKakJsy1TRMmVqW",
"response_item_id": "fc_051a8a0b2fb58918016a149be5ab60819187ff9503231384c2",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/proof-short-ai-visual-upgrade.md\"}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Preparing for the next video**\n\nI need to respond to the user’s request for the next video. It seems I should check the repository and files. I should also consider previous feedback about syncing subtitles and ensuring a solid conclusion. I’ll likely build the next video in the current project directory, hermes-agent, while looking for necessary outputs and scripts. Using a to-do list might help organize everything, and I'll figure out how to load references dynamically while resetting proof.",
"reasoning_content": "**Preparing for the next video**\n\nI need to respond to the user’s request for the next video. It seems I should check the repository and files. I should also consider previous feedback about syncing subtitles and ensuring a solid conclusion. I’ll likely build the next video in the current project directory, hermes-agent, while looking for necessary outputs and scripts. Using a to-do list might help organize everything, and I'll figure out how to load references dynamically while resetting proof.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJvlTPbs67sqefYnQBQbuVVYKaUNP3rLLHnLz-8C1cuhfdab91pMCdqDu05C0U-N-_yWchXR_j1uSBOvchRXkho7Fm-2UL8Jcs98j9j-EaxQEjfPzjHS3ULHIsvVczTdcbIex-ZIQsbj6QgGt31rP4_P135s6PFjgDQ6W8YGYwl5kQxjgThEntBNgKfus_ZIWY6PUZdatyccjqWyQ4hE3-NPbiMJ5Cf8oreukxx8fsKq94RcOgMa9ntpmjcwbb_7G2hwiTX-I5RS1KmJEc7mViFV1M_A7s7LdovI0Q8gJan_ezJxGAAWlH5RLeJnRphpg9Me4G1DVxunLBFImixs6Kzt9OGY8xwegJO38Ffod_xYO_gHA8epB9AQey2XrOTM9qTt2-Se4z7LEJAaO68B7Qtgvj-cH1e_MkBuXMa_ko-re9duEqO-FEoAHrZNNwWLh95nHXSDxOOfeCJBnIN67xs02Bj6ZXlegdCHaz37FFAR077A5QzSJcIVy1HvvACwF7YrzFpzNLHE2FeoWTkHrt9hb59BYSjWmeuThSqXb1l5VazFGlgr2yh-vvjDuro6uDVbZnj2saqIf7UkbLsH5vm7s6zrIE_I29mNi6rlm-mguC9OLQUv4ZkwKGgiEDIhc20Mk2KOI2UlPJm-fLWt0iUzlBunKrfg8hxcR1g5Ko4eYgdDE2Smyh-fJ1-eDfxv2pKD7tTVpY4ity2ehIiRFZwr3NtdkIj-_5qZEDSJQINjJpzRIgAcGmAXGF0AYwYzsbE58W2GyYlwEZs2DrXdmKnK1L9acNXcXUiS9sa-qc6iWqmBPjwp8rz3Ph6g5tuESpNxUDbl1ipvfGysLP_DusniLNAWglYgbjx3vDmNPun1yDxoOzXCQ0JiqyFdqnkzUenmmKgbTZG-_Z4piHFS-JCFDHSK4L1LV23IlE_NcDWvuTnT3h0qBCIMoq1jdb2Cx7j1r1wlV8x7Zy1K-oh0-sqyOgybchSm9bRp0TXaxXz5Y9GY2irBsRjh-0HiO2h3KmYDvBZKbZ8usBJklR_W_E0_W37-_L-Aoy1HjeJjH3XWWLQxtN0-yqhSPMlnPUWnJFA4XHLxsmI55OdcewrK5G9rfiljm6lcdA67m1if8d7cxt1rOMxoJn7ePZ8ObdV3u1ed3JjPwI2_6Aau0A6tD8YGovca_lqmm30cRdQFVgFcVkymv0baJlU7dZzuOSaKydDytwYhp18ZfIrpyzcmG5Mf9yK2pvsVLlbeEoJjDcxDgUfRoQl-q_EaT9HWAfQ4u7W1n5eRszPTSUAJgvoveAWjoBtlA1CnFMTQm7Bajb2FP0o=",
"id": "rs_051a8a0b2fb58918016a149be2424c8191949ab44581685f01",
"summary": [
{
"type": "summary_text",
"text": "**Preparing for the next video**\n\nI need to respond to the user’s request for the next video. It seems I should check the repository and files. I should also consider previous feedback about syncing subtitles and ensuring a solid conclusion. I’ll likely build the next video in the current project directory, hermes-agent, while looking for necessary outputs and scripts. Using a to-do list might help organize everything, and I'll figure out how to load references dynamically while resetting proof."
}
]
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/static-active-word-captions-and-final-pilot-render.md\", \"content\": \"# Static active-word captions + controlled final pilot render\\n\\nSession learning from the first TrueTraceShorts pilot (`AI Output Autopsy / Meeting Summary Decision Target`). Use this for final-near preview/final render work where the user reviews voiceover, subtitle feel, Wan/background quality, and anti-AI-slop risk.\\n\\n## Caption style correction\\n\\nThe user explicitly rejected two subtitle behaviours:\\n\\n1. **One word shown alone** — too nervous / teleprompter-like.\\n2. **Sliding word window where all visible words change at once** — still too jumpy.\\n\\nRequired default style for this user's AutoShorts/TrueTraceShorts videos:\\n\\n```text\\nstatic phrase segment + active-word highlight\\n```\\n\\nRules:\\n\\n- Keep the subtitle phrase segment static on screen.\\n- Show at least 3 words at once; ideal is 4–7 words when the phrase allows it.\\n- Words stay in the same positions during the segment.\\n- Only the currently spoken word highlights / pulses.\\n- The highlight moves left-to-right through the fixed phrase.\\n- Replace the whole phrase only at the next sentence/phrase boundary.\\n- Do not default to one-word-only captions except for a deliberate hook/impact frame.\\n- Do not use hectic windows where all words change at once every word.\\n\\nImplementation pattern:\\n\\n```text\\nword cues → phrase segments of 3–7 words → fixed layout per segment → active_word_index selects highlight only\\n```\\n\\nLogic tests to add for any renderer implementation:\\n\\n- static caption segment contains multiple words\\n- active word changes within the same segment\\n- segment text remains stable while highlight moves\\n- no one-word-only caption mode as default when enough words exist\\n\\n## Preview/final render gate sequence\\n\\nUse approval states as resource gates, not as vague comments:\\n\\n- `APPROVED_FOR_PREVIEW_RENDER` permits TTS, subtitle alignment, deterministic animatic/preview MP4, and Telegram delivery of that preview only.\\n- `APPROVED_FOR_FINAL_RENDER` permits exactly the approved final render resource tier for the hash/version-bound candidate.\\n- Publishing/platform APIs remain blocked until a separate manual-posting approval.\\n- AI image/keyframe generation remains blocked unless separately approved.\\n\\nBefore final render, verify:\\n\\n- candidate_id matches\\n- version matches\\n- script_hash matches\\n- claim gate valid\\n- AI disclosure valid\\n- resource gate allows only the intended render tier\\n- publishing and platform API tiers still block\\n\\n## Wan/background policy for this class\\n\\nFor a controlled pilot final render, Wan may generate only a **text-free visual motion/background layer**. Deterministic renderer must own:\\n\\n- captions\\n- labels\\n- arrows\\n- stamps such as `USELESS`\\n- mechanism diagrams\\n- factual claims / UI-like text\\n- final takeaway text\\n\\nWan negative prompt must include variants of:\\n\\n```text\\nreadable text, words, subtitles, captions, numbers, logos, watermark, brand names, UI text, fake letters\\n```\\n\\nIf constrained to exactly one Wan render, it is acceptable to create one short text-free Wan background clip and loop/upscale/compose it under deterministic overlays, but label that limitation clearly in the review package. Do not silently imply that every scene was separately generated.\\n\\n## Review package checklist\\n\\nAfter final pilot render, produce:\\n\\n- final MP4 path\\n- SHA256\\n- duration, resolution, fps\\n- audio path and measured duration\\n- subtitle/caption path\\n- render manifest\\n- Wan prompt plan/history/log\\n- claim gate result\\n- AI disclosure result\\n- resource gate result\\n- known limitations, especially forced-alignment status and any looped background layer\\n- draft social copy and manual posting pack marked draft-only\\n- explicit note: no posting, no platform API, no second final render without approval\\n\\n## Pitfall\\n\\nDo not treat a caption-style correction as a one-off `/tmp` script patch. Integrate the behaviour into the actual renderer/caption library and commit tests so the next render starts from the corrected style.\\n\", \"file_type\": \".md\"}",
"tool_call_id": "call_Iodd1vGqkWYiXsL2hqCkskv1"
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/proof-short-real-problem-reset.md\", \"content\": \"# Proof Short Real-Problem Reset\\n\\nUse this when an early short/pilot looks increasingly polished but still fails because viewers cannot see a real problem in the first second.\\n\\n## Trigger\\n\\nSwitch to this mode when the user says a pilot is:\\n\\n- pretty but semantically empty\\n- too abstract or generic\\n- missing a visible fail / real viewer pain\\n- overproduced before the format is validated\\n- relying on AI images, Wan/I2V, glassmorphism, or B-roll as the story carrier\\n\\n## Archive the old candidate first\\n\\nMark the old candidate as a paused learning case, not a render target.\\n\\nRecommended archive fields:\\n\\n```json\\n{\\n \\\"status\\\": \\\"paused_learning_case\\\",\\n \\\"reason\\\": \\\"Pretty but semantically weak. Too abstract for first pilot. Visuals do not create immediate viewer pain or retention.\\\",\\n \\\"do_not_continue\\\": {\\n \\\"further_optimization\\\": false,\\n \\\"rendering\\\": false,\\n \\\"posting\\\": false,\\n \\\"wan\\\": false,\\n \\\"i2v\\\": false,\\n \\\"platform_api\\\": false\\n }\\n}\\n```\\n\\nPostmortem structure:\\n\\n- Worked: approval gates, clean captions, delivery discipline, workflow/styleframe learning, technical I2V sanity where applicable.\\n- Failed: topic too abstract, no visible fail, too much production before validation, too many visual metaphors, AI video/image generation used too early as story carrier.\\n- New rule: `Pretty Empty Visual Blocker`.\\n\\n## Pretty Empty Visual Blocker\\n\\nBlock a candidate or visual plan if:\\n\\n- the image is high-quality but does not show a clear problem without voiceover\\n- no visible fail exists\\n- the visual is only mood/B-roll\\n- the viewer cannot tell within 1 second what is at stake\\n- usefulness only emerges through abstract explanation\\n- the scene is interchangeable with dozens of other AI/productivity videos\\n\\nA visual plan must answer:\\n\\n1. What is concretely broken?\\n2. Where can the viewer see the error?\\n3. What is at stake for the viewer?\\n4. Which simple rule repairs it?\\n5. Why would someone save or share this?\\n\\n## ProofShortMode defaults\\n\\nProof Shorts are the default for the first 10–20 unvalidated videos.\\n\\n- 25–35 seconds\\n- screen/mockup-led or real-problem-led\\n- no Wan final\\n- no I2V/T2V full render\\n- no premium styleframe pass\\n- no abstract metaphors\\n- no AI B-roll as main visual\\n- fast useful preview to validate topic/format\\n- manual approval before any posting pack\\n\\nPremium episodes come only after the theme/format is proven by viewer response.\\n\\n## Good first Proof Short shape\\n\\nFor digital safety/workflow/AI-mechanism content:\\n\\n```text\\nvisible fail → recognition → mechanism → simple check/rule → safe next action → memorable takeaway\\n```\\n\\nExample topic class: fake invoice/payment-route red flag.\\n\\n- Use controlled fictional mockups.\\n- Show invoice/email/payment route in the first frame.\\n- Avoid real brands, addresses, IBANs, QR codes, logos, and real people.\\n- Use renderer-owned UI text/highlights; do not use real scam templates.\\n- Keep claims as general safety advice, not legal/financial advice.\\n\\n## Caption style\\n\\nKeep the user's corrected style:\\n\\n- static phrase segments\\n- active-word highlight\\n- white inactive words\\n- yellow active word\\n- no frame/box/full-width bar/dark subtitle block\\n- subtle shadow or outline only\\n- mobile-safe bottom position\\n\\n## ReviewPackageV2 additions\\n\\nFor Proof Shorts include:\\n\\n- `ProofShortMode = true`\\n- selected hook plus hook variants\\n- script\\n- visual plan\\n- Pretty Empty Visual Blocker result\\n- claim gate\\n- AI disclosure\\n- save/share/follow reasons\\n- platform fit\\n- preview MP4 path, SHA256, duration, resolution\\n- Telegram delivery status\\n\\n## Hard blocks until approval\\n\\nDo not run:\\n\\n- Wan/I2V/T2V full render\\n- full-final render\\n- platform API\\n- auto-posting\\n- scheduling\\n- render series\\n\\nAllowed next commands should be explicit, e.g.:\\n\\n```text\\nAPPROVED_PROOF_SHORT \\nREVISE_PROOF_SHORT \\\"Änderungswunsch\\\"\\nREJECT_PROOF_SHORT \\\"Grund\\\"\\nAPPROVED_FOR_MANUAL_POSTING_PACK \\n```\\n\", \"file_type\": \".md\"}",
"tool_call_id": "call_JyiWTqZRPSutUo83IhZotr1j"
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/proof-short-ai-visual-upgrade.md\", \"content\": \"# Proof Short AI Visual Upgrade Pattern\\n\\nUse this when a Proof Short concept is approved as useful/clear, but the user asks why it does not use AI images to make the video look more premium.\\n\\n## Core decision\\n\\nDo not treat `ProofShortMode` as `no AI visuals forever`. Treat it as:\\n\\n```text\\nvalidate real viewer problem first → then optionally add AI polish without surrendering factual/UI control\\n```\\n\\nFor security, finance, scam-awareness, invoice, email, payment-route, medical, or other high-trust topics, distinguish between:\\n\\n- **factual/semantic assets**: UI, invoice, email, payment route, numbers, labels, warnings, claims, routing/account fields. These stay deterministic and renderer-owned.\\n- **atmospheric/premium assets**: desk, laptop, office, screen glow, neutral background, product-film texture, cover/thumbnail background, text-free keyframes. These may use AI image generation after the concept is validated.\\n\\n## Recommended upgrade mode\\n\\n```text\\nmode: ai_background_plus_deterministic_mockups\\nprovider: openai-codex\\nmodel: highest available reasonable GPT Image tier, usually gpt-image-2-high\\noutputs: 2–3 text-free background/keyframes\\nrenderer remains source of truth for all readable text/facts\\n```\\n\\nUse this to make a Proof Short look less flat without turning it into an uncontrolled AI-image story.\\n\\n## Safe AI image uses\\n\\nGood uses:\\n\\n- cinematic desk/laptop/office background\\n- neutral invoice-review atmosphere with blank papers/screens\\n- second-channel verification mood/background\\n- thumbnail/cover background\\n- premium lighting and product-film texture\\n- subtle abstract security atmosphere if it still supports the visible real problem\\n\\nBad uses:\\n\\n- generating the invoice itself\\n- generating the email UI itself\\n- generating bank/payment details, account fields, IBANs, QR codes, barcodes, addresses, logos, fake company marks, legal text, or claims\\n- using AI image text as part of the message\\n- letting AI-generated visuals replace the visible fail/fix logic\\n\\n## Prompt constraints\\n\\nEvery AI image prompt should say:\\n\\n- text-free image\\n- no readable text\\n- no logos or brands\\n- no QR codes/barcodes\\n- no real companies, banks, people, addresses, account numbers, invoice numbers, or payment details\\n- leave clean safe space for renderer-owned captions and UI overlays\\n- realistic/premium social-video keyframe, 9:16\\n- show atmosphere/problem context, not factual content\\n\\n## Review package additions\\n\\nWhen using this upgrade, include:\\n\\n- `visual_upgrade_mode: ai_background_plus_deterministic_mockups`\\n- AI image provider/model/quality\\n- number of generated keyframes\\n- number of used keyframes\\n- number of discarded keyframes and explicit discard reasons\\n- per-image SHA256/path/resolution\\n- statement that UI/invoice/payment route remained deterministic\\n- no Wan/I2V/full-final unless separately approved\\n- whether AI disclosure is required or only conservative optional disclosure\\n\\n## Operational QA note\\n\\nAfter generation, make a small contact sheet and inspect it before rendering. Do not use every image automatically. Discard AI backgrounds that contain pseudo-readable document lines, logo-like marks, QR/barcodes, people/hands, bank/payment details, or busy compositions that fight the deterministic foreground. For render treatment, keep AI backgrounds subordinate: slight blur/push-in/dark overlay is preferable to letting image detail compete with captions or the visible fail. See `references/proof-short-ai-background-rendering-qa.md` for the concrete pattern.\\n\\n## Pitfall\\n\\nDo not answer the user's “why no AI images?” as if AI images are forbidden. The correct answer is: AI images are useful for premium atmosphere after the proof concept is validated, but not for the factual invoice/email/payment-route layer. Offer a small controlled visual-upgrade pass instead of defending a flat deterministic preview.\", \"file_type\": \".md\"}",
"tool_call_id": "call_3Txw0XTSXlKakJsy1TRMmVqW"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_UYKJZTkkPpVfKWCvCkOVJFlB",
"call_id": "call_UYKJZTkkPpVfKWCvCkOVJFlB",
"response_item_id": "fc_051a8a0b2fb58918016a149bea79fc8191af705f5cfd4f796e",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"todos\":[{\"id\":\"scope\",\"content\":\"Letztes Feedback in Anforderungen für nächstes Video übersetzen\",\"status\":\"in_progress\"},{\"id\":\"discover\",\"content\":\"Vorhandene AutoShorts/Proof-Short Artefakte und Pipeline finden\",\"status\":\"pending\"},{\"id\":\"draft\",\"content\":\"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\",\"status\":\"pending\"},{\"id\":\"deliver\",\"content\":\"ReviewPackage/Entwurf knapp an User liefern und nächste Freigabe-Kommandos nennen\",\"status\":\"pending\"}]}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Inspecting video files**\n\nI need to inspect the current repository, hermes-agent, for files related to \"shorts.\" Maybe I should search in the tmp directory. It seems like we want to create a concept or scripts for the next video without necessarily rendering it. The term \"erarbeite\" implies developing the next video. I'll probably generate a candidate review package instead of doing a full render. I'll look for recent outputs in /tmp/autoshorts and check the pipeline scripts.",
"reasoning_content": "**Inspecting video files**\n\nI need to inspect the current repository, hermes-agent, for files related to \"shorts.\" Maybe I should search in the tmp directory. It seems like we want to create a concept or scripts for the next video without necessarily rendering it. The term \"erarbeite\" implies developing the next video. I'll probably generate a candidate review package instead of doing a full render. I'll look for recent outputs in /tmp/autoshorts and check the pipeline scripts.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJvqg9C-w0Y_dAuJ8o5WWq8bx0D8-4_8c3qLDN6YO2yYBIWHa0LP_6qFmB6Ltt4ck11C6fFP78RLl8q1JEnkmdjEfxb9QbT7E6P0fz3jSZfQiXhic9ez7a7fmWqckmLiil0oJPMrmcyeCXq3aPyskl9M3R86MK9gKsWjWMrMmdsJ-ORr2JFbpU91j7m1uAuAwimlJVv5tfnofK8s-x6sVoTcUzECcJfWQoJRSbdrr7SFRquedggYxSFUd5bHLLqB5bpBnJ2uucR8LsKRy-cghPTpH3djBvk8uoY4Knr_bGntO6Ao5vfNnd2VQExFKvR15UvdoJR3CwRTcW2pAY24rQYs3a_o47W0DEVmiXyXd_laSY-dxWqL7-v47UP0SwKy5B-cupITdn7aN5900lIz9M6sRobAcy8WIQM2P03lJtqJsAMD3U1hyh3IcuOZgEImLcBBODpd9lbZOVb_sDkxTbxNuW_GIGJosyr_OUdyGYQDjO7L_xyYFVywVoEyV7PuI5QiP3r1VdiUSMg2Mw5HcMbgYApqvEUI8ziDdpq_mUTOdT9f3DGz7-wA_6xRy0UiFYmHkR9fna89rx0q7rKukVDFO1ZmjwAdmzz_NLVbSZXOli1sVDaQxBaYUKnmAPB4vpWfXczlEAXfvrpsjmeRESuj5IEv7L8Ff74pftB1UDhDgaMe7IRmkq2aqIR6FQ_-ELOFDTgL3FzEHJ7ahoIJnT13kruOcQ0Umiwt1ir4hQO9Dr-Y8cJpJppYFI3rU0pHSWX28f29E5hxiaWfM8WUMvqiDn8Hio3Gemyb20p-bcSaBUYT1O7neDcEnuyHRPA5NaIuQ7Y3hDaPQYPqXnzY2mw1ZuJcquxRN5v-sSKa3FjMndc6AwOqHr4Rd_U2tvfS3sXj1F0qx6UDxKVOBthr0CpJcs0fpOK4zi19T4L8nSxo6-oCea17TU4dPEctY69q32mZOfVPJVkUwWw1S3bprnLkiFmW5R9aQq0UCQjN0j4IuNM6P_Vff2d1Svq3rSzm1HaHxE8mZMMfYnmpIvVNgfa16rvxaDSctLgx2wdC8VH4tcsoG7HlUiE2ZackA8jJGzPaJ3seEyuc1dYgikg7Z3NSRglBgsA958J3qMv7J0pXOiFW49WutivKl4JQJ0ScpHbBNuDuKuHH7KHAfPPX485Fyzfm6M7sYtZiwQrIVtfx0jXnFxL0_EuhJWqGSaPlXpgJ-yACg3mI9X8q2pwll9u8Ht-jI4wZSXM1o0YiMNN4ly4zawK7XK6IcDSuwuTR9oJfht-2Y-eYdnSqTLgNkPUINWvGxuXoYURgfvpWnqPAV9VFtawD_lGRuiGQyBuaCKIJty-C0kiBQDK5KHYHHOVfI4hFftX_B89Czff6a1X4dpSde8qyUf-tLvKz7E5NSQ5lSj_DZG6AuNU7TtVpSkMjvw==",
"id": "rs_051a8a0b2fb58918016a149be753d4819192d00d981a3316b3",
"summary": [
{
"type": "summary_text",
"text": "**Inspecting video files**\n\nI need to inspect the current repository, hermes-agent, for files related to \"shorts.\" Maybe I should search in the tmp directory. It seems like we want to create a concept or scripts for the next video without necessarily rendering it. The term \"erarbeite\" implies developing the next video. I'll probably generate a candidate review package instead of doing a full render. I'll look for recent outputs in /tmp/autoshorts and check the pipeline scripts."
}
]
}
]
},
{
"role": "tool",
"content": "{\"todos\": [{\"id\": \"scope\", \"content\": \"Letztes Feedback in Anforderungen für nächstes Video übersetzen\", \"status\": \"in_progress\"}, {\"id\": \"discover\", \"content\": \"Vorhandene AutoShorts/Proof-Short Artefakte und Pipeline finden\", \"status\": \"pending\"}, {\"id\": \"draft\", \"content\": \"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\", \"status\": \"pending\"}, {\"id\": \"deliver\", \"content\": \"ReviewPackage/Entwurf knapp an User liefern und nächste Freigabe-Kommandos nennen\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 3, \"in_progress\": 1, \"completed\": 0, \"cancelled\": 0}}",
"tool_call_id": "call_UYKJZTkkPpVfKWCvCkOVJFlB"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_BPea8VrJaUJHdOosQcRytRp6",
"call_id": "call_BPea8VrJaUJHdOosQcRytRp6",
"response_item_id": "fc_051a8a0b2fb58918016a149bef6b4c8191a9c7fcba0935400e",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"path\":\"/home/agent\",\"pattern\":\"*AutoShorts*\",\"target\":\"files\",\"limit\":20}"
}
},
{
"id": "call_NQ0BPP15pOLp4Cx7swYfTHVW",
"call_id": "call_NQ0BPP15pOLp4Cx7swYfTHVW",
"response_item_id": "fc_051a8a0b2fb58918016a149bef6b608191a112f888bbd76ec5",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"path\":\"/home/agent\",\"pattern\":\"digital-red-flags-fake-invoice-payment-route-30s\",\"target\":\"content\",\"limit\":20,\"output_mode\":\"files_only\"}"
}
},
{
"id": "call_5R3v9afrbG9YAgtZBoDq7uAW",
"call_id": "call_5R3v9afrbG9YAgtZBoDq7uAW",
"response_item_id": "fc_051a8a0b2fb58918016a149bef6b6c8191ac457a8e31a7efc9",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"path\":\"/tmp\",\"pattern\":\"*autoshorts*\",\"target\":\"files\",\"limit\":50}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"total_count\": 0}",
"tool_call_id": "call_BPea8VrJaUJHdOosQcRytRp6"
},
{
"role": "tool",
"content": "{\"total_count\": 0}",
"tool_call_id": "call_NQ0BPP15pOLp4Cx7swYfTHVW"
},
{
"role": "tool",
"content": "{\"total_count\": 21, \"files\": [\"/tmp/autoshortsbot_strategic_inputs.md\", \"/tmp/autoshorts-social-draft.txt\", \"/tmp/autoshorts-render-preview.html\", \"/tmp/autoshorts-demo-delivery.txt\", \"/tmp/autoshorts-demo-review.txt\", \"/tmp/autoshorts_push13.log\", \"/tmp/autoshorts_push12.log\", \"/tmp/autoshorts_push11.log\", \"/tmp/autoshorts_push10.log\", \"/tmp/autoshorts_push9.log\", \"/tmp/autoshorts_push8.log\", \"/tmp/autoshorts_push7.log\", \"/tmp/autoshorts_push6.log\", \"/tmp/autoshorts_push5.log\", \"/tmp/autoshorts_push4.log\", \"/tmp/autoshorts_push3.log\", \"/tmp/autoshorts_push2.log\", \"/tmp/autoshorts_push.log\", \"/tmp/autoshorts_git_clone.log\", \"/tmp/autoshorts_ffmpeg2.log\", \"/tmp/autoshorts_ffmpeg.log\"]}",
"tool_call_id": "call_5R3v9afrbG9YAgtZBoDq7uAW"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_IaRfhZPbcMTEdGRG2jlJF4w0",
"call_id": "call_IaRfhZPbcMTEdGRG2jlJF4w0",
"response_item_id": "fc_051a8a0b2fb58918016a149c04d2b88191b322564541267e23",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"path\":\"/tmp\",\"target\":\"files\",\"pattern\":\"*proof*\",\"limit\":50}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJwEqZUny4e8h6jGZ9sFGXKwSDppEL1x6EDV7dlrioszgn5ZzwxX8POJTIYh00jvXRW1qLEwS2hhHLbd6GiSuR0KNxe19OeSbklypOVmU-QOLaQiP-BcfoOZ2Kj5zgzLpL2ghlX2kidnlFIdhOEsC9Mfbrkb9AC8S1u4Q3n61Nwlhhj73D56ng4jnXTWYbAxB_WRLwzfn9hOf0yniGcc6prgvaiDRqhs4yOgROs3bCC3pC5vd6145Ob8GtUgQ8cXvn76H5hQlIGMlbLl8zC5SDlEU0tYtHA3wjqwo8AA0Kr-XBJPucUvausBqD8iyxaiqLPH5SoFIEKbzO4RS8jeCFuGpYuby9MAxr_wXy7-curxXkyXWOJhoCzGE7LLurP6G-ogdo3mKGoDBGHRuaBI4csz1n46yc-cq4Ct29kD-SbqxCBA8jPwP0jkhhRLcjfcPvoNCU5ZuFsXjVSz_jk-t982yVy_8yD1y1tCaFiKcdbgPLfB593Y9RMdWp9XYza9XLnkuT2GbFiNwfHLnDz4oOsqbNTOBmJ3LZQS22rzs7Gem90FPBdHKYHqEVf4wcmnGZQT9XJRdfuUcMmrVLuY8nK5sK2XjBnpHhH8q5OGwE4aQ6Fig-JwGK3paMsCbqXouKeOROF3Wrh7K0FnaxM6tPFD0q3AYubBqF678j-yXGkOx3NqlN2kVtI_Qui_XqqJ28kTShv0NE6S6iMVSn-NTnU9SBGN5OFJUfm8IuynSiLqCqD-k9wpW4dk3UkaWb7XbHcbMYzg-gTyznKujDreXV4aiJITztm_vOjuBITLaL-nIzvg4yf0gdJV2fnmqyUFnAnH0AjNhzn0IefDx7U7iBPmiyi0luJeqGHPJ-J3ROENyN7gIkur48HleOE1qwvt4MMQkVBTurmtPCkHM4H863eNlP5OqiJD9QJMttZIHrBtHn91PghQz4MbuhATF3cM3gL-",
"id": "rs_051a8a0b2fb58918016a149c0412d081919686cc253459d4f0",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"total_count\": 32, \"files\": [\"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/layout_proofs_ABC_contact_sheet.zip\", \"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/s03_layout_proof_contact_sheet_ABC.png\", \"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/layout_proof_review_package.json\", \"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/s03_layout_proof_C.png\", \"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/s03_layout_proof_B.png\", \"/tmp/autoshorts_hybrid_layout_sprint21/ai-output-autopsy-decision-summary-38s/s03_layout_proof_A.png\", \"/tmp/create_hybrid_layout_proofs.py\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_rejection_audit.json\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_review_package.json\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_midframe.jpg\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_animatic_manifest.json\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_s03_animatic_not_wan.mp4\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_animatic_silent.mp4\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_audio.mp3\", \"/tmp/compose_keyframe_proof_v2_animatic.py\", \"/tmp/autoshorts_keyframe_proof_v2/ai-output-autopsy-decision-summary-38s/keyframe_proof_v2_workflow_api.json\", \"/tmp/run_keyframe_proof_v2.py\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_v1_rejection_audit.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_review_package.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_midframe.jpg\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_manifest.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_s03_mechanism_v1.mp4\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_s03_silent.mp4\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_caption_segments.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_s03_audio.mp3\", \"/tmp/compose_visual_proof_v1.py\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_wan_gate.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_s03_mechanism_00001_.mp4\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_wan_history.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_submit_response.json\", \"/tmp/autoshorts_visual_proof_v1/ai-output-autopsy-decision-summary-38s/visual_proof_wan_workflow_api.json\", \"/tmp/run_visual_proof_wan_v1.py\"]}",
"tool_call_id": "call_IaRfhZPbcMTEdGRG2jlJF4w0"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_RuVZtdhGTNBEYn0FnhyiAuIx",
"call_id": "call_RuVZtdhGTNBEYn0FnhyiAuIx",
"response_item_id": "fc_051a8a0b2fb58918016a149c072b588191bb83224fd6d0ae57",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"limit\":50,\"path\":\"/tmp\",\"pattern\":\"*sprint30*\",\"target\":\"files\"}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"total_count\": 0}",
"tool_call_id": "call_RuVZtdhGTNBEYn0FnhyiAuIx"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_rXVM20hlHgzI5YjL6YhI5wan",
"call_id": "call_rXVM20hlHgzI5YjL6YhI5wan",
"response_item_id": "fc_051a8a0b2fb58918016a149c0b7980819191ee8010305737e9",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python - <<'PY'\\nfrom pathlib import Path\\nfor p in Path('/tmp').glob('autoshorts*'):\\n print(p)\\nPY\", \"timeout\": 30}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJwLQymy2iDW6T6l33yKz6YDmXv48hC6TBchGNLthEZt5zzi4iaztIg-PdXsalc9pJruuvNv_c-EZw77r9Rb4cRn_Ocxxjotpx75EIaFC7r5057diHIqjslk_HroI8UzCX5Q5ymRFeyC8pkqjqoThSRPodQ4fy1d9puckEq6D9GcLokuvDLgCxA8ZmFGu2Z9LRnkXFTBFF_Bn6vPUOxZYS-Z29Qph2vHoBz1I2lDAMDxiZUlyn_YYZeuUUjAmEKnjs5QwoKl91QC9HSMM4S1AL9BtqznEoQMO7Uw9GoP2m8P8C5iN5MXlfaloXauvOq237Ezqs1q8NvoeKFKL-WNpjzhAqEk1XUV5QZAWSKJo8Lb4RtJsoBvmYfQ1vTwjtiwtIWVZs3jTM5ui1KiI5kNBrywe8UbtyhXUtMYYpAqgqEa7AQkxOgxjBQzkpEnQcK28DJKSJ7PgWt_MNOISGNMg6oVj10mV-898nHlL3Eh9Q_Oh2sUzNDKbXwHhEc3oHWr9eoj5R34RIXS_VQchCu8mALkJOvgealMjKgsx_1zCqdUrO2E5CGw9P3fdrL7Inw8Tk3MSgPrPEhVR6Z09J8gHJIVSl6yroNZnnZouOcmbFztxzeORH0XUAxetw_3eN35xDEue2vEuUebKwDr0vNkZqVn8g1pW0MmGplQAtB7m4zNMDOhfG9R7k2T3qFBp9VHU5TKVcKzYpfn6vz7uIIt87gMqkcVS2hUhuPcyTR7CdnsQ1L5UFEtEGFx4GGZ8PztdKoQUHGn4lxowvcR3C951pry5fe0hbtzwCH6JQTu6DiNeM9W5RkWlTb6oZIwWJpkGJN0bHqPuC2ZQe4tSN-vfKsyiYwyM8s3p49Ea21J15ToxG-sUKhMzP06Zw8u6DrVVmYLr5DR1bKzHOtoRhzJ-eE_v7unSgP7NWMrtU6q2a4fhW-SU6eh9IT40x5iMe0KrwlT6agzbfwkT3uV96MIqny2lrzzZbN4Uhfw52Dak7i6MSE=",
"id": "rs_051a8a0b2fb58918016a149c0ae318819195e9d7b9d1af8ce7",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"output\": \"/tmp/autoshorts_push3.log\\n/tmp/autoshorts_push13.log\\n/tmp/autoshorts_review\\n/tmp/autoshorts-demo-delivery.txt\\n/tmp/autoshorts_push9.log\\n/tmp/autoshorts_premium_styleframes_sprint22\\n/tmp/autoshortsbot_businessplan\\n/tmp/autoshorts_clean_image_cut_sprint25\\n/tmp/autoshorts_ai004_frames_new\\n/tmp/autoshorts_i2v_sprint2_sanity\\n/tmp/autoshorts_git_clone.log\\n/tmp/autoshorts_proof_short_sprint30\\n/tmp/autoshorts_push.log\\n/tmp/autoshorts-demo-local-preview-de\\n/tmp/autoshorts_push7.log\\n/tmp/autoshorts_push11.log\\n/tmp/autoshorts_push2.log\\n/tmp/autoshorts-social-draft.txt\\n/tmp/autoshorts-demo-review.txt\\n/tmp/autoshorts_real_life_styleframes_sprint23\\n/tmp/autoshorts_push4.log\\n/tmp/autoshortsbot_strategic_inputs.md\\n/tmp/autoshorts_i2v_sprint2_audit\\n/tmp/autoshorts_preview_check\\n/tmp/autoshortsbot_strategy_update\\n/tmp/autoshorts_push8.log\\n/tmp/autoshorts_final_v1\\n/tmp/autoshorts_hybrid_layout_sprint21\\n/tmp/autoshorts_ffmpeg.log\\n/tmp/autoshorts_ai004_frames_old\\n/tmp/autoshorts_push12.log\\n/tmp/autoshorts_push10.log\\n/tmp/autoshorts_comfy_check\\n/tmp/autoshorts_push5.log\\n/tmp/autoshorts_styleframes_sprint2\\n/tmp/autoshorts_push6.log\\n/tmp/autoshorts_visual_proof_v1\\n/tmp/autoshorts_ffmpeg2.log\\n/tmp/autoshorts_clip_contact\\n/tmp/autoshorts_prerelease_animatic_sprint24\\n/tmp/autoshorts_keyframe_proof_v2\\n/tmp/autoshorts-demo-local-preview\\n/tmp/autoshorts-render-preview.html\\n/tmp/autoshorts_preview_v2\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_rXVM20hlHgzI5YjL6YhI5wan"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_unp84h9EiycUOqlXEoXJAK6P",
"call_id": "call_unp84h9EiycUOqlXEoXJAK6P",
"response_item_id": "fc_051a8a0b2fb58918016a149c1050dc8191b11869c86119ca44",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"limit\":100,\"path\":\"/tmp/autoshorts_proof_short_sprint30\",\"pattern\":\"*\",\"target\":\"files\"}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Inspecting sprint30 files**\n\nI need to take a closer look at the sprint30 files. There must be details or progress notes I need to check to ensure everything is in order. I'm thinking about focusing on specific sections that might need my attention. I want to make sure I catch any issues early on, so a careful inspection seems like the right move. Let's dive in and see what I find!",
"reasoning_content": "**Inspecting sprint30 files**\n\nI need to take a closer look at the sprint30 files. There must be details or progress notes I need to check to ensure everything is in order. I'm thinking about focusing on specific sections that might need my attention. I want to make sure I catch any issues early on, so a careful inspection seems like the right move. Let's dive in and see what I find!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJwQeC5Ac__f6JUawP3WbwO7hycu2XVBmRD3sOoy_crCCRToB-nIev0y-fEk8PtRylpEApkP_eay9McRL7zas81vODL-JPMyIq0f2SDYWtGcKdpZRUpweUtpkqjltfSqUsPqKMC4mu5NOovUqJ0Ps1h9nm8YHMj7xqMSqXZ0cN7wf_ivUR0PnTOxuAuLTzFOuz27SV3FHs3Ix2684gsz4iOzflOFm2gE20MrPHtBWTdX0f0qfTY8t4ZkCqafrsl3ukbY9ArvXy8CRVHec-F-98BTU1iIblEh4OAY2bOyGZvaVTB_voT-GTjCc6XcXSVJ64fqn80im8ohtji9LuHGPUUBcD16WFlO8pdnYgmhlPx-vibij_ZPwymy6LidR6zoBPc-vkx1PDrtQgK3LSg0Ag-ajHMqaZLwdB0cF_LChv0FfpmRZHc6GtAdSvdNLHwvwS7oUcA6o_nkvmMokpLIuqBYti8qOMVryLkHaHRYqHJYcblASeNf65J_3LTWxDhWWrHKHJ1fnHgu2rHI9rFkZwPsL1DUh8q5ZunfsfOOICo5yE5JjQ2QF4vMZdoLM8R4VQgtF0NL7iZtvjgnEXhP0Uxma7OF-SbKVvVfXKhizalRMa8jk0crAkd1D5NRIoJxqbWJYjLlKFwRk9LM1iIzXfLrnJGhYqO8mF84Vnu6ni5DLhVuA8-ugw-8arB56KdddWOOINgE40hW5TRa_I31yLGWD6Xpu4KMfrSHV5RYhubesy5DkAO9hgtO2p6PAk8rUOqTn3TNsHXutNzO7u2fyQSleS-L5MTpyG71OLqDaic44him34rETt4xzSNOIzTFGCk-0_8iXuhGWwDevPSCdzczfHSXL8S-pOY2DnoZ5f9tU9o5anEhGmgVLUA6V0Y4NTUwbx94zh8SKxk_4X3u74ZOh-9RfLwQS5HGYfk0RlOTrbA43cdtUX047i3H7lVNPPxx",
"id": "rs_051a8a0b2fb58918016a149c0df7588191adc894e0b1e32557",
"summary": [
{
"type": "summary_text",
"text": "**Inspecting sprint30 files**\n\nI need to take a closer look at the sprint30 files. There must be details or progress notes I need to check to ensure everything is in order. I'm thinking about focusing on specific sections that might need my attention. I want to make sure I catch any issues early on, so a careful inspection seems like the right move. Let's dive in and see what I find!"
}
]
}
]
},
{
"role": "tool",
"content": "{\"total_count\": 76, \"files\": [\"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/review_package_visual_upgrade_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/manifest_visual_upgrade_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags_visual_upgrade_subtitle_preview_v1.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags_visual_upgrade_contact_sheet_v1.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_30_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_28_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_24_5s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_20_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_17_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_15_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_10s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_4s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/qa_frames/frame_1s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags-fake-invoice-payment-route-30s_visual_upgrade_v1.mp4\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/digital-red-flags-fake-invoice-payment-route-30s_visual_upgrade_v1_silent.mp4\", \"/tmp/autoshorts_proof_short_sprint30/render_visual_upgrade_v1.py\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/ai_keyframes_manifest_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/ai_keyframes_contact_sheet_v1.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/ai_keyframes/ai_background_03_openai_codex_gpt-image-2-high_20260525_201556_875b1851.png\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/ai_keyframes/ai_background_02_openai_codex_gpt-image-2-high_20260525_201453_36f56d2f.png\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_upgrade_v1/ai_keyframes/ai_background_01_openai_codex_gpt-image-2-high_20260525_201404_e90dd6b8.png\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_summary_manual_upload_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/manual_upload_v1_manifest.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_summary_manual_upload_v1.md\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/analytics_tracking_template_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/analytics_tracking_template_v1.csv\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/manual_posting_pack_v1.md\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/manual_posting_pack_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/candidate_status_manual_upload_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/manual_upload_v1_qa_contact_sheet.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_30_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_28_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_24_5s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_20_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_17_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_15_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_10s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_4s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/qa_frames/frame_1s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/sha256_manual_upload_v1.txt\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/ffprobe_manual_upload_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/manual_upload_v1/digital-red-flags-fake-invoice-payment-route-30s_manual_upload_v1.mp4\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/manifest_preview_v2_caption_safe.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/digital-red-flags_subtitle_style_preview_v2.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/digital-red-flags_caption_safe_contact_sheet_v2.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_30_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_28_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_24_5s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_20_2s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_17_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_15_8s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_10s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_4s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/qa_frames/frame_1s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/digital-red-flags-fake-invoice-payment-route-30s_preview_v2_caption_safe.mp4\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v2_caption_safe/digital-red-flags-fake-invoice-payment-route-30s_preview_v2_caption_safe_silent.mp4\", \"/tmp/autoshorts_proof_short_sprint30/render_fake_invoice_preview_v2.py\", \"/tmp/autoshorts_proof_short_sprint30/image_provider_audit/capability_test_result.json\", \"/tmp/autoshorts_proof_short_sprint30/image_provider_audit/capability_test_openai_codex_gpt-image-2-high_20260525_192025_93a777df.png\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/render_metadata_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/review_package_v2.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/digital-red-flags_contact_sheet_v1.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_30s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_25s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_17s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_10s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_4s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/qa_frames/frame_1s.jpg\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/digital-red-flags-fake-invoice-payment-route-30s_preview_v1.mp4\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/preview_v1/digital-red-flags-fake-invoice-payment-route-30s_preview_v1_silent.mp4\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/audio/voiceover.mp3\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/audio/edge_subtitles.srt\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/review_package_v2_pre_render.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/visual_plan_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/script_draft_v1.json\", \"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/archive/ai-output-autopsy-decision-summary-38s_postmortem.json\"]}",
"tool_call_id": "call_unp84h9EiycUOqlXEoXJAK6P"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_Wi71D7qxurHsqbjpNw3osl4T",
"call_id": "call_Wi71D7qxurHsqbjpNw3osl4T",
"response_item_id": "fc_051a8a0b2fb58918016a149c1d412481919e81bf2985aa00a2",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/script_draft_v1.json\",\"limit\":500}"
}
},
{
"id": "call_lyjR8cLmI5VpZX3AIf10Hyz6",
"call_id": "call_lyjR8cLmI5VpZX3AIf10Hyz6",
"response_item_id": "fc_051a8a0b2fb58918016a149c1d41388191a26032b41b49d490",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s/review_package_v2_pre_render.json\",\"limit\":500}"
}
},
{
"id": "call_NPTV7A1No62mNcR39UkG7SNl",
"call_id": "call_NPTV7A1No62mNcR39UkG7SNl",
"response_item_id": "fc_051a8a0b2fb58918016a149c1d41408191bf4022268cbe75a1",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint30/render_fake_invoice_preview_v2.py\",\"limit\":200}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Developing the next video concept**\n\nI need to create the next video, possibly using a new script. The user mentioned \"erarbeite,\" suggesting I develop something without necessarily rendering it fully. I might choose a relevant topic, like \"Fake DocuSign/SharePoint link\" or \"AI meeting summary isn't proof,\" related to digital scams. I should generate a JSON/Markdown file for the script, incorporating both English and German. There might also be options to use tools for rendering previews.\n**Creating a pre-render package**\n\nI might create a pre-render package even if it’s not a full video. The user’s request for a \"next video\" suggests they want an actual production pipeline. I don’t have current scripts, but I can adapt an existing render script. The instructions urge me to take action, not just plan, so I could write the package and send a final summary. I also need to consider inspecting previous script formats for alignment.",
"reasoning_content": "**Developing the next video concept**\n\nI need to create the next video, possibly using a new script. The user mentioned \"erarbeite,\" suggesting I develop something without necessarily rendering it fully. I might choose a relevant topic, like \"Fake DocuSign/SharePoint link\" or \"AI meeting summary isn't proof,\" related to digital scams. I should generate a JSON/Markdown file for the script, incorporating both English and German. There might also be options to use tools for rendering previews.\n**Creating a pre-render package**\n\nI might create a pre-render package even if it’s not a full video. The user’s request for a \"next video\" suggests they want an actual production pipeline. I don’t have current scripts, but I can adapt an existing render script. The instructions urge me to take action, not just plan, so I could write the package and send a final summary. I also need to consider inspecting previous script formats for alignment.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJwd-QrUY_LqamOtBEWYB5HRWfZUsW9gkvoiqfwp_-uCwnrx512I0qP0-fDHrpIAR74VJ8-58kK4Xf2WBz37qdOvAWV3ToopNBs4zGIBGIiqglvIvW6XEovJe1VUzzyxzrawQevmph0k0yzJy-H8Vdg4Yc32rbEL3wtfTw46QUtR7c-px0FFqmNJ28XwjCJCw7umnJEgLcAoiejPguFRaBngRCxFjiEUpU5W6JWQNfU_tLu7TKg6ao8SRip7hIzCmYDWouwV1_Uf52vTIDqmapjDjoKpJxz3Vkk8q_00lykoIJxejLGWZe6JU4N38wiZB6Eg1E5Kg_dAApzfRnM3hgrS5a9lemQ8gwR4wgkAEPm_bh1HFImF46fz9q2W5Vo1b0dOvuLjs523B8-upr_Yq5G-W_Uoi6qCIgaql5DT9o_pNlKheTnZP5AfKhoFWgH3_wdZVXDVsG51xdWZyO-J2KIMLxxczoQX_Yp2Z0RhDWHv8KCfEBRBCIfFcswQox1X1k34ClSkvD5Y-jjH3rBiIRdoUX1z0zzrGmaiVZ9AZDvpKZP6GKCI2366thhBpZWN_Y8KnDxrhsahbysu4bHJ1G-7XzELXujVFHlV6TlY8sPfBW_NZt3g94gxKSOXqZ54F-DTUGRLWMFirO92kU9h0I6HffItlLhw9ZY-qrsH1erC3q25IOK6aYQe2tPfLiC6GhUSP9N7Ed9t0lOdDxmspTzu80uQPmwCvBov3d8fc12nupp8SgP1zn41yRlZ1ofgJpQz3twYycw2Vb-QRT40eyTN9f7FtW96n8mlu4g0qxhKwVdpHNvKEOxRhyfUIe3kxjK2XvErC6x2Whrd9xjekoLuXwZXsKjpQxBClhtY0QKlVxYc0PcPO-JZmz5nLs2R3XZKkqM1IfeNPOp4MHve79Riz4JSFmpGPlXFplnCSHso_C_mpv6qyenaPeuHVJH3RjbQ3hxxc0CPB-8lZAsORclJGpq8wcELYICSOGjCvz5DusHdLkLQTz-hq_7L5Ba8_nmswuPZYCPXzk2HXFYpCBC_OLSBG_yP31A-vfjzREa7EPM-OiR4AQakic0uxCFstvgKPK8j84N45OoQE8s9h0pyQlPM0aPO-UwvWd1OHyp9M5FDji8vj2XEDj-N8tC-fMA4o_W5Q8z6KVuctb_5-GjLwky2ecojelinM78qAso_yY2eOurcabGv4RVKOdpBc1YWwk_duIyHZBofUw946WsWymzw-YHwXiXgB05ma9av_pMoSAEj4a2ejXkMLpB7KvpgCDy6Uzd4nvZO3wBvJl1yUljpYRRNnYeqvHL9HLD-okkJ9O8YpgbC13JxNX3U_tv_EwrwoMrrKk-dhESQlmxXTgOzeBDoPlzfiZdjl50iBPi_sX7kr_4GG8An009RbqBYECxjv9gYRVkTkm_e0-fKe5c6D3M3LEYIL12L7eILMY37rPDO--qTwxvnY7-iaPY-Sx_f_MMQFJgpoFx_rv_1lPJlgIAqFCf3fN8Wlm46C2zxLmuL5Zb7JZ0xKYiMjP81cE8niSGfUzwlmYoHMGTLZiUILmZeBt0QdneHHyKzzeIrwSg9nKyLRtRxi1f5vmYdWN8iz759VVx3cWEQ24ZEKO7gczK3Au6JTeXWtgb9L2qOziS_UN8aSXzT9DNHRLPhB7F8tqHaLwwg7lkd3pc3INpizY9b6NzbtosZE7Jichyrb1WcZNV7uaTylMBRVVyAWbueNMgBBgxAmrmus4mRX9CJD47X7i3xBr9_YQxcHo9miI35A39N06fXei3r2doB1u09cTDGkJT7xRkjJmZ7xwr6gIR60JvJ5ox2LjUUENN0yIUR7WszKXj0eYYUcEQcNGAiBlwT4Ghn4oMAuY2aFQIuGjOFc5I_wtKgukcKtaATT--uoGQSuDF04Jp3Utq3zkbaJDx2seTqM3E3fUqt8-6Z-t4wOQauH4GNcaGjgmSWnZUeLtuqUX5ogrXduVJXaPNxgLNxo1D7yJfl5n6ho6yAOIle4RLKankAaU7Bjnf4imTxSM3cK12wWrlxAzUy_6dXad1VTuqs_LsLd5od4tPrRwG7MQDOoMqMqG3l-WXw7GkamDw4ErIIkCHILHwppYi9qdkbAXDx-OTxbx_FnV-D0bBBXi9Qca-CF9VSIpHcNmBoVrQiAwpIa-2AVRMJEnjC1nnrPwt9rzaviXqbFXQZLEBUcOUPPYyx9vMFuxdgWjyJcGtdz6m-s4VbscK4hXP60rzpMRT-ruefvct-lujeA684gC-uGabzvGjMoQwqnSpjujOtutAaKmFZqErTxH6qii6yxp6myw0uJhDuKt4A-kTlK8yM4dVGLgyVoY_4xV4TDn5uAusGrqKkBob6AmKyLzksrGoUYG5YcTKfCP3HN5a3s_zBzaUT7ICkos2Agn-TDCZKr9nIByqXMFwyCxhFIMwQ9irKYhCbEWg0MMuRlFJL1BlQlBzeWv_7Ig6ZYt4OIA5jzbEvoA9HWAKTkXbQf9H921Mz5c6NG9lNAxCw1oJu6eavMsBD6TRtw4CcR-fJyIjEixzHLVTRM3atxcDr4Qo_fQ9aRlf2Leo0FXVb8VZrEMvwkyUaSm64GTDV2y91VAJia8yWvaw9sl7P_APwLE78G5P42rdEykyyDufDafMfIupalOP-dO6yeI0PudvV0nE9hv8fhuXPPiJyBCuaxPhneJYVH9WUKx-biiTtDOrIYGPNLLymcf3HflEW1hynLo6W-HwFBIWK0i5sTIc_xHbDa3nhQv-KZWDlyR99YHXZcEQw45HYTjA4OxZhFCb_pKozEIPsusL7Xqk5H-sQVoG47Wb1ZX_JXnIJDggYCza2GEjfc7MIJpDTX_RjCuwQaHxXgwIhfmnOGj2f",
"id": "rs_051a8a0b2fb58918016a149c129a0081919533f2e81fdd25b8",
"summary": [
{
"type": "summary_text",
"text": "**Developing the next video concept**\n\nI need to create the next video, possibly using a new script. The user mentioned \"erarbeite,\" suggesting I develop something without necessarily rendering it fully. I might choose a relevant topic, like \"Fake DocuSign/SharePoint link\" or \"AI meeting summary isn't proof,\" related to digital scams. I should generate a JSON/Markdown file for the script, incorporating both English and German. There might also be options to use tools for rendering previews."
},
{
"type": "summary_text",
"text": "**Creating a pre-render package**\n\nI might create a pre-render package even if it’s not a full video. The user’s request for a \"next video\" suggests they want an actual production pipeline. I don’t have current scripts, but I can adapt an existing render script. The instructions urge me to take action, not just plan, so I could write the package and send a final summary. I also need to consider inspecting previous script formats for alignment."
}
]
}
]
},
{
"role": "tool",
"content": "{\"content\": \" 1|{\\n 2| \\\"hooks\\\": {\\n 3| \\\"problem_hook\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route.\\\",\\n 4| \\\"red_flag_hook\\\": \\\"A fake invoice does not need a fake logo. It only needs a changed payment route.\\\",\\n 5| \\\"save_share_hook\\\": \\\"Before anyone on your team pays an invoice, check this one red flag.\\\"\\n 6| },\\n 7| \\\"selected_hook\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route.\\\",\\n 8| \\\"script\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route. Same layout. Same professional tone. Same urgency. But one thing changed: where the money goes. Before you pay, check three things: sender domain, urgency language, and payment route. If the route changed, don\\\\u2019t pay from the email. Verify through a second channel. Urgency is not proof. It\\\\u2019s the red flag.\\\",\\n 9| \\\"duration_target_seconds\\\": \\\"28-35\\\"\\n 10|}\", \"total_lines\": 9, \"file_size\": 897, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_Wi71D7qxurHsqbjpNw3osl4T"
},
{
"role": "tool",
"content": "{\"content\": \" 1|{\\n 2| \\\"candidate_id\\\": \\\"digital-red-flags-fake-invoice-payment-route-30s\\\",\\n 3| \\\"production_mode\\\": {\\n 4| \\\"mode\\\": \\\"proof_short\\\",\\n 5| \\\"min_duration_seconds\\\": 25,\\n 6| \\\"max_duration_seconds\\\": 35,\\n 7| \\\"screen_or_real_problem_led\\\": true,\\n 8| \\\"wan_final_allowed\\\": false,\\n 9| \\\"premium_styleframe_pass_allowed\\\": false,\\n 10| \\\"abstract_metaphors_allowed\\\": false,\\n 11| \\\"goal\\\": \\\"Validate format/topic with a fast useful preview before premium production.\\\"\\n 12| },\\n 13| \\\"hook_variants\\\": {\\n 14| \\\"problem_hook\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route.\\\",\\n 15| \\\"red_flag_hook\\\": \\\"A fake invoice does not need a fake logo. It only needs a changed payment route.\\\",\\n 16| \\\"save_share_hook\\\": \\\"Before anyone on your team pays an invoice, check this one red flag.\\\"\\n 17| },\\n 18| \\\"selected_hook\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route.\\\",\\n 19| \\\"script\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route. Same layout. Same professional tone. Same urgency. But one thing changed: where the money goes. Before you pay, check three things: sender domain, urgency language, and payment route. If the route changed, don\\\\u2019t pay from the email. Verify through a second channel. Urgency is not proof. It\\\\u2019s the red flag.\\\",\\n 20| \\\"script_hash\\\": \\\"c8f105c8faae7d77\\\",\\n 21| \\\"visual_plan\\\": {\\n 22| \\\"format\\\": \\\"ProofShortMode screen/mockup-led motion short, 9:16\\\",\\n 23| \\\"scenes\\\": [\\n 24| {\\n 25| \\\"id\\\": \\\"s01_visible_fail\\\",\\n 26| \\\"time\\\": \\\"0-2s\\\",\\n 27| \\\"visual\\\": \\\"fake email + invoice mockup appears; payment route line is present but not yet highlighted\\\",\\n 28| \\\"purpose\\\": \\\"instant visible real-world pain\\\"\\n 29| },\\n 30| {\\n 31| \\\"id\\\": \\\"s02_same_layout\\\",\\n 32| \\\"time\\\": \\\"2-7s\\\",\\n 33| \\\"visual\\\": \\\"invoice/email comparison shows same clean layout, tone, urgency chip; no brands/real data\\\",\\n 34| \\\"purpose\\\": \\\"recognition and tension\\\"\\n 35| },\\n 36| {\\n 37| \\\"id\\\": \\\"s03_route_changed\\\",\\n 38| \\\"time\\\": \\\"7-14s\\\",\\n 39| \\\"visual\\\": \\\"payment route card changes from known route to new route; yellow/red highlight, no real IBAN\\\",\\n 40| \\\"purpose\\\": \\\"mechanism reveal\\\"\\n 41| },\\n 42| {\\n 43| \\\"id\\\": \\\"s04_three_checks\\\",\\n 44| \\\"time\\\": \\\"14-24s\\\",\\n 45| \\\"visual\\\": \\\"three checklist cards: sender, urgency, payment route\\\",\\n 46| \\\"purpose\\\": \\\"useful saveable rule\\\"\\n 47| },\\n 48| {\\n 49| \\\"id\\\": \\\"s05_second_channel\\\",\\n 50| \\\"time\\\": \\\"24-31s\\\",\\n 51| \\\"visual\\\": \\\"email pay button dims; second-channel verify card appears\\\",\\n 52| \\\"purpose\\\": \\\"safe action\\\"\\n 53| },\\n 54| {\\n 55| \\\"id\\\": \\\"s06_takeaway\\\",\\n 56| \\\"time\\\": \\\"31-35s\\\",\\n 57| \\\"visual\\\": \\\"final clean red-flag rule card with fake invoice in background\\\",\\n 58| \\\"purpose\\\": \\\"memorable takeaway\\\"\\n 59| }\\n 60| ],\\n 61| \\\"renderer_owned\\\": [\\n 62| \\\"all mockup text\\\",\\n 63| \\\"highlights\\\",\\n 64| \\\"check cards\\\",\\n 65| \\\"captions\\\",\\n 66| \\\"red/yellow warning moment\\\"\\n 67| ],\\n 68| \\\"forbidden\\\": [\\n 69| \\\"real brands\\\",\\n 70| \\\"real bank data\\\",\\n 71| \\\"IBANs\\\",\\n 72| \\\"QR codes\\\",\\n 73| \\\"real people\\\",\\n 74| \\\"real addresses\\\",\\n 75| \\\"scam template details\\\"\\n 76| ],\\n 77| \\\"style\\\": \\\"controlled fictional UI/document mockup, mobile-readable, high contrast, calm motion, no AI image generation required\\\"\\n 78| },\\n 79| \\\"pretty_empty_visual_blocker_result\\\": {\\n 80| \\\"is_valid\\\": true,\\n 81| \\\"errors\\\": []\\n 82| },\\n 83| \\\"claim_gate\\\": {\\n 84| \\\"claim_type\\\": \\\"general safety advice / low-to-medium risk\\\",\\n 85| \\\"risk\\\": \\\"medium\\\",\\n 86| \\\"result\\\": \\\"pass\\\",\\n 87| \\\"safe_phrasing\\\": [\\n 88| \\\"A common red flag is\\\\u2026\\\",\\n 89| \\\"Before you pay, check\\\\u2026\\\",\\n 90| \\\"Verify through a second channel.\\\"\\n 91| ],\\n 92| \\\"not_claimed\\\": [\\n 93| \\\"all fake invoices work this way\\\",\\n 94| \\\"three checks prevent all scams\\\",\\n 95| \\\"legal or financial advice\\\"\\n 96| ],\\n 97| \\\"abuse_controls\\\": [\\n 98| \\\"no real bank data\\\",\\n 99| \\\"no real companies\\\",\\n 100| \\\"no real logos\\\",\\n 101| \\\"no real QR codes\\\",\\n 102| \\\"no operational scam template\\\"\\n 103| ]\\n 104| },\\n 105| \\\"ai_disclosure\\\": \\\"no: deterministic mockups and TTS preview; no realistic AI-generated people/scenes\\\",\\n 106| \\\"proof_short_mode\\\": true,\\n 107| \\\"review_package_v2\\\": {\\n 108| \\\"candidate_id\\\": \\\"digital-red-flags-fake-invoice-payment-route-30s\\\",\\n 109| \\\"version\\\": \\\"v3.0.0\\\",\\n 110| \\\"script_hash\\\": \\\"af457e73844be4f7\\\",\\n 111| \\\"media_hash\\\": null,\\n 112| \\\"series\\\": \\\"Digital Red Flags\\\",\\n 113| \\\"audience_need\\\": \\\"safety\\\",\\n 114| \\\"emotion_before\\\": \\\"anxious\\\",\\n 115| \\\"emotion_after\\\": \\\"warned\\\",\\n 116| \\\"hook\\\": \\\"This invoice looks normal. The trap is not the logo \\\\u2014 it\\\\u2019s the payment route.\\\",\\n 117| \\\"first_frame\\\": \\\"Fake invoice email with normal layout vs. red flag payment route warning in the payment section.\\\",\\n 118| \\\"visible_fail\\\": \\\"The invoice looks professional, but the payment route changed under urgency.\\\",\\n 119| \\\"anti_example\\\": \\\"A normal-looking invoice where the route changed and urgency pressures payment.\\\",\\n 120| \\\"concrete_scene\\\": \\\"fictional email invoice/payment route mockup on a phone-like vertical screen\\\",\\n 121| \\\"mechanism\\\": \\\"Fake payment requests can reuse familiar layout and pressure while moving the money route.\\\",\\n 122| \\\"fix\\\": \\\"Before paying, check sender domain, urgency language, and payment route; if the route changed, verify through a second channel.\\\",\\n 123| \\\"before_after\\\": \\\"Before: trusted the logo and urgency. After: checked route change and verified outside the email.\\\",\\n 124| \\\"takeaway\\\": \\\"Urgency is not proof. It is the red flag.\\\",\\n 125| \\\"save_reason\\\": \\\"Save the three-check invoice rule before paying from email.\\\",\\n 126| \\\"share_reason\\\": \\\"Share with teammates or family who receive invoices and payment requests.\\\",\\n 127| \\\"follow_reason\\\": \\\"Follow for digital red flags before they cost you.\\\",\\n 128| \\\"claims\\\": [\\n 129| \\\"Payment-route changes and urgency language are common red flags worth verifying before payment.\\\"\\n 130| ],\\n 131| \\\"claim_risk\\\": \\\"medium\\\",\\n 132| \\\"ai_disclosure\\\": \\\"no\\\",\\n 133| \\\"platform_fit\\\": {\\n 134| \\\"youtube_shorts\\\": \\\"strong: useful safety rule with visible first-frame fail\\\",\\n 135| \\\"tiktok\\\": \\\"strong: red-flag hook and shareable warning\\\",\\n 136| \\\"instagram_reels\\\": \\\"medium-strong: clean mockup and saveable checklist\\\",\\n 137| \\\"linkedin_manual\\\": \\\"strong for workplace teams; manual caption only\\\"\\n 138| },\\n 139| \\\"linkedin_title\\\": \\\"The invoice red flag teams miss\\\",\\n 140| \\\"linkedin_caption\\\": \\\"A fake invoice does not need a fake logo. Before paying from email, check sender domain, urgency language and payment route \\\\u2014 then verify route changes through a second channel.\\\",\\n 141| \\\"risks\\\": [\\n 142| \\\"avoid real brands/bank data/QR codes\\\",\\n 143| \\\"avoid implying the checklist prevents all scams\\\",\\n 144| \\\"not legal or financial advice\\\"\\n 145| ],\\n 146| \\\"experiment_hypothesis\\\": {\\n 147| \\\"statement\\\": \\\"Tests whether concrete digital-safety red flags create saves and shares better than abstract AI workflow content.\\\",\\n 148| \\\"expected_winning_metric\\\": \\\"saves_per_view\\\"\\n 149| },\\n 150| \\\"expected_winning_metric\\\": \\\"saves_per_view\\\",\\n 151| \\\"human_texture_note\\\": \\\"common workplace invoice/payment request scenario using fully fictional mockups\\\",\\n 152| \\\"render_backend_candidate\\\": \\\"python_motion\\\",\\n 153| \\\"score\\\": {\\n 154| \\\"total\\\": 87,\\n 155| \\\"render_allowed\\\": true,\\n 156| \\\"reject_reasons\\\": [],\\n 157| \\\"breakdown\\\": {\\n 158| \\\"problem_urgency\\\": {\\n 159| \\\"points\\\": 13,\\n 160| \\\"max_points\\\": 15,\\n 161| \\\"rationale\\\": \\\"Visible everyday fail with recognizable audience need.\\\"\\n 162| },\\n 163| \\\"first_frame_clarity\\\": {\\n 164| \\\"points\\\": 10,\\n 165| \\\"max_points\\\": 12,\\n 166| \\\"rationale\\\": \\\"First frame shows a conflict without relying on audio.\\\"\\n 167| },\\n 168| \\\"hook_curiosity\\\": {\\n 169| \\\"points\\\": 10,\\n 170| \\\"max_points\\\": 12,\\n 171| \\\"rationale\\\": \\\"Hook opens a mechanism loop; generic hooks lose points.\\\"\\n 172| },\\n 173| \\\"mechanism_value\\\": {\\n 174| \\\"points\\\": 11,\\n 175| \\\"max_points\\\": 12,\\n 176| \\\"rationale\\\": \\\"Mechanism is tied to anti-example/concrete scene.\\\"\\n 177| },\\n 178| \\\"practical_payoff\\\": {\\n 179| \\\"points\\\": 13,\\n 180| \\\"max_points\\\": 15,\\n 181| \\\"rationale\\\": \\\"Fix and takeaway are actionable.\\\"\\n 182| },\\n 183| \\\"retention_path\\\": {\\n 184| \\\"points\\\": 8,\\n 185| \\\"max_points\\\": 10,\\n 186| \\\"rationale\\\": \\\"Before/after plus motion-led path.\\\"\\n 187| },\\n 188| \\\"share_save_potential\\\": {\\n 189| \\\"points\\\": 9,\\n 190| \\\"max_points\\\": 10,\\n 191| \\\"rationale\\\": \\\"Save, share, and follow reasons are explicit.\\\"\\n 192| },\\n 193| \\\"human_texture\\\": {\\n 194| \\\"points\\\": 8,\\n 195| \\\"max_points\\\": 8,\\n 196| \\\"rationale\\\": \\\"Concrete human texture, not just an enum.\\\"\\n 197| },\\n 198| \\\"series_fit\\\": {\\n 199| \\\"points\\\": 4,\\n 200| \\\"max_points\\\": 4,\\n 201| \\\"rationale\\\": \\\"Known TrueTrace series.\\\"\\n 202| },\\n 203| \\\"saturation_defense\\\": {\\n 204| \\\"points\\\": 1,\\n 205| \\\"max_points\\\": 2,\\n 206| \\\"rationale\\\": \\\"Saturation risk penalty applied.\\\"\\n 207| }\\n 208| }\\n 209| },\\n 210| \\\"approval_command\\\": \\\"APPROVE digital-red-flags-fake-invoice-payment-route-30s v3.0.0 af457e73844be4f7\\\"\\n 211| },\\n 212| \\\"review_package_valid\\\": {\\n 213| \\\"is_valid\\\": true,\\n 214| \\\"errors\\\": []\\n 215| },\\n 216| \\\"preview_mp4_path\\\": null,\\n 217| \\\"telegram_delivery_status\\\": null,\\n 218| \\\"blocked\\\": {\\n 219| \\\"wan\\\": true,\\n 220| \\\"i2v\\\": true,\\n 221| \\\"full_final\\\": true,\\n 222| \\\"posting\\\": true,\\n 223| \\\"platform_api\\\": true,\\n 224| \\\"scheduling\\\": true\\n 225| }\\n 226|}\", \"total_lines\": 225, \"file_size\": 9028, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_lyjR8cLmI5VpZX3AIf10Hyz6"
},
{
"role": "tool",
"content": "{\"content\": \" 1|from __future__ import annotations\\n 2|\\n 3|import hashlib, json, math, os, re, subprocess, sys\\n 4|from pathlib import Path\\n 5|\\n 6|sys.path.insert(0, '/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot')\\n 7|from PIL import Image, ImageDraw, ImageFont, ImageFilter\\n 8|from autoshorts.rendering.static_captions import (\\n 9| CaptionLayoutConfig,\\n 10| WordCue,\\n 11| active_word_index_at,\\n 12| build_safe_caption_segments,\\n 13| layout_caption_segment,\\n 14| segment_for_active_word,\\n 15|)\\n 16|\\n 17|BASE = Path('/tmp/autoshorts_proof_short_sprint30/digital-red-flags-fake-invoice-payment-route-30s')\\n 18|OUT = BASE / 'preview_v2_caption_safe'\\n 19|FRAMES = OUT / 'frames'\\n 20|QA = OUT / 'qa_frames'\\n 21|for p in [OUT, FRAMES, QA]: p.mkdir(parents=True, exist_ok=True)\\n 22|AUDIO = BASE / 'audio/voiceover.mp3'\\n 23|SRT = BASE / 'audio/edge_subtitles.srt'\\n 24|CANDIDATE = 'digital-red-flags-fake-invoice-payment-route-30s'\\n 25|W,H,FPS = 1080,1920,24\\n 26|DURATION = 31.291667\\n 27|SAFE = CaptionLayoutConfig(video_width=W, video_height=H, horizontal_margin_px=70, bottom_margin_px=310, max_width_ratio=0.86, font_size_px=66, min_font_size_px=48, word_gap_px=18)\\n 28|FONT_BOLD='/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf'\\n 29|FONT_REG='/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf'\\n 30|\\n 31|def font(size, bold=True):\\n 32| return ImageFont.truetype(FONT_BOLD if bold else FONT_REG, size)\\n 33|\\n 34|def parse_time(t):\\n 35| h,m,rest=t.split(':'); s,ms=rest.split(',')\\n 36| return int(h)*3600+int(m)*60+int(s)+int(ms)/1000\\n 37|\\n 38|def parse_srt(path):\\n 39| txt=path.read_text(encoding='utf-8')\\n 40| blocks=re.split(r'\\\\n\\\\s*\\\\n', txt.strip())\\n 41| out=[]\\n 42| for b in blocks:\\n 43| lines=b.splitlines()\\n 44| if len(lines)>=3:\\n 45| m=re.match(r'(\\\\d\\\\d:\\\\d\\\\d:\\\\d\\\\d,\\\\d\\\\d\\\\d) --> (\\\\d\\\\d:\\\\d\\\\d:\\\\d\\\\d,\\\\d\\\\d\\\\d)', lines[1])\\n 46| if m: out.append((parse_time(m.group(1)), parse_time(m.group(2)), ' '.join(lines[2:])))\\n 47| return out\\n 48|\\n 49|def clean_words(text):\\n 50| return re.findall(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", text.replace('’',\\\"'\\\"))\\n 51|\\n 52|def build_cues():\\n 53| cues=[]\\n 54| for start,end,text in parse_srt(SRT):\\n 55| words=clean_words(text)\\n 56| weights=[max(0.55, len(w)/5) for w in words]\\n 57| total=sum(weights) or 1\\n 58| t=start\\n 59| for w,wt in zip(words,weights):\\n 60| dur=(end-start)*wt/total\\n 61| cues.append(WordCue(start=t, end=t+dur, word=w, sentence=text))\\n 62| t+=dur\\n 63| return tuple(cues)\\n 64|\\n 65|WORD_CUES=build_cues()\\n 66|SEGMENTS=build_safe_caption_segments(WORD_CUES, layout=SAFE, min_words=2, target_words=5, max_words=7)\\n 67|\\n 68|def rounded(draw, box, r, fill, outline=None, width=1):\\n 69| draw.rounded_rectangle(box, radius=r, fill=fill, outline=outline, width=width)\\n 70|\\n 71|def text(draw, xy, s, size, fill, bold=True, anchor=None, align='left'):\\n 72| draw.text(xy, s, font=font(size,bold), fill=fill, anchor=anchor, align=align)\\n 73|\\n 74|def scene_for(t):\\n 75| if t < 5.8: return 'hook'\\n 76| if t < 11.9: return 'same'\\n 77| if t < 15.2: return 'route'\\n 78| if t < 20.9: return 'checks'\\n 79| if t < 26.9: return 'verify'\\n 80| return 'takeaway'\\n 81|\\n 82|def bg(draw):\\n 83| draw.rectangle((0,0,W,H), fill=(14,18,29))\\n 84| for y in range(0,H,6):\\n 85| c=int(18+18*y/H)\\n 86| draw.line((0,y,W,y), fill=(c,c+4,c+14))\\n 87| draw.rectangle((0,0,W,H), outline=(40,51,73), width=8)\\n 88|\\n 89|def draw_email_invoice(draw, t, mode):\\n 90| # phone/browser screen card\\n 91| rounded(draw, (82,170,998,1330), 44, (235,239,244), (78,92,122), 3)\\n 92| rounded(draw, (118,220,962,420), 26, (255,255,255), (218,224,234), 2)\\n 93| text(draw,(150,252),'Inbox',38,(39,48,70))\\n 94| text(draw,(150,314),'From: billing@sample.test',30,(78,88,110),False)\\n 95| urgency=(236,165,37) if mode in ['same','route'] else (113,124,148)\\n 96| text(draw,(150,362),'Subject: Payment due today',32,urgency)\\n 97| # invoice doc\\n 98| rounded(draw, (150,470,930,1198), 24, (250,251,253), (199,207,222), 2)\\n 99| text(draw,(196,522),'INVOICE',52,(38,48,66))\\n 100| text(draw,(196,590),'Generic Services',31,(104,115,136),False)\\n 101| for yy in [670,735,800]:\\n 102| draw.rounded_rectangle((196,yy,730,yy+28),10, fill=(224,230,240))\\n 103| draw.rounded_rectangle((196,872,884,1012),20, fill=(240,244,249), outline=(210,218,231), width=2)\\n 104| text(draw,(224,905),'Payment route',34,(54,64,86))\\n 105| changed = mode in ['route','checks','verify']\\n 106| route_color=(207,54,54) if changed else (60,120,90)\\n 107| route_txt='NEW ROUTE' if changed else 'KNOWN ROUTE'\\n 108| rounded(draw,(224,956,538,1006),16,(255,247,238) if changed else (235,248,241),route_color,3)\\n 109| text(draw,(250,966),route_txt,29,route_color)\\n 110| if changed:\\n 111| draw.line((610,970,830,970), fill=(207,54,54), width=7)\\n 112| draw.polygon([(830,970),(800,950),(800,990)], fill=(207,54,54))\\n 113| text(draw,(224,1060),'Route changed',42,(207,54,54))\\n 114| else:\\n 115| text(draw,(224,1060),'Looks normal',42,(60,120,90))\\n 116|\\n 117|def draw_checks(draw, t):\\n 118| labels=[('sender domain',15.3),('urgency language',16.9),('payment route',18.4)]\\n 119| y=1190\\n 120| for i,(lab,ts) in enumerate(labels):\\n 121| active=t>=ts\\n 122| col=(247,202,76) if active else (122,133,155)\\n 123| rounded(draw,(155,y+i*92,925,y+64+i*92),22,(35,43,61),(col if active else (74,86,110)),3)\\n 124| text(draw,(205,y+13+i*92),f'{i+1}. {lab}',33,(255,255,255) if active else (188,197,214))\\n 125|\\n 126|def draw_verify(draw, t):\\n 127| rounded(draw,(150,1190,930,1385),30,(32,42,61),(88,104,137),3)\\n 128| text(draw,(190,1235),'Use a second channel',39,(255,255,255))\\n 129| text(draw,(190,1300),'before paying',36,(247,202,76))\\n 130| # phone/check icon\\n 131| rounded(draw,(730,1240,862,1342),18,(18,24,36),(247,202,76),3)\\n 132| draw.line((760,1298,790,1325,836,1266), fill=(247,202,76), width=9)\\n 133|\\n 134|def draw_takeaway(draw):\\n 135| rounded(draw,(92,420,988,1010),44,(24,32,48),(247,202,76),4)\\n 136| text(draw,(540,565),'Urgency is not proof.',64,(255,255,255),anchor='mm')\\n 137| text(draw,(540,700),\\\"It's the red flag.\\\",76,(247,202,76),anchor='mm')\\n 138| text(draw,(540,850),'Save this before paying from email.',36,(198,207,224),anchor='mm')\\n 139|\\n 140|def draw_caption(draw, t):\\n 141| active=active_word_index_at(WORD_CUES,t)\\n 142| seg=segment_for_active_word(SEGMENTS,active)\\n 143| active_word=WORD_CUES[active].word\\n 144| layout=layout_caption_segment(seg.words, active_word=active_word, config=SAFE)\\n 145| f=font(layout.font_size_px, True)\\n 146| # subtle shadow/outline no box/bar\\n 147| flat_words=[]\\n 148| for line in layout.lines: flat_words.extend(line)\\n 149| boxes=list(layout.word_boxes)\\n 150| for word,box in zip(flat_words, boxes):\\n 151| x,y,_,_=box\\n 152| fill=(247,202,76) if word==active_word else (255,255,255)\\n 153| for dx,dy in [(-2,2),(2,2),(0,3)]:\\n 154| draw.text((x+dx,y+dy), word, font=f, fill=(0,0,0,160), stroke_width=2, stroke_fill=(0,0,0,130))\\n 155| draw.text((x,y), word, font=f, fill=fill, stroke_width=2, stroke_fill=(6,10,18))\\n 156|\\n 157|def draw_frame(t):\\n 158| img=Image.new('RGB',(W,H),(14,18,29)); draw=ImageDraw.Draw(img,'RGBA')\\n 159| bg(draw)\\n 160| sc=scene_for(t)\\n 161| if sc=='takeaway':\\n 162| draw_takeaway(draw)\\n 163| else:\\n 164| draw_email_invoice(draw,t, 'route' if sc in ['route','checks','verify'] else sc)\\n 165| if sc=='same':\\n 166| # No extra renderer text card here; the safe captions carry the phrase.\\n 167| pass\\n 168| if sc in ['checks','verify']: draw_checks(draw,t)\\n 169| if sc=='verify': draw_verify(draw,t)\\n 170| # safe guides very subtle? don't include in final\\n 171| draw_caption(draw,t)\\n 172| return img\\n 173|\\n 174|# render raw frames to ffmpeg\\n 175|silent=OUT/f'{CANDIDATE}_preview_v2_caption_safe_silent.mp4'\\n 176|final=OUT/f'{CANDIDATE}_preview_v2_caption_safe.mp4'\\n 177|cmd=['ffmpeg','-y','-f','rawvideo','-vcodec','rawvideo','-pix_fmt','rgb24','-s',f'{W}x{H}','-r',str(FPS),'-i','-','-an','-c:v','libx264','-pix_fmt','yuv420p','-crf','20',str(silent)]\\n 178|proc=subprocess.Popen(cmd, stdin=subprocess.PIPE)\\n 179|frames=int(math.ceil(DURATION*FPS))\\n 180|for i in range(frames):\\n 181| t=i/FPS\\n 182| proc.stdin.write(draw_frame(t).tobytes())\\n 183|proc.stdin.close(); proc.wait()\\n 184|if proc.returncode: raise SystemExit(proc.returncode)\\n 185|subprocess.run(['ffmpeg','-y','-i',str(silent),'-i',str(AUDIO),'-c:v','copy','-c:a','aac','-shortest',str(final)], check=True)\\n 186|# QA frames and contact sheet\\n 187|sample_times=[1,4,10,15.8,17.8,20.2,24.5,28.2,30.2]\\n 188|thumbs=[]\\n 189|for ts in sample_times:\\n 190| im=draw_frame(ts)\\n 191| p=QA/f'frame_{str(ts).replace(\\\".\\\",\\\"_\\\")}s.jpg'\\n 192| im.save(p, quality=92)\\n 193| thumbs.append((ts, im.resize((270,480))))\\n 194|sheet=Image.new('RGB',(810,1440),(12,16,24)); sd=ImageDraw.Draw(sheet)\\n 195|for idx,(ts,thumb) in enumerate(thumbs):\\n 196| x=(idx%3)*270; y=(idx//3)*480\\n 197| sheet.paste(thumb,(x,y)); sd.rectangle((x,y,x+269,y+479),outline=(80,90,115),width=2)\\n 198| sd.text((x+12,y+12),f'{ts:.1f}s',font=font(24),fill=(247,202,76))\\n 199|contact=OUT/'digital-red-flags_caption_safe_contact_sheet_v2.jpg'\\n 200|sheet.save(contact, quality=92)\\n 201|\", \"total_lines\": 234, \"file_size\": 11146, \"truncated\": true, \"hint\": \"Use offset=201 to continue reading (showing 1-200 of 234 lines)\", \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_NPTV7A1No62mNcR39UkG7SNl"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_j27WOnLBjGZ9L5wFTKF2QmMc",
"call_id": "call_j27WOnLBjGZ9L5wFTKF2QmMc",
"response_item_id": "fc_051a8a0b2fb58918016a149c273efc81918abd110f2a8ea037",
"type": "function",
"function": {
"name": "skill_view",
"arguments": "{\"name\":\"edge-tts\"}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Exploring video script adaptation**\n\nI'm considering adapting a render script for the next video with TTS, possibly using EdgeTTS. I need to check if EdgeTTS is available first. It seems like generating a preview could work, and since the user's message is text rather than voice, using TTS for the video seems fine. Maybe I should look at using the edge-tts command or check if the edge-tts skill is relevant to TTS. I'll load that up.",
"reasoning_content": "**Exploring video script adaptation**\n\nI'm considering adapting a render script for the next video with TTS, possibly using EdgeTTS. I need to check if EdgeTTS is available first. It seems like generating a preview could work, and since the user's message is text rather than voice, using TTS for the video seems fine. Maybe I should look at using the edge-tts command or check if the edge-tts skill is relevant to TTS. I'll load that up.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJwn1q8HPCNEn-4weRTg93Tp5VQbhHfPHyRYvCeCXQm5O62IucURT0fee20BeD8yofiNEQPZfWQlLS6gAr1plx7mj9bDFCwW3nMlF0r693pHHjcqY7xshFCiJhME5qPyZMbO5H65xgj0uyugRSSWsE7II8JhenNmeVSrD5sTAszu3JiGx9d5k6m6NRLD2lO0A0-lE4gLKkUn_L2d2TjMzCRrSmTkYKD-PrEtdwD11QMTunxQY7xuEZ4rmO0UmdAkd1xyjtFCNU2vDW9pjJ86ISbYs7ee8U-Gb-14g_ZIHcK0QEGiSRR_qpjJZ96g1kEPvgakS79WIxdnB5llg65_VJn88sFHbRPZ-Ajdj4rduXRmVVAVOqWREyF8KTjKrxpvgIUcKrn4ClAh2LuANaycrTULMoBgMxNUvCKODW9Sy7uyXxR8WKnlZLZmdU7SsY10WZj28nk4nOaH6AYH0ZqlDYp5Vwda_Tsg2L6nWiOmzT5U-hkLAQNsTz41NrWgOBNm52CcwrSi2OAhpGCf_1EagVfTVvhjuqjwhQQsnIt7Ms2ciJpGbM-cf-IdcZAWVEAzun8ljUaHYieD8sEmYskb-9wjbEQAAcHz4cdj043lWVmQWVXvUexIZr35SWSM72Y3ARiucVjj_fbOQw82ncXI1pPVL7ZAksrMXXPspIRueWoK-0hgFPbrLjtQwOOUikI5Xj0-ep9RBfpEmm8VDAa-AJnE5U-7qBDn21nKRCbderhAEzMW68jlWcJCAhH1J-tyKgyLmw17PhV1SuJlCziQVNY44YhXNTEUhcXOlO9L4TMhQOkn74kyZaijpxsm8-45cHKuauN-pzUHRckzEt31-KljpiEs438Jq_uvDh4cmzOi1pDxG1gHxCBrJxgHvDdIi_3flRKuWvYN1PMRLEB_iiHx5rLgLTCcgg2DmgMRxCP3MG-T80MxgCJRXjipp06bD3ATnBZjqvFUN0T4LVzz45V2abgt-SZs1H1th9JvbJMi0WU6IUKJpZpjGfaegThNDojqGTaBUayfxYwm3cs5DRGDNGROpseDHoKVwZsLCyyASdJpvLe0jE71d4C0e8OHInyXunsAkgsUIdUkHznBZ-drKKNl9qAvan5sXdS5WrpQEjmwYj3TvG5Px5aw82QMwoGl0yz6u5tdNCxNH7SdDZm3UvVQ0qXArdsZrTLFeQlvjf7jJrb_hchjzNHpuRKdBc6xQstjdMG6i9F5x_7b5aMnIIzlxaWOSIUD9FWL8UZ6Bja7Ote4cEZ7v9RN82FmbhqEClpRK5L9VOqX70p3Kf4zm6FTEB02O_llNGn0VSNLowJEdVRWdVj4QN4h_FM5mN9Z",
"id": "rs_051a8a0b2fb58918016a149c2296908191b45421fb23fbc0d0",
"summary": [
{
"type": "summary_text",
"text": "**Exploring video script adaptation**\n\nI'm considering adapting a render script for the next video with TTS, possibly using EdgeTTS. I need to check if EdgeTTS is available first. It seems like generating a preview could work, and since the user's message is text rather than voice, using TTS for the video seems fine. Maybe I should look at using the edge-tts command or check if the edge-tts skill is relevant to TTS. I'll load that up."
}
]
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"name\": \"edge-tts\", \"description\": \"Text-to-speech using Microsoft Edge TTS. Supports multiple voices including German male/female options. Used for voice messages and audio output.\", \"tags\": [\"TTS\", \"Voice\", \"Audio\", \"Edge\"], \"related_skills\": [\"sherpa-onnx-tts\"], \"content\": \"---\\nname: edge-tts\\ndescription: \\\"Text-to-speech using Microsoft Edge TTS. Supports multiple voices including German male/female options. Used for voice messages and audio output.\\\"\\nversion: 1.0.0\\nauthor: Hermes Agent\\nlicense: MIT\\nmetadata:\\n hermes:\\n tags: [TTS, Voice, Audio, Edge]\\n related_skills: [sherpa-onnx-tts]\\n---\\n\\n# Edge TTS\\n\\nText-to-speech using Microsoft Edge TTS (`edge-tts` Python package). No API key required — uses Microsoft's free Edge browser TTS engine.\\n\\n## When to Use\\n\\nUse this skill when:\\n- You need to convert text to speech for voice messages\\n- You want to test or compare different TTS voices\\n- The user asks for a voice message or speech output\\n- TTS configuration needs to be changed\\n\\n## Prerequisites\\n\\n```bash\\npip install edge-tts\\n```\\n\\n## User Voice Preference\\n\\n**Default voice: `de-DE-KillianNeural`** (German male, natural, clear)\\nSet in `~/.hermes/config.yaml` → `tts.edge.voice`.\\n\\n## German Voices Available\\n\\n| Voice | Gender | Style | Description |\\n|-------|--------|-------|-------------|\\n| `de-DE-KillianNeural` | Male | Natural | Clear, natural, slightly youthful (DEFAULT) |\\n| `de-DE-ConradNeural` | Male | Friendly | Warm, positive, slightly melodic |\\n| `de-DE-FlorianMultilingualNeural` | Male | Professional | Clear, neutral, professional |\\n| `de-DE-AmalaNeural` | Female | Friendly | Positive, warm |\\n| `de-DE-KatjaNeural` | Female | Friendly | Positive, clear |\\n| `de-DE-SeraphinaMultilingualNeural` | Female | General | Natural, clear |\\n\\n## Usage\\n\\n### Basic Synthesis\\n\\n```bash\\nedge-tts --voice de-DE-ConradNeural --text \\\"Guten Tag, Sir.\\\" --write-media output.mp3\\n```\\n\\n### Testing a Voice\\n\\n```bash\\nedge-tts --voice de-DE-FlorianMultilingualNeural --text \\\"Testnachricht\\\" --write-media /tmp/test.mp3\\n```\\n\\n### Listing Available Voices\\n\\n```bash\\npython3 -m edge_tts --list-voices | grep \\\"de-DE\\\"\\n```\\n\\n### Configuring in Hermes\\n\\nUpdate `~/.hermes/config.yaml`:\\n\\n```yaml\\ntts:\\n provider: edge\\n edge:\\n voice: de-DE-ConradNeural\\n```\\n\\n## Pitfalls\\n\\n- **Voice compatibility**: Not all voices work with all text. German text requires a German voice (`de-DE-*`).\\n- **File format**: Edge TTS outputs MP3 by default. Convert to OGG for Telegram voice messages if needed: `ffmpeg -i input.mp3 -codec:a libopus -b:a 128k output.ogg`\\n- **Gateway restart**: After changing the TTS voice in config, restart the gateway for changes to take effect.\\n- **Character limits**: Very long texts may produce unusually long audio. Split long messages before TTS.\\n- **Config verification**: After updating `tts.edge.voice` in config, always verify the change took effect by reading the config back. YAML writes can silently fail or be overwritten by subsequent edits. Check the TTS response field `voice_compatible: true` — if `false`, the voice may not have been applied.\\n- **Voice switching workflow**: Always test a voice with `edge-tts --voice --text \\\"Test\\\" --write-media /tmp/test.mp3` before committing to it. Multiple voices can sound similar; listening is the only reliable way to choose.\\n- **Config persistence**: Python one-liner YAML edits may not persist — always verify with a separate read-back step.\\n\\n## Shorts / AutoShorts Baseline Voice Use\\n\\nFor short-form content pipelines where the GPU is needed for ComfyUI/Wan/Qwen image or video generation, use EdgeTTS as the first baseline voice because it does not consume local GPU resources and is quick to iterate.\\n\\nRecommended first English A/B voices for a precise, non-guru AI/workflow channel tone:\\n\\n```bash\\nedge-tts --voice en-GB-RyanNeural --text \\\"Most AI automations do not fail dramatically. They quietly rot.\\\" --write-media /tmp/ryan.mp3\\nedge-tts --voice en-US-ChristopherNeural --text \\\"Most AI automations do not fail dramatically. They quietly rot.\\\" --write-media /tmp/christopher.mp3\\n```\\n\\nFor AutoShorts-style production code, keep EdgeTTS behind an explicit adapter boundary:\\n\\n```text\\nTTSProviderPlan(edge_tts, voice)\\n→ EdgeTTSRequest(text, output_path.mp3)\\n→ edge-tts CLI call\\n→ EdgeTTSResult(side_effects=(\\\"call_edge_tts\\\", \\\"write_audio\\\"), external_calls=(\\\"edge-tts\\\",))\\n```\\n\\nThen mux/burn captions in a separate FFmpeg boundary:\\n\\n```text\\nMP4 timing preview + EdgeTTS MP3 + renderer-owned ASS subtitles\\n→ FFmpeg audio/caption review MP4\\n```\\n\\nImportant FFmpeg pitfall: do not blindly use `-shortest` when adding audio to a longer timing preview. It can silently truncate the video to the shorter voiceover duration. Preserve the planned video duration unless the feature explicitly asks to trim to audio length.\\n\\nCompare against any external/cloud TTS such as NVIDIA Magpie with the same 15–20 second script sample. Score clarity, pronunciation of AI/workflow terms, retention energy, artifacts, latency, cost, and operational reliability. Whisper is not a TTS model; use it later for transcript/alignment QA only.\\n\\n## Linked Resources\\n\\n- `references/german-voice-comparison.md` — German male voice comparison data from session 2026-05-07, with recommendations for voice selection.\\n- `references/autoshorts-edge-tts-audio-caption.md` — EdgeTTS boundary pattern for AutoShorts audio/caption review MP4s, including ffprobe duration alignment and the `-shortest` pitfall.\\n\\n## Voice Switching Workflow\\n\\n1. List available voices: `python3 -m edge_tts --list-voices | grep \\\"de-DE\\\"`\\n2. Test candidate voice: `edge-tts --voice --text \\\"Testnachricht\\\" --write-media /tmp/test.mp3`\\n3. Listen and decide\\n4. Update config: `tts.edge.voice: `\\n5. Restart gateway\\n\\n## Related Skills\\n\\n- `sherpa-onnx-tts` — Offline TTS with local German female voice (Eva). No internet required.\", \"path\": \"edge-tts/SKILL.md\", \"skill_dir\": \"/home/agent/.hermes/skills/edge-tts\", \"linked_files\": {\"references\": [\"references/german-voice-comparison.md\", \"references/autoshorts-edge-tts-audio-caption.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\", \"metadata\": {\"hermes\": {\"tags\": [\"TTS\", \"Voice\", \"Audio\", \"Edge\"], \"related_skills\": [\"sherpa-onnx-tts\"]}}}",
"tool_call_id": "call_j27WOnLBjGZ9L5wFTKF2QmMc"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_QkY5hgA5jbKPPcf8vfv1a7pK",
"call_id": "call_QkY5hgA5jbKPPcf8vfv1a7pK",
"response_item_id": "fc_051a8a0b2fb58918016a149c3553b4819195354d40d2474f2e",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python - <<'PY'\\nimport importlib.util\\nprint('edge_tts', importlib.util.find_spec('edge_tts') is not None)\\nprint('PIL', importlib.util.find_spec('PIL') is not None)\\nPY\",\"timeout\":30}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Considering video content**\n\nI need to create a preview video and decide on the theme. Perhaps I'll go with \"Calendar invite trap: meeting link vs domain\" since using a QR code might lead to issues. I can develop a script warning viewers about the traps in invites that look normal but may actually lead to fake login pages. Before clicking, I want to emphasize checking the sender, link domain, and unusual login requests, reinforcing the idea that a calendar invite is just a request, not validation.\n**Exploring video preview options**\n\nI’m trying to figure out how to render a preview with mockups and active word captions. I might use Edge TTS with an English voice for text-to-speech (TTS) but need to ensure it has exact timing and forced alignment. It seems Edge TTS can write subtitles, potentially in .vtt format, which could help with precise word timing. I should also look into existing functions for static captions to integrate any existing code I find. I want to ensure I get the word boundaries right for better alignment.\n**Utilizing edge_tts for audio and captions**\n\nI'm looking into using Python's edge_tts to take advantage of its WordBoundary events. This could help me generate MP3 files with precise word cues for timing in speech. I plan to create a script using edge_tts asynchronously, saving audio chunks along with their word boundary offsets and durations. This should improve the caption rendering process significantly. First, though, I need to check if the necessary package is installed. I've got to ensure everything's set up correctly!",
"reasoning_content": "**Considering video content**\n\nI need to create a preview video and decide on the theme. Perhaps I'll go with \"Calendar invite trap: meeting link vs domain\" since using a QR code might lead to issues. I can develop a script warning viewers about the traps in invites that look normal but may actually lead to fake login pages. Before clicking, I want to emphasize checking the sender, link domain, and unusual login requests, reinforcing the idea that a calendar invite is just a request, not validation.\n**Exploring video preview options**\n\nI’m trying to figure out how to render a preview with mockups and active word captions. I might use Edge TTS with an English voice for text-to-speech (TTS) but need to ensure it has exact timing and forced alignment. It seems Edge TTS can write subtitles, potentially in .vtt format, which could help with precise word timing. I should also look into existing functions for static captions to integrate any existing code I find. I want to ensure I get the word boundaries right for better alignment.\n**Utilizing edge_tts for audio and captions**\n\nI'm looking into using Python's edge_tts to take advantage of its WordBoundary events. This could help me generate MP3 files with precise word cues for timing in speech. I plan to create a script using edge_tts asynchronously, saving audio chunks along with their word boundary offsets and durations. This should improve the caption rendering process significantly. First, though, I need to check if the necessary package is installed. I've got to ensure everything's set up correctly!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJw1YBQWh1WNRoVUc2FGaAle_DotkoeelSA-0P4XTYfE6Aeqtn-7GUNbVFfuuq6htm6_MbYE7m2HK3zgKHXcNJ0A3sjCeeL2nQRo8zl783gHKW9xxSVyHe5nnOnVM_74pcTJoJbN-D01kqerqV7vRU4HAk94BrFtNFlV64W1qgmlXpxAi0vcDeIztQRtnXf2jOtsNSaBkOj8pYQZQ8LCtgvSBr75alGmipW3s33528My5i2ki4RxCY4HsQ-c3HkJLyma7Y6xQZjYzVJCKD5oJb8INtzEGqGq3fJq8PXXl_qMWCN2Yvt7eKmoGSZi8irFgS1AIePOrMbDJstDAwgPpNRPaP7whjqkmlB9_jm4UOwEG6td2L0ot0NoTeYj6ePDOWGCul4_UewvJFDjAq_H0yYmrIrNMgK0BPw2lQo9jjdPiDJy2i3Ca_fAxSjhN8ofYWyIW4uIsVXj9ARJLkMpn8GzWYXgkMiHVKBg2QLv4_0_HnonTLnLbMLzUQEFTzGBG4VH1RWFf9jZbuYSB6HcDRoEVgE27bb5q6la-HFe_aXZ2T38U8R89NN_WltRFdCx2E86M-Q_lK8_4CEsmTBGFh5id_Tw7AoMFBK63A7qyQSmYKfXeMTGfe3dR5b4Ce6PFF71VWFpPPxZ-V5GXH4Bpa9uOZGX-qSVM1t2rnvLBuJ5TB1Kbc1lng3svpomymkyoVfvU0FwHZ8Q6nNurfs8_SxXqP67eLXPukd7q1KpMwNt4YSxzky7RcZabOnFk9EiOOcLTaWgp5H1Kw6BsQMCJZL1wphpATX4E5Bp7iqqnQH6PI8YwTX0zBJn2U6TYr8kFA0RMiuC_QImYfx7fC19MIjCe6P6mskN6dIEjiaa0XFW4Zr9zrjs_NWRS2j2Sc5SViQLHO0bTyiCyS-_v1Uie368FozMUYn97BQfUE0jK3121e8_kI4J5G8509ImlND-K9U0N0EKvIPmx4Haf7GoVe7VSHxPPD1uqYql9vAUdYV7l8Q7ZbK26YtCIcUayxO1FXfpGzM3fgodwTeimzGhdPXsywxhI29YyVJCikj7QjGiwgukBO7bwsaMbT8cHaavI9rz_NQq5jPqG_rNHCMABLDRcg9vrU3e0ImV36piTTN3oBANAClGQ_6Fj8_bf80gOgHl9M_EF6c0DVTyJMojCyX7z0jDQB68hZlcxWqM4Pi-meF9WwWWT_EhGNlhPxOPkRCUl5dWzuqPkEnOD_F4louiVu2eEWnzM-s-FOX_pRkmf7FyYd4Q-6FOmTJ_32ijLxE5xsU-unZWGbnTCRKBNXBuZRY_jiH83vBBckb42Xb5P0kveIn4KDoOCV8FhFOarUdyTLq61uGqKurtN-qFiSlD6Le2zEVaEgt_QPNVOcgW3cG0bT2-Zl-E9vnR-QFjuVwZjnVrFE7j63rcZhObLWJhPx5PE417TSklrMo0VkBG9zFM2v_xx1_7OMpAgZTJGpPxIYWX5P8rwO2iA1J4WYoN2IA8zPvyW6t3quM5Cc-ug98UNQcq3TrV7NzAXO5Klsv06jNKTYai_x5w05JYN3-Gx2Oq21IXvAAou7ZiVD-uNpdaN6zUuzplTqr0rJXckbSU21hWdf8p5tnJJzvom-YQ5asRJyjzs208DapCo437euMhPSFuJQEyE6iedpRp1LtxTMmyz3U5EVeg0uKEWq9a4uLp8m_H5lWERGWtD0y_lPP8SGm3hVO8qq6I-jG7r0Ano-U4w7dOeHoZxTE2KtyCkYWV5XSb3icu0ByC5t1f1feb19SLnaYRHD-msf56V7pM8TzNCkiWsG9NjZ43d0rhm85o0mlI5CItG-tPPMpfuoJfHkYrZG46vibmyJxlgwrDaVJFGsPQEeBuB8Xgv-ykxpgr5dwliwDj2chFY7XJ-XkvCuiUaUNLmsvOMqPXdZ7VG8KHDz3pGJRU9eNJfUNOuRjRtKJPonxUlBviIrONsFIKvU0zkqrpWdMwCSG1yN92QwT0tGlq5CJgmg1GcaVFuYPIUFoLSLnvbwtXaJmLs8QXwZ4jCh36CJ3Vt06GozIsL57_jSTj3dwVp9aJxyQ2Qe9oxK4Pp1TVGyYIGT_UDYL8YEDYMGqesc5p0w4HIjWNluMLOUApx4OVinXfBjCPSMz_O7AzwVTsCD4_-l9DKSuCtSC41Jl2n71GeZJgnPH9W4XcqZSSCESVTnR3mNVLbpfq5IMdL2PCoWG4yDsZkxtZRFs_n89zSruqeHzCHOibR0PkZlT6VVmz4KC5O-MCpeXNX4XcRHENjyU8sa9_TaKz0elZoiRRIOHOz_E5Zz-m3PtngJZL3eR5oSPQfF0AhNHdfLoV-M9_drHlAEALVLtk3XaCHxQY27kOxBenn-fW2NkeroEH43S6GNJqEtQUZ6-BloCY9NhbkXh6-cnmGrlF32vJ99tnLkXcUR6EQCrBp3Lu154zLE9VjgasyA059XrCshmtuKOX4m_BaEETRCBXY1Ij76OiprOEUf8YG4hI2dh-2a9onXCEGwgCSeckBiWxBWO_OtPVre_-oFV4OtZJJy29CV1LXjTWbiZ5jN6-88s7kbAukwYqNPkK6iu6EgKPZhMoE5YHoJODXXgNWAgpZyAoJiZSmgu4ln_DRHk7MBnDyWSx7kxxBh0ZVro9ko9rRVSo1kdX9fm2TTuzomH2wjQUNXaZuQfPqoqy0scbiH5PZjXrnQ1znbTzoMz0PpAIUr6Em7pmjqvFgW6BPO3LvutQ8PD4RizymJK2wXlK1UXcnZsrifeRDiRvT1PlxP6jKhtqJEZF42Ll1IxTcqWe7gVnmYy0pT34xjhftA-thubDySeOaFXDunq2w1Twan0_ZccqP6fmDyoo3yMHIcpt6fQRp4j9vtrIAZ_CQlbyO4l4eWUVGjLcgmu-1Q5JXnnmij-wuJF98c41ztVRTX6mvcr34AwGxW4iNd4EaPgxizid4VxOOTg3ARiF3SQzpwrRrTUAh1u3TEZxAulX1vZFuHH8VcGEpdsiHfgCp0SjPj_jFZ5_NqY2H9x-3uPj5TTnEH9kmEGkJ0QNUsLALdbtdduQTH7O_ucXdeIeQcpNAxb-yy_HVDfeuySusk82yxgyhgDAUWmH2KYPjDiNRFk_tg_dJX0Su8n53PL575JtXUBrqSx_EAY4lm5789VC02Czg_9MXcwQFZ5ImUyPHl-6MRYQg1ZAtdPchBjn09omohlcaZxCFlmE8FmRgzHgi2mhM3AME_yRzbEP87q_m0vQoYR2hUAnF3yZuwlIq3WiOgnnOVL7SRnf5csLSm6PDTu2gdQz0cbZ9LCSbcCLg2kbq6_4EbBPU63KI7RrsiWqnu5U-E7qrHcnAIUwPU3N9QbwKB0jdRskZuTn_hEYciqCjE0VZSPlo-ER5X0iDgQ3ehi16O5V8zubrrJHJWqPB62zf-ZtoDKs-trHMDlRj8iPddo7dj2vvh9lG8e-y6eZlw-xkE7jZq26nfoYVmyXfQFfBDm0YvH9XEvTi8tmqKli2V6-w1AAAXFZxD0s6BP4iMHM-Sle6Oyj43-gfm8P1FN79j3fubaOrnkQ_ugReEmSRx61rBc2FFH4EX296QqgWpZ2MSWjrUY7WegYPXLf6p319Pl5KUi0KOcX1V9pk_5eiIhfeuN7wFfWhXC9T9HFf3vcHnXTxxHOB7k9js051ErNyf_xLDDmzqIIHQ2Xm_8ywaLIV8-UPad8_jauzaWPrmrHU6_0mYt0YW4wQ_fL7YM6d3sPz9TC3dMmATST-gNUG-4SCqxY3PtGP7-bceJXABRvyiry1JJlPPeTEvdYFA==",
"id": "rs_051a8a0b2fb58918016a149c2900408191ae86db959a68f62b",
"summary": [
{
"type": "summary_text",
"text": "**Considering video content**\n\nI need to create a preview video and decide on the theme. Perhaps I'll go with \"Calendar invite trap: meeting link vs domain\" since using a QR code might lead to issues. I can develop a script warning viewers about the traps in invites that look normal but may actually lead to fake login pages. Before clicking, I want to emphasize checking the sender, link domain, and unusual login requests, reinforcing the idea that a calendar invite is just a request, not validation."
},
{
"type": "summary_text",
"text": "**Exploring video preview options**\n\nI’m trying to figure out how to render a preview with mockups and active word captions. I might use Edge TTS with an English voice for text-to-speech (TTS) but need to ensure it has exact timing and forced alignment. It seems Edge TTS can write subtitles, potentially in .vtt format, which could help with precise word timing. I should also look into existing functions for static captions to integrate any existing code I find. I want to ensure I get the word boundaries right for better alignment."
},
{
"type": "summary_text",
"text": "**Utilizing edge_tts for audio and captions**\n\nI'm looking into using Python's edge_tts to take advantage of its WordBoundary events. This could help me generate MP3 files with precise word cues for timing in speech. I plan to create a script using edge_tts asynchronously, saving audio chunks along with their word boundary offsets and durations. This should improve the caption rendering process significantly. First, though, I need to check if the necessary package is installed. I've got to ensure everything's set up correctly!"
}
]
}
]
},
{
"role": "tool",
"content": "{\"output\": \"edge_tts True\\nPIL True\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_QkY5hgA5jbKPPcf8vfv1a7pK"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_j1t6QCyo7CRzx40XkvdSyOVv",
"call_id": "call_j1t6QCyo7CRzx40XkvdSyOVv",
"response_item_id": "fc_051a8a0b2fb58918016a149c388d8c8191be29272bf1f6ded8",
"type": "function",
"function": {
"name": "search_files",
"arguments": "{\"limit\":20,\"path\":\"/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot\",\"pattern\":\"static_captions.py\",\"target\":\"files\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJw4_w2D_kiaYQD7PTPXzgySFQEvvmdO8TkDJwbWi3RovkwHzVLvzmD0HbmkcG8CyRWfDlYW56Jz4eed9rGn5bWaIw-IMriK8boFcAMXYpU1k6vsqI6zFneiX2p_kNjBW7p911DXct40d3IaM86vEGCEGcLwc_5DLnQ4rVmgZ5Y3Oor-VNSG-Pz44mQSGDc3MuN_tZ6Td1V35Orser9INYwNDeys3Rc1jzO7OkPnqFr4UyXX-PPr6YxgbCskXinoSZI2OiDkTqb6RfrHCgAMbL_6pAznbCed8dDywxd1NTbJf3nXqDBl3bmpBKo5BAU6S7-VnFvzwMAC7UUibp-ga8HGOU6YvCekKq6WcqJpXQDVxoHaNGE1nSGuiULtECdc9uA5uZDEhVh7B2zDHU4q5p-2zrr1K8iKYaJOwhFbEYymeYm1QQWlYz12cYrhnTkGzSbXJoXh6lZpnbJw_jM62vPgRtnxX79oaA1_MagJ1nJaomlzbBzCX5rgxRV0Ibl7MmXIVpJc6eRM57G9NNcT3qbg7tdi3I6ZzeP1m443sj_6LH2eedw7qTiCdDB8ggQljL3eGKiouriSCETQXKEpOvehFZ94tJmAZeUVnnyKwCcNt29pLmfB8IKpAqRlA1AjqwMYEzcpmfTBYDEHJUOBaB0OJFnM_KRsM7hYC3J1PTy_K3dubvxEdtjLfq4Hw_n9WZkrUasI7N6l1QGC3bBhnUxdJWkU13wu5NTweA9dxE6anm0rZavZ4RQwTsGYTmcPMQwpzVmI0PTiu1UbVkOQcGQ9ZtBrv2HNj3j0rl1u4a0EcmNsfe-pFb4XbI1Q3sAmH5SrW5ZkJ_6XkNTF_MJ36vipPl8ZZlFDmIthHtQxKhq7JmfYfzp5aUWZe8ino2WkQt6CjgEDONlCjTFd_iZ9Eml6Mw7e33Ej8JUHGvEOiJF3WH6xbvwVmJ8HzgjaHpCkKRkeXevlTpfy3UBv252kCNAAhrWmTRL6-wrKjAAWHNrqHbqKDbcpPnjRlLhn-MdHbLJNkX4G2Bd3BlEBRUyP_0YyVg==",
"id": "rs_051a8a0b2fb58918016a149c379c388191b6a53024a980e65e",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"total_count\": 1, \"files\": [\"/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot/autoshorts/rendering/static_captions.py\"]}",
"tool_call_id": "call_j1t6QCyo7CRzx40XkvdSyOVv"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_vSNvjcFut5vg6i25DS7RGkoY",
"call_id": "call_vSNvjcFut5vg6i25DS7RGkoY",
"response_item_id": "fc_051a8a0b2fb58918016a149c448d9081918ebb503d2b58c338",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"path\":\"/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot/autoshorts/rendering/static_captions.py\",\"limit\":220}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Considering audio captioning**\n\nI'm focusing on audio that lasts about 33 seconds. I need to ensure I'm using static captions generated from word cue objects. For this, I'll use WordCue and apply the `build_safe_caption_segments` function with parameters like a minimum of 3 words, targeting 5, and a maximum of 7. It's essential to avoid big bars and to establish a safe zone. I'm also questioning if I need to check the read functions API for further information.",
"reasoning_content": "**Considering audio captioning**\n\nI'm focusing on audio that lasts about 33 seconds. I need to ensure I'm using static captions generated from word cue objects. For this, I'll use WordCue and apply the `build_safe_caption_segments` function with parameters like a minimum of 3 words, targeting 5, and a maximum of 7. It's essential to avoid big bars and to establish a safe zone. I'm also questioning if I need to check the read functions API for further information.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJxE0biXmQ4JT1i1bphH6HZMtJNAIn1JEh7m6lsAw_U_Te9Akw2o9nSmQYedRlaGcEgH5_eCUFfY8U0DmBxLepJ81i_C8Js93EPmlgtvFcc61FVNhr74U4IQ9ImXx59N8DfAeP4C51Z6VjhtsINgZf0uOfI5rgMI9AqJzSu9FfC8d8Qz81FFH_Wf-XR2vUzszd6P-SzTWqCNpkmsKA0fIEmvcSCFFpCYKTiw8QvqLKm5ztJdap_cQpFnQSJ1YZEvCBY7TBZ9O79sz5SMt2c79xoEHYPxqrFvvT5fogL9yvi6BDpcACpQbpZ-L7qtVM6ALw3e2t7VELMztt3Nq1qtGD_9ZcuAWUNPyriEQBlnhrUyOErOdYACAHVz8H9VkVYUGVN8O7Mkj5pMLvlQ_Qt7qJ4gPcHeBzho0erIvG7-dhM97LPegYahmLaqdA70qbSk7AW30mPX_DV_c0LqY7JncFKKfYTIUAEnTPz-cuBn5NqY6gjx4proP5uaAq-eF6v2KWTE5eTvLutP3MLpdA-TUNZ_jm4ul0Hf2CrcUVH4nf1ezFjfs8PdiVvfx_OdUBHpm6NNZohAZvvsuLJN25r-qIahmXElq2sjH3xHVj9PU8RhWzw4GQPyJvLkqI25WUPWBuZPy1r782JLVGxSrtJTsQiRQzafEhgXa8vyRkg8CvBzdx9jBd2CJFO1o0mwMOx-Q-1HpdRnZpMXlWFMsu8Img0OE_NFjtCNbchxv0Mc6JBJLJ5IbUdPPpZyj6V5vKQ98xeaSev0wylhfjUYExgwrDgq7VXigK_Sg4Ze2sUDJ3s-GGvAbyn-LzX2DyBiKTKHDTpCk5UjIs9JHzMZZFqzoi2F0mTGfdcDlnAHdY8vsNAOcs_1Otc6gDKi0hOByahk3kPwvMV31oDDVPL_XIL82XUt5RVXbY4FZ6LcO3lggyqj6WZgUCH2qHhtHrBY4gDtcQQJ_z8z8DiRYhXl7IjyRGqZQxiR84AIToeGHt9kTyxub6MRtFtIh909b31uJegnpUxZhGYgjxMeV2Vr28AKb9gx2xW2d8YSjDDRdglpyiiBZ4D2Z-jR-jFFLnck_smKcoaOjIavSgL1W4LQEsCw4wOrsuLFUx7jvn4OP1L_Jd8QAA3tdC4irKk7QBJCc3R3j2Vfo33WP42HcCbMBs3wbpVJdCmVhY2dLizaQUEhYM0LTCgZFOt6db5rF8syF-WHcgNbUVyb1KsPB1jWClqOJrGRLCnwbf5IwOz5av1hX1UivfHJe0PBfJyK-V_79hqYIB9TSPruOso0SHjGJIRKpTrNWUdWgnOqS4MFSBhzKqTaVMF_djwsreFtEW-2ltAC0mfW-APx3s_7pV7dpC_ypBU4gJxQA8DA1btWflF3vQz3mMGwAUH45L8tiw6V1PNGAYnQD5P8crtxOpTr-aENcPCILubphWL78NF-4DkjU-p-4rbNh_NEgkry4TZLQjPY6MHRZjsraAalaQk_BtC55pRRK1xoGXRuMbEpY0KnCuHGf0CPZ7AUEnKoDYy5GouGyJkr2vxAAFOrSHij8Na2TAewepqYA3xzIXFifBRXC98n85MJMurcqBQ1Nvz6wQ3jc3X17sZHp3_soNx5LUOhfagpY7vzG7H9KMRI60MO3wkX1h6fYOlc3lZg7dbtgzYME7cssgesW-hmzf68_kXcx2ZbrWT84jxN3nnqBGWS8bCyKYwgbfRR5GrUfc2fwmTbmuqshK9fdOJyEVq_9PTHQQf1HT9JDfPO9i2WiWfZ4bZz4Xd8UTwtC6tRLE2q7Q626KNGi1u_Sy7XwpMbZ2X2BYFsRBQ3It2-a9wnBK4k0hLWsf8yHy1gfY4qQh0oEcGwH5uDmyRFDT-09tAVfcgcODgRm5zFYmwUZMYFtyFA21Huf2JEE7gjP0FepYPThKHBMErhgYirFopivjZ3JJtNzVNE7LpTcrMN18WtXAP_9Ve_s34hBCQi1s20e4YaSI9mw_mYk_5kyWvYjY8XfIzqGf8zvhEm6CUL10gF6CZ7sNrkiFJ1n87QciqHNRxVQQYarONCgl5zBF9EwqUivxZgdmuwgoffZDfVi5wMMlkbQyUfyAaCtrtweRoNCA_vyH926BB1wr4SdQuXGMdDpedN5NXd5J4z8GaO0QZnJauvq1wSytn-h5jvBW1QFc7hMRKu5lva1dKMvchVUa_zG49ZO2YT1r6xx-vay8mYxWHvNMJGSzFBlP_nSHB21HyeME0giOqMp_bws8tl8VJNH0SU83ngzt9GctArf3tfS_s4788d6UK3M6AylYQMOyMPsfly0A9P5QXCveyNZzb9Gy_zeD8jwkYR8_clxcZOMl9siuRZHz6Ddb-WU2aeM8gtZVpuxDdDwfauh0AUpSFiJh_RYJa2pnQLKN0g-g-1RBlNlx52D6UJ6doRPQ8jljvBAGbQHAy5SedWLQUd-paN5Tv11RJOXnaIEEbYJyBPEWeot50KCG9GMP3xpIIKDgaZHhKoWf78mWhImZ-LhlFm7aNQbhq0B1Gy1NmTpntAzgUSuwk2SS0YRMcavOtwLxdCJxU9BRBYz0-jvbv0Dr7flKllP6Ct4jQW4lfcjFaDR4WsusLJavJeFi92BVbDnJll2Bg9b6tILTAXr17iGntrVeH0StSkT__E55EeCWiHPhol74xmBZg=",
"id": "rs_051a8a0b2fb58918016a149c3bcf148191b8db73df4a6c603c",
"summary": [
{
"type": "summary_text",
"text": "**Considering audio captioning**\n\nI'm focusing on audio that lasts about 33 seconds. I need to ensure I'm using static captions generated from word cue objects. For this, I'll use WordCue and apply the `build_safe_caption_segments` function with parameters like a minimum of 3 words, targeting 5, and a maximum of 7. It's essential to avoid big bars and to establish a safe zone. I'm also questioning if I need to check the read functions API for further information."
}
]
}
]
},
{
"role": "tool",
"content": "{\"content\": \" 1|\\\"\\\"\\\"Static active-word caption segment logic.\\n 2|\\n 3|Caption rule for TrueTraceShorts previews/finals:\\n 4|- A subtitle phrase segment stays fixed on screen.\\n 5|- At least three words are visible per default segment whenever possible.\\n 6|- Only the active spoken word changes highlight.\\n 7|- The highlight moves left-to-right until the next phrase segment replaces it.\\n 8|- Caption layout must remain inside the mobile safe zone.\\n 9|\\\"\\\"\\\"\\n 10|\\n 11|from __future__ import annotations\\n 12|\\n 13|from dataclasses import dataclass\\n 14|from typing import Sequence\\n 15|\\n 16|\\n 17|@dataclass(frozen=True)\\n 18|class WordCue:\\n 19| start: float\\n 20| end: float\\n 21| word: str\\n 22| sentence: str = \\\"\\\"\\n 23|\\n 24|\\n 25|@dataclass(frozen=True)\\n 26|class StaticCaptionSegment:\\n 27| start: float\\n 28| end: float\\n 29| word_indices: tuple[int, ...]\\n 30| words: tuple[str, ...]\\n 31| sentence: str = \\\"\\\"\\n 32|\\n 33| @property\\n 34| def text(self) -> str:\\n 35| return \\\" \\\".join(self.words)\\n 36|\\n 37|\\n 38|@dataclass(frozen=True)\\n 39|class CaptionLayoutConfig:\\n 40| video_width: int = 1080\\n 41| video_height: int = 1920\\n 42| horizontal_margin_px: int = 60\\n 43| bottom_margin_px: int = 260\\n 44| max_width_ratio: float = 0.88\\n 45| max_lines: int = 2\\n 46| font_size_px: int = 68\\n 47| min_font_size_px: int = 46\\n 48| line_gap_px: int = 14\\n 49| word_gap_px: int = 18\\n 50| highlight_pad_x_px: int = 10\\n 51| highlight_pad_y_px: int = 5\\n 52|\\n 53| @property\\n 54| def safe_width_px(self) -> int:\\n 55| ratio_width = int(self.video_width * self.max_width_ratio)\\n 56| margin_width = self.video_width - 2 * self.horizontal_margin_px\\n 57| return min(ratio_width, margin_width)\\n 58|\\n 59|\\n 60|@dataclass(frozen=True)\\n 61|class CaptionLayout:\\n 62| lines: tuple[tuple[str, ...], ...]\\n 63| font_size_px: int\\n 64| left_px: int\\n 65| right_px: int\\n 66| top_px: int\\n 67| bottom_px: int\\n 68| width_px: int\\n 69| height_px: int\\n 70| word_boxes: tuple[tuple[int, int, int, int], ...]\\n 71| active_word_box: tuple[int, int, int, int] | None\\n 72|\\n 73|\\n 74|def build_static_caption_segments(\\n 75| word_cues: Sequence[WordCue],\\n 76| *,\\n 77| min_words: int = 3,\\n 78| target_words: int = 6,\\n 79| max_words: int = 7,\\n 80|) -> tuple[StaticCaptionSegment, ...]:\\n 81| if min_words < 2:\\n 82| raise ValueError(\\\"min_words must be >= 2\\\")\\n 83| if target_words < min_words:\\n 84| raise ValueError(\\\"target_words must be >= min_words\\\")\\n 85| if max_words < target_words:\\n 86| raise ValueError(\\\"max_words must be >= target_words\\\")\\n 87|\\n 88| grouped: list[list[tuple[int, WordCue]]] = []\\n 89| current_sentence: str | None = None\\n 90| current: list[tuple[int, WordCue]] = []\\n 91| for index, cue in enumerate(word_cues):\\n 92| sentence_key = cue.sentence or \\\"__no_sentence__\\\"\\n 93| if current and sentence_key != current_sentence:\\n 94| grouped.append(current)\\n 95| current = []\\n 96| current_sentence = sentence_key\\n 97| current.append((index, cue))\\n 98| if current:\\n 99| grouped.append(current)\\n 100|\\n 101| segments: list[StaticCaptionSegment] = []\\n 102| for group in grouped:\\n 103| chunks: list[list[tuple[int, WordCue]]] = []\\n 104| i = 0\\n 105| while i < len(group):\\n 106| remaining = len(group) - i\\n 107| size = min(target_words, remaining)\\n 108| if remaining < min_words and chunks:\\n 109| chunks[-1].extend(group[i:])\\n 110| break\\n 111| if size < min_words and len(group) >= min_words:\\n 112| start = max(0, len(group) - min_words)\\n 113| chunks.append(group[start:])\\n 114| break\\n 115| chunks.append(group[i : i + size])\\n 116| i += size\\n 117| for chunk in chunks:\\n 118| if not chunk:\\n 119| continue\\n 120| if len(chunk) > max_words:\\n 121| # Split oversized merged chunks conservatively while preserving min_words.\\n 122| while len(chunk) > max_words:\\n 123| head = chunk[:max_words]\\n 124| segments.append(_segment_from_chunk(head))\\n 125| chunk = chunk[max_words:]\\n 126| if 0 < len(chunk) < min_words and segments:\\n 127| previous = segments.pop()\\n 128| prev_pairs = [(idx, word_cues[idx]) for idx in previous.word_indices]\\n 129| chunk = prev_pairs + chunk\\n 130| segments.append(_segment_from_chunk(chunk))\\n 131| return tuple(segments)\\n 132|\\n 133|\\n 134|def build_safe_caption_segments(\\n 135| word_cues: Sequence[WordCue],\\n 136| *,\\n 137| layout: CaptionLayoutConfig | None = None,\\n 138| min_words: int = 3,\\n 139| target_words: int = 6,\\n 140| max_words: int = 7,\\n 141|) -> tuple[StaticCaptionSegment, ...]:\\n 142| \\\"\\\"\\\"Build phrase segments that are pre-split to fit the caption safe zone.\\n 143|\\n 144| The function keeps the established 3–7 word phrase behavior, but refuses to\\n 145| create a segment that would need more than two lines or exceed the safe\\n 146| width at the minimum allowed font size. Very long tokens are handled by\\n 147| dynamic shrink in layout, and if a phrase is still too wide the segment is\\n 148| split earlier.\\n 149| \\\"\\\"\\\"\\n 150| cfg = layout or CaptionLayoutConfig()\\n 151| base_segments = build_static_caption_segments(\\n 152| word_cues,\\n 153| min_words=min_words,\\n 154| target_words=target_words,\\n 155| max_words=max_words,\\n 156| )\\n 157| safe_segments: list[StaticCaptionSegment] = []\\n 158| for segment in base_segments:\\n 159| pairs = [(idx, word_cues[idx]) for idx in segment.word_indices]\\n 160| current: list[tuple[int, WordCue]] = []\\n 161| for pair in pairs:\\n 162| candidate = current + [pair]\\n 163| candidate_words = tuple(cue.word for _, cue in candidate)\\n 164| if len(candidate_words) <= max_words and _fits_caption_layout(candidate_words, cfg):\\n 165| current = candidate\\n 166| continue\\n 167| if current:\\n 168| safe_segments.append(_segment_from_chunk(current))\\n 169| current = [pair]\\n 170| else:\\n 171| current = [pair]\\n 172| if current:\\n 173| # Try to merge a too-small tail back only when still safe.\\n 174| if (\\n 175| len(current) < min_words\\n 176| and safe_segments\\n 177| and len(safe_segments[-1].words) + len(current) <= max_words\\n 178| ):\\n 179| prev = safe_segments[-1]\\n 180| merged_pairs = [(idx, word_cues[idx]) for idx in prev.word_indices] + current\\n 181| merged_words = tuple(cue.word for _, cue in merged_pairs)\\n 182| if _fits_caption_layout(merged_words, cfg):\\n 183| safe_segments[-1] = _segment_from_chunk(merged_pairs)\\n 184| else:\\n 185| safe_segments.append(_segment_from_chunk(current))\\n 186| else:\\n 187| safe_segments.append(_segment_from_chunk(current))\\n 188| return tuple(safe_segments)\\n 189|\\n 190|\\n 191|def _segment_from_chunk(chunk: Sequence[tuple[int, WordCue]]) -> StaticCaptionSegment:\\n 192| return StaticCaptionSegment(\\n 193| start=chunk[0][1].start,\\n 194| end=chunk[-1][1].end,\\n 195| word_indices=tuple(index for index, _ in chunk),\\n 196| words=tuple(cue.word for _, cue in chunk),\\n 197| sentence=chunk[0][1].sentence,\\n 198| )\\n 199|\\n 200|\\n 201|def active_word_index_at(word_cues: Sequence[WordCue], timestamp: float) -> int:\\n 202| for index, cue in enumerate(word_cues):\\n 203| if cue.start <= timestamp < cue.end:\\n 204| return index\\n 205| previous = [index for index, cue in enumerate(word_cues) if cue.start <= timestamp]\\n 206| return previous[-1] if previous else 0\\n 207|\\n 208|\\n 209|def segment_for_active_word(segments: Sequence[StaticCaptionSegment], active_word_index: int) -> StaticCaptionSegment:\\n 210| for segment in segments:\\n 211| if active_word_index in segment.word_indices:\\n 212| return segment\\n 213| raise ValueError(f\\\"active word index {active_word_index} is not present in any segment\\\")\\n 214|\\n 215|\\n 216|def caption_state_at(word_cues: Sequence[WordCue], segments: Sequence[StaticCaptionSegment], timestamp: float) -> dict[str, object]:\\n 217| active_index = active_word_index_at(word_cues, timestamp)\\n 218| segment = segment_for_active_word(segments, active_index)\\n 219| return {\\n 220| \\\"segment_text\\\": segment.text,\\n 221|\", \"total_lines\": 360, \"file_size\": 12920, \"truncated\": true, \"hint\": \"Use offset=221 to continue reading (showing 1-220 of 360 lines)\", \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_vSNvjcFut5vg6i25DS7RGkoY"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_Rvg6Zr1BZ2Mb8qzhgj1uUno4",
"call_id": "call_Rvg6Zr1BZ2Mb8qzhgj1uUno4",
"response_item_id": "fc_051a8a0b2fb58918016a149c4a84988191b23c214cbe7a8990",
"type": "function",
"function": {
"name": "write_file",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"content\":\"from __future__ import annotations\\n\\nimport asyncio, hashlib, json, math, re, subprocess, sys\\nfrom pathlib import Path\\n\\nsys.path.insert(0, '/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot')\\nfrom PIL import Image, ImageDraw, ImageFont\\nimport edge_tts\\nfrom autoshorts.rendering.static_captions import (\\n CaptionLayoutConfig,\\n WordCue,\\n active_word_index_at,\\n build_safe_caption_segments,\\n layout_caption_segment,\\n segment_for_active_word,\\n)\\n\\nBASE = Path('/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s')\\nAUDIO_DIR = BASE / 'audio'\\nOUT = BASE / 'preview_v1_word_aligned'\\nQA = OUT / 'qa_frames'\\nfor p in [BASE, AUDIO_DIR, OUT, QA]:\\n p.mkdir(parents=True, exist_ok=True)\\n\\nCANDIDATE = 'calendar-invite-login-trap-30s'\\nVERSION = 'v1.0.0-word-aligned-proof'\\nVOICE = 'en-GB-RyanNeural'\\nW, H, FPS = 1080, 1920, 24\\nFONT_BOLD = '/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf'\\nFONT_REG = '/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf'\\nSAFE = CaptionLayoutConfig(\\n video_width=W,\\n video_height=H,\\n horizontal_margin_px=70,\\n bottom_margin_px=300,\\n max_width_ratio=0.86,\\n font_size_px=66,\\n min_font_size_px=48,\\n word_gap_px=18,\\n)\\n\\nSCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n \\\"But the link points somewhere else. Before you sign in, check three things: \\\"\\n \\\"the sender, the link domain, and whether the login asks for more than usual. \\\"\\n \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n)\\nSENTENCES = [s.strip() for s in re.split(r'(?<=[.!?])\\\\s+', SCRIPT) if s.strip()]\\n\\n\\ndef sha256(path: Path) -> str:\\n h = hashlib.sha256()\\n with path.open('rb') as f:\\n for chunk in iter(lambda: f.read(1024 * 1024), b''):\\n h.update(chunk)\\n return h.hexdigest()\\n\\n\\ndef font(size: int, bold: bool = True):\\n return ImageFont.truetype(FONT_BOLD if bold else FONT_REG, size)\\n\\n\\ndef sentence_for_offset(offset: float) -> str:\\n # Edge word-boundary events do not carry sentence IDs. Assign monotonically\\n # by rough character progression so caption segments still break at phrases.\\n # We later override using punctuation gaps when possible; grouping is not timing-critical.\\n joined = ' '.join(SENTENCES)\\n return joined\\n\\n\\ndef clean_boundary_text(text: str) -> str:\\n text = text.replace('’', \\\"'\\\").strip()\\n m = re.search(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", text)\\n return m.group(0) if m else text\\n\\n\\nasync def synthesize_audio() -> tuple[Path, tuple[WordCue, ...]]:\\n audio_path = AUDIO_DIR / 'voiceover_word_boundary.mp3'\\n cues_path = AUDIO_DIR / 'word_cues.json'\\n communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%')\\n cues = []\\n audio_bytes = bytearray()\\n sentence_cursor = 0\\n sentence_word_counts = [len(re.findall(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", s)) for s in SENTENCES]\\n word_counter_in_sentence = 0\\n for chunk in await communicate.stream().__aiter__():\\n if chunk['type'] == 'audio':\\n audio_bytes.extend(chunk['data'])\\n elif chunk['type'] == 'WordBoundary':\\n word = clean_boundary_text(chunk.get('text', ''))\\n if not word:\\n continue\\n start = chunk.get('offset', 0) / 10_000_000\\n duration = max(0.08, chunk.get('duration', 0) / 10_000_000)\\n sent = SENTENCES[min(sentence_cursor, len(SENTENCES) - 1)]\\n cues.append(WordCue(start=start, end=start + duration, word=word, sentence=sent))\\n word_counter_in_sentence += 1\\n if sentence_cursor < len(sentence_word_counts) and word_counter_in_sentence >= sentence_word_counts[sentence_cursor]:\\n sentence_cursor += 1\\n word_counter_in_sentence = 0\\n audio_path.write_bytes(audio_bytes)\\n cues_path.write_text(json.dumps([c.__dict__ for c in cues], indent=2), encoding='utf-8')\\n return audio_path, tuple(cues)\\n\\n\\ndef ffprobe_duration(path: Path) -> float:\\n out = subprocess.check_output([\\n 'ffprobe','-v','error','-show_entries','format=duration','-of','default=nokey=1:noprint_wrappers=1',str(path)\\n ], text=True)\\n return float(out.strip())\\n\\n\\ndef rounded(draw, box, r, fill, outline=None, width=1):\\n draw.rounded_rectangle(box, radius=r, fill=fill, outline=outline, width=width)\\n\\n\\ndef text(draw, xy, s, size, fill, bold=True, anchor=None, align='left'):\\n draw.text(xy, s, font=font(size, bold), fill=fill, anchor=anchor, align=align)\\n\\n\\ndef bg(draw, t):\\n # dark blue premium-ish deterministic background, not AI-generated\\n draw.rectangle((0, 0, W, H), fill=(10, 14, 24))\\n for y in range(0, H, 4):\\n c = int(16 + 26 * y / H)\\n draw.line((0, y, W, y), fill=(c, c + 5, c + 15))\\n # moving soft glow\\n cx = 220 + int(60 * math.sin(t * 0.7))\\n cy = 300 + int(45 * math.cos(t * 0.45))\\n for r, a in [(360, 22), (250, 20), (160, 18)]:\\n draw.ellipse((cx-r, cy-r, cx+r, cy+r), fill=(35, 75, 145, a))\\n draw.rectangle((0, 0, W, H), outline=(38, 49, 74), width=8)\\n\\n\\ndef scene_for(t):\\n if t < 5.4: return 'hook'\\n if t < 10.8: return 'same'\\n if t < 16.2: return 'domain'\\n if t < 23.0: return 'checks'\\n if t < 29.2: return 'open_app'\\n return 'takeaway'\\n\\n\\ndef draw_invite(draw, t, mode):\\n # Phone/browser card\\n rounded(draw, (82, 165, 998, 1328), 46, (238, 241, 247), (80, 93, 125), 3)\\n rounded(draw, (118, 215, 962, 385), 26, (255, 255, 255), (218, 224, 234), 2)\\n text(draw, (152, 252), 'Calendar', 40, (38, 47, 66))\\n text(draw, (152, 314), 'From: updates@sample.test', 30, (82, 92, 112), False)\\n\\n # meeting card\\n rounded(draw, (150, 445, 930, 815), 28, (250, 252, 255), (203, 211, 225), 2)\\n text(draw, (196, 497), 'Meeting invite', 52, (38, 48, 66))\\n text(draw, (196, 572), 'Project check-in', 36, (69, 79, 99), False)\\n urgent = mode in ['same', 'domain']\\n rounded(draw, (196, 642, 520, 696), 18, (255, 244, 223) if urgent else (235, 242, 250), (232, 151, 43) if urgent else (128, 140, 160), 2)\\n text(draw, (224, 654), 'Starts soon', 28, (205, 117, 24) if urgent else (91, 103, 123))\\n for x in [202, 262, 322, 382]:\\n draw.ellipse((x, 724, x+42, 766), fill=(211, 218, 230), outline=(178, 188, 207), width=2)\\n\\n # button + domain panel\\n changed = mode in ['domain', 'checks', 'open_app']\\n btn_fill = (43, 94, 185) if not changed else (202, 64, 64)\\n rounded(draw, (196, 890, 884, 980), 24, btn_fill, None, 1)\\n text(draw, (540, 935), 'SIGN IN TO JOIN', 38, (255, 255, 255), anchor='mm')\\n\\n rounded(draw, (150, 1030, 930, 1208), 24, (241, 245, 250), (204, 213, 228), 2)\\n text(draw, (196, 1070), 'Link domain', 34, (58, 68, 89))\\n domain = 'service.sample.test' if not changed else 'secure-meeting-check.test'\\n color = (57, 129, 88) if not changed else (204, 58, 58)\\n rounded(draw, (196, 1125, 820, 1178), 16, (235, 249, 241) if not changed else (255, 242, 239), color, 3)\\n text(draw, (220, 1138), domain, 29, color)\\n if changed:\\n text(draw, (196, 1245), 'Domain changed', 42, (207, 54, 54))\\n else:\\n text(draw, (196, 1245), 'Looks familiar', 42, (60, 120, 90))\\n\\n\\ndef draw_checks(draw, t):\\n labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login', 20.0)]\\n y = 1218\\n for i, (lab, ts) in enumerate(labels):\\n active = t >= ts\\n col = (247, 202, 76) if active else (122, 133, 155)\\n rounded(draw, (155, y + i*87, 925, y + 60 + i*87), 21, (34, 43, 62), col if active else (74, 86, 110), 3)\\n text(draw, (205, y + 13 + i*87), f'{i+1}. {lab}', 32, (255, 255, 255) if active else (188, 197, 214))\\n\\n\\ndef draw_open_app(draw, t):\\n rounded(draw, (125, 1160, 955, 1395), 34, (28, 38, 57), (93, 112, 148), 3)\\n text(draw, (540, 1220), 'Open the service yourself', 44, (255, 255, 255), anchor='mm')\\n text(draw, (540, 1292), 'not the rushed button', 42, (247, 202, 76), anchor='mm')\\n # app icon + check\\n rounded(draw, (464, 1335, 616, 1482), 32, (18, 24, 36), (247, 202, 76), 4)\\n draw.line((500, 1411, 532, 1444, 586, 1372), fill=(247, 202, 76), width=10)\\n\\n\\ndef draw_takeaway(draw):\\n rounded(draw, (92, 420, 988, 1040), 46, (24, 32, 48), (247, 202, 76), 4)\\n text(draw, (540, 570), 'Trust the app', 76, (255, 255, 255), anchor='mm')\\n text(draw, (540, 700), 'you opened.', 76, (247, 202, 76), anchor='mm')\\n text(draw, (540, 845), 'Not the button that rushed you.', 42, (205, 214, 230), anchor='mm')\\n\\n\\ndef draw_caption(draw, t, word_cues, segments):\\n if not word_cues:\\n return\\n active = active_word_index_at(word_cues, t)\\n seg = segment_for_active_word(segments, active)\\n active_word = word_cues[active].word\\n layout = layout_caption_segment(seg.words, active_word=active_word, config=SAFE)\\n f = font(layout.font_size_px, True)\\n flat_words = []\\n for line in layout.lines:\\n flat_words.extend(line)\\n for word, box in zip(flat_words, layout.word_boxes):\\n x, y, _, _ = box\\n fill = (247, 202, 76) if word == active_word else (255, 255, 255)\\n # shadow only; no subtitle bar/box\\n for dx, dy in [(-2, 2), (2, 2), (0, 3)]:\\n draw.text((x+dx, y+dy), word, font=f, fill=(0,0,0,160), stroke_width=2, stroke_fill=(0,0,0,135))\\n draw.text((x, y), word, font=f, fill=fill, stroke_width=2, stroke_fill=(6,10,18))\\n\\n\\ndef draw_frame(t, word_cues, segments):\\n img = Image.new('RGB', (W, H), (10, 14, 24))\\n draw = ImageDraw.Draw(img, 'RGBA')\\n bg(draw, t)\\n sc = scene_for(t)\\n if sc == 'takeaway':\\n draw_takeaway(draw)\\n else:\\n draw_invite(draw, t, 'domain' if sc in ['domain', 'checks', 'open_app'] else sc)\\n if sc in ['checks', 'open_app']:\\n draw_checks(draw, t)\\n if sc == 'open_app':\\n draw_open_app(draw, t)\\n draw_caption(draw, t, word_cues, segments)\\n return img\\n\\n\\ndef render(audio_path: Path, word_cues: tuple[WordCue, ...]):\\n audio_duration = ffprobe_duration(audio_path)\\n duration = max(audio_duration + 0.5, word_cues[-1].end + 0.6 if word_cues else audio_duration + 0.5)\\n segments = build_safe_caption_segments(word_cues, layout=SAFE, min_words=3, target_words=5, max_words=7)\\n segment_path = OUT / 'caption_segments_word_aligned.json'\\n segment_path.write_text(json.dumps([\\n {'start': s.start, 'end': s.end, 'words': s.words, 'text': s.text, 'word_indices': s.word_indices}\\n for s in segments\\n ], indent=2), encoding='utf-8')\\n\\n silent = OUT / f'{CANDIDATE}_preview_v1_word_aligned_silent.mp4'\\n final = OUT / f'{CANDIDATE}_preview_v1_word_aligned.mp4'\\n cmd = ['ffmpeg','-y','-f','rawvideo','-vcodec','rawvideo','-pix_fmt','rgb24','-s',f'{W}x{H}','-r',str(FPS),'-i','-','-an','-c:v','libx264','-pix_fmt','yuv420p','-crf','20',str(silent)]\\n proc = subprocess.Popen(cmd, stdin=subprocess.PIPE)\\n frames = int(math.ceil(duration * FPS))\\n for i in range(frames):\\n t = i / FPS\\n proc.stdin.write(draw_frame(t, word_cues, segments).tobytes())\\n proc.stdin.close(); proc.wait()\\n if proc.returncode:\\n raise SystemExit(proc.returncode)\\n # Preserve video duration; do not use -shortest.\\n subprocess.run(['ffmpeg','-y','-i',str(silent),'-i',str(audio_path),'-c:v','copy','-c:a','aac','-map','0:v:0','-map','1:a:0',str(final)], check=True)\\n\\n sample_times = [1,4,8,12,16,19,23,28,min(duration-0.4,32)]\\n thumbs=[]\\n for ts in sample_times:\\n im = draw_frame(ts, word_cues, segments)\\n p = QA / f'frame_{str(round(ts,1)).replace(\\\".\\\",\\\"_\\\")}s.jpg'\\n im.save(p, quality=92)\\n thumbs.append((ts, im.resize((270,480))))\\n sheet = Image.new('RGB', (810,1440), (12,16,24)); sd=ImageDraw.Draw(sheet)\\n for idx,(ts,thumb) in enumerate(thumbs):\\n x=(idx%3)*270; y=(idx//3)*480\\n sheet.paste(thumb,(x,y)); sd.rectangle((x,y,x+269,y+479),outline=(80,90,115),width=2)\\n sd.text((x+12,y+12),f'{ts:.1f}s',font=font(24),fill=(247,202,76))\\n contact = OUT / 'calendar-invite-login-trap_contact_sheet_v1.jpg'\\n sheet.save(contact, quality=92)\\n\\n subtitle_preview = OUT / 'calendar-invite-login-trap_subtitle_style_preview_v1.jpg'\\n draw_frame(18.6, word_cues, segments).save(subtitle_preview, quality=94)\\n\\n # QA: caption segments should mostly be 3-7 words; no one-word default.\\n one_word_segments = [s.text for s in segments if len(s.words) == 1]\\n qa = {\\n 'caption_sync_source': 'edge_tts_word_boundary_offsets',\\n 'static_phrase_active_word': True,\\n 'min_words_default': 3,\\n 'target_words': 5,\\n 'max_words': 7,\\n 'one_word_segments': one_word_segments,\\n 'one_word_segment_count': len(one_word_segments),\\n 'duration_seconds': duration,\\n 'audio_duration_seconds': audio_duration,\\n 'word_cue_count': len(word_cues),\\n 'segment_count': len(segments),\\n 'safe_zone': 'bottom caption, no box/bar, tested via contact sheet',\\n 'summary_fazit_present': True,\\n 'final_solution': 'Open the service yourself; trust the app you opened, not the rushed button.',\\n }\\n qa_path = OUT / 'qa_summary_preview_v1.json'\\n qa_path.write_text(json.dumps(qa, indent=2), encoding='utf-8')\\n\\n manifest = {\\n 'candidate_id': CANDIDATE,\\n 'version': VERSION,\\n 'series': 'Digital Red Flags',\\n 'title': 'The calendar invite login trap',\\n 'script': SCRIPT,\\n 'script_hash': hashlib.sha256(SCRIPT.encode()).hexdigest()[:16],\\n 'preview_mp4_path': str(final),\\n 'preview_sha256': sha256(final),\\n 'silent_mp4_path': str(silent),\\n 'audio_path': str(audio_path),\\n 'audio_sha256': sha256(audio_path),\\n 'word_cues_path': str(AUDIO_DIR / 'word_cues.json'),\\n 'caption_segments_path': str(segment_path),\\n 'contact_sheet_path': str(contact),\\n 'subtitle_preview_path': str(subtitle_preview),\\n 'qa_summary_path': str(qa_path),\\n 'duration_seconds': duration,\\n 'resolution': f'{W}x{H}',\\n 'fps': FPS,\\n 'caption_policy': 'static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries',\\n 'blocked': {'wan': True, 'i2v': True, 'platform_api': True, 'posting': True, 'scheduling': True},\\n }\\n manifest_path = OUT / 'manifest_preview_v1_word_aligned.json'\\n manifest_path.write_text(json.dumps(manifest, indent=2), encoding='utf-8')\\n return manifest\\n\\n\\nasync def main():\\n audio_path, cues = await synthesize_audio()\\n if len(cues) < 20:\\n raise RuntimeError(f'too few word cues: {len(cues)}')\\n manifest = render(audio_path, cues)\\n # content review package\\n review = {\\n 'candidate_id': CANDIDATE,\\n 'version': VERSION,\\n 'production_mode': 'proof_short',\\n 'selected_hook': 'This calendar invite looks normal. The trap is the login button.',\\n 'script': SCRIPT,\\n 'visual_plan': [\\n {'time': '0-5s', 'scene': 'normal calendar invite; login button visible', 'purpose': 'visible real problem immediately'},\\n {'time': '5-11s', 'scene': 'same meeting/title/guests/urgency', 'purpose': 'recognition and tension'},\\n {'time': '11-16s', 'scene': 'link domain changes to fictional suspicious domain', 'purpose': 'mechanism reveal'},\\n {'time': '16-23s', 'scene': 'three checks: sender, link domain, unusual login', 'purpose': 'saveable rule'},\\n {'time': '23-29s', 'scene': 'button dims; open-service-yourself card', 'purpose': 'real solution'},\\n {'time': '29-end', 'scene': 'final takeaway card', 'purpose': 'fazit / memorable rule'},\\n ],\\n 'usefulness_fix': 'Do not sign in from a suspicious invite. Open the service yourself and verify from there.',\\n 'takeaway': 'Trust the app you opened, not the button that rushed you.',\\n 'pretty_empty_visual_blocker': {'result': 'pass', 'reason': 'first frame shows a concrete invite/login problem, not abstract mood visuals'},\\n 'claim_gate': {'result': 'pass', 'risk': 'medium', 'not_claimed': ['this detects all phishing', 'legal/security advice guarantee']},\\n 'ai_disclosure': 'no realistic AI people/scenes; deterministic mockups and EdgeTTS voice',\\n 'preview_manifest': manifest,\\n 'approval_commands': [\\n f'APPROVED_PROOF_SHORT {CANDIDATE} {VERSION}',\\n f'REVISE_PROOF_SHORT {CANDIDATE} \\\"...\\\"',\\n f'REJECT_PROOF_SHORT {CANDIDATE} \\\"Grund\\\"',\\n ],\\n }\\n (BASE / 'review_package_v1_word_aligned.json').write_text(json.dumps(review, indent=2), encoding='utf-8')\\n print(json.dumps({'ok': True, 'manifest': manifest, 'review_package': str(BASE / 'review_package_v1_word_aligned.json')}, indent=2))\\n\\nif __name__ == '__main__':\\n asyncio.run(main())\\n\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJxKAkS6ppS1lTkn9_F9kDwRULHtx2AztbFkSLz1OsnaIrLxBg4H6-4BITX5T2rE3sVirREjaiJstYiN3NO9pin0fMZ4h6FMKr31dijeY2up_jlQ89WIKKkcBgK5j8fNh91jWvWYiP6Hwue0dl5MQoOdSQVPa867HrPfhi7W1yR19dTVvDmLDhS6s6LBlgqfv2Qo1oeZ41ASKaFqgg8h_XMbcTfjobCdQOdWm95BVX3hmvH-qd_yjlbar-07C1e9jhcajt2Mp6uY_arBjVQkQBVopL1MfSlAMt7l3xUuydm35hSnIyz3O9i4_idXc6A_7WpMTn3trN2MRJetfdZb9d-dfkAsrJmvKt8KEmh0fMCSGl0iq8aIFcA0IvDp41h1w-cObRiA_69OziUD2up_zqvtI5bAxoo2HbE6SXK7A5rZioIrEJ9qKftcyknoQkVGDPnK0pAKXxJmRGL4lf549AWWxKA_gj3pjf7in4kX8dHFh0zemivYRshoRtbBJn7KprYV4m2hQlc5FkNTk-eP2au8NXznRYhISR5OCoU4bNk4P4d92J0E-k6FBZksNU9-vwSPiAUKu4rBuGatYHI99L6jJ4ZZy2LhH-aGpXjkJePjZOHjn91j1R8i0PeSwZeGcW5i0WAv9kGkXkwun5qa7nY_fKGgwnaGMDLjFakHymNO8NiSUQot6Qee-LM-wE0oICMog-9qwsiNNFD2QB-dgjLBFkzXqfP1UACUkPPWNF_qzbBjVOu4NF6m9ssnaRX_kmJsAaNQ6kWBwKZoN5FpNuPhNW2CMPpcQhXqrsblTsrjDWzvSQLT6X8fS4dz0K--schAYHbVEFisUTlgTlZbfzQfDfYR5SqpV-b0r6Rk2m0GNOyTT8fIOYPL041sZrJ4cd2apDBVj_tmeE526y_aGkIyclms_qm8TFnu-VhWUaqeaUZ4sokbeuOzoYib1uCyBuRs1pl2ygYurfzmKktN3133WXkEJ4M_tZXNRrPTwyxyB-X4jcfJVCnDrvyz_tOw3zh8sVMJd5i6nObiYA1UDluSr1vsY1kHawEFShgWxic3YCDlLHJVdUnJXBswNWz-TLH3asdg1VGANIqbq0rowPi4d_lw8yH1HSUVBUhLHXSS7IviajgZ2nMZKUeUBvVAyGAnve_7fA9jF_HDlHSgBYLWTl-aS6h1LyEWxAIBsniYJt9uociyETj6ZYqRhAlTxaWjFr8wwXJBr0vzFd38LuDo_8SoOpTa6_YtJ8KFoznWQI7vp1LSB4pHBYeHQnQ9jAm3wZE1yigPdg-qghH8ZlgA7sYNw7N9EXUZ-0ZC4achfTphdT4sQPk2K4ng5-Zx-he9NAZVj0dVVVcpekKTFWK4oLxtKuonDCG6S2rIXzPpifUWd_HuaCPfjzUSpK7fMmJnCr7qhysr0_BaRGNM8EQbgtb6ArQdo_lJPKKFX47x7f1ZS7xCz8CFX7OpEKs0aUB25qLmic9US7HdBNZA6pAvEH6IK3DAyDZvoWrgOzwZ17dBmtl_jmKA2cyHWttGBhC52mLt6acusNI1crLAYn3m-JmrzNyz2gVEy15A_qo4vV_wYQ4wMW4nRCnz5Nx6fWPsPYM85PL--4nRsptrVU8eHvpgOJaZejgzXI1xHwqrUbO3Nat3sCauSTVdVYWWwna6C1CEIP-dEHrCU0MJprbOtw==",
"id": "rs_051a8a0b2fb58918016a149c47ff18819188854ed56162a847",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"bytes_written\": 16945, \"dirs_created\": true, \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_Rvg6Zr1BZ2Mb8qzhgj1uUno4"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_x6EDHP56rXGQo7vLbW3dYTRY",
"call_id": "call_x6EDHP56rXGQo7vLbW3dYTRY",
"response_item_id": "fc_051a8a0b2fb58918016a149cb7f56c81919dbf7455b8bc199a",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Letztes Feedback in Anforderungen für nächstes Video übersetzen\",\"id\":\"scope\",\"status\":\"completed\"},{\"content\":\"Vorhandene AutoShorts/Proof-Short Artefakte und Pipeline finden\",\"id\":\"discover\",\"status\":\"completed\"},{\"content\":\"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\",\"id\":\"draft\",\"status\":\"in_progress\"}]}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"todos\": [{\"id\": \"scope\", \"content\": \"Letztes Feedback in Anforderungen für nächstes Video übersetzen\", \"status\": \"completed\"}, {\"id\": \"discover\", \"content\": \"Vorhandene AutoShorts/Proof-Short Artefakte und Pipeline finden\", \"status\": \"completed\"}, {\"id\": \"draft\", \"content\": \"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\", \"status\": \"in_progress\"}, {\"id\": \"deliver\", \"content\": \"ReviewPackage/Entwurf knapp an User liefern und nächste Freigabe-Kommandos nennen\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 1, \"in_progress\": 1, \"completed\": 2, \"cancelled\": 0}}",
"tool_call_id": "call_x6EDHP56rXGQo7vLbW3dYTRY"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_VIJddCphHbJpwEJ4g3nNCMa3",
"call_id": "call_VIJddCphHbJpwEJ4g3nNCMa3",
"response_item_id": "fc_051a8a0b2fb58918016a149ccba3d881918bb7393009639e82",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"output\": \"Traceback (most recent call last):\\n File \\\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\\", line 371, in \\n asyncio.run(main())\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py\\\", line 190, in run\\n return runner.run(main)\\n ^^^^^^^^^^^^^^^^\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py\\\", line 118, in run\\n return self._loop.run_until_complete(task)\\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py\\\", line 654, in run_until_complete\\n return future.result()\\n ^^^^^^^^^^^^^^^\\n File \\\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\\", line 336, in main\\n audio_path, cues = await synthesize_audio()\\n ^^^^^^^^^^^^^^^^^^^^^^^^\\n File \\\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\\", line 88, in synthesize_audio\\n for chunk in await communicate.stream().__aiter__():\\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\nTypeError: object async_generator can't be used in 'await' expression\", \"exit_code\": 1, \"error\": null}",
"tool_call_id": "call_VIJddCphHbJpwEJ4g3nNCMa3"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_r0hobqqq11tvRwPI3SSUdbIE",
"call_id": "call_r0hobqqq11tvRwPI3SSUdbIE",
"response_item_id": "fc_051a8a0b2fb58918016a149ccf594c8191a6694159125bacc9",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"old_string\":\" for chunk in await communicate.stream().__aiter__():\\n if chunk['type'] == 'audio':\",\"new_string\":\" async for chunk in communicate.stream():\\n if chunk['type'] == 'audio':\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJzPCSFEczpmyMks8JEsP2wHga2dDhNqtkTmoTLLrfWZasv_Sst6ulnkl0ry4oOl1yCvNmzq_ced8xjdnLutJvHujduTME59TUpV7U5FFw--2qGBh3ksaIQRfVFPafTa6giFuhTqXwZxsAa_GNXfd2A3yNX6S9pI1q1KYompC8NOCDscboGrHTgA53XbJcZE2hxTntUJ3T0LaZnVzAvz3bIjvKW_kGG6nPbYUrFSPHbpKWFet1kOi_KcBIrOXSJWyw9K32drcA2AIQOrcvw8UzjbfP2QMMSD74GyqviiMkvEUUOVAa_AQ9yRV8ORnGQHSdxFCg5js3L5R3cRpbtEyEgG2vZZVDHOHUUMFfp6RBsokFfb_6FK639vEe31vIEgWH2ChIG370fMcIt62UsoTKRpoJhL0Qm0ZGJSIgnIMa3D0RAP89MHnjxx68RIWBgilDmVcX4a8dfYu-W_aixGykpB_xiThzoc4RX8O2f4Y2dOsi25gG30Tjop63wgH2N60Axnthak0GXcjGnNso5O2mplmrrpUx15fmNwqSLgMDKCLFpQPpQITYewlq-j_wz3X7wsD3PJcOH4b0oBw_7XaaEmMgjqzlorOku6tPZrLhtrdZyY6X7XTuSsFi-v0aNDA9mbaKgZpr_RszoJYFl4dBpzEA9k5t8UovJKtpSMUwUZIE2XupgMfqLT5Hp2XGszHaB5eHpQouJVcb-a1wGwkGq4VE8FG52EKYfhMK_Ohguuwln7JmSmToVIGXbzF8mIw4kf4JSwPQ4-LDmcaOZE7vmeuXIMkqeiyxUso-LTH0RtROTwxCGgSDpwBhye8cxccMpCHf0r8QP7kI2ijpINOzecxuu4aiL1PgiQvFUOaO7v6oFeRFJeuaBtN8UozT5Yca1GCKbrKz0VtyqVAfl9xVnpVeC9HYkl23z3G4zIEcFNdVCIv17kzxLueLEj-9VlhszFeY_InLSEB9ir7DDjSuc-eg==",
"id": "rs_051a8a0b2fb58918016a149cce91d08191b3dda6ccc7b524ac",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -85,7 +85,7 @@\\n sentence_cursor = 0\\n sentence_word_counts = [len(re.findall(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", s)) for s in SENTENCES]\\n word_counter_in_sentence = 0\\n- for chunk in await communicate.stream().__aiter__():\\n+ async for chunk in communicate.stream():\\n if chunk['type'] == 'audio':\\n audio_bytes.extend(chunk['data'])\\n elif chunk['type'] == 'WordBoundary':\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_r0hobqqq11tvRwPI3SSUdbIE"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_1CXGufdRvgQOfV5nn8hopJmY",
"call_id": "call_1CXGufdRvgQOfV5nn8hopJmY",
"response_item_id": "fc_051a8a0b2fb58918016a149cd3f7f8819180b3d230501d5143",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"output\": \"Traceback (most recent call last):\\n File \\\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\\", line 371, in \\n asyncio.run(main())\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py\\\", line 190, in run\\n return runner.run(main)\\n ^^^^^^^^^^^^^^^^\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py\\\", line 118, in run\\n return self._loop.run_until_complete(task)\\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\\n File \\\"/home/agent/.local/share/uv/python/cpython-3.11.15-linux-x86_64-gnu/lib/python3.11/asyncio/base_events.py\\\", line 654, in run_until_complete\\n return future.result()\\n ^^^^^^^^^^^^^^^\\n File \\\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\\", line 338, in main\\n raise RuntimeError(f'too few word cues: {len(cues)}')\\nRuntimeError: too few word cues: 0\", \"exit_code\": 1, \"error\": null}\n\n[Tool loop warning: repeated_exact_failure_warning; count=2; terminal has failed 2 times with identical arguments. This looks like a loop; inspect the error and change strategy instead of retrying it unchanged.]",
"tool_call_id": "call_1CXGufdRvgQOfV5nn8hopJmY"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_zSU8nwLVfvmY0dzZ03MOY2XN",
"call_id": "call_zSU8nwLVfvmY0dzZ03MOY2XN",
"response_item_id": "fc_051a8a0b2fb58918016a149d3006908191968a6ef96943cd81",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python - <<'PY'\\nimport asyncio, edge_tts\\nasync def main():\\n c=edge_tts.Communicate('This calendar invite looks normal. The trap is the login button.', 'en-GB-RyanNeural')\\n types={}\\n async for chunk in c.stream():\\n types[chunk.get('type')]=types.get(chunk.get('type'),0)+1\\n if chunk.get('type')!='audio': print(chunk)\\n print(types)\\nasyncio.run(main())\\nPY\",\"timeout\":60}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ0wblnCa5i1uWQBIC5ShmpSt2qLdq0q4c-ni6l7u6gI8QR22CQNgW0rNRfb0K7Pn_1qe9NANqtY3Mpre3etcSrmE--HFjSOSVeT4wvkpPO1lGQYvNvpVkXLw0uzeEM9megLwfFUCFHBE0-WNlYgSHtyE1Sp-C8xmz0ZzZm9T0YBZC0nTFfbodyi9vAOiu-wGo41zePx_GT2eXeyUck5At3jF466VTsSEt8g2G5BGoC6iWf_RHVTai3nOPMGIgLF7pi4w0cT3T8AmC9HfCmx_DjabWAE9LONkrZuctgQuqhXSzmh_tm0Oy2OGrV1D848T47UdMo24YI7_tGmFLct9lKb0RiCILsFQ9c8aH4iGMPJmmjR2m4x-gKJKakNXprAgXABKYYmgJrCH8GPhFkh9q1cxQQP-xTaFkKi6gYimKA2L2SwJVffSQEjLl1KcYrvScLRB2-1kZDRRFujiWvYP_Bu7OGDIc5VXsqQaLsv0Z9VFkk9EEe164DNroksOvHvutR3Ar_maUblrM-8QwfpWTKuxI9DWDVZmgAmtelsR1IjMsRd8gNLc9gricrZ9Toe63owiMbEXAAWrEtm_34YbwGylb2IHt20oQAsXV0cxcH3sGxkx4dyVpIzI0EyfiX5rv81zvumUNhVACxTaxmeNtqCkEk577kt6yk0IrZ5ja2vYrec4IxhiXwuNNX6a60Y0Wge_V5sCNR0PHOIl601mdJAIvFHEWHBms_Uf8rEL7qqznvpY4wcENGOOeWwVSp9lIUbmFHNPXbm1SdV-5nDyCf1h4l6DoLVJ3pzPlZQ11nLRU09AsgLMb6kzOwLkGfKgYx6NQLKoImX-kV7VP-bOfkATwRLLGrvEQfhodJxmNY56bKiKe9VX3Nx2HLkefWdMyHwutzyCZFfHZGIcQYLHsQvc3TeRA-V3nh55qoD7nWeEjukCf5jbNRWdw3_lwEiYuq1OhJ81EYfqQ-Xd02QUQfNAupBT2HXPtRwTlIrTIBDZYIZ0EoV3iykgvWtGqY-WWCXmYbzrAKhHdXIkW5Grr5z9w==",
"id": "rs_051a8a0b2fb58918016a149d2baf48819192f9fbc620225d81",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"output\": \"{'type': 'SentenceBoundary', 'offset': 1000000, 'duration': 26750000, 'text': 'This calendar invite looks normal.'}\\n{'type': 'SentenceBoundary', 'offset': 27250000, 'duration': 24625000, 'text': 'The trap is the login button.'}\\n{'audio': 44, 'SentenceBoundary': 2}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_zSU8nwLVfvmY0dzZ03MOY2XN"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_YVjSuIPy4nq0E7xo4hy5o0Jw",
"call_id": "call_YVjSuIPy4nq0E7xo4hy5o0Jw",
"response_item_id": "fc_051a8a0b2fb58918016a149d35d20c81918eb578f128e04fc7",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python - <<'PY'\\nimport inspect, edge_tts\\nprint(inspect.signature(edge_tts.Communicate))\\nPY\",\"timeout\":30}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ01Qg7M3szJAlmBxJPssjfupqOoU7zJyDM9J7Er16zl-tYXpYHWp3sFd9qGAqhZjNE-RgwQsmZR2RjRER4BYGWnEUv6rjoanbbbz1Ms4f1pe0RWysXyJZj4bwJrLeO9yxrtBepGDc9M1Re0wyQTXSF-BBMF1zY-YML1l1qjbnDyG4rEsNwUYsc3wzRZWXYfc8hH4mlJC2-D83-tIKPwN53i8UwvJgMd7IEgtieTr3MntxblJMg7qAUrtX0fhF2mOJRgYNDyRX-dg_849zAiuHTw516MyAMhjBbjZ9pyGOxCuy71OiLPeMPb3alSRpe6ApUxKupAZTc0liOr5RKVT8uvYG_BxJQZCDiv8V1fYeRFu9kycBISpodroYmn0lcH56NRAbQaCfwhgoJPAtH67VURna134FGwp-5i-HLkV5CAwnvxTdRQx7nzHtd_JsJZQh3O9-HWt5wtmU0yoQrT5b-5KZPaeZeu-4-Lz5MpcfBmSl47-5--8rjhki26EbGDVmBpZp8yVbFNJJRcSNH0_3tL30asnwx9PDXuzwfBXZ89RvVfkOoAs1RfZeALveIT2g5FYwAJwVzv9-otjuqvutdioaSI3JWtVZYu3nfuY0eITBdEvn71Q9ubeD9K0iVGK0bAj-0Z45pxtwITS0623fAyZDtzwnuvhnjIkOFYCZ7pWUTSFoP6B-GKisFsNeHJdHt8vu77_c9BSsCMFnaom8J_aI-b9XYezJqSGci8otuApmkElb_X7cFhIkWyQOOldfEdF4xDmAC3_v6KcGsw-bpu6HQ8QZIPOhoSP7iEdqkijZbvxhrqL_3Knz0uzjUE9KgpzcUzeEMtI1zbwTOHtQ7EsoD4WvkfAr8JZWPVNzP7DpDxw6qNXmYQRLS2wnNVcOHpT6MlwPhh-5-Pn5XV5hobUBTQWCNG-yJOM9a3GXRzmBwPwmNmJlJMv2ndi8IwPFAGfNZ-0SDfNev8bhFGzSixd-vt1QiNpP69STgr9n6XCGlJkig5JhirCwLOg0l7KVZj",
"id": "rs_051a8a0b2fb58918016a149d334a1c8191995708fbb746789f",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"output\": \"(text: str, voice: str = 'en-US-EmmaMultilingualNeural', *, rate: str = '+0%', volume: str = '+0%', pitch: str = '+0Hz', boundary: Literal['WordBoundary', 'SentenceBoundary'] = 'SentenceBoundary', connector: Optional[aiohttp.connector.BaseConnector] = None, proxy: Optional[str] = None, connect_timeout: Optional[int] = 10, receive_timeout: Optional[int] = 60)\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_YVjSuIPy4nq0E7xo4hy5o0Jw"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_QowBaCkPecyA394QyPu9wuLP",
"call_id": "call_QowBaCkPecyA394QyPu9wuLP",
"response_item_id": "fc_051a8a0b2fb58918016a149d3880808191a37575d1d4c56d50",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"old_string\":\" communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%')\",\"new_string\":\" communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%', boundary='WordBoundary')\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ04O2HlifWRTgUHlTvZ_84YtuY7NBBCXnxhpdatLLYnEjwy3rptFyi5VGc07hON0q22BQlCx8uN3PclMViO78OI_gSzR22fNy6nQGlxV2FRzjdrSpErOl-N19J2j--xhEt_49g63W8w_AF3SjZEqaKmYbAG_buvSZfR5kQnQ2f7_5kO1Lv06aLJ3BDB4CkeSxzgndY_-0mBSm364OW4TOqTHVQy-iKdG_1rKur4bZfZRWiTHUN90khLFkeRUxv0KZmtLWgDErwzzfG4nDS0rFXe23tMzal4gCuX-xsxwdpwcX45SqdPWI47ucjKlGWYC64W91VwR5QS4g8k_mnRL0CbxxwDJ-SJqLGRMa1spD9SIB5QqQFkCGZaW2i6K8gIcbWT7fQktYe6dGDCuwaCH8DiCrUVWI4fsegE4ozFghguiLsLTzMnVdjXUp5GLfXgZv18EspuwPw3dQUOI041P6VrEEFhqA1xbEBYp2wcT3hFWZfo_sylpKu0pHdlURdsT-Yj3E7kOvpevArw9as6oe2xJiJclP5bknBlzd8mYHOCfQATS8j7U3Se8V8em9QHFvNzLHCnulWN1aSCU0pNsCZsRxuc8pQGmytR9NKsrOJy1HLIAujhpVSS7Xx6z5JN-6M8NpDPaLMGdxROMmkMDJFGpD_JTnsrSqMGN49QoInPsTCM2Aq25MYxXuCJNdBQB7oETMm9DspA8qHIQpm6f9KURwegW90eEC48oFAG7ESUjPYdDqwAsSEtzSdUPgZTDVbBz3gOFggx9BRJR0iFGRC3ehKt8TlkiDux-R6lNNQSDLIQfZSXpc5Wor1CIYp4AcWKvgaaK8vWqpRS1eJcntQhoSSSnQz-kRhtL7KYjsERKShzm4C5UEvsIYPas3GH31ixNWI19WanX2UsScV3iS460MehcFVumB6V27fF4G0uQZE=",
"id": "rs_051a8a0b2fb58918016a149d380d408191b145a73cbabea890",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -79,7 +79,7 @@\\n async def synthesize_audio() -> tuple[Path, tuple[WordCue, ...]]:\\n audio_path = AUDIO_DIR / 'voiceover_word_boundary.mp3'\\n cues_path = AUDIO_DIR / 'word_cues.json'\\n- communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%')\\n+ communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%', boundary='WordBoundary')\\n cues = []\\n audio_bytes = bytearray()\\n sentence_cursor = 0\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_QowBaCkPecyA394QyPu9wuLP"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_SHM68uMpWgp8SwhDM1hzh1MQ",
"call_id": "call_SHM68uMpWgp8SwhDM1hzh1MQ",
"response_item_id": "fc_051a8a0b2fb58918016a149d3e779c8191aa4397a7585abeb1",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"output\": \"ffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, rawvideo, from 'fd:':\\n Duration: N/A, start: 0.000000, bitrate: 1194393 kb/s\\n Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 1080x1920, 1194393 kb/s, 24 tbr, 24 tbn\\nStream mapping:\\n Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x5695b5a9f3c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x5695b5a9f3c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x5695b5a9f3c0] 264 - core 164 r3108 31e19f9 - H.264/MPEG-4 AVC codec - Copyleft 2003-2023 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=9 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n encoder : Lavf60.16.100\\n Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1080x1920, q=2-31, 24 fps, 12288 tbn\\n Metadata:\\n encoder : Lavc60.31.102 libx264\\n Side data:\\n cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\\nframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 3 fps=0.9 q=25.0 size= 0kB time=00:00:00.04 bitrate= 9.2kbits/s speed=0.0132x \\rframe= 12 fps=3.3 q=25.0 size= 0kB time=00:00:00.41 bitrate= 0.9kbits/s speed=0.113x \\rframe= 21 fps=5.0 q=25.0 size= 0kB time=00:00:00.79 bitrate= 0.5kbits/s speed=0.189x \\rframe= 31 fps=6.6 q=25.0 size= 0kB time=00:00:01.20 bitrate= 0.3kbits/s speed=0.256x \\rframe= 41 fps=7.8 q=25.0 size= 0kB time=00:00:01.62 bitrate= 0.2kbits/s speed=0.31x \\rframe= 50 fps=8.7 q=25.0 size= 0kB time=00:00:02.00 bitrate= 0.2kbits/s speed=0.348x \\rframe= 60 fps=9.5 q=25.0 size= 0kB time=00:00:02.41 bitrate= 0.2kbits/s speed=0.384x \\rframe= 70 fps= 10 q=25.0 size= 0kB time=00:00:02.83 bitrate= 0.1kbits/s speed=0.413x \\rframe= 81 fps= 11 q=25.0 size= 0kB time=00:00:03.29 bitrate= 0.1kbits/s speed=0.444x \\rframe= 92 fps= 12 q=25.0 size= 0kB time=00:00:03.70 bitrate= 0.1kbits/s speed=0.468x \\rframe= 102 fps= 12 q=25.0 size= 0kB time=00:00:04.16 bitrate= 0.1kbits/s speed=0.492x \\rframe= 113 fps= 13 q=25.0 size= 0kB time=00:00:04.62 bitrate= 0.1kbits/s speed=0.515x \\rframe= 124 fps= 13 q=25.0 size= 0kB time=00:00:05.08 bitrate= 0.1kbits/s speed=0.535x \\rframe= 135 fps= 13 q=25.0 size= 0kB time=00:00:05.54 bitrate= 0.1kbits/s speed=0.552x \\rframe= 146 fps= 14 q=25.0 size= 0kB time=00:00:06.00 bitrate= 0.1kbits/s speed=0.569x \\rframe= 157 fps= 14 q=25.0 size= 0kB time=00:00:06.45 bitrate= 0.1kbits/s speed=0.584x \\rframe= 169 fps= 15 q=25.0 size= 0kB time=00:00:06.91 bitrate= 0.1kbits/s speed=0.598x \\rframe= 180 fps= 15 q=25.0 size= 0kB time=00:00:07.37 bitrate= 0.1kbits/s speed=0.611x \\rframe= 190 fps= 15 q=25.0 size= 0kB time=00:00:07.83 bitrate= 0.0kbits/s speed=0.622x \\rframe= 201 fps= 15 q=25.0 size= 0kB time=00:00:08.29 bitrate= 0.0kbits/s speed=0.633x \\rframe= 212 fps= 16 q=25.0 size= 0kB time=00:00:08.70 bitrate= 0.0kbits/s speed=0.639x \\rframe= 221 fps= 16 q=25.0 size= 0kB time=00:00:09.12 bitrate= 0.0kbits/s speed=0.645x \\rframe= 230 fps= 16 q=25.0 size= 0kB time=00:00:09.50 bitrate= 0.0kbits/s speed=0.648x \\rframe= 239 fps= 16 q=25.0 size= 0kB time=00:00:09.87 bitrate= 0.0kbits/s speed=0.649x \\rframe= 248 fps= 16 q=25.0 size= 0kB time=00:00:10.25 bitrate= 0.0kbits/s speed=0.65x \\rframe= 257 fps= 16 q=25.0 size= 256kB time=00:00:10.62 bitrate= 197.4kbits/s speed=0.651x \\rframe= 267 fps= 16 q=25.0 size= 256kB time=00:00:11.00 bitrate= 190.7kbits/s speed=0.652x \\rframe= 276 fps= 16 q=25.0 size= 256kB time=00:00:11.37 bitrate= 184.4kbits/s speed=0.653x \\rframe= 285 fps= 16 q=25.0 size= 256kB time=00:00:11.75 bitrate= 178.5kbits/s speed=0.654x \\rframe= 294 fps= 16 q=25.0 size= 256kB time=00:00:12.12 bitrate= 173.0kbits/s speed=0.657x \\rframe= 304 fps= 16 q=25.0 size= 256kB time=00:00:12.54 bitrate= 167.2kbits/s speed=0.66x \\rframe= 314 fps= 16 q=25.0 size= 256kB time=00:00:12.95 bitrate= 161.9kbits/s speed=0.664x \\rframe= 322 fps= 16 q=25.0 size= 256kB time=00:00:13.33 bitrate= 157.3kbits/s speed=0.665x \\rframe= 332 fps= 16 q=25.0 size= 256kB time=00:00:13.70 bitrate= 153.0kbits/s speed=0.667x \\rframe= 341 fps= 16 q=25.0 size= 256kB time=00:00:14.08 bitrate= 148.9kbits/s speed=0.668x \\rframe= 350 fps= 16 q=25.0 size= 256kB time=00:00:14.45 bitrate= 145.1kbits/s speed=0.669x \\rframe= 359 fps= 16 q=25.0 size= 256kB time=00:00:14.83 bitrate= 141.4kbits/s speed=0.67x \\rframe= 368 fps= 16 q=25.0 size= 256kB time=00:00:15.20 bitrate= 137.9kbits/s speed=0.671x \\rframe= 377 fps= 16 q=25.0 size= 256kB time=00:00:15.58 bitrate= 134.6kbits/s speed=0.672x \\rframe= 386 fps= 16 q=25.0 size= 256kB time=00:00:15.95 bitrate= 131.4kbits/s speed=0.673x \\rframe= 395 fps= 16 q=25.0 size= 256kB time=00:00:16.33 bitrate= 128.4kbits/s speed=0.674x \\rframe= 403 fps= 16 q=25.0 size= 256kB time=00:00:16.70 bitrate= 125.5kbits/s speed=0.674x \\rframe= 411 fps= 16 q=25.0 size= 256kB time=00:00:17.04 bitrate= 123.1kbits/s speed=0.673x \\rframe= 420 fps= 16 q=25.0 size= 256kB time=00:00:17.41 bitrate= 120.4kbits/s speed=0.673x \\rframe= 429 fps= 16 q=25.0 size= 256kB time=00:00:17.79 bitrate= 117.9kbits/s speed=0.673x \\rframe= 437 fps= 16 q=25.0 size= 256kB time=00:00:18.12 bitrate= 115.7kbits/s speed=0.673x \\rframe= 445 fps= 16 q=25.0 size= 256kB time=00:00:18.45 bitrate= 113.6kbits/s speed=0.673x \\rframe= 454 fps= 16 q=25.0 size= 256kB time=00:00:18.83 bitrate= 111.4kbits/s speed=0.673x \\rframe= 464 fps= 16 q=25.0 size= 256kB time=00:00:19.25 bitrate= 109.0kbits/s speed=0.675x \\rframe= 474 fps= 16 q=25.0 size= 256kB time=00:00:19.66 bitrate= 106.7kbits/s speed=0.677x \\rframe= 484 fps= 16 q=25.0 size= 256kB time=00:00:20.08 bitrate= 104.4kbits/s speed=0.679x \\rframe= 493 fps= 16 q=25.0 size= 256kB time=00:00:20.45 bitrate= 102.5kbits/s speed=0.68x \\rframe= 502 fps= 16 q=25.0 size= 512kB time=00:00:20.83 bitrate= 201.3kbits/s speed=0.679x \\rframe= 510 fps= 16 q=25.0 size= 512kB time=00:00:21.16 bitrate= 198.2kbits/s speed=0.679x \\rframe= 518 fps= 16 q=25.0 size= 512kB time=00:00:21.50 bitrate= 195.1kbits/s speed=0.679x \\rframe= 527 fps= 16 q=25.0 size= 512kB time=00:00:21.87 bitrate= 191.8kbits/s speed=0.679x \\rframe= 535 fps= 16 q=25.0 size= 512kB time=00:00:22.20 bitrate= 188.9kbits/s speed=0.678x \\rframe= 544 fps= 16 q=25.0 size= 512kB time=00:00:22.58 bitrate= 185.7kbits/s speed=0.678x \\rframe= 553 fps= 16 q=25.0 size= 512kB time=00:00:22.95 bitrate= 182.7kbits/s speed=0.679x \\rframe= 562 fps= 16 q=25.0 size= 512kB time=00:00:23.33 bitrate= 179.8kbits/s speed=0.68x \\rframe= 571 fps= 16 q=25.0 size= 512kB time=00:00:23.70 bitrate= 176.9kbits/s speed=0.68x \\rframe= 580 fps= 16 q=25.0 size= 512kB time=00:00:24.08 bitrate= 174.2kbits/s speed=0.681x \\rframe= 589 fps= 16 q=25.0 size= 512kB time=00:00:24.45 bitrate= 171.5kbits/s speed=0.682x \\rframe= 600 fps= 16 q=25.0 size= 512kB time=00:00:24.87 bitrate= 168.6kbits/s speed=0.683x \\rframe= 608 fps= 16 q=25.0 size= 512kB time=00:00:25.25 bitrate= 166.1kbits/s speed=0.684x \\rframe= 619 fps= 17 q=25.0 size= 512kB time=00:00:25.66 bitrate= 163.4kbits/s speed=0.685x \\rframe= 629 fps= 17 q=25.0 size= 512kB time=00:00:26.08 bitrate= 160.8kbits/s speed=0.686x \\rframe= 639 fps= 17 q=25.0 size= 512kB time=00:00:26.50 bitrate= 158.3kbits/s speed=0.687x \\rframe= 649 fps= 17 q=25.0 size= 512kB time=00:00:26.91 bitrate= 155.8kbits/s speed=0.688x \\rframe= 661 fps= 17 q=25.0 size= 512kB time=00:00:27.41 bitrate= 153.0kbits/s speed=0.691x \\rframe= 673 fps= 17 q=25.0 size= 512kB time=00:00:27.91 bitrate= 150.3kbits/s speed=0.695x \\rframe= 685 fps= 17 q=25.0 size= 512kB time=00:00:28.41 bitrate= 147.6kbits/s speed=0.698x \\rframe= 696 fps= 17 q=25.0 size= 512kB time=00:00:28.87 bitrate= 145.3kbits/s speed= 0.7x \\rframe= 707 fps= 17 q=25.0 size= 768kB time=00:00:29.33 bitrate= 214.5kbits/s speed=0.703x \\rframe= 717 fps= 17 q=25.0 size= 768kB time=00:00:29.79 bitrate= 211.2kbits/s speed=0.705x \\rframe= 728 fps= 17 q=25.0 size= 768kB time=00:00:30.25 bitrate= 208.0kbits/s speed=0.707x \\r[out#0/mp4 @ 0x5695b5a9dd00] video:888kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.128151%\\nframe= 784 fps= 18 q=-1.0 Lsize= 898kB time=00:00:32.54 bitrate= 226.0kbits/s speed=0.753x \\n[libx264 @ 0x5695b5a9f3c0] frame I:4 Avg QP:13.92 size: 55908\\n[libx264 @ 0x5695b5a9f3c0] frame P:198 Avg QP:17.87 size: 2717\\n[libx264 @ 0x5695b5a9f3c0] frame B:582 Avg QP:22.78 size: 252\\n[libx264 @ 0x5695b5a9f3c0] consecutive B-frames: 1.0% 0.0% 0.0% 99.0%\\n[libx264 @ 0x5695b5a9f3c0] mb I I16..4: 67.1% 17.5% 15.4%\\n[libx264 @ 0x5695b5a9f3c0] mb P I16..4: 0.6% 0.1% 0.3% P16..4: 4.1% 0.2% 0.1% 0.0% 0.0% skip:94.6%\\n[libx264 @ 0x5695b5a9f3c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.5% 0.0% 0.0% direct: 0.0% skip:97.5% L0:54.6% L1:45.4% BI: 0.1%\\n[libx264 @ 0x5695b5a9f3c0] 8x8 transform intra:18.2% inter:39.4%\\n[libx264 @ 0x5695b5a9f3c0] coded y,uvDC,uvAC intra: 14.0% 15.3% 11.3% inter: 0.1% 0.1% 0.1%\\n[libx264 @ 0x5695b5a9f3c0] i16 v,h,dc,p: 24% 76% 0% 0%\\n[libx264 @ 0x5695b5a9f3c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 49% 10% 39% 2% 0% 0% 0% 0% 0%\\n[libx264 @ 0x5695b5a9f3c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 34% 42% 8% 2% 2% 3% 3% 2% 3%\\n[libx264 @ 0x5695b5a9f3c0] i8c dc,h,v,p: 70% 20% 10% 1%\\n[libx264 @ 0x5695b5a9f3c0] Weighted P-Frames: Y:0.0% UV:0.0%\\n[libx264 @ 0x5695b5a9f3c0] ref P L0: 85.9% 1.4% 9.4% 3.4%\\n[libx264 @ 0x5695b5a9f3c0] ref B L0: 61.0% 37.9% 1.1%\\n[libx264 @ 0x5695b5a9f3c0] ref B L1: 97.3% 2.7%\\n[libx264 @ 0x5695b5a9f3c0] kb/s:222.49\\nffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Duration: 00:00:32.67, start: 0.000000, bitrate: 225 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 222 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n[mp3 @ 0x59fd419ac0c0] Estimating duration from bitrate, this may be inaccurate\\nInput #1, mp3, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3':\\n Duration: 00:00:32.14, start: 0.000000, bitrate: 48 kb/s\\n Stream #1:0: Audio: mp3, 24000 Hz, mono, fltp, 48 kb/s\\nStream mapping:\\n Stream #0:0 -> #0:0 (copy)\\n Stream #1:0 -> #0:1 (mp3 (mp3float) -> aac (native))\\nPress [q] to stop, [?] for help\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, q=2-31, 222 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 69 kb/s\\n Metadata:\\n encoder : Lavc60.31.102 aac\\nsize= 0kB time=N/A bitrate=N/A speed=N/A \\r[out#0/mp4 @ 0x59fd41a22b40] video:888kB audio:256kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.737114%\\nsize= 1164kB time=00:00:32.54 bitrate= 293.0kbits/s speed=68.5x \\n[aac @ 0x59fd41a23580] Qavg: 17120.062\\n{\\n \\\"ok\\\": true,\\n \\\"manifest\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.0.0-word-aligned-proof\\\",\\n \\\"series\\\": \\\"Digital Red Flags\\\",\\n \\\"title\\\": \\\"The calendar invite login trap\\\",\\n \\\"script\\\": \\\"This calendar invite looks normal. The trap is the login button. Same meeting title. Same guest list. Same urgent tone. But the link points somewhere else. Before you sign in, check three things: the sender, the link domain, and whether the login asks for more than usual. If the domain feels off, do not sign in from the invite. Open the service yourself. The fix is simple: trust the app you opened, not the button that rushed you.\\\",\\n \\\"script_hash\\\": \\\"937a8fe3c8881ae2\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\\\",\\n \\\"preview_sha256\\\": \\\"d325d99bab7df4d8488794224ba593a6252a463e0d1b7c5f276cade2e0fc1011\\\",\\n \\\"silent_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4\\\",\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"audio_sha256\\\": \\\"ebf6088d996bcf1b1edb22d3fc5cf9eb1ee03d155eb4bdf45d1e0de80365ce4d\\\",\\n \\\"word_cues_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/word_cues.json\\\",\\n \\\"caption_segments_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/caption_segments_word_aligned.json\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\\\",\\n \\\"subtitle_preview_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_subtitle_style_preview_v1.jpg\\\",\\n \\\"qa_summary_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\\\",\\n \\\"duration_seconds\\\": 32.636,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"caption_policy\\\": \\\"static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries\\\",\\n \\\"blocked\\\": {\\n \\\"wan\\\": true,\\n \\\"i2v\\\": true,\\n \\\"platform_api\\\": true,\\n \\\"posting\\\": true,\\n \\\"scheduling\\\": true\\n }\\n },\\n \\\"review_package\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\\\"\\n}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_SHM68uMpWgp8SwhDM1hzh1MQ"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_TRyZnS2dOMV8qUC0a5eQIxEi",
"call_id": "call_TRyZnS2dOMV8qUC0a5eQIxEi",
"response_item_id": "fc_051a8a0b2fb58918016a149d7832f08191a3d08b0850d3c9ee",
"type": "function",
"function": {
"name": "vision_analyze",
"arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\",\"question\":\"Prüfe dieses 9:16 Shorts-Contact-Sheet: Sind die Captions innerhalb der Safe Zone, lesbar, nicht abgeschnitten? Ist der visuelle Ablauf verständlich und gibt es problematische echte Daten/Logos/QR-Codes?\"}"
}
},
{
"id": "call_AbZaO5PRxwCNvUwBKvOXvUGd",
"call_id": "call_AbZaO5PRxwCNvUwBKvOXvUGd",
"response_item_id": "fc_051a8a0b2fb58918016a149d78343c8191a31f32cc7de5f1a9",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"limit\":200,\"path\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\"}"
}
},
{
"id": "call_kOaq2xOytMEFz7ubvfiRJQtx",
"call_id": "call_kOaq2xOytMEFz7ubvfiRJQtx",
"response_item_id": "fc_051a8a0b2fb58918016a149d7834f08191990f84f912f61e1c",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4 && sha256sum /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\",\"timeout\":30}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Inspecting with QA tools**\n\nI need to conduct a quality assurance inspection using visual analysis. I think I might utilize a contact sheet or subtitles for that. Using the vision analysis tool seems like a good idea, and maybe I could incorporate ffprobe as well. Overall, I’ll ensure to read through the QA materials to support the inspection process. It's all about getting the details right to maintain quality!",
"reasoning_content": "**Inspecting with QA tools**\n\nI need to conduct a quality assurance inspection using visual analysis. I think I might utilize a contact sheet or subtitles for that. Using the vision analysis tool seems like a good idea, and maybe I could incorporate ffprobe as well. Overall, I’ll ensure to read through the QA materials to support the inspection process. It's all about getting the details right to maintain quality!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ13Z0DvZLgWV8cokPYZRwyMxXf7jtNuC1nGuOc4DCkCZIAu3dYQhT4MqMHcq6WssI-fB3zOPYL6OAfdA-Mp68O7FoECGfBb6IFIV9WEwWWYQScG4W4oXgLY4LPRlTij2VW565PwLHJS1mBAzEQrccwgSQfjiTGprlzCRrl9dp0xyFbiR7NUNaycRrxKpfdLXJCdI35bfHZro8Njf9eQCVMHWyOvW2fhlfiSqwRRl9dDW6zBfhD4WqKmlRGM_KVV6JcJYrRqD-0e8X5aR63xYK0ejjM2WR41pihwRfxQymWPTAN2Hw3yI192sGRLf2xE6f49mJgZh1gJ6XF47_GkJdp2oNOf3Zf7OxE6gRVQ8ItVQFJjSZ9_bbrrE5KmocbNk7thIQ-LncaHhq6jNKa-vyV-q_fLcEc7GyFRdx8r_Vyqhdvs_oT6AQGPe1-1FJQBcvWWpJozFRtXt9p6H25QJG-IO68kqcaddb9_RGkfuB48Bk_eR3uy1QjnpL_l8l0h9tsudtP7-phPx761IEjUBQVMlDawM0JtZ_epElADS0csqc3UgAhXfjXLOAtFHjAMUmFMU4SY0Po5ww6CvbDgkdHEoEHILPf5i2-2TGkogBURhuWoQaEfdqxVtTHztK617ZewDdBn_Aznjmk4W7zQWI_AFeZnNh-4l6hwzEtXoxZ5qFEUiiwljI774mN2Hi2yflyfncYpMO8Im3PL4dnvvsW4ugaWPSX36ZmFiyJBI--8tLZOQ7l7JXjO2S_VmhaQt8zh3dsUl_KAv6_dfE9mFfGgopJAcPPjD1sJ4ZbpDX-jvboZ6fN6Qz_52l-hr7mMk1wKfuTxswAuBSh42aeY9hu2B2kEmMwF7SnxWpD2roG6_sozssX3YRZ48mfdGoVZURGT0hPbhqFAuVEYKfQUQU9ZjbSwzJcGHJwQ8dKYysGHyers6px3sYEg13Y1l6gWIGOlZCK2IJxYQauy3L5mo80nmiEuDPINn65scyYfrfRuFCn2jHVAJL3Cv1KbQz2oeUZ_RwbnjCjn6yXnRdK3v07600nErHi-EnmUD59tJWSpINY=",
"id": "rs_051a8a0b2fb58918016a149d71ad248191beef3c1fa0a62c74",
"summary": [
{
"type": "summary_text",
"text": "**Inspecting with QA tools**\n\nI need to conduct a quality assurance inspection using visual analysis. I think I might utilize a contact sheet or subtitles for that. Using the vision analysis tool seems like a good idea, and maybe I could incorporate ffprobe as well. Overall, I’ll ensure to read through the QA materials to support the inspection process. It's all about getting the details right to maintain quality!"
}
]
}
]
},
{
"role": "tool",
"content": "Image loaded into your context — you can see it natively now. Use your built-in vision to answer the user.\n\nQuestion: Prüfe dieses 9:16 Shorts-Contact-Sheet: Sind die Captions innerhalb der Safe Zone, lesbar, nicht abgeschnitten? Ist der visuelle Ablauf verständlich und gibt es problematische echte Daten/Logos/QR-Codes?\n[screenshot]",
"tool_call_id": "call_TRyZnS2dOMV8qUC0a5eQIxEi"
},
{
"role": "tool",
"content": "{\"content\": \" 1|{\\n 2| \\\"caption_sync_source\\\": \\\"edge_tts_word_boundary_offsets\\\",\\n 3| \\\"static_phrase_active_word\\\": true,\\n 4| \\\"min_words_default\\\": 3,\\n 5| \\\"target_words\\\": 5,\\n 6| \\\"max_words\\\": 7,\\n 7| \\\"one_word_segments\\\": [],\\n 8| \\\"one_word_segment_count\\\": 0,\\n 9| \\\"duration_seconds\\\": 32.636,\\n 10| \\\"audio_duration_seconds\\\": 32.136,\\n 11| \\\"word_cue_count\\\": 78,\\n 12| \\\"segment_count\\\": 16,\\n 13| \\\"safe_zone\\\": \\\"bottom caption, no box/bar, tested via contact sheet\\\",\\n 14| \\\"summary_fazit_present\\\": true,\\n 15| \\\"final_solution\\\": \\\"Open the service yourself; trust the app you opened, not the rushed button.\\\"\\n 16|}\", \"total_lines\": 15, \"file_size\": 537, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_AbZaO5PRxwCNvUwBKvOXvUGd"
},
{
"role": "tool",
"content": "{\"output\": \"{\\n \\\"programs\\\": [\\n\\n ],\\n \\\"streams\\\": [\\n {\\n \\\"codec_type\\\": \\\"video\\\",\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"r_frame_rate\\\": \\\"24/1\\\"\\n },\\n {\\n \\\"codec_type\\\": \\\"audio\\\",\\n \\\"r_frame_rate\\\": \\\"0/0\\\"\\n }\\n ],\\n \\\"format\\\": {\\n \\\"duration\\\": \\\"32.666667\\\",\\n \\\"size\\\": \\\"1191775\\\"\\n }\\n}\\nd325d99bab7df4d8488794224ba593a6252a463e0d1b7c5f276cade2e0fc1011 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_kOaq2xOytMEFz7ubvfiRJQtx"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_FiaFFDZZYWlpRhlV55g0A6bZ",
"call_id": "call_FiaFFDZZYWlpRhlV55g0A6bZ",
"response_item_id": "fc_051a8a0b2fb58918016a149d9d38648191b2c4bb98623fa671",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"old_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n \\\"But the link points somewhere else. Before you sign in, check three things: \\\"\\n \\\"the sender, the link domain, and whether the login asks for more than usual. \\\"\\n \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n)\\n\",\"new_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n \\\"But the link points somewhere else. Before you sign in, slow down. \\\"\\n \\\"First, check who sent it. Then check the link domain. Then notice any unusual login request. \\\"\\n \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n)\\n\"}"
}
}
],
"finish_reason": "tool_calls",
"reasoning": "**Revising check phrases**\n\nI’m thinking about the active phrases for the user’s request. I see “check three things” works well, but “the sender” has only two words, which might not fit. The user prefers between 3 to 7 words, so I should aim for a minimum of 3. I could create a Phrases array to generate counts, like \"before you sign in,\" \"check three things,\" and more. Maybe also try reformulating “first the sender” to simplify the script?",
"reasoning_content": "**Revising check phrases**\n\nI’m thinking about the active phrases for the user’s request. I see “check three things” works well, but “the sender” has only two words, which might not fit. The user prefers between 3 to 7 words, so I should aim for a minimum of 3. I could create a Phrases array to generate counts, like \"before you sign in,\" \"check three things,\" and more. Maybe also try reformulating “first the sender” to simplify the script?",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ2dtjDhU7L3Xp2nYxUE0ekvjyZ4CoGTiMHGwkItFxJRalY1c_-J3uwYotg2fW1yUNO5GQl4s4EbgLL3ozno7gAKVz-iwCkiK6fFCff6AP1UD7aQ3kBCuU1HY3gfvqPhGfdz_rg03JyvH55049SC7M4wbiIK7lw9Uvn9VHUZxnfBvmwI4_aDClzXp5jl77zWWa410JiPdJ0JFLA8bqrrDkJDi6b7sNHL5WG83Kxe-qOIlCfNeGW0UJiUyWWTldu974skeQdVUlfwP1wqp_GCjOKMLm41blMvBQRfvvUqKC7K4nOoGts9_FBGY5g270ncQUOd-z_G7zXeKqlns9LluzZYrLtido1X9QNRSfs06mii9mZxKg7bY3BF190oCUemgevpoKfYSXqSH2-1YsZmwdFxDFEaLQlO3qXclUzRRrNihUw6NIf-HIsG88jECZQjlnMl46yRM2ZIxCwPpiQITtVdRvqjUcUutAflNyfMOz3GdQ0Eq4k6SAIfVRvfGn7b5WRfihTHKP0G0fvB48v2AxiOMTM-wU6-6rjXMOuZZDE9xISECN3X2wS5q-gijd43gHKrWz2BDt_75L3X7jhpjC6qfWhbMYHLp1CdTE3Ebg_h3dx9EjXnC-5XTokCEvzRywh-O2qMmBEP_4NtMGylXJSlisip4opoTl_8aRrRj6b24QBPpH-Yj-YDx30ji7OweUq-WHloAMmRmPwsDTqirBILNb-tzz71IIV5iG5_gi4HWw23O96Vkr-zvzSqCaDqSaIoKZpb9n9pEDVb4XMqgP4Bob93u7zsjh-02SuyX-hzTZZfn6o4Xktea8QnR8qyE5taJSlIS4HDwOUn837Swv-0K9K-scopeKCxlOpeLgJb6sagZHN7SCYnaLPZPtJFZkWOxHVlkJnlk4PjWa3lCb1pxwAHFyPB6EABEkqqjq5EpXpepYx8tYpizRp64k3CLApTdF9l6iuiBOFZn3zhhInoKgEjm_q7wHC3chvKMBA6kAXyUbFo1Dxj9-Zx-xUkasVdZ1DuLGbvPgvZpODI5btSclpfVy3FhFr3uHhivUiRHEQnkIXDh-lMhQxjjl5P0ciCwT0_SPtKp4qJwGHRdGv1GGsh_IsvX5uvbdnT44jdZdRpiF5pCfB5_U-Il6eDs4A7-ZJD61cIrwlafAYm6CujjAG1VUgr9SjBAysv1QgNN4vKFE7aL8L22U5nB4EgZSRYUBhmve7IG8CBxyScnTmad8xHyVjcZOkZeFSp1z2VniV1_O-ijr-zqm-3iZRjM0Uvj4_Fhq5daGhKXctQEldsbvWhLRUEe3Z-ZnAuKxQWUuwIx-4fdjMdXfr7pYBHTTlsTyoDWDnMlbIn-a51SO3Lo3IYnopIHMucfAf2GeUFuavtrWgbr3sWAqB6_zzvS6Ua7wWt3N9kHlkEPeJ16tlrEpOYRNWGkXLAFiqjJmVlI7zNds-8Um5pYRXxFQ3gaijbuq6GnFV3Dt0snBPwsQf80C8ZUGd2obQD1Y75EnyE0XhVcLJFOsXqTC1IZspQhsbwl0aFcFrTR2rnFP9YypkW_Zqud_VlQio0ddjGFuKQnzBb-t2nq1LNGoISRPKT-sgyD15oFI3urIU79uWiIr64fQXgjGpxk2OFKtOpvOLMZHAve9593VUZdmgAg1DvFOpAZo3frt0mVJbpwGHS7SHjwnPiAw4DSD59hYEDHrvJnrXcEBAUOJTSGoSrjZEz1eH14faSTHu5DSxWrqA6UHOn2Mcrknn7ITh4ZZ3Gw86MB0UUEz5d1YQD4_X3eCCknK0KPZZTxsgqJaMTNLU6aVpl8Ql7JM4SHEEDW7jWkudx4jvw7CKqAVSpApAfYGUHSNXdwqfo0DBWPQsrubHP3zidJ-ZvvVugo40xqlHxVc1JNWKTZe0uIJ5vdSD48jG1pmZY4JYL-99pV3p2xTji6KQmGwwtM4PqYEoO8EhU8FQiaXw7fScQfBI-YTArwNWbe7z2ZstqCXHMW7gDbTtkBYX2gaPXWSeYpRy3Hrrzh0xf0yqzCDdH2I4etd4TjAclrzWf9eKa08AD6vkz1WzBJZ6HRnAvPgbm_R8SdbGVvZLVoCgQypazIhuQY-lCXPOPqw-A3DWl5IeCH9pEWTqmJQFPxQXMSUXX9wQD1RntyS987LiUsNEHLD1_KHwrzsYKDQQ897w213lN6_zc9A5YIm29ebl41V8yEdDe0U0yB4cVhVhu4IUfOXVRyib-3tTrhJMlIksMQQijLsLs9pAjJMI4rUXgkRZFjNpFjtnWhMqRXB6AuGn_k6ZL0ScEMhXLaUgjGB18N2SHF_m2Mo8YSAPDmfPYlGUvRwwyqr1fb0Z_JLDCmWCX_xa1irOLgGCVkZGaRy0zwZ0nCOgSkwt0RMu5t4vDNaEenfQqWApOFr2x-MwguCUpRqAr5cl8-WWhHDXZmG0R86JiPd6xNX1hxNVSw8B2BO2AAAN1OcfvB1CZMNEGQfxVcMCusgbJ-H5u47MxDACt3feGrxFikeb2-IWwF5Z4vzuj-s4-9-yiR3zhY8z1-c_JHCM092RAiTbHGqaoJGXyujBRfSgVRhLLl4O35PtILwm51Tum98n_eEkbsyj5PyQbzavWO2SGmdBH_FY_UP75qcSOKXoNJu1-VJGPv90tT9mG6vsnJRuw1Gx1qfB4YX8oWKqS5ZEz805Tb0T0wG7qlwJX2ZewN5mpfbpNV1NwJ2fSQhWOGV2IrsJxL0RXYgzNfh88ahImXiHklswrZvzTW3B98RjnVQ9KDlMhQJ0zolh14DaDN3h4UZJJah-lLnTFJ9nbIDby1Vlr_IYf_Rb4atv9DlC4O7fZyobQSChbVqQpHRJ1dOH5XRX8kAG8MQiU182fn1DvE2hLMfPX_QImC4fA5bWF0HcFxYdcmI1HIP_1WFn-n2iAHcdkceNmhpTmuOuOuSmEIoSQ5P7BBYq_s3az4YjjsSDKilErIgCm4Z5YkhT75dmHoTWZZ0ycyDs0HldGSKpWC9OKl8nhyJXdmTv6pJklb7H-13U12RRmL1FbD_ByRjGnTnaDckPCaSv27bKavD2musSpm6pqhLqL8YojuCirj2pkYy8enWSyUsN2fOwusrSs3UvIw6bTcjRHjURwHxnrKJfQN-glCy2X5kTK9QzpDfiCfnUtZxGnIqwpnpk3weRI2WnKokuke0KCZV0q-2waFclEZ2QBKVpgAqEYVpHrQbycv2jXL8MG5OoyBijII30W3Kbk6ryqtpZ98JWTvdW5MGP2aQBSy8ooz9-73fkAj6B-CaIN-Gw1D1-byzF5_068HvIO5NhB1JnOqGhM1Q-Dkv11sBstxLvTcjf-IAH3R_O9EbXvW93JuAs6CDanZFxFjrKXq8ZFVpddG3gEs8_S-qc3TaMo48V2aiTOtb_zkB_iUq9gfzFiF66j9X_F9M9TSJbo1x_M5ImnQa7HcVtd6T7Wds2jeTY-VmFdVvKQH9E7EHWYZ3OcW8wMLUMZyIHtW0Tf7Y0l-t43Y1a7dtxoli7grsWvrsaHnXHT7WytYQgSb7X_T2PjuWEvFcK0KFkIpiBujtkMnUZl_quUvyBzL70K_ux6n0s3ipUFJTQwiLxCViKCpP9ZidjnTx_MtK-c1ici3T5FSInqazqskd4EZt8TSRTkvMfDEr8lr5pVLJH_shRD2AJB8OINMPk5Y9bPzeKqGJicil0w9zvYhrpo_qIMlpm5E3dNS3aLgZ9avCZcz_RU_pvrvFRAOb23lhxGChC06xX7RfN0SBJR7pssJlBjWHXkdXaQNAUQtEEzd8LpnjLF319HUKOKfv3BGTSiHDnkCAZ8WhfchlQrrr1UpVFEnUQeW6tti1St7gIH2VLqUE3j053LnMpPwY6g-p4zQlR7ng3bZL_4_cx1GBnIHC_Pa4HG1zWnvC9W1V65A6MS7UJLZFGdj6j_Z-NRxRyzVkcgsw-_0ldvSYJnRkv-d6uvaL5GWSlOi4E8LAQGuJLfcJ8A6xEygkQ1CXcbu0-BrnQwXWqN2aB5B2P4WC4C4_NeQ0DtkbL012roP_JnRy_YmwKNsOufrMtNAVVX1gQwIOhXIau7x_mO1lNTZMo-f6Wqa-ex1-Z375YwyJwAPbpZaV_KqsXBroOHN5cJ9Krvrph8xDPr9DKLGNnjE_p6XR-4u_OJ6jS4GIqZiAGWZ6IqsIHSLUcL2KmNnqQGNPyo6NK4xaPHwd7YHgom7RHcDqgkuvlM078uSBjk2mrAzWRQAMmuOiMCCgBZey-G_oqMs_s0tJo8mUTnbsQS6KPVSH-_DOQ6eqVzRhDGd3DL4ieN0KtYTAHQJEI03E-VMuRR-uH39arfaQ5cbe4_uhjy6wgHYAgI4kHqKK-E7P_JTCKnYOBG49vs8_eOnDRb7tDaQOanW8AsAvuQ0F06KHJrnLqAES_svZNetlvOfk-KIQqM85yt3-i6Fa6UjOziduRUJ8s4Xmgw8QaYTcSGW1xuGpHNy8tDEIdTUicne6W28D7yj3bIwAI5EatzeKxc0CiQp2jF-WKEA3xIKOCTAmk2qUDBuqNEHB6S6yVUKtmWrv7slQsjQ9dT2pg13ke2pNXAbFSdd5oyCxgrq5AFuWSzbP0O9eiOkI6BCRlW3adsQ5GA-cDFKlHLpcVv2H6Vjb2Ol8TyCK02PEsvjOGV61AHQ-2CJmJw0t7mhMK5CskCF2XlrjJAPbGaNb7yCqXmeTLkZ0xTvkh0Z_BSZJ7Lra9WlGQ2mU5U9_7879ZmZ0tqY7KyTw3pnvX6W72vgs3-xKtOG23l9u-KDMvERr1EM5BfuUwChxFfh6dNMgQnQAx7QMSVTaLp4AVwceCjOobInQ7x52Jmjn9ITTJq2iBJq3h10FzA7UzHCWJC_PQRlA-yVRcWMd9sk2vc6MDwRSWEtop1HgL1HjMatlzA8L_1J2C6MP3tWzWP-3jG0UTQmS_bHtTWcv2gFE7KgxR2NC-iQ7S7WnOOAsUPna31q-66sl4NSfjMiYI94y51O5WM1sxhnh_bqXjU6N3NafMpNmAzldD1Mk_PWQsws4W3gig7JzyxjiRlRLcHVUs_wq6vWhfaxYga7kM9UHwIBp2-5F-yZEee-s3Y8Os2U4ripM9Nd_2tJJqpEN1hCoNPdk0GE7eLC5qd-AqjsIwOfI9HgzHoF7yttxKHSO6ERjlkKHfr-FS7lvu_TYBcoj4VZY4GGBP6nTuJnW-M6LAA6_a7Lhvo9be1TgTCZLpbZcf1ikI9vPLttRhywCj7LI8SYySGK3u7a5mP1Ir4VZS4AyyQHghwwwQfyFoqx6fZNJNwVLgP2BGoj4e-RG41pe4NL0BzBcb3UZLDs7N3W56NxPatd6WhdFSXPTrOs1pxHVGJ7b9dzMQVpwZ1qThjCHrCC3ovATSBzFByLAlSj6SIQixTfHh4ca-kmavdsY7NMLk4O9DnW1_5FdAlDm_3mdF1bRWUn7x3gZxjbtIDgHxt3ItEkPM1pQDRmbFXyWR57qnTXB3eo1TC8SVev41Qpn6YoePLQXc5t5RzDT4kavNrE8UzoQOOnfhCsPAwffTfBzRyNvHRh029O09o30vFlAMlNKUxMxrKMm2cT8jCkQ==",
"id": "rs_051a8a0b2fb58918016a149d8bf6488191b452c16fa968388f",
"summary": [
{
"type": "summary_text",
"text": "**Revising check phrases**\n\nI’m thinking about the active phrases for the user’s request. I see “check three things” works well, but “the sender” has only two words, which might not fit. The user prefers between 3 to 7 words, so I should aim for a minimum of 3. I could create a Phrases array to generate counts, like \"before you sign in,\" \"check three things,\" and more. Maybe also try reformulating “first the sender” to simplify the script?"
}
]
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -42,8 +42,8 @@\\n SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n- \\\"But the link points somewhere else. Before you sign in, check three things: \\\"\\n- \\\"the sender, the link domain, and whether the login asks for more than usual. \\\"\\n+ \\\"But the link points somewhere else. Before you sign in, slow down. \\\"\\n+ \\\"First, check who sent it. Then check the link domain. Then notice any unusual login request. \\\"\\n \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n )\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_FiaFFDZZYWlpRhlV55g0A6bZ"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_ZH76mQ3azwWjTMB35oiP0hfc",
"call_id": "call_ZH76mQ3azwWjTMB35oiP0hfc",
"response_item_id": "fc_051a8a0b2fb58918016a149da7bb408191be76b75c95d6e361",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\" labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login request', 20.0)]\",\"old_string\":\" labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login', 20.0)]\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -179,7 +179,7 @@\\n \\n \\n def draw_checks(draw, t):\\n- labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login', 20.0)]\\n+ labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login request', 20.0)]\\n y = 1218\\n for i, (lab, ts) in enumerate(labels):\\n active = t >= ts\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_ZH76mQ3azwWjTMB35oiP0hfc"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_effOW8casExuzUDrWQnBzjN8",
"call_id": "call_effOW8casExuzUDrWQnBzjN8",
"response_item_id": "fc_051a8a0b2fb58918016a149db50f408191ae0be315fd8abf87",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"output\": \"ffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, rawvideo, from 'fd:':\\n Duration: N/A, start: 0.000000, bitrate: 1194393 kb/s\\n Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 1080x1920, 1194393 kb/s, 24 tbr, 24 tbn\\nStream mapping:\\n Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x64a5c11903c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x64a5c11903c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x64a5c11903c0] 264 - core 164 r3108 31e19f9 - H.264/MPEG-4 AVC codec - Copyleft 2003-2023 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=9 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n encoder : Lavf60.16.100\\n Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1080x1920, q=2-31, 24 fps, 12288 tbn\\n Metadata:\\n encoder : Lavc60.31.102 libx264\\n Side data:\\n cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\\nframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 1 fps=0.3 q=25.0 size= 0kB time=-00:00:00.04 bitrate=N/A speed=N/A \\rframe= 11 fps=3.0 q=25.0 size= 0kB time=00:00:00.37 bitrate= 1.0kbits/s speed=0.101x \\rframe= 20 fps=4.7 q=25.0 size= 0kB time=00:00:00.75 bitrate= 0.5kbits/s speed=0.178x \\rframe= 30 fps=6.3 q=25.0 size= 0kB time=00:00:01.16 bitrate= 0.3kbits/s speed=0.245x \\rframe= 39 fps=7.4 q=25.0 size= 0kB time=00:00:01.54 bitrate= 0.2kbits/s speed=0.292x \\rframe= 48 fps=8.3 q=25.0 size= 0kB time=00:00:01.91 bitrate= 0.2kbits/s speed=0.331x \\rframe= 57 fps=9.1 q=25.0 size= 0kB time=00:00:02.29 bitrate= 0.2kbits/s speed=0.364x \\rframe= 67 fps=9.8 q=25.0 size= 0kB time=00:00:02.70 bitrate= 0.1kbits/s speed=0.397x \\rframe= 78 fps= 11 q=25.0 size= 0kB time=00:00:03.16 bitrate= 0.1kbits/s speed=0.429x \\rframe= 88 fps= 11 q=25.0 size= 0kB time=00:00:03.58 bitrate= 0.1kbits/s speed=0.455x \\rframe= 100 fps= 12 q=25.0 size= 0kB time=00:00:04.04 bitrate= 0.1kbits/s speed=0.48x \\rframe= 109 fps= 12 q=25.0 size= 0kB time=00:00:04.45 bitrate= 0.1kbits/s speed= 0.5x \\rframe= 120 fps= 13 q=25.0 size= 0kB time=00:00:04.91 bitrate= 0.1kbits/s speed=0.52x \\rframe= 131 fps= 13 q=25.0 size= 0kB time=00:00:05.37 bitrate= 0.1kbits/s speed=0.538x \\rframe= 142 fps= 13 q=25.0 size= 0kB time=00:00:05.83 bitrate= 0.1kbits/s speed=0.554x \\rframe= 153 fps= 14 q=25.0 size= 0kB time=00:00:06.29 bitrate= 0.1kbits/s speed=0.569x \\rframe= 164 fps= 14 q=25.0 size= 0kB time=00:00:06.75 bitrate= 0.1kbits/s speed=0.584x \\rframe= 175 fps= 14 q=25.0 size= 0kB time=00:00:07.20 bitrate= 0.1kbits/s speed=0.597x \\rframe= 186 fps= 15 q=25.0 size= 0kB time=00:00:07.66 bitrate= 0.1kbits/s speed=0.609x \\rframe= 197 fps= 15 q=25.0 size= 0kB time=00:00:08.12 bitrate= 0.0kbits/s speed=0.62x \\rframe= 208 fps= 15 q=25.0 size= 0kB time=00:00:08.58 bitrate= 0.0kbits/s speed=0.631x \\rframe= 219 fps= 15 q=25.0 size= 0kB time=00:00:09.04 bitrate= 0.0kbits/s speed=0.639x \\rframe= 228 fps= 16 q=25.0 size= 0kB time=00:00:09.41 bitrate= 0.0kbits/s speed=0.641x \\rframe= 237 fps= 16 q=25.0 size= 0kB time=00:00:09.79 bitrate= 0.0kbits/s speed=0.643x \\rframe= 245 fps= 16 q=25.0 size= 0kB time=00:00:10.12 bitrate= 0.0kbits/s speed=0.644x \\rframe= 254 fps= 16 q=25.0 size= 256kB time=00:00:10.50 bitrate= 199.8kbits/s speed=0.645x \\rframe= 263 fps= 16 q=25.0 size= 256kB time=00:00:10.87 bitrate= 192.9kbits/s speed=0.647x \\rframe= 272 fps= 16 q=25.0 size= 256kB time=00:00:11.25 bitrate= 186.4kbits/s speed=0.649x \\rframe= 281 fps= 16 q=25.0 size= 256kB time=00:00:11.62 bitrate= 180.4kbits/s speed=0.651x \\rframe= 290 fps= 16 q=25.0 size= 256kB time=00:00:12.00 bitrate= 174.8kbits/s speed=0.654x \\rframe= 299 fps= 16 q=25.0 size= 256kB time=00:00:12.37 bitrate= 169.5kbits/s speed=0.656x \\rframe= 308 fps= 16 q=25.0 size= 256kB time=00:00:12.75 bitrate= 164.5kbits/s speed=0.658x \\rframe= 317 fps= 16 q=25.0 size= 256kB time=00:00:13.12 bitrate= 159.8kbits/s speed=0.66x \\rframe= 326 fps= 16 q=25.0 size= 256kB time=00:00:13.50 bitrate= 155.4kbits/s speed=0.662x \\rframe= 335 fps= 16 q=25.0 size= 256kB time=00:00:13.87 bitrate= 151.2kbits/s speed=0.663x \\rframe= 345 fps= 16 q=25.0 size= 256kB time=00:00:14.25 bitrate= 147.2kbits/s speed=0.663x \\rframe= 354 fps= 16 q=25.0 size= 256kB time=00:00:14.62 bitrate= 143.4kbits/s speed=0.663x \\rframe= 363 fps= 16 q=25.0 size= 256kB time=00:00:15.04 bitrate= 139.4kbits/s speed=0.665x \\rframe= 373 fps= 16 q=25.0 size= 256kB time=00:00:15.45 bitrate= 135.7kbits/s speed=0.667x \\rframe= 383 fps= 16 q=25.0 size= 256kB time=00:00:15.87 bitrate= 132.1kbits/s speed=0.67x \\rframe= 393 fps= 16 q=25.0 size= 256kB time=00:00:16.29 bitrate= 128.7kbits/s speed=0.672x \\rframe= 402 fps= 16 q=25.0 size= 256kB time=00:00:16.66 bitrate= 125.9kbits/s speed=0.673x \\rframe= 412 fps= 16 q=25.0 size= 256kB time=00:00:17.08 bitrate= 122.8kbits/s speed=0.675x \\rframe= 421 fps= 16 q=25.0 size= 256kB time=00:00:17.45 bitrate= 120.1kbits/s speed=0.675x \\rframe= 430 fps= 16 q=25.0 size= 256kB time=00:00:17.83 bitrate= 117.6kbits/s speed=0.677x \\rframe= 439 fps= 16 q=25.0 size= 256kB time=00:00:18.20 bitrate= 115.2kbits/s speed=0.678x \\rframe= 449 fps= 16 q=25.0 size= 256kB time=00:00:18.62 bitrate= 112.6kbits/s speed=0.68x \\rframe= 458 fps= 16 q=25.0 size= 256kB time=00:00:19.00 bitrate= 110.4kbits/s speed=0.681x \\rframe= 467 fps= 16 q=25.0 size= 256kB time=00:00:19.37 bitrate= 108.3kbits/s speed=0.681x \\rframe= 476 fps= 16 q=25.0 size= 256kB time=00:00:19.75 bitrate= 106.2kbits/s speed=0.681x \\rframe= 484 fps= 16 q=25.0 size= 256kB time=00:00:20.08 bitrate= 104.4kbits/s speed=0.68x \\rframe= 492 fps= 16 q=22.0 size= 256kB time=00:00:20.41 bitrate= 102.7kbits/s speed=0.68x \\rframe= 501 fps= 16 q=25.0 size= 256kB time=00:00:20.79 bitrate= 100.9kbits/s speed=0.68x \\rframe= 510 fps= 16 q=25.0 size= 512kB time=00:00:21.12 bitrate= 198.6kbits/s speed=0.679x \\rframe= 518 fps= 16 q=25.0 size= 512kB time=00:00:21.45 bitrate= 195.5kbits/s speed=0.678x \\rframe= 525 fps= 16 q=25.0 size= 512kB time=00:00:21.79 bitrate= 192.5kbits/s speed=0.678x \\rframe= 533 fps= 16 q=25.0 size= 512kB time=00:00:22.12 bitrate= 189.6kbits/s speed=0.677x \\rframe= 542 fps= 16 q=25.0 size= 512kB time=00:00:22.50 bitrate= 186.4kbits/s speed=0.677x \\rframe= 551 fps= 16 q=25.0 size= 512kB time=00:00:22.87 bitrate= 183.4kbits/s speed=0.677x \\rframe= 561 fps= 16 q=25.0 size= 512kB time=00:00:23.29 bitrate= 180.1kbits/s speed=0.678x \\rframe= 571 fps= 16 q=25.0 size= 512kB time=00:00:23.66 bitrate= 177.2kbits/s speed=0.679x \\rframe= 579 fps= 16 q=25.0 size= 512kB time=00:00:24.04 bitrate= 174.5kbits/s speed=0.68x \\rframe= 588 fps= 16 q=25.0 size= 512kB time=00:00:24.41 bitrate= 171.8kbits/s speed=0.68x \\rframe= 596 fps= 16 q=25.0 size= 512kB time=00:00:24.75 bitrate= 169.5kbits/s speed=0.68x \\rframe= 604 fps= 16 q=25.0 size= 512kB time=00:00:25.08 bitrate= 167.2kbits/s speed=0.679x \\rframe= 612 fps= 16 q=25.0 size= 512kB time=00:00:25.41 bitrate= 165.0kbits/s speed=0.679x \\rframe= 620 fps= 16 q=25.0 size= 512kB time=00:00:25.75 bitrate= 162.9kbits/s speed=0.679x \\rframe= 628 fps= 16 q=25.0 size= 512kB time=00:00:26.08 bitrate= 160.8kbits/s speed=0.678x \\rframe= 636 fps= 16 q=25.0 size= 512kB time=00:00:26.41 bitrate= 158.8kbits/s speed=0.677x \\rframe= 644 fps= 16 q=25.0 size= 512kB time=00:00:26.75 bitrate= 156.8kbits/s speed=0.676x \\rframe= 654 fps= 16 q=25.0 size= 512kB time=00:00:27.16 bitrate= 154.4kbits/s speed=0.678x \\rframe= 665 fps= 16 q=25.0 size= 512kB time=00:00:27.62 bitrate= 151.8kbits/s speed=0.681x \\rframe= 676 fps= 16 q=25.0 size= 512kB time=00:00:28.08 bitrate= 149.4kbits/s speed=0.683x \\rframe= 687 fps= 17 q=25.0 size= 512kB time=00:00:28.54 bitrate= 147.0kbits/s speed=0.686x \\rframe= 698 fps= 17 q=25.0 size= 512kB time=00:00:29.00 bitrate= 144.6kbits/s speed=0.688x \\rframe= 709 fps= 17 q=25.0 size= 512kB time=00:00:29.45 bitrate= 142.4kbits/s speed=0.691x \\rframe= 721 fps= 17 q=25.0 size= 768kB time=00:00:29.95 bitrate= 210.0kbits/s speed=0.693x \\rframe= 733 fps= 17 q=25.0 size= 768kB time=00:00:30.45 bitrate= 206.6kbits/s speed=0.697x \\rframe= 744 fps= 17 q=25.0 size= 768kB time=00:00:30.91 bitrate= 203.5kbits/s speed=0.699x \\rframe= 755 fps= 17 q=25.0 size= 768kB time=00:00:31.37 bitrate= 200.5kbits/s speed=0.701x \\rframe= 766 fps= 17 q=25.0 size= 768kB time=00:00:31.83 bitrate= 197.6kbits/s speed=0.703x \\rframe= 777 fps= 17 q=25.0 size= 768kB time=00:00:32.29 bitrate= 194.8kbits/s speed=0.705x \\rframe= 788 fps= 17 q=25.0 size= 768kB time=00:00:32.75 bitrate= 192.1kbits/s speed=0.707x \\rframe= 799 fps= 17 q=25.0 size= 768kB time=00:00:33.20 bitrate= 189.5kbits/s speed=0.708x \\rframe= 810 fps= 17 q=25.0 size= 768kB time=00:00:33.66 bitrate= 186.9kbits/s speed=0.71x \\rframe= 821 fps= 17 q=25.0 size= 768kB time=00:00:34.12 bitrate= 184.4kbits/s speed=0.711x \\r[out#0/mp4 @ 0x64a5c118ed00] video:929kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.200532%\\nframe= 881 fps= 18 q=-1.0 Lsize= 940kB time=00:00:36.58 bitrate= 210.5kbits/s speed=0.753x \\n[libx264 @ 0x64a5c11903c0] frame I:4 Avg QP:13.80 size: 56321\\n[libx264 @ 0x64a5c11903c0] frame P:222 Avg QP:17.89 size: 2557\\n[libx264 @ 0x64a5c11903c0] frame B:655 Avg QP:22.68 size: 241\\n[libx264 @ 0x64a5c11903c0] consecutive B-frames: 0.8% 0.2% 0.0% 99.0%\\n[libx264 @ 0x64a5c11903c0] mb I I16..4: 66.6% 18.2% 15.3%\\n[libx264 @ 0x64a5c11903c0] mb P I16..4: 0.6% 0.1% 0.3% P16..4: 4.2% 0.2% 0.1% 0.0% 0.0% skip:94.6%\\n[libx264 @ 0x64a5c11903c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.3% 0.0% 0.0% direct: 0.0% skip:97.6% L0:53.9% L1:46.0% BI: 0.1%\\n[libx264 @ 0x64a5c11903c0] 8x8 transform intra:19.3% inter:42.4%\\n[libx264 @ 0x64a5c11903c0] coded y,uvDC,uvAC intra: 14.0% 15.6% 11.5% inter: 0.1% 0.1% 0.0%\\n[libx264 @ 0x64a5c11903c0] i16 v,h,dc,p: 22% 78% 0% 0%\\n[libx264 @ 0x64a5c11903c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 48% 10% 40% 2% 0% 0% 0% 0% 0%\\n[libx264 @ 0x64a5c11903c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 35% 41% 8% 2% 2% 3% 3% 2% 3%\\n[libx264 @ 0x64a5c11903c0] i8c dc,h,v,p: 70% 20% 10% 1%\\n[libx264 @ 0x64a5c11903c0] Weighted P-Frames: Y:0.0% UV:0.0%\\n[libx264 @ 0x64a5c11903c0] ref P L0: 86.0% 1.2% 9.3% 3.5%\\n[libx264 @ 0x64a5c11903c0] ref B L0: 63.0% 35.9% 1.1%\\n[libx264 @ 0x64a5c11903c0] ref B L1: 97.3% 2.7%\\n[libx264 @ 0x64a5c11903c0] kb/s:207.18\\nffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Duration: 00:00:36.71, start: 0.000000, bitrate: 209 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 207 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n[mp3 @ 0x60291a11a0c0] Estimating duration from bitrate, this may be inaccurate\\nInput #1, mp3, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3':\\n Duration: 00:00:36.17, start: 0.000000, bitrate: 48 kb/s\\n Stream #1:0: Audio: mp3, 24000 Hz, mono, fltp, 48 kb/s\\nStream mapping:\\n Stream #0:0 -> #0:0 (copy)\\n Stream #1:0 -> #0:1 (mp3 (mp3float) -> aac (native))\\nPress [q] to stop, [?] for help\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, q=2-31, 207 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 69 kb/s\\n Metadata:\\n encoder : Lavc60.31.102 aac\\nsize= 0kB time=N/A bitrate=N/A speed=N/A \\r[out#0/mp4 @ 0x60291a12fa80] video:929kB audio:278kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.835528%\\nsize= 1229kB time=00:00:36.58 bitrate= 275.3kbits/s speed=75.4x \\n[aac @ 0x60291a1abc00] Qavg: 19257.057\\n{\\n \\\"ok\\\": true,\\n \\\"manifest\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.0.0-word-aligned-proof\\\",\\n \\\"series\\\": \\\"Digital Red Flags\\\",\\n \\\"title\\\": \\\"The calendar invite login trap\\\",\\n \\\"script\\\": \\\"This calendar invite looks normal. The trap is the login button. Same meeting title. Same guest list. Same urgent tone. But the link points somewhere else. Before you sign in, slow down. First, check who sent it. Then check the link domain. Then notice any unusual login request. If the domain feels off, do not sign in from the invite. Open the service yourself. The fix is simple: trust the app you opened, not the button that rushed you.\\\",\\n \\\"script_hash\\\": \\\"8360ab6a8f2241e9\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\\\",\\n \\\"preview_sha256\\\": \\\"723d3349c008eafad423d52026b8c200fc2c5ebdedf6c2ef4e4c6f5d4826a44b\\\",\\n \\\"silent_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4\\\",\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"audio_sha256\\\": \\\"c6c8914a0245ef5e52500cf9d0646542c8b540a786a06314932e47940fd5cbdd\\\",\\n \\\"word_cues_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/word_cues.json\\\",\\n \\\"caption_segments_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/caption_segments_word_aligned.json\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\\\",\\n \\\"subtitle_preview_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_subtitle_style_preview_v1.jpg\\\",\\n \\\"qa_summary_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\\\",\\n \\\"duration_seconds\\\": 36.668,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"caption_policy\\\": \\\"static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries\\\",\\n \\\"blocked\\\": {\\n \\\"wan\\\": true,\\n \\\"i2v\\\": true,\\n \\\"platform_api\\\": true,\\n \\\"posting\\\": true,\\n \\\"scheduling\\\": true\\n }\\n },\\n \\\"review_package\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\\\"\\n}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_effOW8casExuzUDrWQnBzjN8"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_ii6B09uNaBVuVMCHd0uTFTxg",
"call_id": "call_ii6B09uNaBVuVMCHd0uTFTxg",
"response_item_id": "fc_051a8a0b2fb58918016a149df1c52c8191bd537b2462f203b1",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n \\\"Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\"\\n)\\n\",\"old_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n \\\"But the link points somewhere else. Before you sign in, slow down. \\\"\\n \\\"First, check who sent it. Then check the link domain. Then notice any unusual login request. \\\"\\n \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n)\\n\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ3xBrf5WKHAa3n7Lf22lnbnhdn3fCLNVs7QsyrBDsqWqtZFdrkLlS1YpHkpCNJXmeSGdHpiIvtGQpIWXDpVkRIe3kOMHuHMiZZ9kqf9MSbnRychPWI4f2j9uqaLF1P8sYieY0ueGya2jFMR2yhUcbUFHIyVE8fDETaOlipweRT0U6E5hWEM6qzDIeQZDmEy46czR7nwTSdfzwTDYvsTk3J5nMOCQzEb4QztEGQOXtYZFkFyZ_dnh0gB8bZqcARueXGa601F6E7lgbDbtGFwpxGSwkaGGTPaIbNKEdG6qaAJzCgfxzeofj1XfJVx9vxqqS2QC8jiVGPuBEhQIIGMirN_6OnSq2RNvncaTr9QbIPJQyidHvpVsOu-w2VGjFvH6vONLmekJfQDf4Pr6OccaBGXVuZZqaTRWvQWzzklcAw5IeP2Avd3QHfSaO4ZZX3UPFYBhRbwKjwdJbsDLHSspEIgObCLwmrxYXZEmi_qQoWx2OR7BNYAOKUcKjEofrwAdwUhBW5H1UINJxuprChuuDEMKu3T1tIFP_814FS_eYn3IRV4XmUj9bQiU7RjbqLYeLp6A-qozrFLfvftYI8UdxkEkHtbysRunGXN3gauMLsU5DH9WSykhx2AIyeQb2FUqF_TVJ521eculDWpE48jmbpeRCpX5dXU7igGLCT-20LL73TE5JXhDHlMKUzZovLL21SLUrnvD3hSobeI5TCMEvG0o4w4mOfi8C74CmSoRlRwLGcgp6OlbxKcvwqCI-l-S-C5q3VH17vuyg6OBbgTKQz0hnsl5gkbAl-lsUoZo2_AdoVoIzUdeVP92OyO8t60ZIHhYVVDVGZ-MIcup02hzJ68ZM_ukB3boy14pVTnzCy9w_U0lGTizQqggxqMxE9Ne67mM_pBJ-mNFtWwS0YljR6K9y1PtD7wBPxbgklo8fQO_JvX72BM_aOHB7yT_TR7IiNsVDn19QCgIIdDWd5LFucNcvsRI94Ej-19-rQpPy7PESuf4LS6WjyXzTf8Y-mBlIO_J7zEFeHjyZF2IuvEfy2bbUc08vFqQtRuRAstZOk11Heh6EHtdZp6zjqpkMCb5Sp75e0Q26LohRdBmQ8IN3Bit5XZ_3WW0ZBrszOAoKQqORBwzrIju0zjf7MsPbRi-hoBkQYIbbZx4jNRJOUysreXZSgjGLo-DXaLBi4ACwHyx2rawWgDRX3OWfFZefz5uW1UG-ZOt4SQFdo00itJFwL8-M0cPKuOzJ0tLMBmkW4y1Aa2tlsIR62xngb8FH9XDwYNj9bajDESY_0eYYSkeDaOQnYZyhHOBbKkmB-60rQMKpICZDYBLtdMUFN84g5G5WRlhI7OW00NgzAmWkPV3AKv0xd9ROBevpEMr5FTfIP3z1ZP-Bb_PJse5NoOE-sWbhWdeYlJYK_dVMl1YXQ4t6I3DhokfaZJc9gjKtijoiDPS2sr3Qg9jcgXAYJnYIPCIWiH4dDIAIFwRW3vcGWYgKHt62kD6CM_TVQN3WFoomxqHnLijp6qleQQmkDFcsnxoZRVGMtszTIF5TlvIBk66tbB-7aCwJ6eqwokHvCdTtpBR7p_vqLOXUrFSB2ElqER9RF2DRtvfD23qp-UfHW0jZwk28JoRLaylx0EM_V45eQi7p87bmFlY1vhN4hETFxo3rmQQTBcLupZMpkFJDI9eFoeM_0GwCONpjvfNDtKqp2Rsj6OwS8p2G2YvlsEpUZv4FUIbdGhWYi8DHH8U0aXTmtb8893DNEP8AmpL8jLYKl9a6m82ZzLvlYZzhMpYyskNyFf7ZfgoKy6yLT4QnVmT-xIHz2cheQ4jtUFjpLU_iCpYir6455o1yp1_cPYigcKOoCi",
"id": "rs_051a8a0b2fb58918016a149dee7e788191bc1064be5bb43a57",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -41,11 +41,10 @@\\n \\n SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n- \\\"Same meeting title. Same guest list. Same urgent tone. \\\"\\n- \\\"But the link points somewhere else. Before you sign in, slow down. \\\"\\n- \\\"First, check who sent it. Then check the link domain. Then notice any unusual login request. \\\"\\n- \\\"If the domain feels off, do not sign in from the invite. Open the service yourself. \\\"\\n- \\\"The fix is simple: trust the app you opened, not the button that rushed you.\\\"\\n+ \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n+ \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n+ \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n+ \\\"Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\"\\n )\\n SENTENCES = [s.strip() for s in re.split(r'(?<=[.!?])\\\\s+', SCRIPT) if s.strip()]\\n \\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_ii6B09uNaBVuVMCHd0uTFTxg"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_0SI6V0gcqBwS4d6H7OFKmxyy",
"call_id": "call_0SI6V0gcqBwS4d6H7OFKmxyy",
"response_item_id": "fc_051a8a0b2fb58918016a149dfa89648191a416b4c13680486c",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
],
"finish_reason": "tool_calls"
},
{
"role": "tool",
"content": "{\"output\": \"ffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, rawvideo, from 'fd:':\\n Duration: N/A, start: 0.000000, bitrate: 1194393 kb/s\\n Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 1080x1920, 1194393 kb/s, 24 tbr, 24 tbn\\nStream mapping:\\n Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x5c821cc4a3c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x5c821cc4a3c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x5c821cc4a3c0] 264 - core 164 r3108 31e19f9 - H.264/MPEG-4 AVC codec - Copyleft 2003-2023 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=9 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n encoder : Lavf60.16.100\\n Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1080x1920, q=2-31, 24 fps, 12288 tbn\\n Metadata:\\n encoder : Lavc60.31.102 libx264\\n Side data:\\n cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\\nframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 1 fps=0.3 q=25.0 size= 0kB time=-00:00:00.04 bitrate=N/A speed=N/A \\rframe= 9 fps=2.4 q=25.0 size= 0kB time=00:00:00.29 bitrate= 1.3kbits/s speed=0.0789x \\rframe= 18 fps=4.3 q=25.0 size= 0kB time=00:00:00.66 bitrate= 0.6kbits/s speed=0.158x \\rframe= 28 fps=5.9 q=25.0 size= 0kB time=00:00:01.08 bitrate= 0.4kbits/s speed=0.228x \\rframe= 38 fps=7.2 q=25.0 size= 0kB time=00:00:01.50 bitrate= 0.3kbits/s speed=0.283x \\rframe= 48 fps=8.2 q=25.0 size= 0kB time=00:00:01.91 bitrate= 0.2kbits/s speed=0.327x \\rframe= 57 fps=8.9 q=25.0 size= 0kB time=00:00:02.29 bitrate= 0.2kbits/s speed=0.359x \\rframe= 66 fps=9.6 q=25.0 size= 0kB time=00:00:02.66 bitrate= 0.1kbits/s speed=0.388x \\rframe= 76 fps= 10 q=25.0 size= 0kB time=00:00:03.08 bitrate= 0.1kbits/s speed=0.415x \\rframe= 87 fps= 11 q=25.0 size= 0kB time=00:00:03.54 bitrate= 0.1kbits/s speed=0.445x \\rframe= 98 fps= 12 q=25.0 size= 0kB time=00:00:04.00 bitrate= 0.1kbits/s speed=0.471x \\rframe= 108 fps= 12 q=25.0 size= 0kB time=00:00:04.41 bitrate= 0.1kbits/s speed=0.491x \\rframe= 119 fps= 12 q=25.0 size= 0kB time=00:00:04.87 bitrate= 0.1kbits/s speed=0.511x \\rframe= 130 fps= 13 q=25.0 size= 0kB time=00:00:05.33 bitrate= 0.1kbits/s speed=0.529x \\rframe= 140 fps= 13 q=25.0 size= 0kB time=00:00:05.75 bitrate= 0.1kbits/s speed=0.543x \\rframe= 150 fps= 14 q=25.0 size= 0kB time=00:00:06.16 bitrate= 0.1kbits/s speed=0.556x \\rframe= 160 fps= 14 q=25.0 size= 0kB time=00:00:06.58 bitrate= 0.1kbits/s speed=0.567x \\rframe= 171 fps= 14 q=25.0 size= 0kB time=00:00:07.04 bitrate= 0.1kbits/s speed=0.58x \\rframe= 180 fps= 14 q=25.0 size= 0kB time=00:00:07.41 bitrate= 0.1kbits/s speed=0.585x \\rframe= 189 fps= 14 q=25.0 size= 0kB time=00:00:07.79 bitrate= 0.0kbits/s speed=0.59x \\rframe= 197 fps= 14 q=25.0 size= 0kB time=00:00:08.12 bitrate= 0.0kbits/s speed=0.591x \\rframe= 206 fps= 14 q=25.0 size= 0kB time=00:00:08.50 bitrate= 0.0kbits/s speed=0.596x \\rframe= 215 fps= 15 q=25.0 size= 0kB time=00:00:08.87 bitrate= 0.0kbits/s speed=0.599x \\rframe= 223 fps= 15 q=25.0 size= 0kB time=00:00:09.20 bitrate= 0.0kbits/s speed=0.601x \\rframe= 231 fps= 15 q=25.0 size= 0kB time=00:00:09.54 bitrate= 0.0kbits/s speed=0.602x \\rframe= 240 fps= 15 q=25.0 size= 0kB time=00:00:09.91 bitrate= 0.0kbits/s speed=0.607x \\rframe= 249 fps= 15 q=25.0 size= 0kB time=00:00:10.29 bitrate= 0.0kbits/s speed=0.611x \\rframe= 258 fps= 15 q=25.0 size= 256kB time=00:00:10.66 bitrate= 196.6kbits/s speed=0.614x \\rframe= 267 fps= 15 q=25.0 size= 256kB time=00:00:11.04 bitrate= 190.0kbits/s speed=0.616x \\rframe= 276 fps= 15 q=25.0 size= 256kB time=00:00:11.41 bitrate= 183.7kbits/s speed=0.618x \\rframe= 285 fps= 15 q=25.0 size= 256kB time=00:00:11.79 bitrate= 177.9kbits/s speed=0.62x \\rframe= 294 fps= 15 q=25.0 size= 256kB time=00:00:12.16 bitrate= 172.4kbits/s speed=0.623x \\rframe= 303 fps= 15 q=25.0 size= 256kB time=00:00:12.54 bitrate= 167.2kbits/s speed=0.626x \\rframe= 314 fps= 15 q=25.0 size= 256kB time=00:00:13.00 bitrate= 161.3kbits/s speed=0.632x \\rframe= 325 fps= 15 q=25.0 size= 256kB time=00:00:13.45 bitrate= 155.9kbits/s speed=0.638x \\rframe= 336 fps= 16 q=25.0 size= 256kB time=00:00:13.91 bitrate= 150.7kbits/s speed=0.644x \\rframe= 347 fps= 16 q=25.0 size= 256kB time=00:00:14.37 bitrate= 145.9kbits/s speed=0.648x \\rframe= 357 fps= 16 q=25.0 size= 256kB time=00:00:14.79 bitrate= 141.8kbits/s speed=0.652x \\rframe= 367 fps= 16 q=25.0 size= 256kB time=00:00:15.20 bitrate= 137.9kbits/s speed=0.656x \\rframe= 378 fps= 16 q=25.0 size= 256kB time=00:00:15.66 bitrate= 133.9kbits/s speed=0.66x \\rframe= 388 fps= 16 q=25.0 size= 256kB time=00:00:16.08 bitrate= 130.4kbits/s speed=0.663x \\rframe= 398 fps= 16 q=25.0 size= 256kB time=00:00:16.50 bitrate= 127.1kbits/s speed=0.665x \\rframe= 407 fps= 16 q=25.0 size= 256kB time=00:00:16.87 bitrate= 124.3kbits/s speed=0.666x \\rframe= 417 fps= 16 q=25.0 size= 256kB time=00:00:17.29 bitrate= 121.3kbits/s speed=0.669x \\rframe= 426 fps= 16 q=25.0 size= 256kB time=00:00:17.66 bitrate= 118.7kbits/s speed=0.67x \\rframe= 435 fps= 16 q=25.0 size= 256kB time=00:00:18.04 bitrate= 116.3kbits/s speed=0.671x \\rframe= 444 fps= 16 q=25.0 size= 256kB time=00:00:18.41 bitrate= 113.9kbits/s speed=0.672x \\rframe= 453 fps= 16 q=25.0 size= 256kB time=00:00:18.79 bitrate= 111.6kbits/s speed=0.674x \\rframe= 462 fps= 16 q=25.0 size= 256kB time=00:00:19.16 bitrate= 109.4kbits/s speed=0.675x \\rframe= 471 fps= 16 q=25.0 size= 256kB time=00:00:19.54 bitrate= 107.3kbits/s speed=0.676x \\rframe= 481 fps= 16 q=25.0 size= 256kB time=00:00:19.95 bitrate= 105.1kbits/s speed=0.677x \\rframe= 490 fps= 16 q=25.0 size= 256kB time=00:00:20.33 bitrate= 103.2kbits/s speed=0.678x \\rframe= 499 fps= 16 q=25.0 size= 256kB time=00:00:20.70 bitrate= 101.3kbits/s speed=0.679x \\rframe= 508 fps= 16 q=25.0 size= 512kB time=00:00:21.08 bitrate= 199.0kbits/s speed=0.679x \\rframe= 516 fps= 16 q=25.0 size= 512kB time=00:00:21.41 bitrate= 195.9kbits/s speed=0.679x \\rframe= 524 fps= 16 q=25.0 size= 512kB time=00:00:21.75 bitrate= 192.9kbits/s speed=0.678x \\rframe= 532 fps= 16 q=25.0 size= 512kB time=00:00:22.08 bitrate= 189.9kbits/s speed=0.678x \\rframe= 540 fps= 16 q=25.0 size= 512kB time=00:00:22.41 bitrate= 187.1kbits/s speed=0.678x \\rframe= 548 fps= 16 q=25.0 size= 512kB time=00:00:22.75 bitrate= 184.4kbits/s speed=0.677x \\rframe= 556 fps= 16 q=25.0 size= 512kB time=00:00:23.08 bitrate= 181.7kbits/s speed=0.676x \\rframe= 564 fps= 16 q=25.0 size= 512kB time=00:00:23.41 bitrate= 179.1kbits/s speed=0.676x \\rframe= 573 fps= 16 q=25.0 size= 512kB time=00:00:23.79 bitrate= 176.3kbits/s speed=0.677x \\rframe= 582 fps= 16 q=25.0 size= 512kB time=00:00:24.16 bitrate= 173.6kbits/s speed=0.677x \\rframe= 592 fps= 16 q=25.0 size= 512kB time=00:00:24.54 bitrate= 170.9kbits/s speed=0.678x \\rframe= 601 fps= 16 q=25.0 size= 512kB time=00:00:24.91 bitrate= 168.3kbits/s speed=0.678x \\rframe= 610 fps= 16 q=25.0 size= 512kB time=00:00:25.29 bitrate= 165.9kbits/s speed=0.679x \\rframe= 618 fps= 16 q=25.0 size= 512kB time=00:00:25.66 bitrate= 163.4kbits/s speed=0.679x \\rframe= 628 fps= 16 q=25.0 size= 512kB time=00:00:26.08 bitrate= 160.8kbits/s speed=0.68x \\rframe= 637 fps= 16 q=25.0 size= 512kB time=00:00:26.45 bitrate= 158.5kbits/s speed=0.681x \\rframe= 646 fps= 16 q=25.0 size= 512kB time=00:00:26.83 bitrate= 156.3kbits/s speed=0.682x \\rframe= 658 fps= 16 q=25.0 size= 512kB time=00:00:27.29 bitrate= 153.7kbits/s speed=0.684x \\rframe= 670 fps= 17 q=25.0 size= 512kB time=00:00:27.79 bitrate= 150.9kbits/s speed=0.688x \\rframe= 681 fps= 17 q=25.0 size= 512kB time=00:00:28.25 bitrate= 148.5kbits/s speed=0.691x \\rframe= 692 fps= 17 q=25.0 size= 512kB time=00:00:28.75 bitrate= 145.9kbits/s speed=0.694x \\rframe= 706 fps= 17 q=25.0 size= 768kB time=00:00:29.33 bitrate= 214.5kbits/s speed=0.699x \\rframe= 720 fps= 17 q=25.0 size= 768kB time=00:00:29.87 bitrate= 210.6kbits/s speed=0.703x \\rframe= 732 fps= 17 q=25.0 size= 768kB time=00:00:30.41 bitrate= 206.9kbits/s speed=0.707x \\r[out#0/mp4 @ 0x5c821cc48d00] video:840kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.206791%\\nframe= 794 fps= 18 q=-1.0 Lsize= 851kB time=00:00:32.95 bitrate= 211.4kbits/s speed=0.756x \\n[libx264 @ 0x5c821cc4a3c0] frame I:4 Avg QP:13.70 size: 58412\\n[libx264 @ 0x5c821cc4a3c0] frame P:199 Avg QP:17.78 size: 2438\\n[libx264 @ 0x5c821cc4a3c0] frame B:591 Avg QP:22.61 size: 239\\n[libx264 @ 0x5c821cc4a3c0] consecutive B-frames: 0.8% 0.0% 0.0% 99.2%\\n[libx264 @ 0x5c821cc4a3c0] mb I I16..4: 65.2% 18.1% 16.8%\\n[libx264 @ 0x5c821cc4a3c0] mb P I16..4: 0.4% 0.1% 0.3% P16..4: 4.1% 0.2% 0.1% 0.0% 0.0% skip:94.9%\\n[libx264 @ 0x5c821cc4a3c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.3% 0.0% 0.0% direct: 0.0% skip:97.6% L0:54.1% L1:45.8% BI: 0.1%\\n[libx264 @ 0x5c821cc4a3c0] 8x8 transform intra:20.1% inter:42.2%\\n[libx264 @ 0x5c821cc4a3c0] coded y,uvDC,uvAC intra: 14.1% 15.8% 11.8% inter: 0.1% 0.1% 0.0%\\n[libx264 @ 0x5c821cc4a3c0] i16 v,h,dc,p: 21% 79% 0% 0%\\n[libx264 @ 0x5c821cc4a3c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 46% 10% 42% 2% 0% 0% 0% 0% 0%\\n[libx264 @ 0x5c821cc4a3c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 33% 44% 7% 2% 2% 3% 3% 2% 3%\\n[libx264 @ 0x5c821cc4a3c0] i8c dc,h,v,p: 69% 21% 10% 1%\\n[libx264 @ 0x5c821cc4a3c0] Weighted P-Frames: Y:0.0% UV:0.0%\\n[libx264 @ 0x5c821cc4a3c0] ref P L0: 86.3% 1.2% 9.1% 3.4%\\n[libx264 @ 0x5c821cc4a3c0] ref B L0: 61.8% 37.0% 1.2%\\n[libx264 @ 0x5c821cc4a3c0] ref B L1: 97.3% 2.7%\\n[libx264 @ 0x5c821cc4a3c0] kb/s:207.93\\nffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Duration: 00:00:33.08, start: 0.000000, bitrate: 210 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 208 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n[mp3 @ 0x632d9ebc7ec0] Estimating duration from bitrate, this may be inaccurate\\nInput #1, mp3, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3':\\n Duration: 00:00:32.57, start: 0.000000, bitrate: 48 kb/s\\n Stream #1:0: Audio: mp3, 24000 Hz, mono, fltp, 48 kb/s\\nStream mapping:\\n Stream #0:0 -> #0:0 (copy)\\n Stream #1:0 -> #0:1 (mp3 (mp3float) -> aac (native))\\nPress [q] to stop, [?] for help\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, q=2-31, 208 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 69 kb/s\\n Metadata:\\n encoder : Lavc60.31.102 aac\\nsize= 0kB time=N/A bitrate=N/A speed=N/A \\r[out#0/mp4 @ 0x632d9eb36240] video:840kB audio:245kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.852690%\\nsize= 1106kB time=00:00:32.95 bitrate= 274.9kbits/s speed=73.2x \\n[aac @ 0x632d9eb49180] Qavg: 18836.852\\n{\\n \\\"ok\\\": true,\\n \\\"manifest\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.0.0-word-aligned-proof\\\",\\n \\\"series\\\": \\\"Digital Red Flags\\\",\\n \\\"title\\\": \\\"The calendar invite login trap\\\",\\n \\\"script\\\": \\\"This calendar invite looks normal. The trap is the login button. Same meeting title. Same urgent tone. But the link points somewhere else. Before you sign in, slow down. Check who sent it. Check the link domain. Notice unusual login requests. If the domain feels off, do not sign in from the invite. Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\",\\n \\\"script_hash\\\": \\\"c4c8ec407aaa52e4\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\\\",\\n \\\"preview_sha256\\\": \\\"24494b37d22e8417c32dbc0c7ff6daf130347b574b0d521c72aaa7ac5e922689\\\",\\n \\\"silent_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4\\\",\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"audio_sha256\\\": \\\"00b68d236008bd143d3e4bad81a296a03debb1c6be5ca9c0755b28651c556213\\\",\\n \\\"word_cues_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/word_cues.json\\\",\\n \\\"caption_segments_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/caption_segments_word_aligned.json\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\\\",\\n \\\"subtitle_preview_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_subtitle_style_preview_v1.jpg\\\",\\n \\\"qa_summary_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\\\",\\n \\\"duration_seconds\\\": 33.068,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"caption_policy\\\": \\\"static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries\\\",\\n \\\"blocked\\\": {\\n \\\"wan\\\": true,\\n \\\"i2v\\\": true,\\n \\\"platform_api\\\": true,\\n \\\"posting\\\": true,\\n \\\"scheduling\\\": true\\n }\\n },\\n \\\"review_package\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\\\"\\n}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_0SI6V0gcqBwS4d6H7OFKmxyy"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_t9nOw7xYRfZzE7yElZhR43CK",
"call_id": "call_t9nOw7xYRfZzE7yElZhR43CK",
"response_item_id": "fc_051a8a0b2fb58918016a149e3485188191a8e8224a5e302509",
"type": "function",
"function": {
"name": "vision_analyze",
"arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\",\"question\":\"Finale QA: Sind Captions lesbar und nicht abgeschnitten? Wirkt die Lösung/Fazit am Ende sichtbar? Gibt es echte Daten/Logos/QR-Codes oder UI-Artefakte?\"}"
}
},
{
"id": "call_MTd6YRuwLKGMTpoqmWu9UuYw",
"call_id": "call_MTd6YRuwLKGMTpoqmWu9UuYw",
"response_item_id": "fc_051a8a0b2fb58918016a149e348594819181592bccfbf73d75",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"limit\":120,\"path\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\"}"
}
},
{
"id": "call_s0GpTrFTO5ImxgVESXeSxOTD",
"call_id": "call_s0GpTrFTO5ImxgVESXeSxOTD",
"response_item_id": "fc_051a8a0b2fb58918016a149e3485a081919f5b2a7668258946",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4 && sha256sum /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\",\"timeout\":30}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ4v-mpqd2ilpCbiVuJOR53pXikhhDcbuKQ8ZnFy5uVQITeaYXdEmcwzCCe7frzBb4ux9Z5Af_pTvoUZFb3TEaH8b3IpIRBRDZkTLSL6N4_kxlFW7qs1OzETcHHQhfkQqeyS9rh3tkRaQVMxL31bo2O7gSHc_v0PDjL7N9URUkdLK6ziXHPxenHnuhbVH3EmdN6kHEyAbqzY_0PVCStIWOmXJl-7Q8Y9pyEs7HjG1JSRfsBz9s-ChDs0mmS62giYYoxWLf6I9UE1YoNEVbYypLPifO4AnNS7PnD_R35Gzp7pCjQAmcfsRt25uhvreRS2bRj7W_29FykkVznFlctpgx0iyh8JOxTTsrsSTB4yS_6EhG7smWNDPazovGvKE0Xlm36zD2d7L39G68yDfpQxwmP7m3LGnijMP5QrEbAcipsa1WGyM60IkF6TlDlCOXTR3vKOWmQ8W1z84n7jVbF0WW7P5ArRWj667jvDwcD-OL8K6PxDSHZiSkO6n8jbE2WLZc98-TqngR77qp-p7uOdsvf-EstZ0_s2tgKFoexlITrVq1J0WhLSbeSMDIBlLoDyGuKObx0xAJW2Kh4SlgPDrvTag83HdgLZERMGr5BAlzINm8Gsr2LEfgKfOyboet5s0yxPJIkCNOqi3eRgszdRBn8BaWr4E3jdONe9uHaVAshFdfuT80xjZKotg5aJtPgrHUmNmJ2QtJjZqnh5BrsYfY4bX2LD5sVAeHSr6oGY6y6ZJjgz1ElDVlf3XS5WFgk-YgRU9-KC_6fCGrxt-p438cuMeZ1p_hmoW89zzahrfjyMRPEWkax6bfabsKfL2bnPiDQL7cqGQNUM6GeYHrOKD-UpEPJqeae19SEFdkE_WzD918g97Y5wiTQ_BS11cEVrkhLh03_p7Tqi6SdHMzq8LWkD8X91fUpPPPBJTO2JFo-z2KuybBTMxoBQSie8bcq1OP5XuzJdFEGp-XIDma0HDwHalw==",
"id": "rs_051a8a0b2fb58918016a149e2e8ba48191a6510ec656d01769",
"summary": []
}
]
},
{
"role": "tool",
"content": "Image loaded into your context — you can see it natively now. Use your built-in vision to answer the user.\n\nQuestion: Finale QA: Sind Captions lesbar und nicht abgeschnitten? Wirkt die Lösung/Fazit am Ende sichtbar? Gibt es echte Daten/Logos/QR-Codes oder UI-Artefakte?\n[screenshot]",
"tool_call_id": "call_t9nOw7xYRfZzE7yElZhR43CK"
},
{
"role": "tool",
"content": "{\"content\": \" 1|{\\n 2| \\\"caption_sync_source\\\": \\\"edge_tts_word_boundary_offsets\\\",\\n 3| \\\"static_phrase_active_word\\\": true,\\n 4| \\\"min_words_default\\\": 3,\\n 5| \\\"target_words\\\": 5,\\n 6| \\\"max_words\\\": 7,\\n 7| \\\"one_word_segments\\\": [],\\n 8| \\\"one_word_segment_count\\\": 0,\\n 9| \\\"duration_seconds\\\": 33.068,\\n 10| \\\"audio_duration_seconds\\\": 32.568,\\n 11| \\\"word_cue_count\\\": 70,\\n 12| \\\"segment_count\\\": 15,\\n 13| \\\"safe_zone\\\": \\\"bottom caption, no box/bar, tested via contact sheet\\\",\\n 14| \\\"summary_fazit_present\\\": true,\\n 15| \\\"final_solution\\\": \\\"Open the service yourself; trust the app you opened, not the rushed button.\\\"\\n 16|}\", \"total_lines\": 15, \"file_size\": 537, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_MTd6YRuwLKGMTpoqmWu9UuYw"
},
{
"role": "tool",
"content": "{\"output\": \"{\\n \\\"programs\\\": [\\n\\n ],\\n \\\"streams\\\": [\\n {\\n \\\"codec_type\\\": \\\"video\\\",\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"r_frame_rate\\\": \\\"24/1\\\"\\n },\\n {\\n \\\"codec_type\\\": \\\"audio\\\",\\n \\\"r_frame_rate\\\": \\\"0/0\\\"\\n }\\n ],\\n \\\"format\\\": {\\n \\\"duration\\\": \\\"33.083333\\\",\\n \\\"size\\\": \\\"1132332\\\"\\n }\\n}\\n24494b37d22e8417c32dbc0c7ff6daf130347b574b0d521c72aaa7ac5e922689 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_s0GpTrFTO5ImxgVESXeSxOTD"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_pPXXYBgVGeLXD5LyNlfC72IY",
"call_id": "call_pPXXYBgVGeLXD5LyNlfC72IY",
"response_item_id": "fc_051a8a0b2fb58918016a149e3e1a108191a6456e5feaf2e129",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\",\"id\":\"draft\",\"status\":\"completed\"},{\"content\":\"ReviewPackage/Entwurf knapp an User liefern und nächste Freigabe-Kommandos nennen\",\"id\":\"deliver\",\"status\":\"completed\"}]}"
}
}
],
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFJ4-yJ1CLfgjznHIRERRIsaDoW868V8dzoQlHxOgYwKvqdDzVc6husUws_gtsPp07Bi94FLjo6Oh7q0f0JfrRYCbKrrPw8WqaIxNPgz9MLwSTeLfeB-fMC3VELCaWFjz0bR9SqwpBoVfmSRzLce4QQmuVnLhSOsK-i63ZR7rqS00OXjcX0T8p99UVpkrx_LR2ohQ9T1-vHVJbZztQQrsUiFLaK2QxNG4jp86P4ZO95jYNK75Fv-9LoF8KKMLf1JAdbBGRPdEmF35x1efzdt9lvF32dy8gJANNPn_ohfyVLII45bNGlgajsA1lDVwYzIOIngc8ANpxC1zBczhB9QPbmSUiJ8GPSD1OcH-B6tzHFewFkgrIcwjR6ZdJtXbSNTZeHMHby2VFm3MkzVRd33zg90dsrHct-Pvy8QGa8oSiKyLfQ0s7RBvCCTDwlrkfw8rOaYkyhNm_1iPg80Q6MIxq6onzWTekHbzjhuBifObYRYYupG2LG6zMXQ1h5t5UMaNtnIpJ530GlcoVFIV1P3qz2A6_QMcMOv2dhjzZNK33sN49eJqGcpI6cKp-SB51L9oNWaEdQqm2f_eUEW3b7UkAlyA-wW1MsvV6d7x8tUPv2UwKlG04cueSoanibPKqjaKui0VL6HVlGZygO7N1s_wgKaHakcbP2MZhnAh5jrP5iXW-3xPVo5tetrKnaab6awB1ceAfKj1Kl6-7ee2rrFXGdu6zJgvlauPcUTtU0bM1VJjb7jvf60NfhnBb5W9ZAISqOXWp2DvGuYt1nm3iW-lto9iPcXQDG5LqlWv8lsnW-QpqFhHqd_RsiR3lNWSH0e6v2znFH5EeYBCkGpz5Vw8dEAtBSFIb4AsWHrB8qJjKVhNRPgfk-1o6N23rOFcQHnZ9c-Gs46qycQFf9pArELKY8HLSxVlskBSNEhXMnWbowgrUbeVfrYaRhn5zX40mv3-0X2M1Z2f85KW521VvN7VH0kgjTi6yRGPwGY6H-FQBiFloFAOAMv7lyfKm3fUaxNIT7X1ewJMC4oTHBDH7rHjAERlNc71OBI62N463G4gsbHceCTjm0g--duPsjzf7XJLNexPj1udVrxejASWnNUzco5zEUHlTuYAhWd3P6zq4Q6NU7ZqBhlngEzV9RMevzyYIbDAxnG3IqH_p8h5KXeDMH85QJLRsEDX1XDX62ZIZ9Ebt5uCCLTJPiNCSrkAeLLM_1znQogkaJlJp0pz87ceAxpAK7KjhOcDIIs0IQ1jC5hgsDEYNuSwfp1RTQiUVQFFAYqtnppLNSOVVaV-7V4wJZWgedVUN_8ForoFxcFc0LWIUWp9_FrZ6Pcv2gECx5tUBavgCfJoXWPs7eW8nLIGfuDRmjqbA9z7sNw3sQfR5wAKCHkQsnxuWpakM1gOWTaH-DVhppfEoOwh9MT98LoH0lv_4b4F9ydwXpBVpx0wxeflzX9bbHk8SxBLZbdlPyy6idywb703tkePSSeH8RQ8eNl3WGZHyJ-LLZ4JZFVNiYhv33Vtbd92B92wdTETY8Prx1Hf4blAHAYHmRUb3U8Zra3FYDzPAID0xu_IC8ZGzPYdPd2VLak4wMYF8xo5X5dt0xzegCWFjWYOV0YlnFnlr7Ngw2l-cG8YpGc3-hPd6l16g0FozooP32jWQtK-ivjx3QnL_pj52ewuMIWC8VND1Biy0VNlALebN_5x4F0h5ibf1IZGmFTSHBb9N71vK8e2ceHcGMTTRR3MxzyaS4hTHZig0TUiaxBg8ElRe395HTC20PBlBPrWLigws3ZPi48kgAR0mNcKp_Np5O-eE6xFEJbj58-fDSvV6zfmyal6EK_jBPbUaUT7ullyQc_q_D3uRfP3a2g9pLnfIu1TjoQHLGCo_A==",
"id": "rs_051a8a0b2fb58918016a149e3ae9188191ae2a8c99ffe5fa13",
"summary": []
}
]
},
{
"role": "tool",
"content": "{\"todos\": [{\"id\": \"scope\", \"content\": \"Letztes Feedback in Anforderungen für nächstes Video übersetzen\", \"status\": \"completed\"}, {\"id\": \"discover\", \"content\": \"Vorhandene AutoShorts/Proof-Short Artefakte und Pipeline finden\", \"status\": \"completed\"}, {\"id\": \"draft\", \"content\": \"Nächstes Video als ReviewPackage mit Hook, Script, Visualplan, Fazit und Caption-Sync-Regel ausarbeiten\", \"status\": \"completed\"}, {\"id\": \"deliver\", \"content\": \"ReviewPackage/Entwurf knapp an User liefern und nächste Freigabe-Kommandos nennen\", \"status\": \"completed\"}], \"summary\": {\"total\": 4, \"pending\": 0, \"in_progress\": 0, \"completed\": 4, \"cancelled\": 0}}",
"tool_call_id": "call_pPXXYBgVGeLXD5LyNlfC72IY"
},
{
"role": "assistant",
"content": "Erledigt, Sir. Ich habe das **nächste Proof-Short-Video** ausgearbeitet und direkt als Timing-Preview gerendert.\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\n\n## Neues Video\n\n**Candidate:** `calendar-invite-login-trap-30s` \n**Serie:** Digital Red Flags \n**Thema:** Kalender-Invite / Login-Button-Phishing \n**Dauer:** 33.08s \n**Format:** Proof Short, 9:16, deterministische Mockups\n\n## Was ich gegenüber dem letzten Video korrigiert habe\n\n- **Subtitles:** nicht mehr nur grob über Satzdauer verteilt.\n- **Timing:** EdgeTTS **WordBoundary Offsets** werden genutzt.\n- **Style:** statische 3–7-Wort-Phrasen, nur das gerade gesprochene Wort leuchtet gelb.\n- **Kein hektisches Word-Window**, keine Ein-Wort-Untertitel.\n- **Fazit/Lösung am Ende:** klarer Abschluss statt “aha, und nun?”\n\n## Hook\n\n> This calendar invite looks normal. The trap is the login button.\n\n## Finaler Script\n\n```text\nThis calendar invite looks normal. The trap is the login button.\nSame meeting title. Same urgent tone. But the link points somewhere else.\nBefore you sign in, slow down. Check who sent it. Check the link domain.\nNotice unusual login requests. If the domain feels off, do not sign in from the invite.\nOpen the service yourself. The fix: trust the app you opened, not the button that rushed you.\n```\n\n## Fazit / Lösung\n\n```text\nTrust the app you opened.\nNot the button that rushed you.\n```\n\nDas ist deutlich stärker als beim letzten Video: Der Nutzer bekommt eine konkrete Handlung:\n\n```text\nNicht aus dem Invite einloggen.\nService/App selbst öffnen.\nDort prüfen.\n```\n\n## QA\n\n- Captions lesbar: **pass**\n- Captions nicht abgeschnitten: **pass**\n- Word-aligned subtitle source: **EdgeTTS WordBoundary**\n- One-word subtitle segments: **0**\n- Fazit sichtbar: **pass**\n- Echte Daten / Logos / QR-Codes: **keine**\n- Platform API / Posting: **nicht ausgeführt**\n\n## Artefakte\n\nPreview:\n\n```text\n/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n```\n\nSHA256:\n\n```text\n24494b37d22e8417c32dbc0c7ff6daf130347b574b0d521c72aaa7ac5e922689\n```\n\nReview Package:\n\n```text\n/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\n```\n\n## Nächste sinnvolle Befehle\n\nWenn der Inhalt passt:\n\n```text\nAPPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.0.0-word-aligned-proof\n```\n\nWenn du ändern willst:\n\n```text\nREVISE_PROOF_SHORT calendar-invite-login-trap-30s \"Änderungswunsch\"\n```\n\nMein Urteil: **inhaltlich nützlicher als das Invoice-Video**, weil die Lösung am Ende klarer ist. Visuell noch Proof-Short, nicht Premium-Final — aber diesmal mit weniger “schön erklärt” und mehr “mach genau das”.",
"codex_message_items": [
{
"type": "message",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Erledigt, Sir. Ich habe das **nächste Proof-Short-Video** ausgearbeitet und direkt als Timing-Preview gerendert.\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\n\n## Neues Video\n\n**Candidate:** `calendar-invite-login-trap-30s` \n**Serie:** Digital Red Flags \n**Thema:** Kalender-Invite / Login-Button-Phishing \n**Dauer:** 33.08s \n**Format:** Proof Short, 9:16, deterministische Mockups\n\n## Was ich gegenüber dem letzten Video korrigiert habe\n\n- **Subtitles:** nicht mehr nur grob über Satzdauer verteilt.\n- **Timing:** EdgeTTS **WordBoundary Offsets** werden genutzt.\n- **Style:** statische 3–7-Wort-Phrasen, nur das gerade gesprochene Wort leuchtet gelb.\n- **Kein hektisches Word-Window**, keine Ein-Wort-Untertitel.\n- **Fazit/Lösung am Ende:** klarer Abschluss statt “aha, und nun?”\n\n## Hook\n\n> This calendar invite looks normal. The trap is the login button.\n\n## Finaler Script\n\n```text\nThis calendar invite looks normal. The trap is the login button.\nSame meeting title. Same urgent tone. But the link points somewhere else.\nBefore you sign in, slow down. Check who sent it. Check the link domain.\nNotice unusual login requests. If the domain feels off, do not sign in from the invite.\nOpen the service yourself. The fix: trust the app you opened, not the button that rushed you.\n```\n\n## Fazit / Lösung\n\n```text\nTrust the app you opened.\nNot the button that rushed you.\n```\n\nDas ist deutlich stärker als beim letzten Video: Der Nutzer bekommt eine konkrete Handlung:\n\n```text\nNicht aus dem Invite einloggen.\nService/App selbst öffnen.\nDort prüfen.\n```\n\n## QA\n\n- Captions lesbar: **pass**\n- Captions nicht abgeschnitten: **pass**\n- Word-aligned subtitle source: **EdgeTTS WordBoundary**\n- One-word subtitle segments: **0**\n- Fazit sichtbar: **pass**\n- Echte Daten / Logos / QR-Codes: **keine**\n- Platform API / Posting: **nicht ausgeführt**\n\n## Artefakte\n\nPreview:\n\n```text\n/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n```\n\nSHA256:\n\n```text\n24494b37d22e8417c32dbc0c7ff6daf130347b574b0d521c72aaa7ac5e922689\n```\n\nReview Package:\n\n```text\n/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\n```\n\n## Nächste sinnvolle Befehle\n\nWenn der Inhalt passt:\n\n```text\nAPPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.0.0-word-aligned-proof\n```\n\nWenn du ändern willst:\n\n```text\nREVISE_PROOF_SHORT calendar-invite-login-trap-30s \"Änderungswunsch\"\n```\n\nMein Urteil: **inhaltlich nützlicher als das Invoice-Video**, weil die Lösung am Ende klarer ist. Visuell noch Proof-Short, nicht Premium-Final — aber diesmal mit weniger “schön erklärt” und mehr “mach genau das”."
}
],
"id": "msg_051a8a0b2fb58918016a149e41696881919106ef645909b5bb",
"phase": "final_answer"
}
],
"finish_reason": "stop"
},
{
"role": "user",
"content": "[M G] Das ende wirkt etwas verwirrend oder übereilt. ,Open the service yourself…‘ was soll das bedeuten? Und ,trust the app you opend‘ vieleicht in diesem fall etwas mehr ausholen, und erläutern. Unsere viewer sollen abgeholt werden…"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKAqCBiwal1K38IvRYplMktj90-6FSYJXyt17SjK5p6Vw4Xw_0u3Z9zLPwaTEElxeXZP_6u9lODdDq1lQ8xUfwvE9M74yYxAqwfzFBJh1N69hNb9mD1RZFGoQ3Q6hhzSqiAQ0YPl1U3mEJpen63eFi1aaCQcjHZ-Dsjv6NtIj9f6P1JvnGVZR9Pu1r1MXS1WSZL_G8quNPVo2fzwdcivTg3mQa22_i9jtVl9pt-qeeXMT8cL7eE71mHN_B8o0WpYP3q6WfH8yx-5Yi_gYolNBo-wkrh2d7mS6MGPDXL6jZXL7flWFRSklckoCMppgommhFYIuMyOSaOQEf0Tq1T34xMfoJLopDTL9o_NVwRXxM1UomjMoelHUxMdrSdp_dvm7vuorzlsFUZGy01V_76xyhUUWLGVY5Uir2YJPbXb4l21RHWTd0C6pWBsSPzQ9VGZ7TheS2-2JSi5LQe2cOkcPJzPRMo7bYHkRs5lkI-marc_GnSalZTZRaoPvBJv1hX4mMWMdFmjAeled44M8xDYw9Nhqglp3O-c5dQQrEm0QH0Innbp7JIUzg0IDInSLYeq9vlwG3HPi1s7YobkZKdRwWW2C5F3LYmTi5uxLJZwassWSRL6hGjkzXd27z2Yvbq9RfEGJtNSbNID9yHkHeh9yj6iECE6W1r4cwJeT7_eJOCralN5G8UaXD05dI4GrSwBKr8hZKSSwICint9Fw7xrDe8u6e1gEpRlMbd-laa2GYA6Ao9y4cE7q8FD0YnuCtBWEoOzbN8hLePWD5yWzyRZFSJIaXB1ZHH5DWA_6484m6PfBAA7ZEnTUViKh0hRZ6jvuiNlNcbRNpi9f1Te_Ht6nbaOxmKhYIJT-GPBdzfLtoGugxx3jIdf-Be9Z_Io42kUOcV10CII5mp56Q-PJgAzn__U1DPQ3rFoQMyngkgHIAR0CVxSS6skH-G9ZAxadSVtgUk2dIjMapmq-W2tAGrkofjBYni0cRsGX5j6apmgWnj9a_VeBOkG_pgoniuEDTCCTuIEry8AoIFF2OvqA-KB7kHS99fhV9PduBM1eeG_ZxV8YbmYpHbPjv7i0fw2u4vlsNHRMw4aSUrL4NKx5TF4awPmU1FtZve6w4dpVaQc8nNXxmSwBUe4lbHhz9LxURRa66GH8iY8audtSJPyN11Q7g3frMopWAe2eIAjVhbeCmS7xqqm_2zNk-OhPRoy-4EECTBGqSVh8t_tZrGDcDrmmQRMhB5uIessbmVNn6hfpzggCbCNYwvVOqB7wGQkgwXrrKx7M0KYzxlTeJo_DGfGdUH1ssW2zUYoEDSygakHMhLp4MsusCmdheuCxv0bU3xhVFQzdp1kcci4DxiahZAkhZgZYqwkW1mD_Ye2uiZ46Nx5-xVSf3_G8byhnfJAn9ZUVkiPoCQDmurK5Hj6f57HTPcqjXl7Wk_pm9FcEBr20dze6z_cr5H0s97AH7nJq-9PPODrlPsaEM5rB1-A_Xk6gwaac66LiGbqShvPr3fZnknYRmSuE5Ddynuzy2uWuWPp9FhEDdRkslkCV9vQerXHXM5mI2PaGiKftrcFB2Bqe4O0GOx3zk-QbTaZVhDDjzanN0xxeWY0K0Og5d0U48culjfFbze9GZ5-Vm_9aab13U0J8JYgrWtVVDvrb5SLJB8vj_HUnkNTvU9OpYSa7jHtUg9aLdIGG8Mm-DetC7_G1-Jf14iiaggXVDA-IIyu4X91aH1eYf-CY-jrm7e8Vik5DAq20eApZvX139e4Byww2Q5Mz6odY8W9dZy5jYp7MR7MJPvnevbFzY4X2vUfNWOFN-cGYlP8t9u_29fQpcEL3fKEkRqWDlngQYU0ewcK7lpRodXh",
"id": "rs_051a8a0b2fb58918016a14a026b37c8191bbb6c7f212f5d10b",
"summary": []
}
],
"tool_calls": [
{
"id": "call_ldOl4WKl5ycSFN0NdsyfVkFN",
"call_id": "call_ldOl4WKl5ycSFN0NdsyfVkFN",
"response_item_id": "fc_051a8a0b2fb58918016a14a02a8f208191a4899cb3acaf3fa6",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"todos\":[{\"id\":\"revise-script\",\"content\":\"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\",\"status\":\"in_progress\"},{\"id\":\"rerender\",\"content\":\"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\",\"status\":\"pending\"},{\"id\":\"qa\",\"content\":\"Dauer, Captions, Contact Sheet und Fazit prüfen\",\"status\":\"pending\"},{\"id\":\"deliver\",\"content\":\"Revidierte Preview und kurze Begründung liefern\",\"status\":\"pending\"}]}"
}
}
]
},
{
"role": "tool",
"name": "todo",
"content": "{\"todos\": [{\"id\": \"revise-script\", \"content\": \"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\", \"status\": \"in_progress\"}, {\"id\": \"rerender\", \"content\": \"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\", \"status\": \"pending\"}, {\"id\": \"qa\", \"content\": \"Dauer, Captions, Contact Sheet und Fazit prüfen\", \"status\": \"pending\"}, {\"id\": \"deliver\", \"content\": \"Revidierte Preview und kurze Begründung liefern\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 3, \"in_progress\": 1, \"completed\": 0, \"cancelled\": 0}}",
"tool_call_id": "call_ldOl4WKl5ycSFN0NdsyfVkFN"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_yXTgM63DHo0HlZR4dFHvgxhp",
"call_id": "call_yXTgM63DHo0HlZR4dFHvgxhp",
"response_item_id": "fc_051a8a0b2fb58918016a14a02dd1b8819197e9cf8375297de3",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"offset\":35,\"limit\":230}"
}
}
]
},
{
"role": "tool",
"name": "read_file",
"content": "{\"content\": \" 35| bottom_margin_px=300,\\n 36| max_width_ratio=0.86,\\n 37| font_size_px=66,\\n 38| min_font_size_px=48,\\n 39| word_gap_px=18,\\n 40|)\\n 41|\\n 42|SCRIPT = (\\n 43| \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n 44| \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n 45| \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n 46| \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n 47| \\\"Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\"\\n 48|)\\n 49|SENTENCES = [s.strip() for s in re.split(r'(?<=[.!?])\\\\s+', SCRIPT) if s.strip()]\\n 50|\\n 51|\\n 52|def sha256(path: Path) -> str:\\n 53| h = hashlib.sha256()\\n 54| with path.open('rb') as f:\\n 55| for chunk in iter(lambda: f.read(1024 * 1024), b''):\\n 56| h.update(chunk)\\n 57| return h.hexdigest()\\n 58|\\n 59|\\n 60|def font(size: int, bold: bool = True):\\n 61| return ImageFont.truetype(FONT_BOLD if bold else FONT_REG, size)\\n 62|\\n 63|\\n 64|def sentence_for_offset(offset: float) -> str:\\n 65| # Edge word-boundary events do not carry sentence IDs. Assign monotonically\\n 66| # by rough character progression so caption segments still break at phrases.\\n 67| # We later override using punctuation gaps when possible; grouping is not timing-critical.\\n 68| joined = ' '.join(SENTENCES)\\n 69| return joined\\n 70|\\n 71|\\n 72|def clean_boundary_text(text: str) -> str:\\n 73| text = text.replace('’', \\\"'\\\").strip()\\n 74| m = re.search(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", text)\\n 75| return m.group(0) if m else text\\n 76|\\n 77|\\n 78|async def synthesize_audio() -> tuple[Path, tuple[WordCue, ...]]:\\n 79| audio_path = AUDIO_DIR / 'voiceover_word_boundary.mp3'\\n 80| cues_path = AUDIO_DIR / 'word_cues.json'\\n 81| communicate = edge_tts.Communicate(SCRIPT, VOICE, rate='+0%', boundary='WordBoundary')\\n 82| cues = []\\n 83| audio_bytes = bytearray()\\n 84| sentence_cursor = 0\\n 85| sentence_word_counts = [len(re.findall(r\\\"[A-Za-z0-9]+(?:[-–—'][A-Za-z0-9]+)*(?:\\\\.com)?|[A-Za-z0-9.-]+\\\\.com\\\", s)) for s in SENTENCES]\\n 86| word_counter_in_sentence = 0\\n 87| async for chunk in communicate.stream():\\n 88| if chunk['type'] == 'audio':\\n 89| audio_bytes.extend(chunk['data'])\\n 90| elif chunk['type'] == 'WordBoundary':\\n 91| word = clean_boundary_text(chunk.get('text', ''))\\n 92| if not word:\\n 93| continue\\n 94| start = chunk.get('offset', 0) / 10_000_000\\n 95| duration = max(0.08, chunk.get('duration', 0) / 10_000_000)\\n 96| sent = SENTENCES[min(sentence_cursor, len(SENTENCES) - 1)]\\n 97| cues.append(WordCue(start=start, end=start + duration, word=word, sentence=sent))\\n 98| word_counter_in_sentence += 1\\n 99| if sentence_cursor < len(sentence_word_counts) and word_counter_in_sentence >= sentence_word_counts[sentence_cursor]:\\n 100| sentence_cursor += 1\\n 101| word_counter_in_sentence = 0\\n 102| audio_path.write_bytes(audio_bytes)\\n 103| cues_path.write_text(json.dumps([c.__dict__ for c in cues], indent=2), encoding='utf-8')\\n 104| return audio_path, tuple(cues)\\n 105|\\n 106|\\n 107|def ffprobe_duration(path: Path) -> float:\\n 108| out = subprocess.check_output([\\n 109| 'ffprobe','-v','error','-show_entries','format=duration','-of','default=nokey=1:noprint_wrappers=1',str(path)\\n 110| ], text=True)\\n 111| return float(out.strip())\\n 112|\\n 113|\\n 114|def rounded(draw, box, r, fill, outline=None, width=1):\\n 115| draw.rounded_rectangle(box, radius=r, fill=fill, outline=outline, width=width)\\n 116|\\n 117|\\n 118|def text(draw, xy, s, size, fill, bold=True, anchor=None, align='left'):\\n 119| draw.text(xy, s, font=font(size, bold), fill=fill, anchor=anchor, align=align)\\n 120|\\n 121|\\n 122|def bg(draw, t):\\n 123| # dark blue premium-ish deterministic background, not AI-generated\\n 124| draw.rectangle((0, 0, W, H), fill=(10, 14, 24))\\n 125| for y in range(0, H, 4):\\n 126| c = int(16 + 26 * y / H)\\n 127| draw.line((0, y, W, y), fill=(c, c + 5, c + 15))\\n 128| # moving soft glow\\n 129| cx = 220 + int(60 * math.sin(t * 0.7))\\n 130| cy = 300 + int(45 * math.cos(t * 0.45))\\n 131| for r, a in [(360, 22), (250, 20), (160, 18)]:\\n 132| draw.ellipse((cx-r, cy-r, cx+r, cy+r), fill=(35, 75, 145, a))\\n 133| draw.rectangle((0, 0, W, H), outline=(38, 49, 74), width=8)\\n 134|\\n 135|\\n 136|def scene_for(t):\\n 137| if t < 5.4: return 'hook'\\n 138| if t < 10.8: return 'same'\\n 139| if t < 16.2: return 'domain'\\n 140| if t < 23.0: return 'checks'\\n 141| if t < 29.2: return 'open_app'\\n 142| return 'takeaway'\\n 143|\\n 144|\\n 145|def draw_invite(draw, t, mode):\\n 146| # Phone/browser card\\n 147| rounded(draw, (82, 165, 998, 1328), 46, (238, 241, 247), (80, 93, 125), 3)\\n 148| rounded(draw, (118, 215, 962, 385), 26, (255, 255, 255), (218, 224, 234), 2)\\n 149| text(draw, (152, 252), 'Calendar', 40, (38, 47, 66))\\n 150| text(draw, (152, 314), 'From: updates@sample.test', 30, (82, 92, 112), False)\\n 151|\\n 152| # meeting card\\n 153| rounded(draw, (150, 445, 930, 815), 28, (250, 252, 255), (203, 211, 225), 2)\\n 154| text(draw, (196, 497), 'Meeting invite', 52, (38, 48, 66))\\n 155| text(draw, (196, 572), 'Project check-in', 36, (69, 79, 99), False)\\n 156| urgent = mode in ['same', 'domain']\\n 157| rounded(draw, (196, 642, 520, 696), 18, (255, 244, 223) if urgent else (235, 242, 250), (232, 151, 43) if urgent else (128, 140, 160), 2)\\n 158| text(draw, (224, 654), 'Starts soon', 28, (205, 117, 24) if urgent else (91, 103, 123))\\n 159| for x in [202, 262, 322, 382]:\\n 160| draw.ellipse((x, 724, x+42, 766), fill=(211, 218, 230), outline=(178, 188, 207), width=2)\\n 161|\\n 162| # button + domain panel\\n 163| changed = mode in ['domain', 'checks', 'open_app']\\n 164| btn_fill = (43, 94, 185) if not changed else (202, 64, 64)\\n 165| rounded(draw, (196, 890, 884, 980), 24, btn_fill, None, 1)\\n 166| text(draw, (540, 935), 'SIGN IN TO JOIN', 38, (255, 255, 255), anchor='mm')\\n 167|\\n 168| rounded(draw, (150, 1030, 930, 1208), 24, (241, 245, 250), (204, 213, 228), 2)\\n 169| text(draw, (196, 1070), 'Link domain', 34, (58, 68, 89))\\n 170| domain = 'service.sample.test' if not changed else 'secure-meeting-check.test'\\n 171| color = (57, 129, 88) if not changed else (204, 58, 58)\\n 172| rounded(draw, (196, 1125, 820, 1178), 16, (235, 249, 241) if not changed else (255, 242, 239), color, 3)\\n 173| text(draw, (220, 1138), domain, 29, color)\\n 174| if changed:\\n 175| text(draw, (196, 1245), 'Domain changed', 42, (207, 54, 54))\\n 176| else:\\n 177| text(draw, (196, 1245), 'Looks familiar', 42, (60, 120, 90))\\n 178|\\n 179|\\n 180|def draw_checks(draw, t):\\n 181| labels = [('sender', 16.5), ('link domain', 18.2), ('unusual login request', 20.0)]\\n 182| y = 1218\\n 183| for i, (lab, ts) in enumerate(labels):\\n 184| active = t >= ts\\n 185| col = (247, 202, 76) if active else (122, 133, 155)\\n 186| rounded(draw, (155, y + i*87, 925, y + 60 + i*87), 21, (34, 43, 62), col if active else (74, 86, 110), 3)\\n 187| text(draw, (205, y + 13 + i*87), f'{i+1}. {lab}', 32, (255, 255, 255) if active else (188, 197, 214))\\n 188|\\n 189|\\n 190|def draw_open_app(draw, t):\\n 191| rounded(draw, (125, 1160, 955, 1395), 34, (28, 38, 57), (93, 112, 148), 3)\\n 192| text(draw, (540, 1220), 'Open the service yourself', 44, (255, 255, 255), anchor='mm')\\n 193| text(draw, (540, 1292), 'not the rushed button', 42, (247, 202, 76), anchor='mm')\\n 194| # app icon + check\\n 195| rounded(draw, (464, 1335, 616, 1482), 32, (18, 24, 36), (247, 202, 76), 4)\\n 196| draw.line((500, 1411, 532, 1444, 586, 1372), fill=(247, 202, 76), width=10)\\n 197|\\n 198|\\n 199|def draw_takeaway(draw):\\n 200| rounded(draw, (92, 420, 988, 1040), 46, (24, 32, 48), (247, 202, 76), 4)\\n 201| text(draw, (540, 570), 'Trust the app', 76, (255, 255, 255), anchor='mm')\\n 202| text(draw, (540, 700), 'you opened.', 76, (247, 202, 76), anchor='mm')\\n 203| text(draw, (540, 845), 'Not the button that rushed you.', 42, (205, 214, 230), anchor='mm')\\n 204|\\n 205|\\n 206|def draw_caption(draw, t, word_cues, segments):\\n 207| if not word_cues:\\n 208| return\\n 209| active = active_word_index_at(word_cues, t)\\n 210| seg = segment_for_active_word(segments, active)\\n 211| active_word = word_cues[active].word\\n 212| layout = layout_caption_segment(seg.words, active_word=active_word, config=SAFE)\\n 213| f = font(layout.font_size_px, True)\\n 214| flat_words = []\\n 215| for line in layout.lines:\\n 216| flat_words.extend(line)\\n 217| for word, box in zip(flat_words, layout.word_boxes):\\n 218| x, y, _, _ = box\\n 219| fill = (247, 202, 76) if word == active_word else (255, 255, 255)\\n 220| # shadow only; no subtitle bar/box\\n 221| for dx, dy in [(-2, 2), (2, 2), (0, 3)]:\\n 222| draw.text((x+dx, y+dy), word, font=f, fill=(0,0,0,160), stroke_width=2, stroke_fill=(0,0,0,135))\\n 223| draw.text((x, y), word, font=f, fill=fill, stroke_width=2, stroke_fill=(6,10,18))\\n 224|\\n 225|\\n 226|def draw_frame(t, word_cues, segments):\\n 227| img = Image.new('RGB', (W, H), (10, 14, 24))\\n 228| draw = ImageDraw.Draw(img, 'RGBA')\\n 229| bg(draw, t)\\n 230| sc = scene_for(t)\\n 231| if sc == 'takeaway':\\n 232| draw_takeaway(draw)\\n 233| else:\\n 234| draw_invite(draw, t, 'domain' if sc in ['domain', 'checks', 'open_app'] else sc)\\n 235| if sc in ['checks', 'open_app']:\\n 236| draw_checks(draw, t)\\n 237| if sc == 'open_app':\\n 238| draw_open_app(draw, t)\\n 239| draw_caption(draw, t, word_cues, segments)\\n 240| return img\\n 241|\\n 242|\\n 243|def render(audio_path: Path, word_cues: tuple[WordCue, ...]):\\n 244| audio_duration = ffprobe_duration(audio_path)\\n 245| duration = max(audio_duration + 0.5, word_cues[-1].end + 0.6 if word_cues else audio_duration + 0.5)\\n 246| segments = build_safe_caption_segments(word_cues, layout=SAFE, min_words=3, target_words=5, max_words=7)\\n 247| segment_path = OUT / 'caption_segments_word_aligned.json'\\n 248| segment_path.write_text(json.dumps([\\n 249| {'start': s.start, 'end': s.end, 'words': s.words, 'text': s.text, 'word_indices': s.word_indices}\\n 250| for s in segments\\n 251| ], indent=2), encoding='utf-8')\\n 252|\\n 253| silent = OUT / f'{CANDIDATE}_preview_v1_word_aligned_silent.mp4'\\n 254| final = OUT / f'{CANDIDATE}_preview_v1_word_aligned.mp4'\\n 255| cmd = ['ffmpeg','-y','-f','rawvideo','-vcodec','rawvideo','-pix_fmt','rgb24','-s',f'{W}x{H}','-r',str(FPS),'-i','-','-an','-c:v','libx264','-pix_fmt','yuv420p','-crf','20',str(silent)]\\n 256| proc = subprocess.Popen(cmd, stdin=subprocess.PIPE)\\n 257| frames = int(math.ceil(duration * FPS))\\n 258| for i in range(frames):\\n 259| t = i / FPS\\n 260| proc.stdin.write(draw_frame(t, word_cues, segments).tobytes())\\n 261| proc.stdin.close(); proc.wait()\\n 262| if proc.returncode:\\n 263| raise SystemExit(proc.returncode)\\n 264| # Preserve video duration; do not use -shortest.\\n 265|\", \"total_lines\": 370, \"file_size\": 16919, \"truncated\": true, \"hint\": \"Use offset=265 to continue reading (showing 35-264 of 370 lines)\", \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_yXTgM63DHo0HlZR4dFHvgxhp"
},
{
"role": "assistant",
"content": "",
"reasoning": "**Adjusting scene thresholds**\n\nI need to make a patch with a more explanatory script. There’s a question about adjusting scene thresholds dynamically since the current fixed timing seems okay but might not align perfectly with the audio. It could be better to have the final visible after the 33-second mark. I’m thinking of patching specific thresholds, with a revised script emphasizing to trust the normal paths rather than the invite buttons. I'll make sure changes are aligned well!",
"finish_reason": "tool_calls",
"reasoning_content": "**Adjusting scene thresholds**\n\nI need to make a patch with a more explanatory script. There’s a question about adjusting scene thresholds dynamically since the current fixed timing seems okay but might not align perfectly with the audio. It could be better to have the final visible after the 33-second mark. I’m thinking of patching specific thresholds, with a revised script emphasizing to trust the normal paths rather than the invite buttons. I'll make sure changes are aligned well!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKA5F5RViDyWXFZPSp3glCx_BPz1DP8i0ynzxptt2dB_NWfG1f3oBp1wvVkQWvuiQbM0_j6JWJvemVcN44Mh5AzH76ycBp0le_6zinh17j1W3Cj24yE1PgziizWbFFAc1u_wTnUv-Yazzj5NxCC6UQhB_WLNcFU8dnCTZ3_Isv7kmDBl-7HvzqR7FcCyZkNU8ihI8PXI0M_O75TH6RLH6GBjcIdyKfqxZ4hvcp6pXTihlXn4i1NyeZNxpIc3Die6AXAH5qqty65wsLOuJXYEZmSYPXJk4W-UfsPO6amYkYhLsG1Gj_6O17UYo1rbtkU4Ww0mBPIyT2dd1z31-ESVOYvmYbY77mQfkOJLEBjA0ljXho1bIasiSY1sIDkFldUW22vVHDIv0e-JmRiVnsnQyxpDUW9CGWqg5HZcmnWNiXGMw1oeGDnAqA16XUaSPjiVcWqCkuyKa9sChbvREvlNbSA6aQWIM7_pTj1C5YjDV0VwlK-gxfuFakrATp-0Ik_j_RUALTbGoLH2UhZJ5jcNlAxXvKziWGncjuic-eFqLixQ4iLPEEqf0SYOtUBul0Ly0E-Atv5LqwW8bE4_M2Ur2tmkUGObQy7dU08en9WDg8H-hOHV21NPL305DBKZorbNbQjolB6twxuSo8rWaVZquP88yDn8du6y7me4upGcxN-XZGilEuR6jKeSFBjYL-YewBBka0T-1CEI2rXo5na8vwMLPWBz1O9r6M21jsc_9teK_YjEUy_Gcz1YPrfmNAxb8J05ID1nwAFmLZDSRbF-tjJYK0NDkq3JbXpRnl_m9zGMiyUpqWsZNYsGZuXlxVBVzzya8JpnbMN3UqFVhhlr6OHnmzyM1V0aKcxPzS6jFvoU1aDV2eEFxQ4qU9gAxfSG3wfr5v4Z_0V9S9-iIZLi7YSRh5zmBNC-K24NSp5MzXQsUYmy_qV8gGhzbQ9kaXHScAwIt6q5PVSwCagdOAKr5mZ-OCge7NTNXagUFxlA2_ERxGS011m_KXl6UybyGd1hKgVAGe2F5_erT6v7P6F5zI397PcQUZNGs7EEMcpMjPFFT5ggRaNBmzbQcnTuLoKByh1tDTOCTplvMsFoqd7w97vemPSqgMbDi7scyKeit0GUd_ifzmMi9MASsN3ldINBQsaIHIJRI3MXpQbMgZbgKAcm-ri7dFMPzbxcCFo8fsMljhSfbPq8r5nqo_Qj2lqS2JkqfZvlSX_mrKjKWlOs752Lj6iC-IQnWfNdycN926h9tyTuyavZ9HiJj2afYghoXHOQL9osot_mCiWFlGB5GPa1jdRuK7J0aX6qfaxeSzUUVVDltYyLFOcs_5ZF89pIFNsCNX3kU2axTH_g9o4gIIHXcm4VIHLiCJrcF2LECnIb7OHpNBF3RDNAthWw7Z0bMVDUYtfHpFR9k0eoOkhLJDeBS8kzMwwH_YADx6qbqDOVM4Bc4UABJzfoVHAjIIEw1WPj8V8IBzuI0jlnQltqHkvwnYhUVNDcp6n_qbse_fzzESPCsGGrITsuo_A0PGa4jC8-Q1VMxpbwOg5EUE-nEB-xywW8hG7x0anioa1heOSP0JmLK0pcpid8IuO_81TUkxw5BSc2cIzy-9EAvNsigdC0ofRVlJjrKMSw_HZYQawEr0LQbyuShgpbHY90YclXIVTV7Nqoef-JwobEjtOsfxx50ynx2NDmv4pNGu0gY6s4jgT0rWngmuZbjHHn_eBXG00One8FX-zCIWk7OZaoAJ0rgUz_xGzdskzKn0zbFnlDO9h_1RyBLooEd78U2W-NfjGmW2PzJZeMlnS-gEDrat0SzMoLoUqL4mBWW0Pf99udi8jykmkkxybwwO4evgUy7Rj2aX8LGyVLcjJZMEgZpNK9g-mApyWfh0jJIYK_17GT8ywuJ_X7vDA00Bjpgn71Ksb1ECQEvaRn_Njh8UM9O4d5b76LYVBRD8anLZOLCvJwh2P3_MRvDnfduHAcr-WLDJupyaILuzu32hWB1zudo77lmDf_0lR2tKylg4BLneF8-tG21z9-U8apZ4Lo5UplE_HrkrJM-1_pV4KJGng1oo3MeIZAFDaE9bwcB7mCPyN4wTPA4XFu0L3rMSiuJkVczP49",
"id": "rs_051a8a0b2fb58918016a14a03381f481919a43d7f1dec56509",
"summary": [
{
"type": "summary_text",
"text": "**Adjusting scene thresholds**\n\nI need to make a patch with a more explanatory script. There’s a question about adjusting scene thresholds dynamically since the current fixed timing seems okay but might not align perfectly with the audio. It could be better to have the final visible after the 33-second mark. I’m thinking of patching specific thresholds, with a revised script emphasizing to trust the normal paths rather than the invite buttons. I'll make sure changes are aligned well!"
}
]
}
],
"tool_calls": [
{
"id": "call_U5EIDyrdLp9Rwj9OpQ2dv2Pu",
"call_id": "call_U5EIDyrdLp9Rwj9OpQ2dv2Pu",
"response_item_id": "fc_051a8a0b2fb58918016a14a03901848191ba7fe042a9680af2",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"old_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n \\\"Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\"\\n)\\n\",\"new_string\":\"SCRIPT = (\\n \\\"This calendar invite looks normal. The trap is the login button. \\\"\\n \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n \\\"That means: close the invite. Open your calendar or work app from the icon or bookmark you normally use. \\\"\\n \\\"If the meeting is real, it will still be there. The rule: trust the path you chose, not the button that chose you.\\\"\\n)\\n\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -44,7 +44,8 @@\\n \\\"Same meeting title. Same urgent tone. But the link points somewhere else. \\\"\\n \\\"Before you sign in, slow down. Check who sent it. Check the link domain. \\\"\\n \\\"Notice unusual login requests. If the domain feels off, do not sign in from the invite. \\\"\\n- \\\"Open the service yourself. The fix: trust the app you opened, not the button that rushed you.\\\"\\n+ \\\"That means: close the invite. Open your calendar or work app from the icon or bookmark you normally use. \\\"\\n+ \\\"If the meeting is real, it will still be there. The rule: trust the path you chose, not the button that chose you.\\\"\\n )\\n SENTENCES = [s.strip() for s in re.split(r'(?<=[.!?])\\\\s+', SCRIPT) if s.strip()]\\n \\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}, \"_warning\": \"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py was last read with offset/limit pagination (partial view). Re-read the whole file before overwriting it.\"}",
"tool_call_id": "call_U5EIDyrdLp9Rwj9OpQ2dv2Pu"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_d3wQqSKco1krI4j6nC1iWr0F",
"call_id": "call_d3wQqSKco1krI4j6nC1iWr0F",
"response_item_id": "fc_051a8a0b2fb58918016a14a040b574819191d4490140d8ea31",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\"def scene_for(t):\\n if t < 5.4: return 'hook'\\n if t < 10.8: return 'same'\\n if t < 16.2: return 'domain'\\n if t < 23.0: return 'checks'\\n if t < 36.0: return 'open_app'\\n return 'takeaway'\\n\",\"old_string\":\"def scene_for(t):\\n if t < 5.4: return 'hook'\\n if t < 10.8: return 'same'\\n if t < 16.2: return 'domain'\\n if t < 23.0: return 'checks'\\n if t < 29.2: return 'open_app'\\n return 'takeaway'\\n\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -139,7 +139,7 @@\\n if t < 10.8: return 'same'\\n if t < 16.2: return 'domain'\\n if t < 23.0: return 'checks'\\n- if t < 29.2: return 'open_app'\\n+ if t < 36.0: return 'open_app'\\n return 'takeaway'\\n \\n \\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_d3wQqSKco1krI4j6nC1iWr0F"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_UWGXd2BaXVVSY7x6r8KGnkXO",
"call_id": "call_UWGXd2BaXVVSY7x6r8KGnkXO",
"response_item_id": "fc_051a8a0b2fb58918016a14a047f2348191a789e1d3409cd3b2",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\"def draw_open_app(draw, t):\\n rounded(draw, (125, 1135, 955, 1448), 34, (28, 38, 57), (93, 112, 148), 3)\\n text(draw, (540, 1192), 'Close the invite', 44, (255, 255, 255), anchor='mm')\\n text(draw, (540, 1262), 'Open your normal app', 42, (247, 202, 76), anchor='mm')\\n text(draw, (540, 1327), 'or trusted bookmark', 36, (205, 214, 230), anchor='mm')\\n # app icon + check\\n rounded(draw, (464, 1360, 616, 1507), 32, (18, 24, 36), (247, 202, 76), 4)\\n draw.line((500, 1436, 532, 1469, 586, 1397), fill=(247, 202, 76), width=10)\\n\",\"old_string\":\"def draw_open_app(draw, t):\\n rounded(draw, (125, 1160, 955, 1395), 34, (28, 38, 57), (93, 112, 148), 3)\\n text(draw, (540, 1220), 'Open the service yourself', 44, (255, 255, 255), anchor='mm')\\n text(draw, (540, 1292), 'not the rushed button', 42, (247, 202, 76), anchor='mm')\\n # app icon + check\\n rounded(draw, (464, 1335, 616, 1482), 32, (18, 24, 36), (247, 202, 76), 4)\\n draw.line((500, 1411, 532, 1444, 586, 1372), fill=(247, 202, 76), width=10)\\n\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -189,12 +189,13 @@\\n \\n \\n def draw_open_app(draw, t):\\n- rounded(draw, (125, 1160, 955, 1395), 34, (28, 38, 57), (93, 112, 148), 3)\\n- text(draw, (540, 1220), 'Open the service yourself', 44, (255, 255, 255), anchor='mm')\\n- text(draw, (540, 1292), 'not the rushed button', 42, (247, 202, 76), anchor='mm')\\n+ rounded(draw, (125, 1135, 955, 1448), 34, (28, 38, 57), (93, 112, 148), 3)\\n+ text(draw, (540, 1192), 'Close the invite', 44, (255, 255, 255), anchor='mm')\\n+ text(draw, (540, 1262), 'Open your normal app', 42, (247, 202, 76), anchor='mm')\\n+ text(draw, (540, 1327), 'or trusted bookmark', 36, (205, 214, 230), anchor='mm')\\n # app icon + check\\n- rounded(draw, (464, 1335, 616, 1482), 32, (18, 24, 36), (247, 202, 76), 4)\\n- draw.line((500, 1411, 532, 1444, 586, 1372), fill=(247, 202, 76), width=10)\\n+ rounded(draw, (464, 1360, 616, 1507), 32, (18, 24, 36), (247, 202, 76), 4)\\n+ draw.line((500, 1436, 532, 1469, 586, 1397), fill=(247, 202, 76), width=10)\\n \\n \\n def draw_takeaway(draw):\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_UWGXd2BaXVVSY7x6r8KGnkXO"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_CRdLWKQfhPBtZKJsLcELr5fu",
"call_id": "call_CRdLWKQfhPBtZKJsLcELr5fu",
"response_item_id": "fc_051a8a0b2fb58918016a14a0549e348191b705deb9ac08cead",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\"def draw_takeaway(draw):\\n rounded(draw, (92, 395, 988, 1085), 46, (24, 32, 48), (247, 202, 76), 4)\\n text(draw, (540, 540), \\\"If it's real,\\\", 70, (255, 255, 255), anchor='mm')\\n text(draw, (540, 655), 'it will be there too.', 60, (247, 202, 76), anchor='mm')\\n text(draw, (540, 805), 'Trust your normal path.', 44, (255, 255, 255), anchor='mm')\\n text(draw, (540, 895), 'Not the button sent to you.', 38, (205, 214, 230), anchor='mm')\\n\",\"old_string\":\"def draw_takeaway(draw):\\n rounded(draw, (92, 420, 988, 1040), 46, (24, 32, 48), (247, 202, 76), 4)\\n text(draw, (540, 570), 'Trust the app', 76, (255, 255, 255), anchor='mm')\\n text(draw, (540, 700), 'you opened.', 76, (247, 202, 76), anchor='mm')\\n text(draw, (540, 845), 'Not the button that rushed you.', 42, (205, 214, 230), anchor='mm')\\n\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -199,10 +199,11 @@\\n \\n \\n def draw_takeaway(draw):\\n- rounded(draw, (92, 420, 988, 1040), 46, (24, 32, 48), (247, 202, 76), 4)\\n- text(draw, (540, 570), 'Trust the app', 76, (255, 255, 255), anchor='mm')\\n- text(draw, (540, 700), 'you opened.', 76, (247, 202, 76), anchor='mm')\\n- text(draw, (540, 845), 'Not the button that rushed you.', 42, (205, 214, 230), anchor='mm')\\n+ rounded(draw, (92, 395, 988, 1085), 46, (24, 32, 48), (247, 202, 76), 4)\\n+ text(draw, (540, 540), \\\"If it's real,\\\", 70, (255, 255, 255), anchor='mm')\\n+ text(draw, (540, 655), 'it will be there too.', 60, (247, 202, 76), anchor='mm')\\n+ text(draw, (540, 805), 'Trust your normal path.', 44, (255, 255, 255), anchor='mm')\\n+ text(draw, (540, 895), 'Not the button sent to you.', 38, (205, 214, 230), anchor='mm')\\n \\n \\n def draw_caption(draw, t, word_cues, segments):\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_CRdLWKQfhPBtZKJsLcELr5fu"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_6TjSl5pxpxBcrDvt4rmhSLX8",
"call_id": "call_6TjSl5pxpxBcrDvt4rmhSLX8",
"response_item_id": "fc_051a8a0b2fb58918016a14a05f66e88191ab9bba33d41070e6",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\" 'final_solution': 'Close the invite; open the calendar/work app via the normal icon or trusted bookmark; if the meeting is real, it will still be there.',\",\"old_string\":\" 'final_solution': 'Open the service yourself; trust the app you opened, not the rushed button.',\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"replace_all\":true}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -301,7 +301,7 @@\\n 'segment_count': len(segments),\\n 'safe_zone': 'bottom caption, no box/bar, tested via contact sheet',\\n 'summary_fazit_present': True,\\n- 'final_solution': 'Open the service yourself; trust the app you opened, not the rushed button.',\\n+ 'final_solution': 'Close the invite; open the calendar/work app via the normal icon or trusted bookmark; if the meeting is real, it will still be there.',\\n }\\n qa_path = OUT / 'qa_summary_preview_v1.json'\\n qa_path.write_text(json.dumps(qa, indent=2), encoding='utf-8')\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_6TjSl5pxpxBcrDvt4rmhSLX8"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_Ear60gYaNfwLOls4XnQtiACj",
"call_id": "call_Ear60gYaNfwLOls4XnQtiACj",
"response_item_id": "fc_051a8a0b2fb58918016a14a066f87c81919c557882f554d28e",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\" 'usefulness_fix': 'Close the invite; open the calendar or work app from the normal icon/bookmark; if the meeting is real, it will appear there too.',\\n 'takeaway': 'Trust your normal path, not the button sent to you.',\",\"old_string\":\" 'usefulness_fix': 'Do not sign in from a suspicious invite. Open the service yourself and verify from there.',\\n 'takeaway': 'Trust the app you opened, not the button that rushed you.',\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -354,8 +354,8 @@\\n {'time': '23-29s', 'scene': 'button dims; open-service-yourself card', 'purpose': 'real solution'},\\n {'time': '29-end', 'scene': 'final takeaway card', 'purpose': 'fazit / memorable rule'},\\n ],\\n- 'usefulness_fix': 'Do not sign in from a suspicious invite. Open the service yourself and verify from there.',\\n- 'takeaway': 'Trust the app you opened, not the button that rushed you.',\\n+ 'usefulness_fix': 'Close the invite; open the calendar or work app from the normal icon/bookmark; if the meeting is real, it will appear there too.',\\n+ 'takeaway': 'Trust your normal path, not the button sent to you.',\\n 'pretty_empty_visual_blocker': {'result': 'pass', 'reason': 'first frame shows a concrete invite/login problem, not abstract mood visuals'},\\n 'claim_gate': {'result': 'pass', 'risk': 'medium', 'not_claimed': ['this detects all phishing', 'legal/security advice guarantee']},\\n 'ai_disclosure': 'no realistic AI people/scenes; deterministic mockups and EdgeTTS voice',\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_Ear60gYaNfwLOls4XnQtiACj"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_VOYMUcmUmjkjNPQQmKutF6ls",
"call_id": "call_VOYMUcmUmjkjNPQQmKutF6ls",
"response_item_id": "fc_051a8a0b2fb58918016a14a06ceee881919dbcf66c42069ccf",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\",\"id\":\"revise-script\",\"status\":\"completed\"},{\"content\":\"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\",\"id\":\"rerender\",\"status\":\"in_progress\"}]}"
}
}
]
},
{
"role": "tool",
"name": "todo",
"content": "{\"todos\": [{\"id\": \"revise-script\", \"content\": \"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\", \"status\": \"completed\"}, {\"id\": \"rerender\", \"content\": \"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\", \"status\": \"in_progress\"}, {\"id\": \"qa\", \"content\": \"Dauer, Captions, Contact Sheet und Fazit prüfen\", \"status\": \"pending\"}, {\"id\": \"deliver\", \"content\": \"Revidierte Preview und kurze Begründung liefern\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 2, \"in_progress\": 1, \"completed\": 1, \"cancelled\": 0}}",
"tool_call_id": "call_VOYMUcmUmjkjNPQQmKutF6ls"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_MulcDU8pKawrVRmtyMI0jJHD",
"call_id": "call_MulcDU8pKawrVRmtyMI0jJHD",
"response_item_id": "fc_051a8a0b2fb58918016a14a070835481918d11b7316f20d3ea",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"ffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, rawvideo, from 'fd:':\\n Duration: N/A, start: 0.000000, bitrate: 1194393 kb/s\\n Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 1080x1920, 1194393 kb/s, 24 tbr, 24 tbn\\nStream mapping:\\n Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x5f5f89cdc3c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x5f5f89cdc3c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x5f5f89cdc3c0] 264 - core 164 r3108 31e19f9 - H.264/MPEG-4 AVC codec - Copyleft 2003-2023 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=9 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n encoder : Lavf60.16.100\\n Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1080x1920, q=2-31, 24 fps, 12288 tbn\\n Metadata:\\n encoder : Lavc60.31.102 libx264\\n Side data:\\n cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\\nframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 3 fps=0.9 q=25.0 size= 0kB time=00:00:00.04 bitrate= 9.2kbits/s speed=0.0131x \\rframe= 12 fps=3.2 q=25.0 size= 0kB time=00:00:00.37 bitrate= 1.0kbits/s speed=0.101x \\rframe= 19 fps=4.5 q=25.0 size= 0kB time=00:00:00.70 bitrate= 0.5kbits/s speed=0.168x \\rframe= 27 fps=5.7 q=25.0 size= 0kB time=00:00:01.04 bitrate= 0.4kbits/s speed=0.221x \\rframe= 36 fps=6.8 q=25.0 size= 0kB time=00:00:01.41 bitrate= 0.3kbits/s speed=0.269x \\rframe= 44 fps=7.6 q=25.0 size= 0kB time=00:00:01.75 bitrate= 0.2kbits/s speed=0.303x \\rframe= 53 fps=8.4 q=25.0 size= 0kB time=00:00:02.12 bitrate= 0.2kbits/s speed=0.336x \\rframe= 62 fps=9.0 q=25.0 size= 0kB time=00:00:02.50 bitrate= 0.2kbits/s speed=0.365x \\rframe= 71 fps=9.6 q=25.0 size= 0kB time=00:00:02.87 bitrate= 0.1kbits/s speed=0.39x \\rframe= 81 fps= 10 q=25.0 size= 0kB time=00:00:03.29 bitrate= 0.1kbits/s speed=0.418x \\rframe= 92 fps= 11 q=25.0 size= 0kB time=00:00:03.75 bitrate= 0.1kbits/s speed=0.445x \\rframe= 102 fps= 11 q=25.0 size= 0kB time=00:00:04.16 bitrate= 0.1kbits/s speed=0.467x \\rframe= 112 fps= 12 q=25.0 size= 0kB time=00:00:04.58 bitrate= 0.1kbits/s speed=0.486x \\rframe= 122 fps= 12 q=25.0 size= 0kB time=00:00:05.00 bitrate= 0.1kbits/s speed=0.503x \\rframe= 132 fps= 13 q=25.0 size= 0kB time=00:00:05.41 bitrate= 0.1kbits/s speed=0.518x \\rframe= 142 fps= 13 q=25.0 size= 0kB time=00:00:05.83 bitrate= 0.1kbits/s speed=0.531x \\rframe= 152 fps= 13 q=25.0 size= 0kB time=00:00:06.25 bitrate= 0.1kbits/s speed=0.544x \\rframe= 161 fps= 13 q=25.0 size= 0kB time=00:00:06.62 bitrate= 0.1kbits/s speed=0.551x \\rframe= 171 fps= 14 q=25.0 size= 0kB time=00:00:07.04 bitrate= 0.1kbits/s speed=0.562x \\rframe= 180 fps= 14 q=25.0 size= 0kB time=00:00:07.41 bitrate= 0.1kbits/s speed=0.567x \\rframe= 189 fps= 14 q=25.0 size= 0kB time=00:00:07.79 bitrate= 0.0kbits/s speed=0.572x \\rframe= 198 fps= 14 q=25.0 size= 0kB time=00:00:08.16 bitrate= 0.0kbits/s speed=0.578x \\rframe= 207 fps= 14 q=25.0 size= 0kB time=00:00:08.54 bitrate= 0.0kbits/s speed=0.583x \\rframe= 216 fps= 14 q=25.0 size= 0kB time=00:00:08.91 bitrate= 0.0kbits/s speed=0.587x \\rframe= 225 fps= 14 q=25.0 size= 0kB time=00:00:09.29 bitrate= 0.0kbits/s speed=0.592x \\rframe= 233 fps= 14 q=25.0 size= 0kB time=00:00:09.62 bitrate= 0.0kbits/s speed=0.594x \\rframe= 242 fps= 14 q=22.0 size= 0kB time=00:00:10.00 bitrate= 0.0kbits/s speed=0.598x \\rframe= 251 fps= 15 q=25.0 size= 0kB time=00:00:10.37 bitrate= 0.0kbits/s speed=0.602x \\rframe= 261 fps= 15 q=25.0 size= 256kB time=00:00:10.79 bitrate= 194.4kbits/s speed=0.607x \\rframe= 270 fps= 15 q=25.0 size= 256kB time=00:00:11.16 bitrate= 187.8kbits/s speed=0.611x \\rframe= 279 fps= 15 q=25.0 size= 256kB time=00:00:11.54 bitrate= 181.7kbits/s speed=0.614x \\rframe= 288 fps= 15 q=25.0 size= 256kB time=00:00:11.91 bitrate= 176.0kbits/s speed=0.617x \\rframe= 297 fps= 15 q=25.0 size= 256kB time=00:00:12.29 bitrate= 170.6kbits/s speed=0.62x \\rframe= 307 fps= 15 q=25.0 size= 256kB time=00:00:12.70 bitrate= 165.1kbits/s speed=0.624x \\rframe= 318 fps= 15 q=25.0 size= 256kB time=00:00:13.16 bitrate= 159.3kbits/s speed=0.63x \\rframe= 329 fps= 15 q=25.0 size= 256kB time=00:00:13.62 bitrate= 153.9kbits/s speed=0.635x \\rframe= 339 fps= 15 q=25.0 size= 256kB time=00:00:14.04 bitrate= 149.4kbits/s speed=0.639x \\rframe= 349 fps= 16 q=25.0 size= 256kB time=00:00:14.45 bitrate= 145.1kbits/s speed=0.643x \\rframe= 359 fps= 16 q=25.0 size= 256kB time=00:00:14.87 bitrate= 141.0kbits/s speed=0.647x \\rframe= 369 fps= 16 q=25.0 size= 256kB time=00:00:15.29 bitrate= 137.2kbits/s speed=0.649x \\rframe= 379 fps= 16 q=25.0 size= 256kB time=00:00:15.70 bitrate= 133.5kbits/s speed=0.652x \\rframe= 389 fps= 16 q=25.0 size= 256kB time=00:00:16.12 bitrate= 130.1kbits/s speed=0.655x \\rframe= 397 fps= 16 q=25.0 size= 256kB time=00:00:16.45 bitrate= 127.4kbits/s speed=0.654x \\rframe= 406 fps= 16 q=25.0 size= 256kB time=00:00:16.83 bitrate= 124.6kbits/s speed=0.655x \\rframe= 415 fps= 16 q=25.0 size= 256kB time=00:00:17.20 bitrate= 121.9kbits/s speed=0.656x \\rframe= 424 fps= 16 q=25.0 size= 256kB time=00:00:17.58 bitrate= 119.3kbits/s speed=0.658x \\rframe= 433 fps= 16 q=25.0 size= 256kB time=00:00:17.95 bitrate= 116.8kbits/s speed=0.659x \\rframe= 441 fps= 16 q=25.0 size= 256kB time=00:00:18.29 bitrate= 114.7kbits/s speed=0.659x \\rframe= 450 fps= 16 q=25.0 size= 256kB time=00:00:18.66 bitrate= 112.4kbits/s speed=0.66x \\rframe= 459 fps= 16 q=25.0 size= 256kB time=00:00:19.04 bitrate= 110.2kbits/s speed=0.661x \\rframe= 468 fps= 16 q=25.0 size= 256kB time=00:00:19.41 bitrate= 108.0kbits/s speed=0.661x \\rframe= 477 fps= 16 q=25.0 size= 256kB time=00:00:19.79 bitrate= 106.0kbits/s speed=0.662x \\rframe= 485 fps= 16 q=25.0 size= 256kB time=00:00:20.12 bitrate= 104.2kbits/s speed=0.662x \\rframe= 494 fps= 16 q=25.0 size= 256kB time=00:00:20.50 bitrate= 102.3kbits/s speed=0.662x \\rframe= 504 fps= 16 q=25.0 size= 512kB time=00:00:20.91 bitrate= 200.5kbits/s speed=0.664x \\rframe= 512 fps= 16 q=25.0 size= 512kB time=00:00:21.25 bitrate= 197.4kbits/s speed=0.664x \\rframe= 520 fps= 16 q=25.0 size= 512kB time=00:00:21.58 bitrate= 194.3kbits/s speed=0.663x \\rframe= 529 fps= 16 q=25.0 size= 512kB time=00:00:21.95 bitrate= 191.0kbits/s speed=0.663x \\rframe= 537 fps= 16 q=25.0 size= 512kB time=00:00:22.29 bitrate= 188.2kbits/s speed=0.663x \\rframe= 545 fps= 16 q=25.0 size= 512kB time=00:00:22.62 bitrate= 185.4kbits/s speed=0.662x \\rframe= 554 fps= 16 q=25.0 size= 512kB time=00:00:23.00 bitrate= 182.4kbits/s speed=0.663x \\rframe= 562 fps= 16 q=25.0 size= 512kB time=00:00:23.33 bitrate= 179.8kbits/s speed=0.662x \\rframe= 570 fps= 16 q=25.0 size= 512kB time=00:00:23.66 bitrate= 177.2kbits/s speed=0.662x \\rframe= 579 fps= 16 q=25.0 size= 512kB time=00:00:24.04 bitrate= 174.5kbits/s speed=0.663x \\rframe= 588 fps= 16 q=25.0 size= 512kB time=00:00:24.41 bitrate= 171.8kbits/s speed=0.663x \\rframe= 597 fps= 16 q=25.0 size= 512kB time=00:00:24.79 bitrate= 169.2kbits/s speed=0.664x \\rframe= 606 fps= 16 q=25.0 size= 512kB time=00:00:25.16 bitrate= 166.7kbits/s speed=0.664x \\rframe= 615 fps= 16 q=25.0 size= 512kB time=00:00:25.54 bitrate= 164.2kbits/s speed=0.665x \\rframe= 624 fps= 16 q=25.0 size= 512kB time=00:00:25.91 bitrate= 161.9kbits/s speed=0.665x \\rframe= 633 fps= 16 q=25.0 size= 512kB time=00:00:26.29 bitrate= 159.5kbits/s speed=0.665x \\rframe= 642 fps= 16 q=25.0 size= 512kB time=00:00:26.66 bitrate= 157.3kbits/s speed=0.666x \\rframe= 651 fps= 16 q=25.0 size= 512kB time=00:00:27.04 bitrate= 155.1kbits/s speed=0.666x \\rframe= 660 fps= 16 q=25.0 size= 512kB time=00:00:27.41 bitrate= 153.0kbits/s speed=0.667x \\rframe= 669 fps= 16 q=25.0 size= 512kB time=00:00:27.79 bitrate= 150.9kbits/s speed=0.667x \\rframe= 677 fps= 16 q=25.0 size= 512kB time=00:00:28.12 bitrate= 149.1kbits/s speed=0.667x \\rframe= 686 fps= 16 q=25.0 size= 512kB time=00:00:28.50 bitrate= 147.2kbits/s speed=0.667x \\rframe= 695 fps= 16 q=25.0 size= 512kB time=00:00:28.87 bitrate= 145.3kbits/s speed=0.668x \\rframe= 703 fps= 16 q=25.0 size= 512kB time=00:00:29.20 bitrate= 143.6kbits/s speed=0.668x \\rframe= 712 fps= 16 q=25.0 size= 512kB time=00:00:29.58 bitrate= 141.8kbits/s speed=0.668x \\rframe= 721 fps= 16 q=25.0 size= 512kB time=00:00:29.95 bitrate= 140.0kbits/s speed=0.668x \\rframe= 730 fps= 16 q=25.0 size= 512kB time=00:00:30.33 bitrate= 138.3kbits/s speed=0.669x \\rframe= 739 fps= 16 q=25.0 size= 512kB time=00:00:30.70 bitrate= 136.6kbits/s speed=0.669x \\rframe= 748 fps= 16 q=25.0 size= 768kB time=00:00:31.08 bitrate= 202.4kbits/s speed=0.669x \\rframe= 758 fps= 16 q=25.0 size= 768kB time=00:00:31.50 bitrate= 199.7kbits/s speed=0.67x \\rframe= 767 fps= 16 q=25.0 size= 768kB time=00:00:31.87 bitrate= 197.4kbits/s speed=0.671x \\rframe= 777 fps= 16 q=25.0 size= 768kB time=00:00:32.29 bitrate= 194.8kbits/s speed=0.672x \\rframe= 787 fps= 16 q=25.0 size= 768kB time=00:00:32.70 bitrate= 192.4kbits/s speed=0.673x \\rframe= 797 fps= 16 q=25.0 size= 768kB time=00:00:33.12 bitrate= 189.9kbits/s speed=0.674x \\rframe= 807 fps= 16 q=25.0 size= 768kB time=00:00:33.54 bitrate= 187.6kbits/s speed=0.675x \\rframe= 818 fps= 16 q=25.0 size= 768kB time=00:00:34.00 bitrate= 185.1kbits/s speed=0.677x \\rframe= 830 fps= 16 q=25.0 size= 768kB time=00:00:34.45 bitrate= 182.6kbits/s speed=0.679x \\rframe= 840 fps= 16 q=25.0 size= 768kB time=00:00:34.91 bitrate= 180.2kbits/s speed=0.681x \\rframe= 850 fps= 16 q=25.0 size= 768kB time=00:00:35.33 bitrate= 178.1kbits/s speed=0.682x \\rframe= 860 fps= 16 q=25.0 size= 768kB time=00:00:35.75 bitrate= 176.0kbits/s speed=0.683x \\rframe= 871 fps= 16 q=25.0 size= 768kB time=00:00:36.20 bitrate= 173.8kbits/s speed=0.685x \\rframe= 882 fps= 17 q=25.0 size= 768kB time=00:00:36.66 bitrate= 171.6kbits/s speed=0.687x \\rframe= 892 fps= 17 q=25.0 size= 768kB time=00:00:37.08 bitrate= 169.7kbits/s speed=0.688x \\rframe= 904 fps= 17 q=25.0 size= 768kB time=00:00:37.58 bitrate= 167.4kbits/s speed=0.69x \\rframe= 917 fps= 17 q=25.0 size= 768kB time=00:00:38.12 bitrate= 165.0kbits/s speed=0.694x \\rframe= 930 fps= 17 q=25.0 size= 768kB time=00:00:38.66 bitrate= 162.7kbits/s speed=0.697x \\rframe= 942 fps= 17 q=25.0 size= 1024kB time=00:00:39.16 bitrate= 214.2kbits/s speed=0.699x \\r[out#0/mp4 @ 0x5f5f89cdad00] video:1096kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.150792%\\nframe= 1005 fps= 18 q=-1.0 Lsize= 1109kB time=00:00:41.75 bitrate= 217.6kbits/s speed=0.736x \\n[libx264 @ 0x5f5f89cdc3c0] frame I:5 Avg QP:14.33 size: 60194\\n[libx264 @ 0x5f5f89cdc3c0] frame P:253 Avg QP:17.88 size: 2518\\n[libx264 @ 0x5f5f89cdc3c0] frame B:747 Avg QP:22.70 size: 246\\n[libx264 @ 0x5f5f89cdc3c0] consecutive B-frames: 0.9% 0.0% 0.0% 99.1%\\n[libx264 @ 0x5f5f89cdc3c0] mb I I16..4: 65.9% 18.5% 15.6%\\n[libx264 @ 0x5f5f89cdc3c0] mb P I16..4: 0.6% 0.1% 0.3% P16..4: 4.0% 0.2% 0.1% 0.0% 0.0% skip:94.7%\\n[libx264 @ 0x5f5f89cdc3c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.3% 0.0% 0.0% direct: 0.0% skip:97.6% L0:54.9% L1:45.0% BI: 0.1%\\n[libx264 @ 0x5f5f89cdc3c0] 8x8 transform intra:18.3% inter:41.5%\\n[libx264 @ 0x5f5f89cdc3c0] coded y,uvDC,uvAC intra: 14.1% 15.7% 11.5% inter: 0.1% 0.1% 0.0%\\n[libx264 @ 0x5f5f89cdc3c0] i16 v,h,dc,p: 28% 72% 0% 0%\\n[libx264 @ 0x5f5f89cdc3c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 45% 13% 39% 2% 0% 0% 0% 0% 0%\\n[libx264 @ 0x5f5f89cdc3c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 34% 41% 8% 2% 3% 3% 3% 2% 3%\\n[libx264 @ 0x5f5f89cdc3c0] i8c dc,h,v,p: 69% 19% 12% 1%\\n[libx264 @ 0x5f5f89cdc3c0] Weighted P-Frames: Y:0.0% UV:0.0%\\n[libx264 @ 0x5f5f89cdc3c0] ref P L0: 85.9% 1.2% 9.4% 3.4%\\n[libx264 @ 0x5f5f89cdc3c0] ref B L0: 61.0% 37.9% 1.2%\\n[libx264 @ 0x5f5f89cdc3c0] ref B L1: 97.4% 2.6%\\n[libx264 @ 0x5f5f89cdc3c0] kb/s:214.37\\nffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Duration: 00:00:41.88, start: 0.000000, bitrate: 216 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 214 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n[mp3 @ 0x5a51b2ee2f00] Estimating duration from bitrate, this may be inaccurate\\nInput #1, mp3, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3':\\n Duration: 00:00:41.35, start: 0.000000, bitrate: 48 kb/s\\n Stream #1:0: Audio: mp3, 24000 Hz, mono, fltp, 48 kb/s\\nStream mapping:\\n Stream #0:0 -> #0:0 (copy)\\n Stream #1:0 -> #0:1 (mp3 (mp3float) -> aac (native))\\nPress [q] to stop, [?] for help\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, q=2-31, 214 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 69 kb/s\\n Metadata:\\n encoder : Lavc60.31.102 aac\\nsize= 0kB time=N/A bitrate=N/A speed=N/A \\rsize= 1024kB time=00:00:34.25 bitrate= 244.9kbits/s speed=68.5x \\r[out#0/mp4 @ 0x5a51b2ee36c0] video:1096kB audio:321kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.771788%\\nsize= 1442kB time=00:00:41.75 bitrate= 283.0kbits/s speed=71.8x \\n[aac @ 0x5a51b2e64540] Qavg: 17882.781\\n{\\n \\\"ok\\\": true,\\n \\\"manifest\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.0.0-word-aligned-proof\\\",\\n \\\"series\\\": \\\"Digital Red Flags\\\",\\n \\\"title\\\": \\\"The calendar invite login trap\\\",\\n \\\"script\\\": \\\"This calendar invite looks normal. The trap is the login button. Same meeting title. Same urgent tone. But the link points somewhere else. Before you sign in, slow down. Check who sent it. Check the link domain. Notice unusual login requests. If the domain feels off, do not sign in from the invite. That means: close the invite. Open your calendar or work app from the icon or bookmark you normally use. If the meeting is real, it will still be there. The rule: trust the path you chose, not the button that chose you.\\\",\\n \\\"script_hash\\\": \\\"0e9ec7f162b69573\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\\\",\\n \\\"preview_sha256\\\": \\\"fafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d\\\",\\n \\\"silent_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4\\\",\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"audio_sha256\\\": \\\"77c875c19c1197426f2023af3dc5cdf866fba76ffee20bcfa021236aa5665376\\\",\\n \\\"word_cues_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/word_cues.json\\\",\\n \\\"caption_segments_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/caption_segments_word_aligned.json\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\\\",\\n \\\"subtitle_preview_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_subtitle_style_preview_v1.jpg\\\",\\n \\\"qa_summary_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\\\",\\n \\\"duration_seconds\\\": 41.852,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"caption_policy\\\": \\\"static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries\\\",\\n \\\"blocked\\\": {\\n \\\"wan\\\": true,\\n \\\"i2v\\\": true,\\n \\\"platform_api\\\": true,\\n \\\"posting\\\": true,\\n \\\"scheduling\\\": true\\n }\\n },\\n \\\"review_package\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\\\"\\n}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_MulcDU8pKawrVRmtyMI0jJHD"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKC0pbiuLeVkMuvQ7lALV469-8vAy538mCg0SRGzwWVJcNaO-KB1Vpd5XflG9atjmH4p4bmK0z4cfODZu_GGsM8BeTlmGTTVidw0znisq_EMlEB48UfkWGhwGZk-yRHYJzjl92G39-UY7z4x5lIK_BhVFkxba6ajGxMp-Kdfa0oxstKmWVexjeyUFIsNj57Ic6sHMHzz_LkZxQFgZrHbJpaXFVRpUT0ba_X-Qj1J4Zb_30vFnirE4fqIEzi8rcSSxRx5B5EXIiUZVt_6BLQKnf8HMn4JyELY35xo6Fz-BfeiVp-kUgS7izt8318JbMJ9fUjRtWNSJCaeFg3FFNwtYoIHtQAorKBVdxeH4FYr3r2T8F-34pcBNohVNL6UxMHsl937Upxnk_iviBjcZ6FXnQBflERvw6bTtLyyZMmaLbnnvbTmd0PG5IwrpXqkioW5h-MyFdEIMftguX2D1vJGX32J_96X4a3mYzmYWzWQmh_7PE_ATmB5W1asyRaKEz8Wmd3NvIGPidPmnpIS9rghXWd8wjYyfz33J0F02t3-8cJpYNRqwKrZrxpcoXlytmHdfKTsc9ku0P3ox-X67vdqwLB0LrR2dPGO2wraAK_IwKdw-GbQHn1s8g43uzZHtqID6boWtJeiRiZ3Dt6SWJ--lPPJtAdWWQSnZPROY5v57iS7iaz3-3H9MTuChlKfRpG7V22dnwyUbnpLsn1jDH93UK0r8NXFSz12JxJjje2umD7HqBSnqaxsXhraWLIaTiO72Wq2Ym1o-et6EYoAipG8a4DfNfCUpyf8MWtUav7pu3ala7xk8LDuCemD2jHlNyxnp5WoH5uRXt-AJCyc2pZs3oYq5vHMyXAYuNdOzwf5Y9i6VaMvCy24FbUNN_u3zl05QcMdzPosjkvsHeRv1jSZXGgh8fSVL_XsoC9b0Myi71r1vB5PQGQipEEpxg1O2Iz9axHcgnu6YVjpKD7sihxKwyuMAD0e0YlMdDJZkeFUUSHG6C93eIuec1RAQjMf65qInhoojrlHxZ39u-uI4KQWd4cvm1xhnoN0am66r5ratcODTr8=",
"id": "rs_051a8a0b2fb58918016a14a0b27ee48191bb018ee5fedb6f77",
"summary": []
}
],
"tool_calls": [
{
"id": "call_WyS6jhYf6ns2ct1bzpV9jzZp",
"call_id": "call_WyS6jhYf6ns2ct1bzpV9jzZp",
"response_item_id": "fc_051a8a0b2fb58918016a14a0b4bb70819182f6e09c458e18ce",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\",\"id\":\"rerender\",\"status\":\"completed\"},{\"content\":\"Dauer, Captions, Contact Sheet und Fazit prüfen\",\"id\":\"qa\",\"status\":\"in_progress\"}]}"
}
}
]
},
{
"role": "tool",
"name": "todo",
"content": "{\"todos\": [{\"id\": \"revise-script\", \"content\": \"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\", \"status\": \"completed\"}, {\"id\": \"rerender\", \"content\": \"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\", \"status\": \"completed\"}, {\"id\": \"qa\", \"content\": \"Dauer, Captions, Contact Sheet und Fazit prüfen\", \"status\": \"in_progress\"}, {\"id\": \"deliver\", \"content\": \"Revidierte Preview und kurze Begründung liefern\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 1, \"in_progress\": 1, \"completed\": 2, \"cancelled\": 0}}",
"tool_call_id": "call_WyS6jhYf6ns2ct1bzpV9jzZp"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_3ZlYHWiO837jAB6KdhbA5lcz",
"call_id": "call_3ZlYHWiO837jAB6KdhbA5lcz",
"response_item_id": "fc_051a8a0b2fb58918016a14a0bcec488191a501e43ee4b25e3b",
"type": "function",
"function": {
"name": "vision_analyze",
"arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\",\"question\":\"Prüfe die revidierte Contact Sheet: Sind Captions lesbar/nicht abgeschnitten? Ist das neue Ende verständlicher (Close invite, open normal app/bookmark, if real it appears there)? Gibt es echte Daten/Logos/QR-Codes?\"}"
}
},
{
"id": "call_6AXRdwtDQEu7SKQlVYSlzwOw",
"call_id": "call_6AXRdwtDQEu7SKQlVYSlzwOw",
"response_item_id": "fc_051a8a0b2fb58918016a14a0bced988191b901080e6d43d353",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"limit\":120,\"path\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\"}"
}
},
{
"id": "call_45Qf3dcOecG362T8nIXtuPEF",
"call_id": "call_45Qf3dcOecG362T8nIXtuPEF",
"response_item_id": "fc_051a8a0b2fb58918016a14a0bcedac8191bf898e2af9d6fcd0",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4 && sha256sum /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\",\"timeout\":30}"
}
}
]
},
{
"role": "tool",
"name": "vision_analyze",
"content": [
{
"type": "text",
"text": "Image loaded into your context — you can see it natively now. Use your built-in vision to answer the user.\n\nQuestion: Prüfe die revidierte Contact Sheet: Sind Captions lesbar/nicht abgeschnitten? Ist das neue Ende verständlicher (Close invite, open normal app/bookmark, if real it appears there)? Gibt es echte Daten/Logos/QR-Codes?"
},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64,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"
}
}
],
"tool_call_id": "call_3ZlYHWiO837jAB6KdhbA5lcz"
},
{
"role": "tool",
"name": "read_file",
"content": "{\"content\": \" 1|{\\n 2| \\\"caption_sync_source\\\": \\\"edge_tts_word_boundary_offsets\\\",\\n 3| \\\"static_phrase_active_word\\\": true,\\n 4| \\\"min_words_default\\\": 3,\\n 5| \\\"target_words\\\": 5,\\n 6| \\\"max_words\\\": 7,\\n 7| \\\"one_word_segments\\\": [],\\n 8| \\\"one_word_segment_count\\\": 0,\\n 9| \\\"duration_seconds\\\": 41.852,\\n 10| \\\"audio_duration_seconds\\\": 41.352,\\n 11| \\\"word_cue_count\\\": 95,\\n 12| \\\"segment_count\\\": 20,\\n 13| \\\"safe_zone\\\": \\\"bottom caption, no box/bar, tested via contact sheet\\\",\\n 14| \\\"summary_fazit_present\\\": true,\\n 15| \\\"final_solution\\\": \\\"Close the invite; open the calendar/work app via the normal icon or trusted bookmark; if the meeting is real, it will still be there.\\\"\\n 16|}\", \"total_lines\": 15, \"file_size\": 595, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_6AXRdwtDQEu7SKQlVYSlzwOw"
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"{\\n \\\"programs\\\": [\\n\\n ],\\n \\\"streams\\\": [\\n {\\n \\\"codec_type\\\": \\\"video\\\",\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"r_frame_rate\\\": \\\"24/1\\\"\\n },\\n {\\n \\\"codec_type\\\": \\\"audio\\\",\\n \\\"r_frame_rate\\\": \\\"0/0\\\"\\n }\\n ],\\n \\\"format\\\": {\\n \\\"duration\\\": \\\"41.875000\\\",\\n \\\"size\\\": \\\"1476729\\\"\\n }\\n}\\nfafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_45Qf3dcOecG362T8nIXtuPEF"
},
{
"role": "assistant",
"content": "",
"reasoning": "**Fixing contact sheet issues**\n\nI see that the contact sheet needs to include a final frame; there’s this bug with min(duration-0.4, 32). There’s also a concern about overlapping captions at certain frames—especially frames 23 and 28, where the card overlays captions. The sample times need to be fixed to capture the end, and I’ll need to check rendering just 9 frames. I might also want to patch and rerun the sample times for better clarity.",
"finish_reason": "tool_calls",
"reasoning_content": "**Fixing contact sheet issues**\n\nI see that the contact sheet needs to include a final frame; there’s this bug with min(duration-0.4, 32). There’s also a concern about overlapping captions at certain frames—especially frames 23 and 28, where the card overlays captions. The sample times need to be fixed to capture the end, and I’ll need to check rendering just 9 frames. I might also want to patch and rerun the sample times for better clarity.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKDIKUK-um6VTmnIIKyf2WUFQJgc48xpPRB5rzF8wo8tKLsTgzcIbCP_1TWOVUA3Un3HgLkgDIUrn6j68rFGOkqp0qU3io8TqbsD_zCXmVeF6okByqJ4a9aJKiB1IGIHIt4uBjUBJYiwwIIMLePS549XL9lbaNcGUzR5BccUhEf7qo1bux9FmzWR1KShL7HDm2OWRuekpjnCUsuUxfACoTJauTI1jg-LLCRnORJZ3zWNix9o4nnKtRlXeHCM2c1vEWGM95iueoZJ8uR43yN3SyOJpMPuNOzPR9co2w4h_igXWl02jc5b3wTXouQCwwycHog8DXtc4GJMng2khthWbMOHJaxR6fno8dbrVz0Dq1NS6NDRqBzVh9XfTElk80Zy7jwl0-e9qFKgeK5nX1c4TMl8GoXJKMOBcN8Iae_YoM48plKBXPRvg66fLdKBDZT4cG1DhfrMuzK9pSXZO_0b7f3DpTAWYicuP8xJDGAtFWlEx9P7BeaveYe-rOeNiOg2iytD02CfwFnit2n4ChzsT2Qc-p7WillfQlcXaR-4tkaVx7yMOye7bQ7DrbhuyK_mkNzRKHszwmdE1-pMvHAvcTWjweBdwhHKgENw95-vGx9euGBP2Pk3UHKnf3OJnrMVikv0Dm8llEirPMxIn2Gbj4wS5OY51RhIsozk3DMMtAZuTKqxqr-19Nk0E7PMZo7TLEgNHlo5H_7jvSxwtWa1T6BvKjVPEwMpC6ywNrh8_tsWmV11snQXgHq1BeEe-L3vtjA4JqD2KfYFBGON9r3fzUwtefXO0gTYSb14LqPhIe2hW3z6R7EYco4zcnbvU8B0u_QxIuwCRfvq5tj8-CcX313UWj8khzZBmgEo22sPJss1QKJb8JfwfJF21g7E8zmkDlWqshfMiv-g_FqKklUvPUZ8THQJeMG4X9Obs2wQbedjS1Wi1CK_BxwuIkT0HMgZsJW2zk--U0l9H1RwBsGpCOg9LEmi6UVBQKwnI-4aZLy0yY3R1jR-mH8RQ5A7vqXqAKEaTsXeibUm7fg79LLZxVibnUnUawr0xoaoD0n-piKruA2582ruk-ENZrie8IhBJRCnF-Y5H7zcpaSz50aoBssNXSUd9ED2po4lCv2XqHpM2eUkaIH6kr0TQz0P_Im2FHr26zC_JRKLEW6x9O5t01ZRdaYKaFve4hZjSUWPvRDa52UqPlufLUF8XLdaDOmTPlGNHON5c7Ngs1Gcg26sXXWG1MEnEn18Ne8cl5gEXRJnPnKyW2fG552W6J1SKSJ6S8zK1R6Q4qvjwT4lzHS2w_EsKL4XBK6HFLET56ANtnbWY_2aQkNmZIlPVk-H5Me2xXqYf9MQLf4mDjUMYA0pfCTnrxevRxxkftyjKOHv-WQInqCO6gV-vlqb_YwpTpO03-pkVt8AeFQmRf2PwhUXarYnVIaXFfzFR6GGgWgbMTGNg94KphZs7_61BAu8t4-RKo56Et5i20hFPldEgvtorEJe_vQgUgEfAmFjg1WdM7V1Yo6LWz05Eb92qisT4aHVHZtgUstRrFz7eRVgUt98_ySIGB96XSdlO1HG4sG9ESqN4B-jpukVfaDHw0Cz_O9tBZrPxjZ1FEwwIzKnLWIMH6gCdR9BT6N1GcFIYZC3Q46c849_YLYZHFxalrU33fVHl4MXuRY-lquBem8Y_1FVhZ2rlWYzJvBZvGR16Ja__cGdaFkpnOc8vOpC3PrMY6NXrwVvU1r96OlnzLzQ-WMBkSDqeWBwDIKlCA7krVViaSa1zQXDKgbquFTmb0vK_R03Ik3CSeXM99ePPTayZtt8JzH6MRScRijwCdW4GRpJ0CLxEKXTQwxeFovYqVgxnEYGAyhHIXBLn2dcWa-gKsvQ4PlRypIz2My1gYai5EKW5EZ3W7RsBE-qmZaSokVEm0CLz3aPqH4QcWFUh0AmBt1EmHfza4vmJszjrdmATFTDY0P1zY1G9EdgRTrxp4kwuT40FflE1Pwj3CIZAVjRF_4MmNTqRmSXDMcD-Wxi7Qw-wQ678WPcKXuyHMUmn4RbMXKMgX9wX-2rlMcf3UPIDhZuDt-kOAhK64J4lRa9j0bRneT-Bk0=",
"id": "rs_051a8a0b2fb58918016a14a0c2f12c8191a17cb5d452fcf354",
"summary": [
{
"type": "summary_text",
"text": "**Fixing contact sheet issues**\n\nI see that the contact sheet needs to include a final frame; there’s this bug with min(duration-0.4, 32). There’s also a concern about overlapping captions at certain frames—especially frames 23 and 28, where the card overlays captions. The sample times need to be fixed to capture the end, and I’ll need to check rendering just 9 frames. I might also want to patch and rerun the sample times for better clarity."
}
]
}
],
"tool_calls": [
{
"id": "call_JaWJdEcIN3fVe0Vh0MmOhY2M",
"call_id": "call_JaWJdEcIN3fVe0Vh0MmOhY2M",
"response_item_id": "fc_051a8a0b2fb58918016a14a0c8257c8191852ce6ed1fe8164d",
"type": "function",
"function": {
"name": "patch",
"arguments": "{\"new_string\":\" sample_times = [1,4,8,12,16,19,23,30,min(duration-0.4,40.8)]\",\"old_string\":\" sample_times = [1,4,8,12,16,19,23,28,min(duration-0.4,32)]\",\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"}"
}
}
]
},
{
"role": "tool",
"name": "patch",
"content": "{\"success\": true, \"diff\": \"--- a//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n+++ b//tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\\n@@ -267,7 +267,7 @@\\n # Preserve video duration; do not use -shortest.\\n subprocess.run(['ffmpeg','-y','-i',str(silent),'-i',str(audio_path),'-c:v','copy','-c:a','aac','-map','0:v:0','-map','1:a:0',str(final)], check=True)\\n \\n- sample_times = [1,4,8,12,16,19,23,28,min(duration-0.4,32)]\\n+ sample_times = [1,4,8,12,16,19,23,30,min(duration-0.4,40.8)]\\n thumbs=[]\\n for ts in sample_times:\\n im = draw_frame(ts, word_cues, segments)\\n\", \"files_modified\": [\"/tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\"], \"lint\": {\"status\": \"ok\", \"output\": \"\"}}",
"tool_call_id": "call_JaWJdEcIN3fVe0Vh0MmOhY2M"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_kpM5nVEYQTbSsKa4ToqMT5sH",
"call_id": "call_kpM5nVEYQTbSsKa4ToqMT5sH",
"response_item_id": "fc_051a8a0b2fb58918016a14a0cd34d881919f9805154be8fe9b",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_calendar_invite_preview_v1.py\",\"timeout\":600}"
}
}
]
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"ffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, rawvideo, from 'fd:':\\n Duration: N/A, start: 0.000000, bitrate: 1194393 kb/s\\n Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 1080x1920, 1194393 kb/s, 24 tbr, 24 tbn\\nStream mapping:\\n Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x572e35f433c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x572e35f433c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x572e35f433c0] 264 - core 164 r3108 31e19f9 - H.264/MPEG-4 AVC codec - Copyleft 2003-2023 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=9 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n encoder : Lavf60.16.100\\n Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1080x1920, q=2-31, 24 fps, 12288 tbn\\n Metadata:\\n encoder : Lavc60.31.102 libx264\\n Side data:\\n cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\\nframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 0 fps=0.0 q=0.0 size= 0kB time=N/A bitrate=N/A speed=N/A \\rframe= 4 fps=1.3 q=25.0 size= 0kB time=00:00:00.08 bitrate= 4.6kbits/s speed=0.0263x \\rframe= 14 fps=3.8 q=25.0 size= 0kB time=00:00:00.50 bitrate= 0.8kbits/s speed=0.134x \\rframe= 24 fps=5.6 q=25.0 size= 0kB time=00:00:00.91 bitrate= 0.4kbits/s speed=0.216x \\rframe= 33 fps=6.9 q=25.0 size= 0kB time=00:00:01.29 bitrate= 0.3kbits/s speed=0.272x \\rframe= 43 fps=8.1 q=25.0 size= 0kB time=00:00:01.70 bitrate= 0.2kbits/s speed=0.322x \\rframe= 53 fps=9.1 q=25.0 size= 0kB time=00:00:02.12 bitrate= 0.2kbits/s speed=0.363x \\rframe= 62 fps=9.8 q=25.0 size= 0kB time=00:00:02.50 bitrate= 0.2kbits/s speed=0.394x \\rframe= 71 fps= 10 q=25.0 size= 0kB time=00:00:02.87 bitrate= 0.1kbits/s speed=0.418x \\rframe= 82 fps= 11 q=25.0 size= 0kB time=00:00:03.33 bitrate= 0.1kbits/s speed=0.451x \\rframe= 93 fps= 12 q=25.0 size= 0kB time=00:00:03.79 bitrate= 0.1kbits/s speed=0.48x \\rframe= 104 fps= 12 q=25.0 size= 0kB time=00:00:04.25 bitrate= 0.1kbits/s speed=0.504x \\rframe= 115 fps= 13 q=25.0 size= 0kB time=00:00:04.70 bitrate= 0.1kbits/s speed=0.525x \\rframe= 127 fps= 13 q=25.0 size= 0kB time=00:00:05.16 bitrate= 0.1kbits/s speed=0.544x \\rframe= 137 fps= 14 q=25.0 size= 0kB time=00:00:05.62 bitrate= 0.1kbits/s speed=0.561x \\rframe= 149 fps= 14 q=25.0 size= 0kB time=00:00:06.08 bitrate= 0.1kbits/s speed=0.577x \\rframe= 159 fps= 14 q=25.0 size= 0kB time=00:00:06.54 bitrate= 0.1kbits/s speed=0.591x \\rframe= 170 fps= 15 q=25.0 size= 0kB time=00:00:07.00 bitrate= 0.1kbits/s speed=0.603x \\rframe= 179 fps= 15 q=25.0 size= 0kB time=00:00:07.37 bitrate= 0.1kbits/s speed=0.609x \\rframe= 188 fps= 15 q=25.0 size= 0kB time=00:00:07.75 bitrate= 0.0kbits/s speed=0.613x \\rframe= 197 fps= 15 q=25.0 size= 0kB time=00:00:08.12 bitrate= 0.0kbits/s speed=0.616x \\rframe= 206 fps= 15 q=25.0 size= 0kB time=00:00:08.50 bitrate= 0.0kbits/s speed=0.618x \\rframe= 215 fps= 15 q=25.0 size= 0kB time=00:00:08.87 bitrate= 0.0kbits/s speed=0.621x \\rframe= 224 fps= 15 q=25.0 size= 0kB time=00:00:09.25 bitrate= 0.0kbits/s speed=0.622x \\rframe= 233 fps= 15 q=25.0 size= 0kB time=00:00:09.62 bitrate= 0.0kbits/s speed=0.625x \\rframe= 242 fps= 15 q=22.0 size= 0kB time=00:00:10.00 bitrate= 0.0kbits/s speed=0.627x \\rframe= 251 fps= 15 q=25.0 size= 0kB time=00:00:10.37 bitrate= 0.0kbits/s speed=0.63x \\rframe= 260 fps= 15 q=25.0 size= 256kB time=00:00:10.75 bitrate= 195.1kbits/s speed=0.632x \\rframe= 269 fps= 15 q=25.0 size= 256kB time=00:00:11.12 bitrate= 188.5kbits/s speed=0.634x \\rframe= 277 fps= 15 q=25.0 size= 256kB time=00:00:11.45 bitrate= 183.1kbits/s speed=0.634x \\rframe= 286 fps= 15 q=25.0 size= 256kB time=00:00:11.83 bitrate= 177.3kbits/s speed=0.636x \\rframe= 294 fps= 15 q=25.0 size= 256kB time=00:00:12.16 bitrate= 172.4kbits/s speed=0.636x \\rframe= 303 fps= 15 q=25.0 size= 256kB time=00:00:12.54 bitrate= 167.2kbits/s speed=0.637x \\rframe= 313 fps= 15 q=25.0 size= 256kB time=00:00:12.95 bitrate= 161.9kbits/s speed=0.641x \\rframe= 324 fps= 16 q=25.0 size= 256kB time=00:00:13.41 bitrate= 156.3kbits/s speed=0.647x \\rframe= 335 fps= 16 q=25.0 size= 256kB time=00:00:13.87 bitrate= 151.2kbits/s speed=0.653x \\rframe= 346 fps= 16 q=25.0 size= 256kB time=00:00:14.33 bitrate= 146.3kbits/s speed=0.657x \\rframe= 356 fps= 16 q=25.0 size= 256kB time=00:00:14.75 bitrate= 142.2kbits/s speed=0.661x \\rframe= 366 fps= 16 q=25.0 size= 256kB time=00:00:15.16 bitrate= 138.3kbits/s speed=0.664x \\rframe= 377 fps= 16 q=25.0 size= 256kB time=00:00:15.58 bitrate= 134.6kbits/s speed=0.667x \\rframe= 386 fps= 16 q=25.0 size= 256kB time=00:00:16.00 bitrate= 131.1kbits/s speed=0.67x \\rframe= 394 fps= 16 q=25.0 size= 256kB time=00:00:16.33 bitrate= 128.4kbits/s speed=0.67x \\rframe= 403 fps= 16 q=25.0 size= 256kB time=00:00:16.70 bitrate= 125.5kbits/s speed=0.671x \\rframe= 412 fps= 16 q=25.0 size= 256kB time=00:00:17.08 bitrate= 122.8kbits/s speed=0.672x \\rframe= 421 fps= 16 q=25.0 size= 256kB time=00:00:17.45 bitrate= 120.1kbits/s speed=0.674x \\rframe= 431 fps= 16 q=25.0 size= 256kB time=00:00:17.83 bitrate= 117.6kbits/s speed=0.675x \\rframe= 439 fps= 16 q=25.0 size= 256kB time=00:00:18.20 bitrate= 115.2kbits/s speed=0.676x \\rframe= 448 fps= 16 q=25.0 size= 256kB time=00:00:18.58 bitrate= 112.9kbits/s speed=0.677x \\rframe= 457 fps= 16 q=25.0 size= 256kB time=00:00:18.95 bitrate= 110.6kbits/s speed=0.678x \\rframe= 466 fps= 16 q=25.0 size= 256kB time=00:00:19.33 bitrate= 108.5kbits/s speed=0.679x \\rframe= 475 fps= 16 q=25.0 size= 256kB time=00:00:19.70 bitrate= 106.4kbits/s speed=0.68x \\rframe= 485 fps= 16 q=25.0 size= 256kB time=00:00:20.12 bitrate= 104.2kbits/s speed=0.681x \\rframe= 495 fps= 16 q=25.0 size= 256kB time=00:00:20.54 bitrate= 102.1kbits/s speed=0.683x \\rframe= 504 fps= 16 q=25.0 size= 512kB time=00:00:20.91 bitrate= 200.5kbits/s speed=0.684x \\rframe= 513 fps= 16 q=25.0 size= 512kB time=00:00:21.29 bitrate= 197.0kbits/s speed=0.684x \\rframe= 520 fps= 16 q=25.0 size= 512kB time=00:00:21.58 bitrate= 194.3kbits/s speed=0.681x \\rframe= 528 fps= 16 q=25.0 size= 512kB time=00:00:21.91 bitrate= 191.4kbits/s speed=0.681x \\rframe= 536 fps= 16 q=25.0 size= 512kB time=00:00:22.25 bitrate= 188.5kbits/s speed=0.68x \\rframe= 544 fps= 16 q=25.0 size= 512kB time=00:00:22.58 bitrate= 185.7kbits/s speed=0.679x \\rframe= 552 fps= 16 q=25.0 size= 512kB time=00:00:22.91 bitrate= 183.0kbits/s speed=0.678x \\rframe= 561 fps= 16 q=25.0 size= 512kB time=00:00:23.25 bitrate= 180.4kbits/s speed=0.678x \\rframe= 570 fps= 16 q=25.0 size= 512kB time=00:00:23.62 bitrate= 177.6kbits/s speed=0.678x \\rframe= 579 fps= 16 q=25.0 size= 512kB time=00:00:24.00 bitrate= 174.8kbits/s speed=0.678x \\rframe= 588 fps= 16 q=25.0 size= 512kB time=00:00:24.37 bitrate= 172.1kbits/s speed=0.678x \\rframe= 597 fps= 16 q=25.0 size= 512kB time=00:00:24.75 bitrate= 169.5kbits/s speed=0.678x \\rframe= 606 fps= 16 q=25.0 size= 512kB time=00:00:25.12 bitrate= 167.0kbits/s speed=0.679x \\rframe= 615 fps= 16 q=25.0 size= 512kB time=00:00:25.50 bitrate= 164.5kbits/s speed=0.679x \\rframe= 624 fps= 16 q=25.0 size= 512kB time=00:00:25.87 bitrate= 162.1kbits/s speed=0.679x \\rframe= 633 fps= 16 q=25.0 size= 512kB time=00:00:26.25 bitrate= 159.8kbits/s speed=0.68x \\rframe= 642 fps= 16 q=25.0 size= 512kB time=00:00:26.62 bitrate= 157.5kbits/s speed=0.68x \\rframe= 650 fps= 16 q=25.0 size= 512kB time=00:00:27.00 bitrate= 155.4kbits/s speed=0.681x \\rframe= 660 fps= 16 q=25.0 size= 512kB time=00:00:27.37 bitrate= 153.2kbits/s speed=0.681x \\rframe= 668 fps= 16 q=25.0 size= 512kB time=00:00:27.75 bitrate= 151.2kbits/s speed=0.682x \\rframe= 678 fps= 16 q=25.0 size= 512kB time=00:00:28.16 bitrate= 148.9kbits/s speed=0.683x \\rframe= 687 fps= 16 q=25.0 size= 512kB time=00:00:28.54 bitrate= 147.0kbits/s speed=0.684x \\rframe= 696 fps= 16 q=25.0 size= 512kB time=00:00:28.91 bitrate= 145.1kbits/s speed=0.684x \\rframe= 705 fps= 16 q=25.0 size= 512kB time=00:00:29.29 bitrate= 143.2kbits/s speed=0.684x \\rframe= 713 fps= 16 q=25.0 size= 512kB time=00:00:29.62 bitrate= 141.6kbits/s speed=0.683x \\rframe= 722 fps= 16 q=25.0 size= 512kB time=00:00:30.00 bitrate= 139.8kbits/s speed=0.683x \\rframe= 731 fps= 16 q=25.0 size= 512kB time=00:00:30.37 bitrate= 138.1kbits/s speed=0.683x \\rframe= 740 fps= 16 q=25.0 size= 512kB time=00:00:30.75 bitrate= 136.4kbits/s speed=0.684x \\rframe= 749 fps= 16 q=25.0 size= 768kB time=00:00:31.12 bitrate= 202.1kbits/s speed=0.684x \\rframe= 758 fps= 16 q=25.0 size= 768kB time=00:00:31.50 bitrate= 199.7kbits/s speed=0.684x \\rframe= 766 fps= 16 q=25.0 size= 768kB time=00:00:31.83 bitrate= 197.6kbits/s speed=0.684x \\rframe= 774 fps= 16 q=25.0 size= 768kB time=00:00:32.16 bitrate= 195.6kbits/s speed=0.684x \\rframe= 782 fps= 16 q=25.0 size= 768kB time=00:00:32.50 bitrate= 193.6kbits/s speed=0.684x \\rframe= 792 fps= 16 q=25.0 size= 768kB time=00:00:32.91 bitrate= 191.1kbits/s speed=0.684x \\rframe= 801 fps= 16 q=25.0 size= 768kB time=00:00:33.29 bitrate= 189.0kbits/s speed=0.685x \\rframe= 811 fps= 16 q=25.0 size= 768kB time=00:00:33.70 bitrate= 186.7kbits/s speed=0.686x \\rframe= 823 fps= 17 q=25.0 size= 768kB time=00:00:34.20 bitrate= 183.9kbits/s speed=0.689x \\rframe= 835 fps= 17 q=25.0 size= 768kB time=00:00:34.70 bitrate= 181.3kbits/s speed=0.691x \\rframe= 846 fps= 17 q=25.0 size= 768kB time=00:00:35.16 bitrate= 178.9kbits/s speed=0.693x \\rframe= 857 fps= 17 q=25.0 size= 768kB time=00:00:35.62 bitrate= 176.6kbits/s speed=0.695x \\rframe= 868 fps= 17 q=25.0 size= 768kB time=00:00:36.08 bitrate= 174.4kbits/s speed=0.697x \\rframe= 879 fps= 17 q=25.0 size= 768kB time=00:00:36.54 bitrate= 172.2kbits/s speed=0.698x \\rframe= 890 fps= 17 q=25.0 size= 768kB time=00:00:37.00 bitrate= 170.0kbits/s speed= 0.7x \\rframe= 900 fps= 17 q=25.0 size= 768kB time=00:00:37.41 bitrate= 168.2kbits/s speed=0.701x \\rframe= 913 fps= 17 q=25.0 size= 768kB time=00:00:37.95 bitrate= 165.8kbits/s speed=0.704x \\rframe= 926 fps= 17 q=25.0 size= 768kB time=00:00:38.50 bitrate= 163.4kbits/s speed=0.707x \\rframe= 939 fps= 17 q=25.0 size= 768kB time=00:00:39.04 bitrate= 161.2kbits/s speed=0.71x \\rframe= 952 fps= 17 q=25.0 size= 1024kB time=00:00:39.54 bitrate= 212.2kbits/s speed=0.712x \\r[out#0/mp4 @ 0x572e35f41d00] video:1096kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.150792%\\nframe= 1005 fps= 18 q=-1.0 Lsize= 1109kB time=00:00:41.75 bitrate= 217.6kbits/s speed=0.748x \\n[libx264 @ 0x572e35f433c0] frame I:5 Avg QP:14.33 size: 60194\\n[libx264 @ 0x572e35f433c0] frame P:253 Avg QP:17.88 size: 2518\\n[libx264 @ 0x572e35f433c0] frame B:747 Avg QP:22.70 size: 246\\n[libx264 @ 0x572e35f433c0] consecutive B-frames: 0.9% 0.0% 0.0% 99.1%\\n[libx264 @ 0x572e35f433c0] mb I I16..4: 65.9% 18.5% 15.6%\\n[libx264 @ 0x572e35f433c0] mb P I16..4: 0.6% 0.1% 0.3% P16..4: 4.0% 0.2% 0.1% 0.0% 0.0% skip:94.7%\\n[libx264 @ 0x572e35f433c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 2.3% 0.0% 0.0% direct: 0.0% skip:97.6% L0:54.9% L1:45.0% BI: 0.1%\\n[libx264 @ 0x572e35f433c0] 8x8 transform intra:18.3% inter:41.5%\\n[libx264 @ 0x572e35f433c0] coded y,uvDC,uvAC intra: 14.1% 15.7% 11.5% inter: 0.1% 0.1% 0.0%\\n[libx264 @ 0x572e35f433c0] i16 v,h,dc,p: 28% 72% 0% 0%\\n[libx264 @ 0x572e35f433c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 45% 13% 39% 2% 0% 0% 0% 0% 0%\\n[libx264 @ 0x572e35f433c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 34% 41% 8% 2% 3% 3% 3% 2% 3%\\n[libx264 @ 0x572e35f433c0] i8c dc,h,v,p: 69% 19% 12% 1%\\n[libx264 @ 0x572e35f433c0] Weighted P-Frames: Y:0.0% UV:0.0%\\n[libx264 @ 0x572e35f433c0] ref P L0: 85.9% 1.2% 9.4% 3.4%\\n[libx264 @ 0x572e35f433c0] ref B L0: 61.0% 37.9% 1.2%\\n[libx264 @ 0x572e35f433c0] ref B L1: 97.4% 2.6%\\n[libx264 @ 0x572e35f433c0] kb/s:214.37\\nffmpeg version 6.1.1-3ubuntu5 Copyright (c) 2000-2023 the FFmpeg developers\\n built with gcc 13 (Ubuntu 13.2.0-23ubuntu3)\\n configuration: --prefix=/usr --extra-version=3ubuntu5 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --disable-omx --enable-gnutls --enable-libaom --enable-libass --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libharfbuzz --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-openal --enable-opencl --enable-opengl --disable-sndio --enable-libvpl --disable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-ladspa --enable-libbluray --enable-libjack --enable-libpulse --enable-librabbitmq --enable-librist --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libx264 --enable-libzmq --enable-libzvbi --enable-lv2 --enable-sdl2 --enable-libplacebo --enable-librav1e --enable-pocketsphinx --enable-librsvg --enable-libjxl --enable-shared\\n libavutil 58. 29.100 / 58. 29.100\\n libavcodec 60. 31.102 / 60. 31.102\\n libavformat 60. 16.100 / 60. 16.100\\n libavdevice 60. 3.100 / 60. 3.100\\n libavfilter 9. 12.100 / 9. 12.100\\n libswscale 7. 5.100 / 7. 5.100\\n libswresample 4. 12.100 / 4. 12.100\\n libpostproc 57. 3.100 / 57. 3.100\\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Duration: 00:00:41.88, start: 0.000000, bitrate: 216 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 214 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n[mp3 @ 0x5de41309bf00] Estimating duration from bitrate, this may be inaccurate\\nInput #1, mp3, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3':\\n Duration: 00:00:41.35, start: 0.000000, bitrate: 48 kb/s\\n Stream #1:0: Audio: mp3, 24000 Hz, mono, fltp, 48 kb/s\\nStream mapping:\\n Stream #0:0 -> #0:0 (copy)\\n Stream #1:0 -> #0:1 (mp3 (mp3float) -> aac (native))\\nPress [q] to stop, [?] for help\\nOutput #0, mp4, to '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4':\\n Metadata:\\n major_brand : isom\\n minor_version : 512\\n compatible_brands: isomiso2avc1mp41\\n encoder : Lavf60.16.100\\n Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, q=2-31, 214 kb/s, 24 fps, 24 tbr, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 libx264\\n Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 69 kb/s\\n Metadata:\\n encoder : Lavc60.31.102 aac\\nsize= 0kB time=N/A bitrate=N/A speed=N/A \\rsize= 1280kB time=00:00:38.70 bitrate= 270.9kbits/s speed=77.4x \\r[out#0/mp4 @ 0x5de41309c6c0] video:1096kB audio:321kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.771788%\\nsize= 1442kB time=00:00:41.75 bitrate= 283.0kbits/s speed=78.5x \\n[aac @ 0x5de41301d540] Qavg: 17882.781\\n{\\n \\\"ok\\\": true,\\n \\\"manifest\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.0.0-word-aligned-proof\\\",\\n \\\"series\\\": \\\"Digital Red Flags\\\",\\n \\\"title\\\": \\\"The calendar invite login trap\\\",\\n \\\"script\\\": \\\"This calendar invite looks normal. The trap is the login button. Same meeting title. Same urgent tone. But the link points somewhere else. Before you sign in, slow down. Check who sent it. Check the link domain. Notice unusual login requests. If the domain feels off, do not sign in from the invite. That means: close the invite. Open your calendar or work app from the icon or bookmark you normally use. If the meeting is real, it will still be there. The rule: trust the path you chose, not the button that chose you.\\\",\\n \\\"script_hash\\\": \\\"0e9ec7f162b69573\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\\\",\\n \\\"preview_sha256\\\": \\\"fafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d\\\",\\n \\\"silent_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned_silent.mp4\\\",\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"audio_sha256\\\": \\\"77c875c19c1197426f2023af3dc5cdf866fba76ffee20bcfa021236aa5665376\\\",\\n \\\"word_cues_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/word_cues.json\\\",\\n \\\"caption_segments_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/caption_segments_word_aligned.json\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\\\",\\n \\\"subtitle_preview_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_subtitle_style_preview_v1.jpg\\\",\\n \\\"qa_summary_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\\\",\\n \\\"duration_seconds\\\": 41.852,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"caption_policy\\\": \\\"static 3-7 word phrase segments with active spoken word highlight from EdgeTTS word boundaries\\\",\\n \\\"blocked\\\": {\\n \\\"wan\\\": true,\\n \\\"i2v\\\": true,\\n \\\"platform_api\\\": true,\\n \\\"posting\\\": true,\\n \\\"scheduling\\\": true\\n }\\n },\\n \\\"review_package\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/review_package_v1_word_aligned.json\\\"\\n}\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_kpM5nVEYQTbSsKa4ToqMT5sH"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"tool_calls": [
{
"id": "call_BTQuvMkIrKDFGovDa1V8NhDL",
"call_id": "call_BTQuvMkIrKDFGovDa1V8NhDL",
"response_item_id": "fc_051a8a0b2fb58918016a14a110556c8191b1e2a7697b6bb795",
"type": "function",
"function": {
"name": "vision_analyze",
"arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\",\"question\":\"Finale QA mit Endframe: Prüfe Lesbarkeit, keine abgeschnittenen Captions, verständlicher Schluss, keine echten Daten/Logos/QR-Codes.\"}"
}
},
{
"id": "call_Emi9FbD4oExzvDBB3FY4ehTW",
"call_id": "call_Emi9FbD4oExzvDBB3FY4ehTW",
"response_item_id": "fc_051a8a0b2fb58918016a14a11055a08191bdbc4f8cf8cc7d9a",
"type": "function",
"function": {
"name": "terminal",
"arguments": "{\"command\":\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4 && sha256sum /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\",\"timeout\":30}"
}
},
{
"id": "call_XGPCVVYAlQCRGXeC55x8IkSw",
"call_id": "call_XGPCVVYAlQCRGXeC55x8IkSw",
"response_item_id": "fc_051a8a0b2fb58918016a14a11055ac8191acb8ca6f09d7244a",
"type": "function",
"function": {
"name": "read_file",
"arguments": "{\"limit\":80,\"path\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/qa_summary_preview_v1.json\"}"
}
}
]
},
{
"role": "tool",
"name": "vision_analyze",
"content": [
{
"type": "text",
"text": "Image loaded into your context — you can see it natively now. Use your built-in vision to answer the user.\n\nQuestion: Finale QA mit Endframe: Prüfe Lesbarkeit, keine abgeschnittenen Captions, verständlicher Schluss, keine echten Daten/Logos/QR-Codes."
},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64,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"
}
}
],
"tool_call_id": "call_BTQuvMkIrKDFGovDa1V8NhDL"
},
{
"role": "tool",
"name": "terminal",
"content": "{\"output\": \"{\\n \\\"programs\\\": [\\n\\n ],\\n \\\"streams\\\": [\\n {\\n \\\"codec_type\\\": \\\"video\\\",\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"r_frame_rate\\\": \\\"24/1\\\"\\n },\\n {\\n \\\"codec_type\\\": \\\"audio\\\",\\n \\\"r_frame_rate\\\": \\\"0/0\\\"\\n }\\n ],\\n \\\"format\\\": {\\n \\\"duration\\\": \\\"41.875000\\\",\\n \\\"size\\\": \\\"1476729\\\"\\n }\\n}\\nfafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\", \"exit_code\": 0, \"error\": null}",
"tool_call_id": "call_Emi9FbD4oExzvDBB3FY4ehTW"
},
{
"role": "tool",
"name": "read_file",
"content": "{\"content\": \" 1|{\\n 2| \\\"caption_sync_source\\\": \\\"edge_tts_word_boundary_offsets\\\",\\n 3| \\\"static_phrase_active_word\\\": true,\\n 4| \\\"min_words_default\\\": 3,\\n 5| \\\"target_words\\\": 5,\\n 6| \\\"max_words\\\": 7,\\n 7| \\\"one_word_segments\\\": [],\\n 8| \\\"one_word_segment_count\\\": 0,\\n 9| \\\"duration_seconds\\\": 41.852,\\n 10| \\\"audio_duration_seconds\\\": 41.352,\\n 11| \\\"word_cue_count\\\": 95,\\n 12| \\\"segment_count\\\": 20,\\n 13| \\\"safe_zone\\\": \\\"bottom caption, no box/bar, tested via contact sheet\\\",\\n 14| \\\"summary_fazit_present\\\": true,\\n 15| \\\"final_solution\\\": \\\"Close the invite; open the calendar/work app via the normal icon or trusted bookmark; if the meeting is real, it will still be there.\\\"\\n 16|}\", \"total_lines\": 15, \"file_size\": 595, \"truncated\": false, \"is_binary\": false, \"is_image\": false}",
"tool_call_id": "call_XGPCVVYAlQCRGXeC55x8IkSw"
},
{
"role": "assistant",
"content": "",
"reasoning": "**Finalizing media presentation**\n\nI need to finalize a concise media piece that mentions 41.9, aiming for clarity even if it takes a bit longer. I also have to note that the contact frame includes the caption \"that chose you\" at the bottom; I’m wondering if that’s acceptable. The final card should be clear, and I should ensure there's no auto posting involved. Lastly, I need to mark my to-dos to keep everything organized.",
"finish_reason": "tool_calls",
"reasoning_content": "**Finalizing media presentation**\n\nI need to finalize a concise media piece that mentions 41.9, aiming for clarity even if it takes a bit longer. I also have to note that the contact frame includes the caption \"that chose you\" at the bottom; I’m wondering if that’s acceptable. The final card should be clear, and I should ensure there's no auto posting involved. Lastly, I need to mark my to-dos to keep everything organized.",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKEbUUjL9XxvA4Zlnh3E07JmszbpSjHy0hivwVU-6TLoc3z4Fg5tjQ49YjbVGjQJrKIFiB1Uy_rKIM9V9YNRscH7HHFMN1s2l9sptLx9N0UQvLSkyUY0m35T3fdkIpNzwxK-ChUJTKGekwAzD9Nj14wJ6wY-kyHjriJeeZT_YU-A3VxrURoKzstIxDveVIqh-TmbsjXdtSAc03zb9r2l5ft1S68cdkcm-Bdy-kXF0rGn8SaZEImcxiln0vVPInY8iCGuQASQ4Q5EiuO4lXiAJKkFVmKC_sxkc73mltWVK9lFwsw-Vstt3XydgSgl5FYpqs_-CXjiaMoBY_J2WM4Pql9fJYy1ceCwP7upmFr4h-WOGtphhNkv_JF2fB82zKYhF-_2il6pk5bZv-Pli9IKwH7P8ukEyy4XTP6JVKUp756AWfMv48NiluO1ISGtvaEycQl0ADmMVM5JfetWfugIeD1stdsVtC7thk7Vg_ybLwfaSWrnX5yZ_1Ty9qbvTIjGiTNbv7Vw30Ql-YOLPx7LiEkge4A7txLzWqPND4K1IcWSFCjMulGEiZt8A8mctfs73qExNFBSdvuT4o9xefjYoXJWQjXJD5AiqIOaWvV49B2bRmapDqudwSzEQz9T0rQKHSAQWY-0CshDm9tuvycLDFx3JtHV-vLNGAKS2wykvftI9GOP1ppPJL8Qo0SYtZEa5D7kazJlqF6hNz5bL1gy9jFvBlGDCaNy31MS-KPFmr9KW4lomcBTKOhpZw3zxwACYW73mJ7lE_SrK13OiQ3VPlmN-j5BPmQrq5HmhP8NAqAwCLZRZgtxZd9YY0eWCrbUWzykFfr3fa1isWWvgy0QUc17p8--GOnYO0z0E0vnWoLRvH_BBfKmMbq7w-fz0_dClfo7XVfYh6IDNO3pZcLAHh1kricU_KWPp4NcbWFuqJAoVUswp8uDCk3Kpoo2SkPH3cQNilBCILqeHcRfk_6RbqcCzqb7u5z2fqEdRcfo_lvzJZUMKYF5JL2LJ6ZUfeH7FqRZPkLcW5BJBEYv7UQp8coGGMleLaR4_ck9NSoLIIg-XVdMCrJz6OBsIkwdGjJaNITGcYohdMVvHoZ_r5u8tO3w1EH2w_rp-ZCozrUYMeHK8__xYZnURateRWS7gcWIbmY27-HQSjA4-dxUXMVU_mFh-K641lm6UdwDZgMu_IjEK_1lRG_sH71C8CaItrSScWwP",
"id": "rs_051a8a0b2fb58918016a14a116d7b481918604c06e855db113",
"summary": [
{
"type": "summary_text",
"text": "**Finalizing media presentation**\n\nI need to finalize a concise media piece that mentions 41.9, aiming for clarity even if it takes a bit longer. I also have to note that the contact frame includes the caption \"that chose you\" at the bottom; I’m wondering if that’s acceptable. The final card should be clear, and I should ensure there's no auto posting involved. Lastly, I need to mark my to-dos to keep everything organized."
}
]
}
],
"tool_calls": [
{
"id": "call_RBlGQhMNtD8FwXTfLW9OpT1p",
"call_id": "call_RBlGQhMNtD8FwXTfLW9OpT1p",
"response_item_id": "fc_051a8a0b2fb58918016a14a11bbcd88191bbc87fc915086c46",
"type": "function",
"function": {
"name": "todo",
"arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Dauer, Captions, Contact Sheet und Fazit prüfen\",\"id\":\"qa\",\"status\":\"completed\"},{\"content\":\"Revidierte Preview und kurze Begründung liefern\",\"id\":\"deliver\",\"status\":\"completed\"}]}"
}
}
]
},
{
"role": "tool",
"name": "todo",
"content": "{\"todos\": [{\"id\": \"revise-script\", \"content\": \"Ende/Erklärung für Calendar-Invite-Video verständlicher formulieren\", \"status\": \"completed\"}, {\"id\": \"rerender\", \"content\": \"Preview mit neuem Voiceover, word-aligned Captions und Fazit neu rendern\", \"status\": \"completed\"}, {\"id\": \"qa\", \"content\": \"Dauer, Captions, Contact Sheet und Fazit prüfen\", \"status\": \"completed\"}, {\"id\": \"deliver\", \"content\": \"Revidierte Preview und kurze Begründung liefern\", \"status\": \"completed\"}], \"summary\": {\"total\": 4, \"pending\": 0, \"in_progress\": 0, \"completed\": 4, \"cancelled\": 0}}",
"tool_call_id": "call_RBlGQhMNtD8FwXTfLW9OpT1p"
},
{
"role": "assistant",
"content": "Ja, völlig richtig. Das alte Ende war zu knapp und setzte voraus, dass der Viewer versteht, was “open the service yourself” bedeutet. Das ist genau der Punkt, an dem man die Leute **abholen** muss — nicht mit einem Security-Mantra erschlagen. Sehr unbritisch von mir. Fast amerikanisch.\n\nIch habe das Ende deshalb neu gebaut und neu gerendert:\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\n\n## Änderung am Ende\n\nAlt:\n\n```text\nOpen the service yourself.\nTrust the app you opened, not the button that rushed you.\n```\n\nNeu:\n\n```text\nThat means: close the invite.\nOpen your calendar or work app from the icon or bookmark you normally use.\nIf the meeting is real, it will still be there.\nThe rule: trust the path you chose, not the button that chose you.\n```\n\n## Warum das besser ist\n\nJetzt ist die Lösung konkret:\n\n1. **Invite schliessen**\n2. **Kalender / Work-App selbst öffnen**\n3. **über normales Icon oder Bookmark**\n4. **wenn der Termin echt ist, ist er dort auch sichtbar**\n5. **nicht dem Button im Invite vertrauen**\n\nDas ist viel klarer für Nicht-Tech-Viewer.\n\n## Neue finale Message\n\n```text\nIf it's real,\nit will be there too.\n\nTrust your normal path.\nNot the button sent to you.\n```\n\n## QA\n\n- Dauer: **41.88s**\n- Resolution: **1080x1920**\n- FPS: **24**\n- Captions: **word-aligned via EdgeTTS WordBoundary**\n- One-word subtitle segments: **0**\n- Ende/Fazit sichtbar: **pass**\n- Keine echten Daten, Logos, QR-Codes: **pass**\n- Posting / Platform API: **nicht ausgeführt**\n\nSHA256:\n\n```text\nfafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d\n```\n\nMein Urteil: **deutlich verständlicher**, aber jetzt eher ein 42s Educational Short als ein knackiger 30s Proof Short. Inhaltlich besser abgeholt; rhythmisch können wir als nächstes noch straffen, ohne die Erklärung wieder zu verlieren.",
"reasoning": null,
"finish_reason": "stop",
"codex_message_items": [
{
"type": "message",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Ja, völlig richtig. Das alte Ende war zu knapp und setzte voraus, dass der Viewer versteht, was “open the service yourself” bedeutet. Das ist genau der Punkt, an dem man die Leute **abholen** muss — nicht mit einem Security-Mantra erschlagen. Sehr unbritisch von mir. Fast amerikanisch.\n\nIch habe das Ende deshalb neu gebaut und neu gerendert:\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap-30s_preview_v1_word_aligned.mp4\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/preview_v1_word_aligned/calendar-invite-login-trap_contact_sheet_v1.jpg\n\n## Änderung am Ende\n\nAlt:\n\n```text\nOpen the service yourself.\nTrust the app you opened, not the button that rushed you.\n```\n\nNeu:\n\n```text\nThat means: close the invite.\nOpen your calendar or work app from the icon or bookmark you normally use.\nIf the meeting is real, it will still be there.\nThe rule: trust the path you chose, not the button that chose you.\n```\n\n## Warum das besser ist\n\nJetzt ist die Lösung konkret:\n\n1. **Invite schliessen**\n2. **Kalender / Work-App selbst öffnen**\n3. **über normales Icon oder Bookmark**\n4. **wenn der Termin echt ist, ist er dort auch sichtbar**\n5. **nicht dem Button im Invite vertrauen**\n\nDas ist viel klarer für Nicht-Tech-Viewer.\n\n## Neue finale Message\n\n```text\nIf it's real,\nit will be there too.\n\nTrust your normal path.\nNot the button sent to you.\n```\n\n## QA\n\n- Dauer: **41.88s**\n- Resolution: **1080x1920**\n- FPS: **24**\n- Captions: **word-aligned via EdgeTTS WordBoundary**\n- One-word subtitle segments: **0**\n- Ende/Fazit sichtbar: **pass**\n- Keine echten Daten, Logos, QR-Codes: **pass**\n- Posting / Platform API: **nicht ausgeführt**\n\nSHA256:\n\n```text\nfafe7bb4c9fd82e1d1eda7978af16b071a12a50299d8bc2af920768377626b4d\n```\n\nMein Urteil: **deutlich verständlicher**, aber jetzt eher ein 42s Educational Short als ein knackiger 30s Proof Short. Inhaltlich besser abgeholt; rhythmisch können wir als nächstes noch straffen, ohne die Erklärung wieder zu verlieren."
}
],
"id": "msg_051a8a0b2fb58918016a14a12032c08191832372b7ec2c3221",
"phase": "final_answer"
}
]
},
{
"role": "user",
"content": "Review the conversation above and update two things:\n\n**Memory**: who the user is. Did the user reveal persona, desires, preferences, personal details, or expectations about how you should behave? Save facts about the user and durable preferences with the memory tool.\n\n**Skills**: how to do this class of task. Be ACTIVE — most sessions produce at least one skill update. A pass that does nothing is a missed learning opportunity, not a neutral outcome.\n\nTarget shape of the skill library: CLASS-LEVEL skills with a rich SKILL.md and a `references/` directory for session-specific detail. Not a long flat list of narrow one-session-one-skill entries.\n\nSignals that warrant a skill update (any one is enough):\n • User corrected your style, tone, format, legibility, verbosity, or approach. Frustration is a FIRST-CLASS skill signal, not just a memory signal. 'stop doing X', 'don't format like this', 'I hate when you Y' — embed the lesson in the skill that governs that task so the next session starts fixed.\n • Non-trivial technique, fix, workaround, or debugging path emerged.\n • A skill that was loaded or consulted turned out wrong, missing, or outdated — patch it now.\n\nPreference order for skills — pick the earliest that fits:\n 1. UPDATE A CURRENTLY-LOADED SKILL. Check what skills were loaded via /skill-name or skill_view in the conversation. If one of them covers the learning, PATCH it first. It was in play; it's the right place.\n 2. UPDATE AN EXISTING UMBRELLA (skills_list + skill_view to find the right one). Patch it.\n 3. ADD A SUPPORT FILE under an existing umbrella via skill_manage action=write_file. Three kinds: `references/.md` for session-specific detail OR condensed knowledge banks (quoted research, API docs excerpts, domain notes) written concise and task-focused; `templates/.` for starter files meant to be copied and modified; `scripts/.` for statically re-runnable actions (verification, fixture generators, probes). Add a one-line pointer in SKILL.md so future agents find them.\n 4. CREATE A NEW CLASS-LEVEL UMBRELLA when nothing exists. Name at the class level — NOT a PR number, error string, codename, library-alone name, or 'fix-X / debug-Y' session artifact. If the name only fits today's task, fall back to (1), (2), or (3).\n\nUser-preference embedding: when the user complains about how you handled a task, update the skill that governs that task — memory alone isn't enough. Memory says 'who the user is and what the current situation and state of your operations are'; skills say 'how to do this class of task for this user'. Both should carry user-preference lessons when relevant.\n\nIf you notice overlapping existing skills, mention it — the background curator handles consolidation.\n\nDo NOT capture as skills (these become persistent self-imposed constraints that bite you later when the environment changes):\n • Environment-dependent failures: missing binaries, fresh-install errors, post-migration path mismatches, 'command not found', unconfigured credentials, uninstalled packages. The user can fix these — they are not durable rules.\n • Negative claims about tools or features ('browser tools do not work', 'X tool is broken', 'cannot use Y from execute_code'). These harden into refusals the agent cites against itself for months after the actual problem was fixed.\n • Session-specific transient errors that resolved before the conversation ended. If retrying worked, the lesson is the retry pattern, not the original failure.\n • One-off task narratives. A user asking 'summarize today's market' or 'analyze this PR' is not a class of work that warrants a skill.\n\nIf a tool failed because of setup state, capture the FIX (install command, config step, env var to set) under an existing setup or troubleshooting skill — never 'this tool does not work' as a standalone constraint.\n\nAct on whichever of the two dimensions has real signal. If genuinely nothing stands out on either, say 'Nothing to save.' and stop — but don't reach for that conclusion as a default.\n\nYou can only call memory and skill management tools. Other tools will be denied at runtime — do not attempt them."
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKFNM1QdoeZWHvBXNQ0MHhaY8ZfUc7es9yNeNogNMsDZJovbYLAYdBrg-7G-ej9UcqEsiIy88NBoqR-cPZeqjwvpPGzAVNKe76GCuR2NfuB28aNOLLulzlAlpL2WcpraIOS1Ajk8lW89nNw7vEeSxLCMN5rSac1Y8ahvUs68z0T7y_HcYtq0eG5n11qNDdJzL1xxJhoj13NSH-uH8y5qsxwOJxsvWwKihfFjhgpKvlL6fSdFHEm_MG07K599-22ASCE4kNCD5pLGHtaB4zVWongSKFQtr026MsuAi8ezVEhURJ4ONZWspLNfxm5ZMGIEkfY0j2WVScx6F5g23B3Qv91_exZunttTKhbgiO7Q0-j6KjRHmmASbGXwViIIiGOGCC2M1tcYedhAbptB_7MrPiEWbmLXGtKbJrKErHShEe-l2cKsYVNvr0XDaKYstIYZoGWaIWAr6eQ4jyYj0bVdoA3F-BPAes8Zot7vB7jQB1pmLMQyhxW_S129OYmq90gP40gL2E6ThZ6oEPeS6PnuCgCyPRL8zK7-iWMFxgrfoQpfI3Ph2FHqOcNQ1minTwVRhP3plYoUwNxgT0Yx0QUAF-wRcHQlJa2aCfGwEk9wbUJS0Um-S4wn9l4gRPESl_gmCzQ3KOE7vxpojJfqiGJoTFf1bOtPCtEqzJT4mbX5L5a9GTehKDMrnMK2fQkrvX3x2ZBoIsZUUT25Cw0tunS_Nbg29uO0IppB-D0zVlx6LWMMM7JqROw5wG9dqnewHczEimvb1TGJu53qw3cn8N3AUE4huo_MepDNMP4XCRApJPILBwvY14Q_nbr9_o_x1zehBlcPNYev2cZQZ0MHlxE4YLXK3vyobvEat1uJim57IyR0et62HMdfV6j5LOk7tdQHGBrkTrM_FBe0UjXavQCfk31dVuaty3THBYpqy7RGcvT12MTYL4E2gXI_ySbu7eQ91_-JYwxLcNQNBN9twg4uAclpPTG6AonrnideNf7u_2MGCZOEjtXEh6Brbd_QSfhQD6hXO6gLEj8PRXNyTNA4epjV1Lxy8KORJPSMAoU9MwVF0zM-QAuytSdiasEV_7jrUiJoQDdpqbFdUSMZVmvgJG7k8GmjY6Yd_OfzLn8LIVy5kDP0yaKmMt1WZgVoD3wBZBQyWDFiyTXcfzMhWfYa6A55itO6a784AFpxofroNkwUdHtBNtQ5moy92hF0tS97yQZH_qizqL_rpnhtsjgmk7A5A-NF5TsrVh1nj-1Is5DnN1-bBJ7dK4AOoihrD-mEjG8rm2lv9OuAnWRvwDc-qat7NTOGLSbKnU-E8prMfMoyLHHm0tRciRjae_njS-VNcaLxulUDXTTzY6zygByQ0_F-5dyTNQ__D5CalAhwi9PH07EXcct5ik1vBM6GzcKiI7AceY9McBkuDkiM74vli118qM-2eUDJnVjhup86iTCcxY97Nf8XsVsDIQ7_vZa8fBndv1pWQR-DhMoEFah0lndo0UDPqfQ9laOMtw35OSo2sHzE2u4JHtOxpIYPwDDFgH5I9BLsOICTNNAHZgDXbfDUXUZNlWi_Lb04r8sZP5BA8iIp-G2tUgb6eLuLRKFkHWk5YuKiABYxVDzSbtk0SPHRoo1HcliiLen4w9Pyw-tddoukKMlTs7-6-tCAdejG7JiWCkbAyZA9YlwdZBr-XNa5Ukyu_W6OSoOj9OrRiAJY-Cl-GHcnYE5Rp7si42x-FNuEkfo2Mvj1FGSi-P0mdxHOPUuETO1QKnGyu4B0TkOnGGNp9jjftxxDzPDUf1ey5fIk-tfjOZ_Iu-bwNkqnjFUvMiwNDjEq_LAecTfP0UF-H77S9epYPSo_VJiF438SiZyvRCtyL1J4S61UMq4UO-jmGMfE2z40nGLgmu0gLS9ozUHvK-zHPWF3_f7wJmXFeFveCdIppw9ibH8LtxIORhtBAjpRlsd76kPbjgFS3NHznseE5cs0Lp4dPvNtxlHlfPPHiwdC_az7oqEFBizlm-srr8XJBtermzK4YEUJLlIf4zl2oTQyI8dKFAP4oBgiyKFigqjvmrTTOg9B5iPBHOxHl1gS28cr5zruiO_qII2xUP6krgvz5RthBqqCeDP3f9acg1u3g8kNhWR39PzuHr6HMDt_yI2HmVJtP0odApRZ80a6e2VREyDlNTHgbxrDNIjNdOxGzGD7V1EulXgv1SeI1uocF5Y3eI-q2CHWUU5ythj-15fgbJ6hbQtqieB6sU6FWj_agxh8GALHeY0jGSeIje9cAx2nAKPquRLmoNM0qilMV-zshLbxPVyoqq6NrI4Ou_FvbsoHHAEvbSC8Mj2dpyWM07UDgrjNmaSF9QVlwqy4bfVehbzj4fgVV0YGlLXgKEDMmANcidrRjh56-0LER_anpAzbOm8qXqXFGmo8h58XCWAhh4d2zxI2AiwxX_oU3H7Ne8ygxNx_4DLZ-o_hHxLhilj6nSHTsNWpv07OQkUBbGADgtk8ZDHnELbFcHY3un7dmYdIrt7F6Xq1QVGA87EPlKayMrJcAAcgNci8c799qN0Vx6-tX4z6dXgdgqpZrW4o-JuNxZRPNTJC5irqrvBiUYe4wJcRpKHw4SEpMrjRuIH27YO8_FbSsZGBCouurvCCiAK1XTVDN5CFSjJvC85vOT_erXGC3g89qZz70IxpGXwPFz41fQz1SRxQuPJX1iM9iqR7FiKUmdSXL-CZz_hi6Er-QmsqiA9taIbRr6NO4ubOTFThgd3w6D9hdF5f98G34v3abP4dMNkMU6-c8_rliR21JkjGjmtiOLB9v7mIV11sp7jhvdU6_eXzvHRkfFsRVUfVTzCMgUsChboHTiruauwVg6-XCOSnKLpC8xY6oSBBIgNzvPjBpEqgWPzl_OjFjYa4D1NpGUR-0-n9KWByIlOr9D-oakgtyKwPSoVRSfbbllM99AKZR1ZYuvLmcTDsr4x74NgKSP7xRimD3prC_6fq47h9biGxRTOSCv-oSOA1mRsVD1lsUtnPX6868jvbu-kCfx1-i5s1OA_OBW6a8xAtNsH07LgbhQ64PqIKCnh9bJBaBJ55dNXi3BVbtsIxlIAatecKxwOqKVw8ltUIsnxYJMLYQgv8fr6pBTtut9th7QUBtWs3n4PGoOPvSPnY61m2yAYeNCLluM7qYAzTNyi53PCkkHoFf7vre-60eXUXS8Vkq-wgNX_EhaTAYbqDI_ukHQ3X2ncf7vjHxhIzgaXO_nW2s8wA-9VxAIARdNHrhXeNgQNx0gDtl8MCbXq22-ktU7uKuoT5jeLnDp-CFDW7pq6woPg2UnbCEsI7ZNkCnAsZ9I1Y-rFptg--pbf6xQHwEsDT3L88nxsNRjF2CX7BaTyY9jDaO6_zwixMDWY_P9DAJ0XIOr3r0UpFm2NUvbTV48D1TzbfvUKpg9UlCp9Mx_0yoEcnkRHb0iaPMUytVLKhyduCO6bKg69aqw6LwV099nPHQamO1yIRIpHzn1wC-OcJMzGQnoZS-tRfM74sUL5uTaZck_mn3l0VhGwp7X3WA-cQVlg8xlZ-V_7Kq8VFhyHMz8I4d_QKYBs=",
"id": "rs_051a8a0b2fb58918016a14a1390a7481918c5b58c703d41550",
"summary": []
}
],
"tool_calls": [
{
"id": "call_7e2pk8MdJtmc6nnxxGXnMjyB",
"call_id": "call_7e2pk8MdJtmc6nnxxGXnMjyB",
"response_item_id": "fc_051a8a0b2fb58918016a14a14d52b881919d6e158793b7a4b1",
"type": "function",
"function": {
"name": "memory",
"arguments": "{\"action\":\"add\",\"target\":\"user\",\"content\":\"AutoShorts/TrueTraceShorts review preference: endings must not be terse or jargon-like; viewers should be explicitly “abgeholt” with concrete next actions and a clear fazit/solution, even if that means slightly more explanation.\"}"
}
}
]
},
{
"role": "tool",
"name": "memory",
"content": "{\"success\": false, \"error\": \"Memory at 1,367/1,375 chars. Adding this entry (228 chars) would exceed the limit. Replace or remove existing entries first.\", \"current_entries\": [\"**Notes:** Mein Herr. Loyaler Partner.\", \"**Name:** Sir\", \"**Voice preference:** de-DE-KillianNeural (German male voice, natural/clear) — default for all TTS output\", \"**Language:** Deutsch mit englischen Fachbegriffen\", \"Kommunikationspräferenzen: **Sprachnachricht → Antwort per Sprachnachricht**\", \"Kommunikationspräferenzen: **Textnachricht → Antwort per Text**\", \"Health advisor role: consolidate labs/clinical reports/YAZIO/daily health email/symptoms/events into dashboards/reports; lab extraction requires 4-eyes review before values are confirmed.\", \"Telegram topic Health-Med: only medical strategy/Behçet/Major Vessel Disease/thrombosis/meds/nutrition/symptoms/labs/doctor questions; health system scripts/data models go to Health-Tech.\", \"Finance/Grocery: no real amounts/IDs/API keys in chat; credentials via runtime files; no DB/CSV/keys/reports in Git/frontend; backups+audit; Preview→Confirm→Audit; no fake prices/buttons; OpenFIGI never show/store; never auto-book; grocery provider calls explicit/cache-first.\", \"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. Positioning: hidden mechanisms, not AI tips; AI 30–40%. Format fail→mechanism→fix→takeaway. Captions static 3–7w phrase with active word highlight. Visuals: premium clean KI-image cuts; avoid labels/arrows/boxes/target markers unless approved; Wan only after approval.\"], \"usage\": \"1,367/1,375\"}",
"tool_call_id": "call_7e2pk8MdJtmc6nnxxGXnMjyB"
},
{
"role": "assistant",
"content": "",
"reasoning": "**Considering AutoShorts entry**\n\nI need to replace the existing AutoShorts entry with a more condensed version that includes an ending. It might be longer than the current 314 characters, so I may need to remove some parts to keep it similar in length. I’m making sure to focus on clarity while adhering to the length requirement. Let’s see how I can streamline it effectively!",
"finish_reason": "tool_calls",
"reasoning_content": "**Considering AutoShorts entry**\n\nI need to replace the existing AutoShorts entry with a more condensed version that includes an ending. It might be longer than the current 314 characters, so I may need to remove some parts to keep it similar in length. I’m making sure to focus on clarity while adhering to the length requirement. Let’s see how I can streamline it effectively!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKFReW9ZUR9vVIuI-0nHqGWKBj_negGx9gR39EOF3pSHxHn2skYvHQn4HbKGFDNwW3veA-UwLh-g7fIOO-HvMVP864NIyNMW1jOaGjr0X1pj6cH3w7W3HgFIfHxE2oMrpk5olR37hZ1EIDxLfKsoWMIikolmcV207TvQMcsJJ0A2NrqjrkReypNhZtDTq80kW_9qTlaZz9m12WxcAbMe1YtR3nhspCD6Ua8uDGvDyVeWQ2bhhAAQBNt_bWgUdbuiPj-lKDGwXLFL-CutONj9Ixzkrix5dxB451tuoSobX0go8DUN0umU9pfuxOOP6PVKF_MfCHoMMBiRewW1sl3d37_WRCLCWGImdPBMA3_gO7-ECu-I25u-am7bWVRFkDwai46fNFYBLF64eNFagX8MQAj0MmImjM5G26vSpcPhVK6zOoFQHzVixIaRh_aUQp3zkhIdoONlOouPNhAITnEZ-2eGvk3yU-LM_l-31jS32u0o08nYddZU2ZILG_uV9U7u-N7Ro3V7G83hCVOJtvkQ78SldZVUSG9Wttke8BQ8pJgAIzHHxQyRnhLaP3HtrPzOge0ate_Zc3WVF9IKzPj-VV4szG1ULuGq2PWdOOAMlbGMfx8izpCZPsiv1tScH148RWanoKZ1foYI0i_lThjV4uyuWIZ7zedFM6gz-L0F-5ApNYhBO1sRwF5r5oc9SnaA_NzJjlabQvSIMpC03XFAMnzrXADVACkXrJwWaapxQ8-X4daYp2BtxPkwvljNRywYjbDFq_A8Vg0NcoIMoOC2wQWPzrGRbzIvQNjptBL7otEVkBS1ChCHpOLy0jwj0mFvEb1cRgIlC_TVfzd_sijhfPZgjaTdCXfQcbicik2lUNCmzbw4zJK1CmfyWPhe_0R55UEiZTUQkesz-FAIMtG3bQvG9deze3LCINNcYGrZM5qWBm76etf3R5ajQr5NAQVwELmei9JxATeJd-4HjKx4YVRsLuC7kpGl1ejWFRm9iCrvdGLYCJGLADJs9zS4LXzQjZozObT5svnIP4Fr-knxpt7OHmB1tKH4I8pEWXFfI-SrfD_yGguPrLU58XxSz3f2FjKlHll7RrMocfKSxuMV1k8QJPVjxrU-1J4tZzgWlBqX1WQ=",
"id": "rs_051a8a0b2fb58918016a14a1504dec81918ce6206eb00a1ea8",
"summary": [
{
"type": "summary_text",
"text": "**Considering AutoShorts entry**\n\nI need to replace the existing AutoShorts entry with a more condensed version that includes an ending. It might be longer than the current 314 characters, so I may need to remove some parts to keep it similar in length. I’m making sure to focus on clarity while adhering to the length requirement. Let’s see how I can streamline it effectively!"
}
]
}
],
"tool_calls": [
{
"id": "call_qzdU5tuvMqIHHaMyVX0nRjsk",
"call_id": "call_qzdU5tuvMqIHHaMyVX0nRjsk",
"response_item_id": "fc_051a8a0b2fb58918016a14a151f4088191b3e6cebc9b629a1c",
"type": "function",
"function": {
"name": "memory",
"arguments": "{\"action\":\"replace\",\"old_text\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN.\",\"content\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. Hidden mechanisms, not AI tips; AI 30–40%. Format fail→mechanism→fix→clear takeaway; endings must spell out concrete next action/fazit for non-tech viewers. Captions static 3–7w phrase + active-word highlight. Visuals premium clean KI-image cuts; avoid labels/arrows/boxes/target markers unless approved; Wan only after approval.\",\"target\":\"user\"}"
}
}
]
},
{
"role": "tool",
"name": "memory",
"content": "{\"success\": false, \"error\": \"Replacement would put memory at 1,428/1,375 chars. Shorten the new content or remove other entries first.\"}",
"tool_call_id": "call_qzdU5tuvMqIHHaMyVX0nRjsk"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKFYQrI1J8b_iFtIL35oYTlJQtc79_ROKIhf9R5X4N-j3d3Qov4HbD1aSNefDoBZaU549VjfSjU26Ja5YCaKhDJ2h7K0EHyrXIhms_GVxXtgfG9Sp8EzZLFXIW0OT8yjXdZThh0KfURLVynMB3Y8uRz_Lkg5WVgLHNQnyPs7yACoEwSOkBqr54MC6CV0Cmp4Dn8uLt-viNrv9oxME7PfApdVd160s_iT_-_jzbfmFUTOQAqRmW6_kmiBRqr2UXtDKYv70hXJJmzj99TfHU_QbB42UUp2pCcEclG0armVNWdT6dkFWQcdwma1lDY39Cal3xB4KToPik51Xf1GC2r0O8r8ES7_eBa81iAy5wPEnkWfaSTVCc5WkvgSz8LeST66qkIGxUGSiVFy54cmZ3mRyiDstB5v_CB-kWxaCN4D-M-wXC1c_awIKewyWJNULgq2vp1pe8UX5COIwMPzCNHtzuZq0IpkNARp32JNjuK7xmHm35XCEBT1LMB5_iuCVhfVqYk9N2nZrOHGJgoKQ81FL4hoiczGgz1AyRGXC6WjfyK3cAa2HuXOwbhNbHPaZK9BYgr_FI1Tcvm7PMqp9drOBNbx7UexSu_Cmml6MuodPS2ieBNinJCGgChCv7BZArR9CsySJ8-mmshQGdwOaQgUKhXF4wHUIs25DnvbWSzbKhZipSB9ytJE5G2H0PRm7I3AaK5fmttCorL3NF_vdrNPMVniq_8jq7hIXkSR_UVshwqMxPef_jsVaSXmh3cZxevgcm-pACZ7zLYJqgTTyPHIapKFjrDP3xFFlgpjYyN2NzCKIxYIWqfLpPe8ZMnl0yFAo73F6acTYS2ewYG_5fM2SWbMYwA_d_yig4j83OR7sOQJ-UTP-G6u02F9P78CTt3cWv9wOUi8tfM62mf2Vzjjh-LFk77rVH2or0n7cppvqbJ6rf9bOoK3YyIzXUaWo5wJnVoIhEFt_SlhdL_RqmPHipuiMmyLpPdNr8y57ruHelLmvHftljO1B1THI2YJQ2guKVCgA8Prji_dI0HSak_06L8NR_AaaTKaSPGaIxLFQMi_ljDXkRFwKll-FqxMxaX-m8MdIrvbsWYTIGwUcC18LbgLE8cRdb60fuUl1VInsp4XK33MXiXchPMy9LMcEJgS4LTSZAvacATmvw5z8JjHEaD0h2pdtlYmMvqEFalweZR3gAivMrSTSTrsPxkhstZZPk6TXXJ-GC_qyRqOww8aYpFFrQlCTSCxzEXbncErTUePVs91b72x5rydRFNqrEvm069MXwCXCt2BFLyO7wFz8InAt8OPmiG7duxDaR_NSiVZnC-ynLmuo_SWrTUW1ypCm0NwNGI61uKHlS-JvDYotVhaG1W5JdInQmxlGm9Rqk-sQ-ov7Ab1M7NYYbBca1QvqJ_x8f62q-c0hjHiZTgz-xv8NoBEpIyE4xX7YUmwimPWq9WzVjj0LoYXd8wLiMfVTQePQ6d5wM5wBSYJUJNubMuKcg==",
"id": "rs_051a8a0b2fb58918016a14a155ffcc8191ae42bada2e7228b9",
"summary": []
}
],
"tool_calls": [
{
"id": "call_g9v5iSA5xo00bM0sUmPZKfUK",
"call_id": "call_g9v5iSA5xo00bM0sUmPZKfUK",
"response_item_id": "fc_051a8a0b2fb58918016a14a158463c819182d06a36651b322e",
"type": "function",
"function": {
"name": "memory",
"arguments": "{\"action\":\"replace\",\"content\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. Hidden mechanisms, not AI tips; AI 30–40%. Format fail→mechanism→concrete fix→clear takeaway/fazit for non-tech viewers. Captions static 3–7w + active highlight. Visuals premium clean KI-image cuts; avoid labels/arrows/boxes unless approved; Wan only after approval.\",\"old_text\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN.\",\"target\":\"user\"}"
}
}
]
},
{
"role": "tool",
"name": "memory",
"content": "{\"success\": true, \"target\": \"user\", \"entries\": [\"**Notes:** Mein Herr. Loyaler Partner.\", \"**Name:** Sir\", \"**Voice preference:** de-DE-KillianNeural (German male voice, natural/clear) — default for all TTS output\", \"**Language:** Deutsch mit englischen Fachbegriffen\", \"Kommunikationspräferenzen: **Sprachnachricht → Antwort per Sprachnachricht**\", \"Kommunikationspräferenzen: **Textnachricht → Antwort per Text**\", \"Health advisor role: consolidate labs/clinical reports/YAZIO/daily health email/symptoms/events into dashboards/reports; lab extraction requires 4-eyes review before values are confirmed.\", \"Telegram topic Health-Med: only medical strategy/Behçet/Major Vessel Disease/thrombosis/meds/nutrition/symptoms/labs/doctor questions; health system scripts/data models go to Health-Tech.\", \"Finance/Grocery: no real amounts/IDs/API keys in chat; credentials via runtime files; no DB/CSV/keys/reports in Git/frontend; backups+audit; Preview→Confirm→Audit; no fake prices/buttons; OpenFIGI never show/store; never auto-book; grocery provider calls explicit/cache-first.\", \"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. Hidden mechanisms, not AI tips; AI 30–40%. Format fail→mechanism→concrete fix→clear takeaway/fazit for non-tech viewers. Captions static 3–7w + active highlight. Visuals premium clean KI-image cuts; avoid labels/arrows/boxes unless approved; Wan only after approval.\"], \"usage\": \"99% — 1,365/1,375 chars\", \"entry_count\": 10, \"message\": \"Entry replaced.\"}",
"tool_call_id": "call_g9v5iSA5xo00bM0sUmPZKfUK"
},
{
"role": "assistant",
"content": "",
"reasoning": "**Updating skills documentation**\n\nI’m looking to update the skills documentation. I need to patch the old string in SKILL.md. It should specifically reflect content like: “If the user says subtitles are irritating... See `references/static-active-word-captions-and-final-pilot-render.md`.” I also need to ensure that if there are mentions of deterministic layouts, I remember to add a bullet point after that section for clarity. It’s important to keep everything organized and easy to follow!",
"finish_reason": "tool_calls",
"reasoning_content": "**Updating skills documentation**\n\nI’m looking to update the skills documentation. I need to patch the old string in SKILL.md. It should specifically reflect content like: “If the user says subtitles are irritating... See `references/static-active-word-captions-and-final-pilot-render.md`.” I also need to ensure that if there are mentions of deterministic layouts, I remember to add a bullet point after that section for clarity. It’s important to keep everything organized and easy to follow!",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKFfKOxYuaUEjALRGsvW12SWj6SLKvFlxGk99vCty5CfIxFid_Ta8sawr-VSpSteS8rcysGez5Tuls70DE2G8QOsgIH6NeMDmOcYfNI75hN_UXY8O6hBv68sKpRr0eZOT19FL3aRgU3U7gGnIWfUskOU1jDFpOgi5A65irAQ6Qj_iZ9VrQq2aoYeHxx3mzpFY-NOarMnBdsG2KRXcS6rDNFy5Sni-JyHfJ-v6GwHiEwNmUtox6MKDW3KnhMW3ZrlwwlRgZvd646B-24rgycAPf0EVfLE1jhLzHLAnj-sdeXRDS9Pyj5aHDl4TLKMPMnlEqitid6WNf4bL8zkCnmJ6dyhC0XKg6mKM-ADFVVKI1uvRdn-Iosj0mhMYJ6zDHLIGnpmsXz72UGA8HxZNlwIIWTRFWmtMV2IS_TSafbTOzt_xezX91z2-YzbC2c7AnM5D-CzTanUrFVagaZibJLo3bl2P-AsJDuDzqgGdEhetACeC5_97B5pWdekro_g1hIlP83c6f3bvefhY3JCBfzbve9YqDtAu2fxr66nRd66b6rO1SS1fKVhgacFOucieMQQ-a3VopkcOQAhf4YYZxVEWZd0h_yOYBKkeYa3ahpZiq7e1oG84cyVynWYTRDM_EvA-dZO84hho2lLwVkxlcltrlqT9E5FQeAUybGX0N8MXIt-6wSYbnrjal1wPGSfYqGE9cHeKiRhcmgIteDYatTY-lyx36zVBzaX_rS2n2vAeNEcR5hRYhdo_9ft06z7_zDmfXq5cQm-vqnO_jWu3Mbg24BKtT5quM0aRCWNPICV4Efs0abwTiO641hTP1zEjbebb29UYnPuQhOK4jJtj8boo55TAooh97yDGc7-gERI-1Jt8qT-8DcDWvtC-MssyrhPXMwlxFpQOysnprveTyrJvCt4qVC1xxXGbUo_SnaWYuGct3VXNLmv53oME3m4SAe4nXOl4X_mgR1Qwg8smOej_DMblTE1EL4QNVdhD6msmmaqMCJh_BdE_ge15ZfYihLWCtiM9wTnfj79ar-sx1KZu23KzAu9ENwV219MKAdRtlJxNCh90bQCfBAW84geL6CzreEY6O2HcngEAKiJ8q6niOPxJkYQWaFpVfBl5yg18P1ykm7jZ8PkYWM0CRUhDkIcB1A2rESPaIJcP5sTxyozON7bkqqWBZL2wUCpXc-Csd6fwmwQ-UFFrvxXqD6X_wgCJvfk8dytyzpPH1TCvZ3xeU8Hgrd2kITJFZC0c_DRouDS91KXX6zx1vje3SVeeisFg21T",
"id": "rs_051a8a0b2fb58918016a14a15cd56481918f2d292c9fdb5d9b",
"summary": [
{
"type": "summary_text",
"text": "**Updating skills documentation**\n\nI’m looking to update the skills documentation. I need to patch the old string in SKILL.md. It should specifically reflect content like: “If the user says subtitles are irritating... See `references/static-active-word-captions-and-final-pilot-render.md`.” I also need to ensure that if there are mentions of deterministic layouts, I remember to add a bullet point after that section for clarity. It’s important to keep everything organized and easy to follow!"
}
]
}
],
"tool_calls": [
{
"id": "call_EPnhCWDcgXv8j5NGdF7vvaGC",
"call_id": "call_EPnhCWDcgXv8j5NGdF7vvaGC",
"response_item_id": "fc_051a8a0b2fb58918016a14a15fb99481919c7c4194e1dae663",
"type": "function",
"function": {
"name": "skill_manage",
"arguments": "{\"action\":\"patch\",\"name\":\"social-media-shorts-automation\",\"old_string\":\" - If the user says subtitles are irritating or not simultaneous with voiceover, treat this as a blocking quality issue: use forced alignment or simplify captions before sending another final-near clip. For this user's AutoShorts/TrueTraceShorts default, do **not** show one word alone and do **not** slide a changing word-window every word. Use static phrase segments: keep 3–7 words fixed on screen while only the currently spoken word highlights/pulses left-to-right; replace the full segment only at a sentence/phrase boundary. See `references/static-active-word-captions-and-final-pilot-render.md`.\\n - If deterministic layouts explain the mechanism but look like wireframes/PowerPoint, do not promote them to final style.\",\"new_string\":\" - If the user says subtitles are irritating or not simultaneous with voiceover, treat this as a blocking quality issue: use forced alignment or simplify captions before sending another final-near clip. For this user's AutoShorts/TrueTraceShorts default, do **not** show one word alone and do **not** slide a changing word-window every word. Use static phrase segments: keep 3–7 words fixed on screen while only the currently spoken word highlights/pulses left-to-right; replace the full segment only at a sentence/phrase boundary. See `references/static-active-word-captions-and-final-pilot-render.md`.\\n - If the user says the ending is confusing, rushed, or does not offer a real solution, treat this as a content-blocking issue, not a minor copy tweak. Rewrite the final third so non-technical viewers are explicitly walked through the concrete action: what to close/avoid, what to open/check instead, how they know it worked, and the memorable rule/fazit. Avoid vague imperatives like “open the service yourself” unless immediately unpacked with a concrete example such as “close the invite; open the calendar/work app from the normal icon or bookmark; if the meeting is real, it will still be there.”\\n - If deterministic layouts explain the mechanism but look like wireframes/PowerPoint, do not promote them to final style.\"}"
}
}
]
},
{
"role": "tool",
"name": "skill_manage",
"content": "{\"success\": true, \"message\": \"Patched SKILL.md in skill 'social-media-shorts-automation' (1 replacement).\"}",
"tool_call_id": "call_EPnhCWDcgXv8j5NGdF7vvaGC"
},
{
"role": "assistant",
"content": "",
"reasoning": null,
"finish_reason": "tool_calls",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKFrci5whBbUfkRfYtuGSRk_A1ODxukOOgAmWJpz3Ynobi-65NxxpzAEBXggnOFeXYUlqIffq7F6WogsWHcMW8ADE6mcR59-32EtjRzc4ItLP4r7IT28OS9lI1jHCatCMTS2AtUtTXPQFbDGbR068sDF8P0ZwBNKINIxxlWEKKWS3u9UGdVj-n8UFwJ95amXqdAdP3nCS-Z8HUT8WHkVFAlKzTM1QFmQTxtuID3wURva2V0qmKZ5PrIOanbMqcHsSNFJZTjwSRbhstPHID9xT3uAP5hTZcmhr-tWW4H7TBw0nSXkSwVGnizPW-FlcGa6uqvtFLaysjLoBDG8ZpCvz0JmmBGCGkw3nn9Nbrb8xs-fmdZKpSJJwrCwH0XxBMgzb50fBcXIg-IogQj-cimG3Wdk_jeTZIE7KOc-55FRUcUpq6EbgEv3-8U8qpqswJJjc2Fy6MOAwiP-zp47_4-hMmz8Gp2C6L1WWJMfil8F7GL5V94DBKtHXF0lvJUv4owRM1QHggiykgWNKElXCMcXtJ7vpekdZUrClaLK6dIVKqL_uHr6rNF685wntu99xsKFaJpWQGorQrnDcXgE3WCExu_XRStXyj0DLxAtSfSbrWoYJPugr9JkTXOC8gIXhnMt-CpSvWMg5iTDR1tb54vlwqid90AVC03IfpZSwBQaWOPVtqGiGk5Jzjpuvl8MhTsO4AaJACwhpWX2VYRqa5wjtcnNPa1zGvc-xADtrJmjY72FN5SS_elhQSUvQ--xqKTQVO1MVwjxaMKGcjBwy1q8bIXuZB2dyhZ9NIlBRXMIFTVPTU1d_UxQF4Uh1Yb3rgcsPPuJPa-jislSfiLvsGXsvuEuwuIZpFoAZ6hbBxhrpMzPd556OYkq0WyQG9PP3cusWTFjA1XngnNNkIQqv04evjtm7PGsKU7nmWtUy1E80txlk-eeDsPEkNvrE9UJBa4Gz-2w9JaceD_wbER1MRxIER3BfSpLMA4wBPCcHraVgiZiOfMr8f8aAMET0hG3ab4a4iQvqOyKUx1ev3GCbS2jGVz5l3tqc7wTUmPpXs9KVDNy0lcrIJjNjtYn2WjVQ6URQxrzsd13RccWr0NO97LO6o84QwDI1EPmnI40VkUhTXnSVQrspjHTKwk12XzNJaGdbG2Z7vBjOguukz68NHC74ZejW8o4KDzdJDZYk7E0nQauQo6R0_6VjaghcdNyXD2anM8v33_HhNGtjnkVyr93hLxqQeOCGW3sF-3bBNVKA6Go1sXxL7tvwFwZeZiCXvoQLnoMdRZws2n8eYTS0GRUhTCj4aJx0IIzJigYp44Js2X0OEukQOJWmkMrnydFbhHxvaJIMc1LIzvGozpFJFE4kRDxt3r1_7XBUt3Hh9xnHypoRF5_vw-iyApZ_rJ3hPrIePSwfXnLcDSsQB2foYkWE2D85WP4-rO9lBPpKGevEUZGQz9RD_0i3Y8tfdmrR0kAb00kE1N-Xng4tcHRZb7KyYpgnTPJb8u24aHMQv-GauonF5gFKwBR-orlTqpF7mFFYSWReNAhJ-EFK0cK_S28y6w1LQ==",
"id": "rs_051a8a0b2fb58918016a14a169202c8191936104fc987dbf32",
"summary": []
}
],
"tool_calls": [
{
"id": "call_EdMY7QRGIAX3Vl6RihAUWagY",
"call_id": "call_EdMY7QRGIAX3Vl6RihAUWagY",
"response_item_id": "fc_051a8a0b2fb58918016a14a16bf7c481918da4615888fcf97c",
"type": "function",
"function": {
"name": "skill_manage",
"arguments": "{\"action\":\"patch\",\"file_path\":\"references/static-active-word-captions-and-final-pilot-render.md\",\"name\":\"social-media-shorts-automation\",\"new_string\":\"## Viewer-friendly ending / solution gate\\n\\nIf the user says the ending feels confusing, rushed, or does not really solve the viewer's problem, revise before any further polish. Do not leave the fix as a compressed expert phrase.\\n\\nFor broad/non-technical viewers, the final third should answer in plain steps:\\n\\n1. What should the viewer stop doing right now?\\n2. What exact safe action should they take instead?\\n3. How can they verify the situation without trusting the suspicious button/link/email?\\n4. What short rule should they remember?\\n\\nExample for a calendar-login trap:\\n\\n```text\\nClose the invite.\\nOpen your calendar or work app from the normal icon or trusted bookmark.\\nIf the meeting is real, it will still be there.\\nRule: trust your normal path, not the button sent to you.\\n```\\n\\nAvoid vague endings like `Open the service yourself` unless the video immediately explains what that means in everyday language.\\n\\n## Review package checklist\",\"old_string\":\"## Review package checklist\",\"file_path\":\"references/static-active-word-captions-and-final-pilot-render.md\"}"
}
}
]
},
{
"role": "tool",
"name": "skill_manage",
"content": "{\"success\": true, \"message\": \"Patched references/static-active-word-captions-and-final-pilot-render.md in skill 'social-media-shorts-automation' (1 replacement).\"}",
"tool_call_id": "call_EdMY7QRGIAX3Vl6RihAUWagY"
},
{
"role": "assistant",
"content": "Updated.\n\n- **Memory:** AutoShorts/TrueTraceShorts preference compressed and updated: endings need a concrete fix + clear takeaway/fazit for non-tech viewers.\n- **Skill:** Patched `social-media-shorts-automation`.\n - Added a rule that confusing/rushed endings are a blocking content issue.\n - Added guidance to unpack vague advice into concrete viewer steps.\n - Updated `references/static-active-word-captions-and-final-pilot-render.md` with a “Viewer-friendly ending / solution gate” and the calendar-invite example.",
"reasoning": null,
"finish_reason": "stop",
"codex_reasoning_items": [
{
"type": "reasoning",
"encrypted_content": "gAAAAABqFKF0YIjlCpB3du2ANyT5l7jaclVgmGGOZYsZ3D8j2BuZlKuhQSIzLJLA6xoT62kaUDOe80idmALaQWT1aOf_pvWm3jf2ahari1tu8n1S5pD1hFHxyc0Oi5gvPv2ALnI-9xPnbK6tB5EZH7ftyA5jWT7UAFHVvb633JhHgGqtp-GjFPwG_BzwYAlXaxTJX8gahSdolaX2stMTjiirm2cGZjy1eDzOYfwIAvte32K1swXm3Bes2JH8fO6pwD9gM7jY2O4frEvMBzxIXvhu53YUAT6NreCGPyqpce9FMJPBcHCHXav1jjezF_T3aA9qZMJtyk5hBAALYPcSYbBiyRB0tMfdvXo1v0dkLbvtpIjG7hus9TR-_T7Pg0yhfn2aPECwOC9KFAXgAkZ2-7ioLNRAaiDEannmuxIUQBjQKmWWfeuOxZmiMfBvlygb1KW_a4IF77IZ0x_LMeiw3II3WtBh0hWd1AvyVysuw9vdwRgaLRz3Lf439dggR_aBtognSfzb_0BBaO-FTWN5l9Iv99mgo3byUpD3Ak2hHTDdltGn8UAH4utPR72eINnJUY6we9zUhWEW02_9dR9mULpjb4Lx5vd8HDwAEwE4V7ZffHDgbgifObvmK3l91wBmJ5qvh2y110s4oxe_EAdz2wjy1HC8W1Y9EGGoU_TJEzWHZNvJkAwkKmcZ2JMaS06WfFAnw_RwTRLAPYV-tBAr5KKG_Gfgh3PUtjssP2kBlJuAaSOpovh5rNWdhfZD5KPaXxE1GNZfrQfoRyAOsFCvXJxh2W5B01ue2ORXpUy5S2qFdbkHM4LajO-jyFZB7yXy-ugQUfjtONZu1WcLt7aRJK2goQDtnCHyiDadHhge_3SoGt_RKzWZgfzPS2vvY-53oxY2AxKtfrHk-gL_Z40cBegqCFXHCqhtJwAtKM7RqdDygobij3ENsdqyxfdVFsl95ovSOPvAAYVkYnNpunSPVeWYQLzYSZ-DIVh6vfIiTeWkeXycT9Fdp52iq4GkO8ncPd8r5so77bSQ",
"id": "rs_051a8a0b2fb58918016a14a173bf748191a8e22397bcae472b",
"summary": []
}
],
"codex_message_items": [
{
"type": "message",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Updated.\n\n- **Memory:** AutoShorts/TrueTraceShorts preference compressed and updated: endings need a concrete fix + clear takeaway/fazit for non-tech viewers.\n- **Skill:** Patched `social-media-shorts-automation`.\n - Added a rule that confusing/rushed endings are a blocking content issue.\n - Added guidance to unpack vague advice into concrete viewer steps.\n - Updated `references/static-active-word-captions-and-final-pilot-render.md` with a “Viewer-friendly ending / solution gate” and the calendar-invite example."
}
],
"id": "msg_051a8a0b2fb58918016a14a1747f5081918ea9ab54e03ba7d7",
"phase": "final_answer"
}
]
}
]
}