{ "session_id": "20260525_225614_efb6a8", "model": "gpt-5.5", "base_url": "https://chatgpt.com/backend-api/codex", "platform": "telegram", "session_start": "2026-05-25T19:17:42.666196", "last_updated": "2026-05-25T23:37:10.100238", "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save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked.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 ![alt](url) 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% — 1,365/1,375 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. 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.\n\nConversation started: Monday, May 25, 2026 10:56 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": "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 ![description](url-or-path) 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": "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": "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": 92, "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": "[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. 193 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." }, { "role": "user", "content": "[M G] OK, los." }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_CJDhKgwOvG8rmmzdQVAFGik1", "call_id": "call_CJDhKgwOvG8rmmzdQVAFGik1", "response_item_id": "fc_051a8a0b2fb58918016a14ae458ef0819186baf7ef9c58d3c3", "type": "function", "function": { "name": "todo", "arguments": "{\"todos\":[{\"id\":\"gen\",\"content\":\"6 konkrete Visible-Invite-Cinematic KI-Keyframes erzeugen\",\"status\":\"in_progress\"},{\"id\":\"qaimg\",\"content\":\"Keyframes prüfen: sichtbare Einladung, kein lesbarer Text/Logo/QR/People\",\"status\":\"pending\"},{\"id\":\"render-b1\",\"content\":\"Variant B1 rendern: AI-visible invite only + Voiceover + Subtitles\",\"status\":\"pending\"},{\"id\":\"render-b2\",\"content\":\"Variant B2 rendern: AI-visible invite + minimaler Fokus-Layer + Subtitles\",\"status\":\"pending\"},{\"id\":\"qa-deliver\",\"content\":\"A/B QA, Manifest, SHA256 und Lieferung mit Empfehlung\",\"status\":\"pending\"}]}" } } ], "finish_reason": "tool_calls", "reasoning": "**Generating image variants**\n\nI see that I need to take action now! I have the relevant skills ready, but I might need to use the clean-image function. The task is to build variants, so I'll need the right tools for that. It seems like generating around six images is a good target. I'll also want to use a to-do list to keep everything organized as I proceed. Let’s get started on this!", "reasoning_content": "**Generating image variants**\n\nI see that I need to take action now! I have the relevant skills ready, but I might need to use the clean-image function. The task is to build variants, so I'll need the right tools for that. It seems like generating around six images is a good target. I'll also want to use a to-do list to keep everything organized as I proceed. Let’s get started on this!", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFK5FTHoPT9cjgX5ZzbFdei7E2t7N6m4VwY6_-eVq0Fe4b3BFV3munCmo8WmpOzadl-4aroPyKNmnc-ajXf0Ty7W_JGGu0sl540xTnnAwihQH5N2Zt1aIatgvL2aZenDwU6qHuCbl9a6dCudB1mX18zKmV9M63YMhEaOkNKIa3fwOsJqAW9s3lXopSMskX9epte7z16T9qY-G5CmP2IuRP_eGb7DIiY-ovOO_9DrlHVAeAd1YvHX2LXr97O3psXzVXBgFSLt8cIyVnvl9Ng6K9JOc_jzOLDd-MmuhsiHWII_fxwp-pEuHng8pfQwNBfGOPKBT7-Gyv0k3F2ctQ8SQ1H_5mOt5nOVKwr9kP7LkeWHhAssKRbDnbzdmk9yjq7x9UqyS_qOe2ZSD9KLvyqbiyKnqthmjAQjdz6hmAbKCqF58mP57kW52clBcipp7UdSk_489XHgLd9I5D8QrVYSyMH8UtXP2nKCQy8YaquPNcTOuE4HrUgazsZZ_U5MYYK3SkcHlwV2VtUOPNgKVWVqzVMcqMPzgq5NucJRu1RiErbBF7jNn5p4XYlQYDV2DCI1StH2LQyGbsiGygxfV6disWBXIVXVQ8vvN4lNRzbvDAPG4KOKd_oLqgjsaHHjSSo9glP2sDHkPq3zoiGG6oI-v16ZTfdU0yIqtiw4CSKMGUVpIv87iux5zG_2NsFTPjkfn61osh6pOk78GA4aYKVm6iQ_2Dn-E5UIo-DsCk-y5vw79NxJ8Q0wMKKLOn1PGO8kGmDqU_ETtP6k4sHJFUZS8475mttyKzgVLpZeOSjbRmpBDSnRIz7PwI40r0DkY0gc9mkw7qhV618JuWbpk5RZl0-ScBgUMCqO9gxmNw7ubyJIC7H-XI2l7Lh6U0pf_GZ6oRBZmvhzZmAOfLWiWmPhcwDRDWD-wOlY-o6uvR5kt286NbBsAXTks4x78yskbyovQ4y7Knlc9SYdBHXTBknVH8ElteqXxU8XKCeKxpSuKJtdZQ7uRCJLvEoCABr2IH0hEQTyFVqKLzXiH7-ax7FvGuGo13vPmOhIttx3NSDRZLhoE8w4Dd7Y71BY5zRpHcPxyN06hQ3DWSEaCvQwitetg2O3X71ed4zoG1-QQgA2QKC97V1U=", "id": "rs_051a8a0b2fb58918016a14ae42d19c81919db0516a206695a8", "summary": [ { "type": "summary_text", "text": "**Generating image variants**\n\nI see that I need to take action now! I have the relevant skills ready, but I might need to use the clean-image function. The task is to build variants, so I'll need the right tools for that. It seems like generating around six images is a good target. I'll also want to use a to-do list to keep everything organized as I proceed. Let’s get started on this!" } ] } ] }, { "role": "tool", "content": "{\"todos\": [{\"id\": \"gen\", \"content\": \"6 konkrete Visible-Invite-Cinematic KI-Keyframes erzeugen\", \"status\": \"in_progress\"}, {\"id\": \"qaimg\", \"content\": \"Keyframes prüfen: sichtbare Einladung, kein lesbarer Text/Logo/QR/People\", \"status\": \"pending\"}, {\"id\": \"render-b1\", \"content\": \"Variant B1 rendern: AI-visible invite only + Voiceover + Subtitles\", \"status\": \"pending\"}, {\"id\": \"render-b2\", \"content\": \"Variant B2 rendern: AI-visible invite + minimaler Fokus-Layer + Subtitles\", \"status\": \"pending\"}, {\"id\": \"qa-deliver\", \"content\": \"A/B QA, Manifest, SHA256 und Lieferung mit Empfehlung\", \"status\": \"pending\"}], \"summary\": {\"total\": 5, \"pending\": 4, \"in_progress\": 1, \"completed\": 0, \"cancelled\": 0}}", "tool_call_id": "call_CJDhKgwOvG8rmmzdQVAFGik1" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_LIDQqzshLK04yWSGXc0ywLkM", "call_id": "call_LIDQqzshLK04yWSGXc0ywLkM", "response_item_id": "fc_051a8a0b2fb58918016a14b16ef49081919e3a24565f96f2cc", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic keyframe for a cybersecurity short. Shot 1 visible problem: a laptop on a modern desk clearly shows a large calendar invitation card layout on screen: blank title block, blank time row, attendee dots, large blank JOIN button shape. It must be instantly recognizable as a calendar invite, but completely text-free. No readable words, no letters, no numbers, no logos, no brand icons, no QR/barcodes, no people, no hands, no faces, no watermarks. High-end navy/amber lighting, shallow depth of field, clean lower safe space for subtitles.\"}" } }, { "id": "call_Rw7I9D9rI0fhsLrlxN1x5wen", "call_id": "call_Rw7I9D9rI0fhsLrlxN1x5wen", "response_item_id": "fc_051a8a0b2fb58918016a14b16ef4a88191bfaf3897e8d140d9", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic keyframe for cybersecurity. Shot 2: close-up of a phone on desk with a clear calendar invite notification/card UI layout, prominent blank join/sign-in button shape, empty content blocks, attendee circles. The viewer should understand 'calendar invite on phone'. Absolutely no readable text, no pseudo text, no letters/numbers, no logos, no QR/barcodes, no hands/people/faces, no watermarks. Subtle warning amber/red glow, premium social video look.\"}" } }, { "id": "call_3t3PhWU1WWvCvNEmCcnjTLT5", "call_id": "call_3t3PhWU1WWvCvNEmCcnjTLT5", "response_item_id": "fc_051a8a0b2fb58918016a14b16ef4b48191a4b5e171fe21bffa", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 keyframe. Shot 3 suspicious moment: laptop screen displays a large blank calendar invite card, the join button area glows subtly red/amber, and a blank link strip underneath suggests a risky path without any readable content. Keep all UI shapes abstract and text-free. No words, no letters, no numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Cinematic dark office desk, negative space for subtitles.\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223248_ad88505c.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic keyframe for a cybersecurity short. Shot 1 visible problem: a laptop on a modern desk clearly shows a large calendar invitation card layout on screen: blank title block, blank time row, attendee dots, large blank JOIN button shape. It must be instantly recognizable as a calendar invite, but completely text-free. No readable words, no letters, no numbers, no logos, no brand icons, no QR/barcodes, no people, no hands, no faces, no watermarks. High-end navy/amber lighting, shallow depth of field, clean lower safe space for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_LIDQqzshLK04yWSGXc0ywLkM" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223352_1fc7d917.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic keyframe for cybersecurity. Shot 2: close-up of a phone on desk with a clear calendar invite notification/card UI layout, prominent blank join/sign-in button shape, empty content blocks, attendee circles. The viewer should understand 'calendar invite on phone'. Absolutely no readable text, no pseudo text, no letters/numbers, no logos, no QR/barcodes, no hands/people/faces, no watermarks. Subtle warning amber/red glow, premium social video look.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_Rw7I9D9rI0fhsLrlxN1x5wen" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223442_75635a77.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 keyframe. Shot 3 suspicious moment: laptop screen displays a large blank calendar invite card, the join button area glows subtly red/amber, and a blank link strip underneath suggests a risky path without any readable content. Keep all UI shapes abstract and text-free. No words, no letters, no numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Cinematic dark office desk, negative space for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_3t3PhWU1WWvCvNEmCcnjTLT5" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_z1CWrLOHnJXrebSOYtYUxlIp", "call_id": "call_z1CWrLOHnJXrebSOYtYUxlIp", "response_item_id": "fc_051a8a0b2fb58918016a14b26c429481918c7f0ac9789490b3", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic keyframe. Shot 4: the suspicious calendar invite is being avoided, shown as a laptop or phone with the invite card dimmed/fading out, screen still shows blank calendar-card shapes but no readable text. Mood: decisive pause, not panic. No words, no letters, no numbers, no logos, no QR/barcodes, no people, no hands, no faces, no watermarks. High-end dark navy desk scene, clean space for subtitles.\"}" } }, { "id": "call_7kpulTUXUPmmdOxsIgg8Opu9", "call_id": "call_7kpulTUXUPmmdOxsIgg8Opu9", "response_item_id": "fc_051a8a0b2fb58918016a14b26c42b0819184759a939049a2d5", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 keyframe. Shot 5 trusted path: a calm laptop/phone screen shows a blank calendar app-like layout with same meeting-card shape visible in a safe context, but all text is abstract empty blocks. It should suggest 'open the calendar/work app directly'. No readable text, no pseudo text, no letters, no numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Soft blue secure glow, cinematic lighting.\"}" } }, { "id": "call_STWEZjmMogeGYYGJmybR6AZi", "call_id": "call_STWEZjmMogeGYYGJmybR6AZi", "response_item_id": "fc_051a8a0b2fb58918016a14b26c42c48191b68e63e1bcf8b2f5", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 final keyframe. Shot 6 resolution: modern desk with laptop and phone showing a calm blank calendar card layout in the background, warm safe light, subtle sense that the meeting is verified through the normal path. No readable text, no letters/numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Clean lower safe space for subtitles, premium social short style.\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223537_97eed68b.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic keyframe. Shot 4: the suspicious calendar invite is being avoided, shown as a laptop or phone with the invite card dimmed/fading out, screen still shows blank calendar-card shapes but no readable text. Mood: decisive pause, not panic. No words, no letters, no numbers, no logos, no QR/barcodes, no people, no hands, no faces, no watermarks. High-end dark navy desk scene, clean space for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_z1CWrLOHnJXrebSOYtYUxlIp" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223623_228b1c81.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 keyframe. Shot 5 trusted path: a calm laptop/phone screen shows a blank calendar app-like layout with same meeting-card shape visible in a safe context, but all text is abstract empty blocks. It should suggest 'open the calendar/work app directly'. No readable text, no pseudo text, no letters, no numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Soft blue secure glow, cinematic lighting.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_7kpulTUXUPmmdOxsIgg8Opu9" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223710_95a32ed7.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 final keyframe. Shot 6 resolution: modern desk with laptop and phone showing a calm blank calendar card layout in the background, warm safe light, subtle sense that the meeting is verified through the normal path. No readable text, no letters/numbers, no logos/icons, no QR/barcodes, no people/hands/faces, no watermarks. Clean lower safe space for subtitles, premium social short style.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_STWEZjmMogeGYYGJmybR6AZi" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_hCXPGhzWStJpvEP5LCEzBZfU", "call_id": "call_hCXPGhzWStJpvEP5LCEzBZfU", "response_item_id": "fc_051a8a0b2fb58918016a14b2f98cb481918e66d1025c6f674b", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from pathlib import Path\\nimport shutil, json, hashlib\\nfrom PIL import Image, ImageDraw\\nsrcs=['/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223248_ad88505c.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223352_1fc7d917.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223442_75635a77.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223537_97eed68b.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223623_228b1c81.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_223710_95a32ed7.png']\\nbase=Path('/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1')\\nai=base/'ai_keyframes'; ai.mkdir(parents=True, exist_ok=True)\\nitems=[]\\nfor i,s in enumerate(srcs,1):\\n dst=ai/f'visible_invite_keyframe_{i:02d}_openai_codex_gpt-image-2-high.png'\\n shutil.copy2(s,dst)\\n im=Image.open(dst)\\n items.append({'index':i,'path':str(dst),'sha256':hashlib.sha256(dst.read_bytes()).hexdigest(),'resolution':f'{im.width}x{im.height}','provider':'openai-codex','model':'gpt-image-2-high','quality':'high'})\\nsheet=Image.new('RGB',(1080,1120),(12,16,24)); d=ImageDraw.Draw(sheet)\\nfor idx,item in enumerate(items):\\n im=Image.open(item['path']).convert('RGB'); im.thumbnail((330,495))\\n cell=Image.new('RGB',(360,560),(12,16,24)); cd=ImageDraw.Draw(cell)\\n cell.paste(im,((360-im.width)//2,42)); cd.text((14,14),f\\\"KF {item['index']:02d}\\\",fill=(247,202,76)); cd.text((14,525),item['resolution'],fill=(220,225,235))\\n x=(idx%3)*360; y=(idx//3)*560\\n sheet.paste(cell,(x,y)); d.rectangle((x,y,x+359,y+559),outline=(55,65,90),width=2)\\ncontact=base/'visible_invite_keyframes_contact_sheet_v1.jpg'; sheet.save(contact,quality=92)\\nmanifest={'generated_keyframes':items,'contact_sheet':str(contact),'purpose':'Visible Invite Cinematic A/B: B1 AI-visible invite only; B2 same images with minimal deterministic focus layer.'}\\n(base/'visible_invite_keyframes_manifest_v1.json').write_text(json.dumps(manifest,indent=2),encoding='utf-8')\\nprint(contact)\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"status\": \"success\", \"output\": \"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/visible_invite_keyframes_contact_sheet_v1.jpg\\n\", \"tool_calls_made\": 0, \"duration_seconds\": 0.45}", "tool_call_id": "call_hCXPGhzWStJpvEP5LCEzBZfU" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_Xaw8tNjVTB6cQLTXTcFueToh", "call_id": "call_Xaw8tNjVTB6cQLTXTcFueToh", "response_item_id": "fc_051a8a0b2fb58918016a14b30d0b0081919caf16cafc3b72f4", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/visible_invite_keyframes_contact_sheet_v1.jpg\",\"question\":\"QA these six visible-invite keyframes. Which are usable? Check: recognizable calendar invite/login/join situation, no readable text/pseudo-text/logos/QR/people/hands/faces. Note any weak frames or risks.\"}" } } ], "finish_reason": "tool_calls" }, { "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: QA these six visible-invite keyframes. Which are usable? Check: recognizable calendar invite/login/join situation, no readable text/pseudo-text/logos/QR/people/hands/faces. Note any weak frames or risks.\n[screenshot]", "tool_call_id": "call_Xaw8tNjVTB6cQLTXTcFueToh" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_ibwi8rQYZrHkNFxNIdNrHlSX", "call_id": "call_ibwi8rQYZrHkNFxNIdNrHlSX", "response_item_id": "fc_051a8a0b2fb58918016a14b5c415848191b80ea436755edf7c", "type": "function", "function": { "name": "write_file", "arguments": "{\"path\":\"/tmp/autoshorts_proof_short_sprint31/render_visible_invite_cinematic_ab_v1.py\",\"content\":\"from __future__ import annotations\\n\\nimport hashlib, json, math, subprocess, sys\\nfrom pathlib import Path\\nfrom PIL import Image, ImageDraw, ImageFont, ImageEnhance\\n\\nsys.path.insert(0, '/home/agent/jarvis_runtime/autoshortsbot/AutoShortsBot')\\nfrom autoshorts.rendering.static_captions import CaptionLayoutConfig, WordCue, active_word_index_at, build_safe_caption_segments, layout_caption_segment, segment_for_active_word\\n\\nBASE = Path('/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s')\\nOUT = BASE / 'visible_invite_cinematic_ab_v1'\\nAUDIO = BASE / 'audio/voiceover_word_boundary.mp3'\\nWORD_CUES_JSON = BASE / 'audio/word_cues.json'\\nCANDIDATE = 'calendar-invite-login-trap-30s'\\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(video_width=W, video_height=H, horizontal_margin_px=70, bottom_margin_px=300, max_width_ratio=0.86, font_size_px=66, min_font_size_px=48, word_gap_px=18)\\nSCRIPT = \\\"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.\\\"\\nKEYFRAMES = [OUT/'ai_keyframes'/f'visible_invite_keyframe_{i:02d}_openai_codex_gpt-image-2-high.png' for i in range(1,7)]\\nSCENES = [(0,6.2,0),(6.2,13.4,1),(13.4,20.8,2),(20.8,28.8,3),(28.8,35.6,4),(35.6,42.0,5)]\\nFADE=0.75\\n\\n\\ndef sha256(path: Path)->str:\\n h=hashlib.sha256()\\n with path.open('rb') as f:\\n for c in iter(lambda:f.read(1024*1024), b''): h.update(c)\\n return h.hexdigest()\\n\\ndef font(size,bold=True): return ImageFont.truetype(FONT_BOLD if bold else FONT_REG, size)\\n\\ndef ffprobe_duration(path: Path)->float:\\n return float(subprocess.check_output(['ffprobe','-v','error','-show_entries','format=duration','-of','default=nokey=1:noprint_wrappers=1',str(path)], text=True).strip())\\n\\ndef load_cues():\\n return tuple(WordCue(start=float(x['start']),end=float(x['end']),word=x['word'],sentence=x.get('sentence','')) for x in json.loads(WORD_CUES_JSON.read_text()))\\nWORD_CUES=load_cues(); SEGMENTS=build_safe_caption_segments(WORD_CUES, layout=SAFE, min_words=3, target_words=5, max_words=7)\\nAUDIO_DURATION=ffprobe_duration(AUDIO); DURATION=max(AUDIO_DURATION+0.5, WORD_CUES[-1].end+0.6)\\nSCENES[-1]=(SCENES[-1][0],DURATION,SCENES[-1][2])\\n\\ndef cover_resize(im):\\n im=im.convert('RGB'); target=W/H; ratio=im.width/im.height\\n if ratio>target:\\n nw=int(im.height*target); left=(im.width-nw)//2; im=im.crop((left,0,left+nw,im.height))\\n else:\\n nh=int(im.width/target); top=(im.height-nh)//2; im=im.crop((0,top,im.width,top+nh))\\n return im.resize((W,H), Image.Resampling.LANCZOS)\\nIMAGES=[]\\nfor p in KEYFRAMES:\\n im=cover_resize(Image.open(p)); im=ImageEnhance.Contrast(im).enhance(1.03); im=ImageEnhance.Color(im).enhance(0.96); IMAGES.append(im)\\n\\ndef scene_at(t):\\n for i,(s,e,idx) in enumerate(SCENES):\\n if s<=t #0:0 (rawvideo (native) -> h264 (libx264))\\n[libx264 @ 0x5787249ae3c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x5787249ae3c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x5787249ae3c0] 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=18.0 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/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1_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= 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=23.0 size= 0kB time=-00:00:00.08 bitrate= -0.0kbits/s speed=N/A \\rframe= 5 fps=0.9 q=23.0 size= 0kB time=00:00:00.12 bitrate= 3.1kbits/s speed=0.023x \\rframe= 11 fps=1.8 q=23.0 size= 0kB time=00:00:00.37 bitrate= 1.0kbits/s speed=0.0621x \\rframe= 17 fps=2.6 q=23.0 size= 256kB time=00:00:00.58 bitrate=3595.8kbits/s speed=0.089x \\rframe= 22 fps=3.1 q=23.0 size= 256kB time=00:00:00.83 bitrate=2517.0kbits/s speed=0.117x \\rframe= 27 fps=3.5 q=23.0 size= 256kB time=00:00:01.04 bitrate=2013.6kbits/s speed=0.136x \\rframe= 32 fps=3.9 q=23.0 size= 256kB time=00:00:01.25 bitrate=1678.0kbits/s speed=0.153x \\rframe= 37 fps=4.3 q=23.0 size= 256kB time=00:00:01.45 bitrate=1438.3kbits/s speed=0.168x \\rframe= 41 fps=4.5 q=23.0 size= 512kB time=00:00:01.62 bitrate=2581.3kbits/s speed=0.177x \\rframe= 48 fps=4.9 q=23.0 size= 512kB time=00:00:01.87 bitrate=2237.2kbits/s speed=0.191x \\rframe= 52 fps=5.0 q=23.0 size= 512kB time=00:00:02.08 bitrate=2013.5kbits/s speed=0.201x \\rframe= 57 fps=5.2 q=23.0 size= 512kB time=00:00:02.29 bitrate=1830.4kbits/s speed=0.21x \\rframe= 63 fps=5.5 q=23.0 size= 512kB time=00:00:02.54 bitrate=1650.4kbits/s speed=0.221x \\rframe= 68 fps=5.6 q=23.0 size= 768kB time=00:00:02.75 bitrate=2287.9kbits/s speed=0.228x \\rframe= 73 fps=5.8 q=23.0 size= 768kB time=00:00:02.95 bitrate=2126.8kbits/s speed=0.235x \\rframe= 78 fps=6.0 q=23.0 size= 768kB time=00:00:03.16 bitrate=1986.9kbits/s speed=0.242x \\rframe= 82 fps=6.0 q=23.0 size= 768kB time=00:00:03.33 bitrate=1887.6kbits/s speed=0.243x \\rframe= 86 fps=6.0 q=23.0 size= 768kB time=00:00:03.50 bitrate=1797.7kbits/s speed=0.244x \\rframe= 90 fps=6.0 q=23.0 size= 768kB time=00:00:03.66 bitrate=1716.0kbits/s speed=0.245x \\rframe= 94 fps=6.0 q=23.0 size= 1024kB time=00:00:03.83 bitrate=2188.4kbits/s speed=0.246x \\rframe= 98 fps=6.1 q=23.0 size= 1024kB time=00:00:04.00 bitrate=2097.2kbits/s speed=0.248x \\rframe= 104 fps=6.2 q=23.0 size= 1024kB time=00:00:04.25 bitrate=1973.9kbits/s speed=0.255x \\rframe= 110 fps=6.4 q=23.0 size= 1024kB time=00:00:04.50 bitrate=1864.2kbits/s speed=0.261x \\rframe= 116 fps=6.5 q=23.0 size= 1280kB time=00:00:04.75 bitrate=2207.6kbits/s speed=0.266x \\rframe= 122 fps=6.6 q=23.0 size= 1280kB time=00:00:05.00 bitrate=2097.2kbits/s speed=0.272x \\rframe= 128 fps=6.7 q=23.0 size= 1280kB time=00:00:05.25 bitrate=1997.4kbits/s speed=0.277x \\rframe= 133 fps=6.8 q=23.0 size= 1280kB time=00:00:05.45 bitrate=1921.1kbits/s speed=0.28x \\rframe= 139 fps=6.9 q=23.0 size= 1536kB time=00:00:05.70 bitrate=2204.4kbits/s speed=0.285x \\rframe= 144 fps=7.0 q=23.0 size= 1536kB time=00:00:05.91 bitrate=2126.8kbits/s speed=0.287x \\rframe= 149 fps=7.1 q=23.0 size= 1792kB time=00:00:06.12 bitrate=2396.8kbits/s speed=0.29x \\rframe= 154 fps=7.1 q=23.0 size= 1792kB time=00:00:06.33 bitrate=2318.0kbits/s speed=0.293x \\rframe= 160 fps=7.2 q=23.0 size= 2048kB time=00:00:06.58 bitrate=2548.5kbits/s speed=0.296x \\rframe= 165 fps=7.3 q=23.0 size= 2048kB time=00:00:06.79 bitrate=2470.3kbits/s speed=0.299x \\rframe= 171 fps=7.3 q=23.0 size= 2048kB time=00:00:07.04 bitrate=2382.6kbits/s speed=0.302x \\rframe= 176 fps=7.4 q=23.0 size= 2048kB time=00:00:07.25 bitrate=2314.2kbits/s speed=0.304x \\rframe= 181 fps=7.4 q=23.0 size= 2304kB time=00:00:07.45 bitrate=2530.7kbits/s speed=0.306x \\rframe= 186 fps=7.5 q=23.0 size= 2304kB time=00:00:07.66 bitrate=2461.9kbits/s speed=0.308x \\rframe= 191 fps=7.5 q=23.0 size= 2304kB time=00:00:07.87 bitrate=2396.8kbits/s speed=0.309x \\rframe= 197 fps=7.6 q=23.0 size= 2304kB time=00:00:08.08 bitrate=2335.0kbits/s speed=0.311x \\rframe= 201 fps=7.6 q=23.0 size= 2304kB time=00:00:08.29 bitrate=2276.4kbits/s speed=0.312x \\rframe= 206 fps=7.6 q=23.0 size= 2560kB time=00:00:08.50 bitrate=2467.3kbits/s speed=0.314x \\rframe= 211 fps=7.6 q=23.0 size= 2560kB time=00:00:08.70 bitrate=2408.3kbits/s speed=0.315x \\rframe= 216 fps=7.7 q=23.0 size= 2560kB time=00:00:08.91 bitrate=2352.0kbits/s speed=0.317x \\rframe= 221 fps=7.7 q=23.0 size= 2560kB time=00:00:09.12 bitrate=2298.3kbits/s speed=0.318x \\rframe= 227 fps=7.8 q=23.0 size= 2560kB time=00:00:09.33 bitrate=2247.0kbits/s speed=0.32x \\rframe= 232 fps=7.8 q=23.0 size= 2816kB time=00:00:09.54 bitrate=2417.7kbits/s speed=0.321x \\rframe= 237 fps=7.8 q=23.0 size= 2816kB time=00:00:09.75 bitrate=2366.1kbits/s speed=0.322x \\rframe= 242 fps=7.9 q=23.0 size= 2816kB time=00:00:09.95 bitrate=2316.6kbits/s speed=0.324x \\rframe= 247 fps=7.9 q=23.0 size= 2816kB time=00:00:10.20 bitrate=2259.8kbits/s speed=0.326x \\rframe= 253 fps=7.9 q=23.0 size= 3072kB time=00:00:10.41 bitrate=2416.0kbits/s speed=0.327x \\rframe= 257 fps=7.9 q=23.0 size= 3072kB time=00:00:10.58 bitrate=2377.9kbits/s speed=0.326x \\rframe= 260 fps=7.8 q=23.0 size= 3072kB time=00:00:10.75 bitrate=2341.0kbits/s speed=0.325x \\rframe= 264 fps=7.8 q=23.0 size= 3328kB time=00:00:10.91 bitrate=2497.4kbits/s speed=0.323x \\rframe= 268 fps=7.8 q=23.0 size= 3328kB time=00:00:11.08 bitrate=2459.9kbits/s speed=0.322x \\rframe= 273 fps=7.8 q=23.0 size= 3328kB time=00:00:11.29 bitrate=2414.5kbits/s speed=0.323x \\rframe= 279 fps=7.9 q=23.0 size= 3328kB time=00:00:11.54 bitrate=2362.2kbits/s speed=0.325x \\rframe= 285 fps=7.9 q=23.0 size= 3328kB time=00:00:11.79 bitrate=2312.1kbits/s speed=0.327x \\rframe= 291 fps=7.9 q=23.0 size= 3328kB time=00:00:12.04 bitrate=2264.1kbits/s speed=0.328x \\rframe= 297 fps=8.0 q=23.0 size= 3584kB time=00:00:12.29 bitrate=2388.7kbits/s speed=0.33x \\rframe= 302 fps=8.0 q=23.0 size= 3584kB time=00:00:12.50 bitrate=2348.8kbits/s speed=0.331x \\rframe= 308 fps=8.0 q=23.0 size= 3584kB time=00:00:12.75 bitrate=2302.8kbits/s speed=0.332x \\rframe= 314 fps=8.1 q=23.0 size= 3840kB time=00:00:13.00 bitrate=2419.8kbits/s speed=0.333x \\rframe= 320 fps=8.1 q=23.0 size= 3840kB time=00:00:13.25 bitrate=2374.2kbits/s speed=0.335x \\rframe= 326 fps=8.1 q=23.0 size= 4096kB time=00:00:13.50 bitrate=2485.5kbits/s speed=0.336x \\rframe= 331 fps=8.1 q=23.0 size= 4096kB time=00:00:13.70 bitrate=2447.8kbits/s speed=0.337x \\rframe= 337 fps=8.2 q=23.0 size= 4096kB time=00:00:13.95 bitrate=2403.9kbits/s speed=0.339x \\rframe= 343 fps=8.2 q=23.0 size= 4352kB time=00:00:14.20 bitrate=2509.2kbits/s speed=0.34x \\rframe= 349 fps=8.2 q=23.0 size= 4352kB time=00:00:14.45 bitrate=2465.8kbits/s speed=0.341x \\rframe= 355 fps=8.3 q=23.0 size= 4352kB time=00:00:14.70 bitrate=2423.9kbits/s speed=0.343x \\rframe= 362 fps=8.3 q=23.0 size= 4352kB time=00:00:14.95 bitrate=2383.4kbits/s speed=0.344x \\rframe= 367 fps=8.3 q=23.0 size= 4352kB time=00:00:15.20 bitrate=2344.2kbits/s speed=0.345x \\rframe= 373 fps=8.4 q=23.0 size= 4608kB time=00:00:15.45 bitrate=2442.0kbits/s speed=0.347x \\rframe= 379 fps=8.4 q=23.0 size= 4608kB time=00:00:15.70 bitrate=2403.1kbits/s speed=0.348x \\rframe= 385 fps=8.4 q=23.0 size= 4608kB time=00:00:15.95 bitrate=2365.5kbits/s speed=0.349x \\rframe= 391 fps=8.4 q=23.0 size= 4608kB time=00:00:16.20 bitrate=2329.0kbits/s speed=0.35x \\rframe= 396 fps=8.5 q=23.0 size= 4864kB time=00:00:16.41 bitrate=2427.2kbits/s speed=0.351x \\rframe= 402 fps=8.5 q=23.0 size= 4864kB time=00:00:16.66 bitrate=2390.8kbits/s speed=0.352x \\rframe= 407 fps=8.5 q=23.0 size= 4864kB time=00:00:16.87 bitrate=2361.3kbits/s speed=0.352x \\rframe= 412 fps=8.5 q=23.0 size= 4864kB time=00:00:17.08 bitrate=2332.5kbits/s speed=0.353x \\rframe= 417 fps=8.5 q=23.0 size= 4864kB time=00:00:17.29 bitrate=2304.4kbits/s speed=0.353x \\rframe= 422 fps=8.5 q=23.0 size= 4864kB time=00:00:17.50 bitrate=2276.9kbits/s speed=0.354x \\rframe= 427 fps=8.5 q=23.0 size= 5120kB time=00:00:17.70 bitrate=2368.6kbits/s speed=0.354x \\rframe= 431 fps=8.5 q=23.0 size= 5120kB time=00:00:17.87 bitrate=2346.5kbits/s speed=0.354x \\rframe= 435 fps=8.5 q=23.0 size= 5120kB time=00:00:18.04 bitrate=2324.8kbits/s speed=0.353x \\rframe= 440 fps=8.5 q=23.0 size= 5120kB time=00:00:18.20 bitrate=2303.5kbits/s speed=0.352x \\rframe= 443 fps=8.5 q=23.0 size= 5120kB time=00:00:18.37 bitrate=2282.6kbits/s speed=0.351x \\rframe= 447 fps=8.4 q=23.0 size= 5120kB time=00:00:18.54 bitrate=2262.1kbits/s speed=0.35x \\rframe= 452 fps=8.4 q=23.0 size= 5376kB time=00:00:18.75 bitrate=2348.8kbits/s speed=0.35x \\rframe= 458 fps=8.5 q=23.0 size= 5376kB time=00:00:18.95 bitrate=2323.0kbits/s speed=0.351x \\rframe= 462 fps=8.5 q=23.0 size= 5376kB time=00:00:19.16 bitrate=2297.8kbits/s speed=0.351x \\rframe= 467 fps=8.5 q=23.0 size= 5376kB time=00:00:19.37 bitrate=2273.1kbits/s speed=0.352x \\rframe= 472 fps=8.5 q=23.0 size= 5376kB time=00:00:19.58 bitrate=2248.9kbits/s speed=0.352x \\rframe= 478 fps=8.5 q=23.0 size= 5632kB time=00:00:19.83 bitrate=2326.3kbits/s speed=0.353x \\rframe= 484 fps=8.5 q=23.0 size= 5632kB time=00:00:20.08 bitrate=2297.3kbits/s speed=0.353x \\rframe= 489 fps=8.5 q=23.0 size= 5632kB time=00:00:20.29 bitrate=2273.7kbits/s speed=0.354x \\rframe= 494 fps=8.5 q=23.0 size= 5888kB time=00:00:20.50 bitrate=2352.9kbits/s speed=0.354x \\rframe= 499 fps=8.6 q=23.0 size= 5888kB time=00:00:20.70 bitrate=2329.2kbits/s speed=0.355x \\rframe= 504 fps=8.6 q=23.0 size= 6144kB time=00:00:20.91 bitrate=2406.3kbits/s speed=0.355x \\rframe= 510 fps=8.6 q=23.0 size= 6144kB time=00:00:21.16 bitrate=2377.9kbits/s speed=0.356x \\rframe= 515 fps=8.6 q=23.0 size= 6144kB time=00:00:21.37 bitrate=2354.7kbits/s speed=0.356x \\rframe= 520 fps=8.6 q=23.0 size= 6144kB time=00:00:21.58 bitrate=2332.0kbits/s speed=0.356x \\rframe= 525 fps=8.6 q=23.0 size= 6144kB time=00:00:21.79 bitrate=2309.7kbits/s speed=0.357x \\rframe= 530 fps=8.6 q=23.0 size= 6400kB time=00:00:22.00 bitrate=2383.1kbits/s speed=0.357x \\rframe= 536 fps=8.6 q=23.0 size= 6400kB time=00:00:22.25 bitrate=2356.4kbits/s speed=0.358x \\rframe= 542 fps=8.6 q=23.0 size= 6400kB time=00:00:22.45 bitrate=2334.5kbits/s speed=0.358x \\rframe= 546 fps=8.6 q=23.0 size= 6400kB time=00:00:22.66 bitrate=2313.1kbits/s speed=0.359x \\rframe= 551 fps=8.6 q=23.0 size= 6400kB time=00:00:22.87 bitrate=2292.0kbits/s speed=0.359x \\rframe= 556 fps=8.7 q=23.0 size= 6400kB time=00:00:23.08 bitrate=2271.3kbits/s speed=0.359x \\rframe= 561 fps=8.7 q=23.0 size= 6656kB time=00:00:23.29 bitrate=2341.0kbits/s speed=0.359x \\rframe= 566 fps=8.7 q=23.0 size= 6656kB time=00:00:23.50 bitrate=2320.3kbits/s speed=0.36x \\rframe= 572 fps=8.7 q=23.0 size= 6656kB time=00:00:23.70 bitrate=2299.9kbits/s speed=0.36x \\rframe= 577 fps=8.7 q=23.0 size= 6656kB time=00:00:23.91 bitrate=2279.8kbits/s speed=0.36x \\rframe= 581 fps=8.7 q=23.0 size= 6656kB time=00:00:24.12 bitrate=2260.2kbits/s speed=0.361x \\rframe= 586 fps=8.7 q=23.0 size= 6656kB time=00:00:24.33 bitrate=2240.8kbits/s speed=0.361x \\rframe= 592 fps=8.7 q=23.0 size= 6912kB time=00:00:24.58 bitrate=2303.3kbits/s speed=0.362x \\rframe= 597 fps=8.7 q=23.0 size= 6912kB time=00:00:24.79 bitrate=2284.0kbits/s speed=0.362x \\rframe= 603 fps=8.7 q=23.0 size= 6912kB time=00:00:25.00 bitrate=2264.9kbits/s speed=0.362x \\rframe= 608 fps=8.7 q=23.0 size= 6912kB time=00:00:25.25 bitrate=2242.5kbits/s speed=0.362x \\rframe= 614 fps=8.7 q=23.0 size= 6912kB time=00:00:25.50 bitrate=2220.5kbits/s speed=0.363x \\rframe= 619 fps=8.7 q=23.0 size= 6912kB time=00:00:25.70 bitrate=2202.5kbits/s speed=0.363x \\rframe= 623 fps=8.7 q=23.0 size= 7168kB time=00:00:25.87 bitrate=2269.4kbits/s speed=0.363x \\rframe= 627 fps=8.7 q=23.0 size= 7168kB time=00:00:26.04 bitrate=2254.9kbits/s speed=0.362x \\rframe= 631 fps=8.7 q=23.0 size= 7168kB time=00:00:26.20 bitrate=2240.5kbits/s speed=0.361x \\rframe= 635 fps=8.7 q=23.0 size= 7168kB time=00:00:26.37 bitrate=2226.4kbits/s speed=0.36x \\rframe= 639 fps=8.7 q=23.0 size= 7168kB time=00:00:26.54 bitrate=2212.4kbits/s speed=0.359x \\rframe= 645 fps=8.7 q=23.0 size= 7168kB time=00:00:26.79 bitrate=2191.8kbits/s speed=0.36x \\rframe= 650 fps=8.7 q=23.0 size= 7168kB time=00:00:27.00 bitrate=2174.8kbits/s speed=0.36x \\rframe= 655 fps=8.7 q=23.0 size= 7168kB time=00:00:27.20 bitrate=2158.2kbits/s speed=0.361x \\rframe= 660 fps=8.7 q=23.0 size= 7424kB time=00:00:27.41 bitrate=2218.3kbits/s speed=0.361x \\rframe= 665 fps=8.7 q=23.0 size= 7424kB time=00:00:27.62 bitrate=2201.5kbits/s speed=0.361x \\rframe= 671 fps=8.7 q=23.0 size= 7424kB time=00:00:27.87 bitrate=2181.8kbits/s speed=0.361x \\rframe= 676 fps=8.7 q=23.0 size= 7424kB time=00:00:28.08 bitrate=2165.6kbits/s speed=0.362x \\rframe= 681 fps=8.7 q=23.0 size= 7680kB time=00:00:28.29 bitrate=2223.8kbits/s speed=0.362x \\rframe= 687 fps=8.7 q=23.0 size= 7680kB time=00:00:28.54 bitrate=2204.3kbits/s speed=0.362x \\rframe= 692 fps=8.7 q=23.0 size= 7936kB time=00:00:28.75 bitrate=2261.3kbits/s speed=0.363x \\rframe= 697 fps=8.7 q=23.0 size= 7936kB time=00:00:28.95 bitrate=2245.0kbits/s speed=0.363x \\rframe= 703 fps=8.7 q=23.0 size= 8192kB time=00:00:29.20 bitrate=2297.6kbits/s speed=0.363x \\rframe= 709 fps=8.8 q=23.0 size= 8192kB time=00:00:29.45 bitrate=2278.1kbits/s speed=0.364x \\rframe= 714 fps=8.8 q=23.0 size= 8192kB time=00:00:29.66 bitrate=2262.1kbits/s speed=0.364x \\rframe= 720 fps=8.8 q=23.0 size= 8192kB time=00:00:29.91 bitrate=2243.2kbits/s speed=0.364x \\rframe= 726 fps=8.8 q=23.0 size= 8448kB time=00:00:30.16 bitrate=2294.1kbits/s speed=0.365x \\rframe= 732 fps=8.8 q=23.0 size= 8448kB time=00:00:30.41 bitrate=2275.3kbits/s speed=0.365x \\rframe= 737 fps=8.8 q=23.0 size= 8448kB time=00:00:30.62 bitrate=2259.8kbits/s speed=0.365x \\rframe= 742 fps=8.8 q=20.0 size= 8448kB time=00:00:30.83 bitrate=2244.5kbits/s speed=0.366x \\rframe= 748 fps=8.8 q=23.0 size= 8704kB time=00:00:31.08 bitrate=2293.9kbits/s speed=0.366x \\rframe= 754 fps=8.8 q=23.0 size= 8960kB time=00:00:31.33 bitrate=2342.6kbits/s speed=0.366x \\rframe= 759 fps=8.8 q=23.0 size= 8960kB time=00:00:31.54 bitrate=2327.1kbits/s speed=0.367x \\rframe= 764 fps=8.8 q=23.0 size= 8960kB time=00:00:31.75 bitrate=2311.8kbits/s speed=0.367x \\rframe= 770 fps=8.8 q=23.0 size= 8960kB time=00:00:32.00 bitrate=2293.8kbits/s speed=0.367x \\rframe= 775 fps=8.8 q=23.0 size= 8960kB time=00:00:32.20 bitrate=2278.9kbits/s speed=0.367x \\rframe= 780 fps=8.8 q=23.0 size= 9216kB time=00:00:32.41 bitrate=2329.0kbits/s speed=0.367x \\rframe= 785 fps=8.8 q=23.0 size= 9216kB time=00:00:32.62 bitrate=2314.1kbits/s speed=0.367x \\rframe= 789 fps=8.8 q=23.0 size= 9216kB time=00:00:32.79 bitrate=2302.3kbits/s speed=0.367x \\rframe= 793 fps=8.8 q=23.0 size= 9216kB time=00:00:32.95 bitrate=2290.7kbits/s speed=0.366x \\rframe= 797 fps=8.8 q=23.0 size= 9216kB time=00:00:33.12 bitrate=2279.2kbits/s speed=0.365x \\rframe= 801 fps=8.8 q=23.0 size= 9472kB time=00:00:33.29 bitrate=2330.8kbits/s speed=0.364x \\rframe= 806 fps=8.8 q=23.0 size= 9472kB time=00:00:33.50 bitrate=2316.3kbits/s speed=0.365x \\rframe= 812 fps=8.8 q=23.0 size= 9472kB time=00:00:33.75 bitrate=2299.1kbits/s speed=0.365x \\rframe= 817 fps=8.8 q=23.0 size= 9472kB time=00:00:33.95 bitrate=2285.0kbits/s speed=0.365x \\rframe= 823 fps=8.8 q=23.0 size= 9728kB time=00:00:34.20 bitrate=2329.6kbits/s speed=0.366x \\rframe= 829 fps=8.8 q=23.0 si\\n\\n... [OUTPUT TRUNCATED - 11879 chars omitted out of 61879 total] ...\\n\\n0 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=0.2 q=23.0 size= 0kB time=-00:00:00.04 bitrate=N/A speed=N/A \\rframe= 6 fps=1.0 q=23.0 size= 0kB time=00:00:00.16 bitrate= 2.3kbits/s speed=0.0281x \\rframe= 11 fps=1.7 q=23.0 size= 0kB time=00:00:00.37 bitrate= 1.0kbits/s speed=0.0577x \\rframe= 17 fps=2.4 q=23.0 size= 256kB time=00:00:00.58 bitrate=3595.8kbits/s speed=0.0827x \\rframe= 21 fps=2.8 q=23.0 size= 256kB time=00:00:00.79 bitrate=2649.5kbits/s speed=0.104x \\rframe= 26 fps=3.2 q=23.0 size= 256kB time=00:00:01.00 bitrate=2097.5kbits/s speed=0.123x \\rframe= 31 fps=3.6 q=23.0 size= 256kB time=00:00:01.20 bitrate=1735.9kbits/s speed=0.14x \\rframe= 37 fps=4.0 q=23.0 size= 256kB time=00:00:01.45 bitrate=1438.3kbits/s speed=0.158x \\rframe= 42 fps=4.3 q=23.0 size= 512kB time=00:00:01.66 bitrate=2516.8kbits/s speed=0.171x \\rframe= 47 fps=4.6 q=23.0 size= 512kB time=00:00:01.87 bitrate=2237.2kbits/s speed=0.182x \\rframe= 53 fps=4.9 q=23.0 size= 512kB time=00:00:02.08 bitrate=2013.5kbits/s speed=0.192x \\rframe= 58 fps=5.1 q=23.0 size= 512kB time=00:00:02.29 bitrate=1830.4kbits/s speed=0.202x \\rframe= 62 fps=5.2 q=23.0 size= 512kB time=00:00:02.50 bitrate=1677.9kbits/s speed=0.21x \\rframe= 67 fps=5.4 q=23.0 size= 768kB time=00:00:02.70 bitrate=2323.1kbits/s speed=0.218x \\rframe= 73 fps=5.6 q=23.0 size= 768kB time=00:00:02.95 bitrate=2126.8kbits/s speed=0.227x \\rframe= 79 fps=5.8 q=23.0 size= 768kB time=00:00:03.16 bitrate=1986.9kbits/s speed=0.234x \\rframe= 81 fps=5.7 q=23.0 size= 768kB time=00:00:03.29 bitrate=1911.4kbits/s speed=0.234x \\rframe= 85 fps=5.8 q=23.0 size= 768kB time=00:00:03.45 bitrate=1819.3kbits/s speed=0.235x \\rframe= 89 fps=5.8 q=23.0 size= 1024kB time=00:00:03.62 bitrate=2314.2kbits/s speed=0.237x \\rframe= 93 fps=5.8 q=23.0 size= 1024kB time=00:00:03.79 bitrate=2212.5kbits/s speed=0.237x \\rframe= 96 fps=5.8 q=23.0 size= 1024kB time=00:00:03.91 bitrate=2141.9kbits/s speed=0.238x \\rframe= 102 fps=6.0 q=23.0 size= 1024kB time=00:00:04.16 bitrate=2013.4kbits/s speed=0.245x \\rframe= 109 fps=6.2 q=23.0 size= 1024kB time=00:00:04.41 bitrate=1899.4kbits/s speed=0.251x \\rframe= 114 fps=6.3 q=23.0 size= 1280kB time=00:00:04.66 bitrate=2247.0kbits/s speed=0.256x \\rframe= 120 fps=6.4 q=23.0 size= 1280kB time=00:00:04.91 bitrate=2132.8kbits/s speed=0.261x \\rframe= 126 fps=6.5 q=23.0 size= 1280kB time=00:00:05.16 bitrate=2029.6kbits/s speed=0.266x \\rframe= 132 fps=6.6 q=23.0 size= 1280kB time=00:00:05.37 bitrate=1950.9kbits/s speed=0.269x \\rframe= 137 fps=6.7 q=23.0 size= 1536kB time=00:00:05.58 bitrate=2253.7kbits/s speed=0.272x \\rframe= 142 fps=6.7 q=23.0 size= 1536kB time=00:00:05.83 bitrate=2157.1kbits/s speed=0.277x \\rframe= 147 fps=6.8 q=23.0 size= 1792kB time=00:00:06.04 bitrate=2429.9kbits/s speed=0.28x \\rframe= 153 fps=6.9 q=23.0 size= 2048kB time=00:00:06.29 bitrate=2666.6kbits/s speed=0.284x \\rframe= 160 fps=7.0 q=23.0 size= 2048kB time=00:00:06.54 bitrate=2564.7kbits/s speed=0.288x \\rframe= 165 fps=7.1 q=23.0 size= 2048kB time=00:00:06.79 bitrate=2470.3kbits/s speed=0.291x \\rframe= 171 fps=7.2 q=23.0 size= 2048kB time=00:00:07.04 bitrate=2382.6kbits/s speed=0.295x \\rframe= 176 fps=7.2 q=23.0 size= 2048kB time=00:00:07.25 bitrate=2314.2kbits/s speed=0.297x \\rframe= 181 fps=7.3 q=23.0 size= 2304kB time=00:00:07.45 bitrate=2530.7kbits/s speed=0.299x \\rframe= 186 fps=7.3 q=23.0 size= 2304kB time=00:00:07.66 bitrate=2461.9kbits/s speed=0.301x \\rframe= 191 fps=7.4 q=23.0 size= 2304kB time=00:00:07.87 bitrate=2396.8kbits/s speed=0.303x \\rframe= 196 fps=7.4 q=23.0 size= 2304kB time=00:00:08.08 bitrate=2335.0kbits/s speed=0.305x \\rframe= 201 fps=7.4 q=23.0 size= 2304kB time=00:00:08.29 bitrate=2276.4kbits/s speed=0.307x \\rframe= 206 fps=7.5 q=23.0 size= 2560kB time=00:00:08.50 bitrate=2467.3kbits/s speed=0.308x \\rframe= 211 fps=7.5 q=23.0 size= 2560kB time=00:00:08.70 bitrate=2408.3kbits/s speed=0.31x \\rframe= 216 fps=7.5 q=23.0 size= 2560kB time=00:00:08.91 bitrate=2352.0kbits/s speed=0.311x \\rframe= 221 fps=7.6 q=23.0 size= 2560kB time=00:00:09.12 bitrate=2298.3kbits/s speed=0.312x \\rframe= 227 fps=7.6 q=23.0 size= 2560kB time=00:00:09.33 bitrate=2247.0kbits/s speed=0.313x \\rframe= 231 fps=7.6 q=23.0 size= 2816kB time=00:00:09.54 bitrate=2417.7kbits/s speed=0.315x \\rframe= 236 fps=7.7 q=23.0 size= 2816kB time=00:00:09.75 bitrate=2366.1kbits/s speed=0.316x \\rframe= 242 fps=7.7 q=23.0 size= 2816kB time=00:00:09.95 bitrate=2316.6kbits/s speed=0.317x \\rframe= 247 fps=7.7 q=23.0 size= 2816kB time=00:00:10.16 bitrate=2269.1kbits/s speed=0.319x \\rframe= 251 fps=7.7 q=23.0 size= 2816kB time=00:00:10.37 bitrate=2223.5kbits/s speed=0.32x \\rframe= 255 fps=7.7 q=23.0 size= 3072kB time=00:00:10.54 bitrate=2387.3kbits/s speed=0.319x \\rframe= 259 fps=7.7 q=23.0 size= 3072kB time=00:00:10.70 bitrate=2350.2kbits/s speed=0.318x \\rframe= 263 fps=7.7 q=23.0 size= 3328kB time=00:00:10.87 bitrate=2507.0kbits/s speed=0.317x \\rframe= 267 fps=7.6 q=23.0 size= 3328kB time=00:00:11.04 bitrate=2469.1kbits/s speed=0.316x \\rframe= 272 fps=7.7 q=23.0 size= 3328kB time=00:00:11.20 bitrate=2432.4kbits/s speed=0.316x \\rframe= 278 fps=7.7 q=23.0 size= 3328kB time=00:00:11.45 bitrate=2379.3kbits/s speed=0.318x \\rframe= 282 fps=7.7 q=23.0 size= 3328kB time=00:00:11.66 bitrate=2336.9kbits/s speed=0.319x \\rframe= 287 fps=7.7 q=23.0 size= 3328kB time=00:00:11.87 bitrate=2295.9kbits/s speed=0.32x \\rframe= 292 fps=7.8 q=23.0 size= 3584kB time=00:00:12.08 bitrate=2429.8kbits/s speed=0.321x \\rframe= 297 fps=7.8 q=23.0 size= 3584kB time=00:00:12.29 bitrate=2388.7kbits/s speed=0.322x \\rframe= 302 fps=7.8 q=23.0 size= 3584kB time=00:00:12.50 bitrate=2348.8kbits/s speed=0.323x \\rframe= 308 fps=7.8 q=23.0 size= 3584kB time=00:00:12.75 bitrate=2302.8kbits/s speed=0.325x \\rframe= 314 fps=7.9 q=23.0 size= 3840kB time=00:00:13.00 bitrate=2419.8kbits/s speed=0.326x \\rframe= 320 fps=7.9 q=23.0 size= 4096kB time=00:00:13.25 bitrate=2532.4kbits/s speed=0.328x \\rframe= 326 fps=8.0 q=23.0 size= 4096kB time=00:00:13.50 bitrate=2485.5kbits/s speed=0.329x \\rframe= 332 fps=8.0 q=23.0 size= 4096kB time=00:00:13.75 bitrate=2440.4kbits/s speed=0.331x \\rframe= 339 fps=8.0 q=23.0 size= 4096kB time=00:00:14.00 bitrate=2396.8kbits/s speed=0.332x \\rframe= 344 fps=8.0 q=23.0 size= 4352kB time=00:00:14.25 bitrate=2501.9kbits/s speed=0.333x \\rframe= 350 fps=8.1 q=23.0 size= 4352kB time=00:00:14.50 bitrate=2458.8kbits/s speed=0.335x \\rframe= 355 fps=8.1 q=23.0 size= 4352kB time=00:00:14.70 bitrate=2423.9kbits/s speed=0.335x \\rframe= 360 fps=8.1 q=23.0 size= 4352kB time=00:00:14.91 bitrate=2390.1kbits/s speed=0.336x \\rframe= 365 fps=8.1 q=23.0 size= 4608kB time=00:00:15.12 bitrate=2495.8kbits/s speed=0.336x \\rframe= 371 fps=8.2 q=23.0 size= 4608kB time=00:00:15.33 bitrate=2461.9kbits/s speed=0.337x \\rframe= 376 fps=8.2 q=23.0 size= 4608kB time=00:00:15.58 bitrate=2422.4kbits/s speed=0.338x \\rframe= 382 fps=8.2 q=23.0 size= 4608kB time=00:00:15.83 bitrate=2384.2kbits/s speed=0.34x \\rframe= 389 fps=8.2 q=23.0 size= 4608kB time=00:00:16.08 bitrate=2347.1kbits/s speed=0.341x \\rframe= 394 fps=8.2 q=23.0 size= 4864kB time=00:00:16.33 bitrate=2439.6kbits/s speed=0.342x \\rframe= 400 fps=8.3 q=23.0 size= 4864kB time=00:00:16.58 bitrate=2402.8kbits/s speed=0.343x \\rframe= 405 fps=8.3 q=23.0 size= 4864kB time=00:00:16.79 bitrate=2373.0kbits/s speed=0.343x \\rframe= 410 fps=8.3 q=23.0 size= 4864kB time=00:00:17.00 bitrate=2343.9kbits/s speed=0.344x \\rframe= 415 fps=8.3 q=23.0 size= 4864kB time=00:00:17.20 bitrate=2315.5kbits/s speed=0.344x \\rframe= 420 fps=8.3 q=23.0 size= 5120kB time=00:00:17.41 bitrate=2408.2kbits/s speed=0.345x \\rframe= 425 fps=8.3 q=23.0 size= 5120kB time=00:00:17.62 bitrate=2379.8kbits/s speed=0.345x \\rframe= 430 fps=8.3 q=23.0 size= 5120kB time=00:00:17.83 bitrate=2352.0kbits/s speed=0.345x \\rframe= 433 fps=8.3 q=23.0 size= 5120kB time=00:00:17.95 bitrate=2335.6kbits/s speed=0.344x \\rframe= 437 fps=8.3 q=23.0 size= 5120kB time=00:00:18.12 bitrate=2314.1kbits/s speed=0.343x \\rframe= 441 fps=8.2 q=23.0 size= 5120kB time=00:00:18.29 bitrate=2293.0kbits/s speed=0.342x \\rframe= 444 fps=8.2 q=23.0 size= 5120kB time=00:00:18.41 bitrate=2277.5kbits/s speed=0.341x \\rframe= 447 fps=8.2 q=23.0 size= 5120kB time=00:00:18.54 bitrate=2262.1kbits/s speed=0.34x \\rframe= 452 fps=8.2 q=23.0 size= 5376kB time=00:00:18.75 bitrate=2348.8kbits/s speed=0.34x \\rframe= 457 fps=8.2 q=23.0 size= 5376kB time=00:00:18.95 bitrate=2323.0kbits/s speed=0.341x \\rframe= 462 fps=8.2 q=23.0 size= 5376kB time=00:00:19.16 bitrate=2297.8kbits/s speed=0.341x \\rframe= 467 fps=8.2 q=23.0 size= 5376kB time=00:00:19.37 bitrate=2273.1kbits/s speed=0.342x \\rframe= 472 fps=8.3 q=23.0 size= 5376kB time=00:00:19.58 bitrate=2248.9kbits/s speed=0.343x \\rframe= 478 fps=8.3 q=23.0 size= 5632kB time=00:00:19.83 bitrate=2326.3kbits/s speed=0.343x \\rframe= 483 fps=8.3 q=23.0 size= 5632kB time=00:00:20.04 bitrate=2302.1kbits/s speed=0.344x \\rframe= 488 fps=8.3 q=23.0 size= 5632kB time=00:00:20.25 bitrate=2278.4kbits/s speed=0.344x \\rframe= 493 fps=8.3 q=23.0 size= 5888kB time=00:00:20.45 bitrate=2357.7kbits/s speed=0.345x \\rframe= 498 fps=8.3 q=23.0 size= 5888kB time=00:00:20.66 bitrate=2333.9kbits/s speed=0.345x \\rframe= 503 fps=8.3 q=23.0 size= 6144kB time=00:00:20.87 bitrate=2411.1kbits/s speed=0.346x \\rframe= 509 fps=8.4 q=23.0 size= 6144kB time=00:00:21.08 bitrate=2387.3kbits/s speed=0.346x \\rframe= 513 fps=8.3 q=23.0 size= 6144kB time=00:00:21.29 bitrate=2363.9kbits/s speed=0.347x \\rframe= 518 fps=8.4 q=23.0 size= 6144kB time=00:00:21.50 bitrate=2341.0kbits/s speed=0.347x \\rframe= 523 fps=8.4 q=23.0 size= 6144kB time=00:00:21.70 bitrate=2318.6kbits/s speed=0.347x \\rframe= 528 fps=8.4 q=23.0 size= 6400kB time=00:00:21.91 bitrate=2392.2kbits/s speed=0.347x \\rframe= 535 fps=8.4 q=23.0 size= 6400kB time=00:00:22.16 bitrate=2365.2kbits/s speed=0.348x \\rframe= 539 fps=8.4 q=23.0 size= 6400kB time=00:00:22.37 bitrate=2343.2kbits/s speed=0.348x \\rframe= 544 fps=8.4 q=23.0 size= 6400kB time=00:00:22.58 bitrate=2321.6kbits/s speed=0.348x \\rframe= 549 fps=8.4 q=23.0 size= 6400kB time=00:00:22.79 bitrate=2300.4kbits/s speed=0.349x \\rframe= 554 fps=8.4 q=23.0 size= 6400kB time=00:00:23.00 bitrate=2279.5kbits/s speed=0.349x \\rframe= 559 fps=8.4 q=23.0 size= 6656kB time=00:00:23.20 bitrate=2349.4kbits/s speed=0.349x \\rframe= 564 fps=8.4 q=23.0 size= 6656kB time=00:00:23.41 bitrate=2328.5kbits/s speed=0.35x \\rframe= 569 fps=8.4 q=23.0 size= 6656kB time=00:00:23.62 bitrate=2308.0kbits/s speed=0.35x \\rframe= 574 fps=8.4 q=23.0 size= 6656kB time=00:00:23.83 bitrate=2287.8kbits/s speed=0.35x \\rframe= 580 fps=8.5 q=23.0 size= 6656kB time=00:00:24.08 bitrate=2264.1kbits/s speed=0.351x \\rframe= 586 fps=8.5 q=23.0 size= 6656kB time=00:00:24.33 bitrate=2240.8kbits/s speed=0.352x \\rframe= 591 fps=8.5 q=23.0 size= 6912kB time=00:00:24.54 bitrate=2307.2kbits/s speed=0.352x \\rframe= 596 fps=8.5 q=23.0 size= 6912kB time=00:00:24.75 bitrate=2287.8kbits/s speed=0.352x \\rframe= 602 fps=8.5 q=23.0 size= 6912kB time=00:00:25.00 bitrate=2264.9kbits/s speed=0.353x \\rframe= 609 fps=8.5 q=23.0 size= 6912kB time=00:00:25.25 bitrate=2242.5kbits/s speed=0.353x \\rframe= 614 fps=8.5 q=23.0 size= 6912kB time=00:00:25.50 bitrate=2220.5kbits/s speed=0.354x \\rframe= 620 fps=8.5 q=23.0 size= 6912kB time=00:00:25.75 bitrate=2199.0kbits/s speed=0.355x \\rframe= 624 fps=8.5 q=23.0 size= 7168kB time=00:00:25.91 bitrate=2265.7kbits/s speed=0.354x \\rframe= 627 fps=8.5 q=23.0 size= 7168kB time=00:00:26.04 bitrate=2254.9kbits/s speed=0.353x \\rframe= 631 fps=8.5 q=23.0 size= 7168kB time=00:00:26.20 bitrate=2240.5kbits/s speed=0.353x \\rframe= 635 fps=8.5 q=23.0 size= 7168kB time=00:00:26.37 bitrate=2226.4kbits/s speed=0.352x \\rframe= 639 fps=8.5 q=23.0 size= 7168kB time=00:00:26.54 bitrate=2212.4kbits/s speed=0.351x \\rframe= 645 fps=8.5 q=23.0 size= 7168kB time=00:00:26.79 bitrate=2191.8kbits/s speed=0.352x \\rframe= 651 fps=8.5 q=23.0 size= 7424kB time=00:00:27.04 bitrate=2249.0kbits/s speed=0.353x \\rframe= 656 fps=8.5 q=23.0 size= 7424kB time=00:00:27.25 bitrate=2231.8kbits/s speed=0.353x \\rframe= 661 fps=8.5 q=23.0 size= 7424kB time=00:00:27.45 bitrate=2214.9kbits/s speed=0.353x \\rframe= 666 fps=8.5 q=23.0 size= 7424kB time=00:00:27.66 bitrate=2198.2kbits/s speed=0.354x \\rframe= 671 fps=8.5 q=23.0 size= 7424kB time=00:00:27.87 bitrate=2181.8kbits/s speed=0.354x \\rframe= 676 fps=8.5 q=23.0 size= 7424kB time=00:00:28.08 bitrate=2165.6kbits/s speed=0.354x \\rframe= 681 fps=8.5 q=23.0 size= 7680kB time=00:00:28.29 bitrate=2223.8kbits/s speed=0.354x \\rframe= 686 fps=8.5 q=23.0 size= 7680kB time=00:00:28.50 bitrate=2207.5kbits/s speed=0.354x \\rframe= 691 fps=8.5 q=23.0 size= 7936kB time=00:00:28.70 bitrate=2264.6kbits/s speed=0.355x \\rframe= 696 fps=8.5 q=23.0 size= 7936kB time=00:00:28.91 bitrate=2248.3kbits/s speed=0.355x \\rframe= 701 fps=8.5 q=23.0 size= 8192kB time=00:00:29.12 bitrate=2304.2kbits/s speed=0.355x \\rframe= 706 fps=8.6 q=23.0 size= 8192kB time=00:00:29.33 bitrate=2287.8kbits/s speed=0.355x \\rframe= 712 fps=8.6 q=23.0 size= 8192kB time=00:00:29.54 bitrate=2271.7kbits/s speed=0.356x \\rframe= 716 fps=8.6 q=23.0 size= 8192kB time=00:00:29.75 bitrate=2255.8kbits/s speed=0.356x \\rframe= 721 fps=8.6 q=23.0 size= 8192kB time=00:00:29.95 bitrate=2240.1kbits/s speed=0.356x \\rframe= 726 fps=8.6 q=23.0 size= 8448kB time=00:00:30.16 bitrate=2294.1kbits/s speed=0.356x \\rframe= 731 fps=8.6 q=23.0 size= 8448kB time=00:00:30.37 bitrate=2278.4kbits/s speed=0.356x \\rframe= 736 fps=8.6 q=23.0 size= 8448kB time=00:00:30.58 bitrate=2262.9kbits/s speed=0.357x \\rframe= 741 fps=8.6 q=23.0 size= 8448kB time=00:00:30.79 bitrate=2247.6kbits/s speed=0.357x \\rframe= 746 fps=8.6 q=23.0 size= 8704kB time=00:00:31.00 bitrate=2300.1kbits/s speed=0.357x \\rframe= 753 fps=8.6 q=23.0 size= 8960kB time=00:00:31.25 bitrate=2348.8kbits/s speed=0.358x \\rframe= 758 fps=8.6 q=23.0 size= 8960kB time=00:00:31.45 bitrate=2333.3kbits/s speed=0.358x \\rframe= 762 fps=8.6 q=23.0 size= 8960kB time=00:00:31.66 bitrate=2317.9kbits/s speed=0.358x \\rframe= 767 fps=8.6 q=23.0 size= 8960kB time=00:00:31.87 bitrate=2302.8kbits/s speed=0.359x \\rframe= 772 fps=8.6 q=23.0 size= 8960kB time=00:00:32.08 bitrate=2287.8kbits/s speed=0.359x \\rframe= 778 fps=8.6 q=23.0 size= 9216kB time=00:00:32.29 bitrate=2338.0kbits/s speed=0.359x \\rframe= 782 fps=8.6 q=23.0 size= 9216kB time=00:00:32.50 bitrate=2323.0kbits/s speed=0.359x \\rframe= 786 fps=8.6 q=23.0 size= 9216kB time=00:00:32.66 bitrate=2311.2kbits/s speed=0.359x \\rframe= 790 fps=8.6 q=23.0 size= 9216kB time=00:00:32.83 bitrate=2299.4kbits/s speed=0.358x \\rframe= 793 fps=8.6 q=23.0 size= 9216kB time=00:00:32.95 bitrate=2290.7kbits/s speed=0.357x \\rframe= 797 fps=8.6 q=23.0 size= 9216kB time=00:00:33.12 bitrate=2279.2kbits/s speed=0.357x \\rframe= 801 fps=8.6 q=23.0 size= 9472kB time=00:00:33.29 bitrate=2330.8kbits/s speed=0.356x \\rframe= 806 fps=8.6 q=23.0 size= 9472kB time=00:00:33.50 bitrate=2316.3kbits/s speed=0.356x \\rframe= 812 fps=8.6 q=23.0 size= 9472kB time=00:00:33.75 bitrate=2299.1kbits/s speed=0.356x \\rframe= 818 fps=8.6 q=23.0 size= 9472kB time=00:00:34.00 bitrate=2282.2kbits/s speed=0.357x \\rframe= 823 fps=8.6 q=23.0 size= 9728kB time=00:00:34.20 bitrate=2329.6kbits/s speed=0.357x \\rframe= 829 fps=8.6 q=23.0 size= 9728kB time=00:00:34.45 bitrate=2312.7kbits/s speed=0.358x \\rframe= 834 fps=8.6 q=23.0 size= 9728kB time=00:00:34.66 bitrate=2298.8kbits/s speed=0.358x \\rframe= 839 fps=8.6 q=23.0 size= 9728kB time=00:00:34.87 bitrate=2285.1kbits/s speed=0.358x \\rframe= 844 fps=8.6 q=23.0 size= 9984kB time=00:00:35.08 bitrate=2331.3kbits/s speed=0.358x \\rframe= 849 fps=8.6 q=23.0 size= 9984kB time=00:00:35.29 bitrate=2317.5kbits/s speed=0.358x \\rframe= 854 fps=8.6 q=23.0 size= 10240kB time=00:00:35.50 bitrate=2363.0kbits/s speed=0.359x \\rframe= 860 fps=8.6 q=23.0 size= 10496kB time=00:00:35.75 bitrate=2405.1kbits/s speed=0.359x \\rframe= 866 fps=8.6 q=23.0 size= 10496kB time=00:00:36.00 bitrate=2388.4kbits/s speed=0.359x \\rframe= 871 fps=8.6 q=23.0 size= 10496kB time=00:00:36.20 bitrate=2374.7kbits/s speed=0.36x \\rframe= 876 fps=8.7 q=23.0 size= 10496kB time=00:00:36.41 bitrate=2361.1kbits/s speed=0.36x \\rframe= 881 fps=8.7 q=23.0 size= 10496kB time=00:00:36.62 bitrate=2347.7kbits/s speed=0.36x \\rframe= 886 fps=8.7 q=23.0 size= 10752kB time=00:00:36.83 bitrate=2391.3kbits/s speed=0.36x \\rframe= 891 fps=8.7 q=23.0 size= 10752kB time=00:00:37.04 bitrate=2377.9kbits/s speed=0.361x \\rframe= 896 fps=8.7 q=23.0 size= 10752kB time=00:00:37.25 bitrate=2364.6kbits/s speed=0.361x \\rframe= 901 fps=8.7 q=23.0 size= 10752kB time=00:00:37.45 bitrate=2351.4kbits/s speed=0.361x \\rframe= 907 fps=8.7 q=23.0 size= 10752kB time=00:00:37.70 bitrate=2335.8kbits/s speed=0.362x \\rframe= 913 fps=8.7 q=23.0 size= 11008kB time=00:00:37.95 bitrate=2375.7kbits/s speed=0.362x \\rframe= 919 fps=8.7 q=23.0 size= 11008kB time=00:00:38.20 bitrate=2360.2kbits/s speed=0.363x \\rframe= 925 fps=8.7 q=23.0 size= 11008kB time=00:00:38.45 bitrate=2344.8kbits/s speed=0.363x \\rframe= 931 fps=8.7 q=23.0 size= 11008kB time=00:00:38.70 bitrate=2329.7kbits/s speed=0.363x \\rframe= 937 fps=8.8 q=23.0 size= 11264kB time=00:00:38.95 bitrate=2368.6kbits/s speed=0.364x \\rframe= 943 fps=8.8 q=23.0 size= 11264kB time=00:00:39.20 bitrate=2353.5kbits/s speed=0.364x \\rframe= 949 fps=8.8 q=23.0 size= 11264kB time=00:00:39.45 bitrate=2338.5kbits/s speed=0.365x \\r[out#0/mp4 @ 0x5776c0e02d00] video:12009kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.105985%\\nframe= 1005 fps=9.2 q=-1.0 Lsize= 12022kB time=00:00:41.75 bitrate=2358.8kbits/s speed=0.381x \\n[libx264 @ 0x5776c0e043c0] frame I:5 Avg QP:11.78 size:175779\\n[libx264 @ 0x5776c0e043c0] frame P:259 Avg QP:14.12 size: 29732\\n[libx264 @ 0x5776c0e043c0] frame B:741 Avg QP:17.00 size: 5016\\n[libx264 @ 0x5776c0e043c0] consecutive B-frames: 0.5% 2.6% 3.0% 93.9%\\n[libx264 @ 0x5776c0e043c0] mb I I16..4: 8.1% 71.6% 20.3%\\n[libx264 @ 0x5776c0e043c0] mb P I16..4: 1.5% 3.3% 1.8% P16..4: 43.2% 16.8% 9.3% 0.0% 0.0% skip:24.1%\\n[libx264 @ 0x5776c0e043c0] mb B I16..4: 0.1% 0.1% 0.0% B16..8: 37.5% 1.1% 0.1% direct: 1.2% skip:59.8% L0:49.0% L1:48.0% BI: 3.0%\\n[libx264 @ 0x5776c0e043c0] 8x8 transform intra:53.3% inter:89.5%\\n[libx264 @ 0x5776c0e043c0] coded y,uvDC,uvAC intra: 55.0% 50.0% 27.5% inter: 10.6% 6.9% 0.8%\\n[libx264 @ 0x5776c0e043c0] i16 v,h,dc,p: 34% 26% 7% 33%\\n[libx264 @ 0x5776c0e043c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 22% 28% 4% 4% 4% 4% 3% 5%\\n[libx264 @ 0x5776c0e043c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 38% 27% 15% 3% 4% 5% 4% 2% 2%\\n[libx264 @ 0x5776c0e043c0] i8c dc,h,v,p: 52% 22% 22% 4%\\n[libx264 @ 0x5776c0e043c0] Weighted P-Frames: Y:4.6% UV:4.2%\\n[libx264 @ 0x5776c0e043c0] ref P L0: 57.6% 2.5% 22.5% 17.2% 0.1%\\n[libx264 @ 0x5776c0e043c0] ref B L0: 80.1% 12.6% 7.3%\\n[libx264 @ 0x5776c0e043c0] ref B L1: 93.3% 6.7%\\n[libx264 @ 0x5776c0e043c0] kb/s:2349.15\\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/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2_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: 2351 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 2349 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 @ 0x58f63beff600] 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/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.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, 2349 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= 10496kB time=00:00:35.50 bitrate=2422.1kbits/s speed= 71x \\r[out#0/mp4 @ 0x58f63be5f1c0] video:12009kB audio:321kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.203251%\\nsize= 12354kB time=00:00:41.75 bitrate=2424.1kbits/s speed=73.8x \\n[aac @ 0x58f63be71a80] Qavg: 17882.781\\n{\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.3.0-visible-invite-cinematic-ab\\\",\\n \\\"status\\\": \\\"review_preview_only_not_posted\\\",\\n \\\"variants\\\": {\\n \\\"b1\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.3.0-b1-visible-invite-ai-only\\\",\\n \\\"variant\\\": \\\"b1\\\",\\n \\\"mode\\\": \\\"visible_invite_cinematic_ai_only\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4\\\",\\n \\\"preview_sha256\\\": \\\"04d26c5eff645ec852755f072695693c3f862232ad9e49b891656054933ab16e\\\",\\n \\\"duration_seconds\\\": 41.852,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"script_hash\\\": \\\"0e9ec7f162b69573\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/b1_contact_sheet_v1.jpg\\\",\\n \\\"keyframes_contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/visible_invite_keyframes_contact_sheet_v1.jpg\\\",\\n \\\"keyframes\\\": [\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_01_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_02_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_03_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_04_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_05_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_06_openai_codex_gpt-image-2-high.png\\\"\\n ],\\n \\\"NoOverlayPolicy\\\": {\\n \\\"result\\\": \\\"pass\\\",\\n \\\"allowed\\\": [\\n \\\"subtitles_only\\\"\\n ]\\n },\\n \\\"blocked\\\": {\\n \\\"wan_used\\\": false,\\n \\\"i2v_used\\\": false,\\n \\\"t2v_used\\\": false,\\n \\\"platform_api_used\\\": false,\\n \\\"posting\\\": false\\n }\\n },\\n \\\"b2\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.3.0-b2-visible-invite-minimal-focus\\\",\\n \\\"variant\\\": \\\"b2\\\",\\n \\\"mode\\\": \\\"visible_invite_cinematic_minimal_focus_layer\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4\\\",\\n \\\"preview_sha256\\\": \\\"63d8cdd8347f27b86ed4e03046160a1d19e10491ad747b0c1df72fa0897480b7\\\",\\n \\\"duration_seconds\\\": 41.852,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"script_hash\\\": \\\"0e9ec7f162b69573\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/b2_contact_sheet_v1.jpg\\\",\\n \\\"keyframes_contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/visible_invite_keyframes_contact_sheet_v1.jpg\\\",\\n \\\"keyframes\\\": [\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_01_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_02_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_03_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_04_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_05_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes/visible_invite_keyframe_06_openai_codex_gpt-image-2-high.png\\\"\\n ],\\n \\\"NoOverlayPolicy\\\": {\\n \\\"result\\\": \\\"modified_for_B2_minimal_focus\\\",\\n \\\"allowed\\\": [\\n \\\"subtitles\\\",\\n \\\"subtle_focus_outline_no_text_no_labels_no_arrows\\\"\\n ]\\n },\\n \\\"blocked\\\": {\\n \\\"wan_used\\\": false,\\n \\\"i2v_used\\\": false,\\n \\\"t2v_used\\\": false,\\n \\\"platform_api_used\\\": false,\\n \\\"posting\\\": false\\n }\\n }\\n },\\n \\\"assessment\\\": \\\"B1 tests whether visible AI invite images carry the story alone. B2 adds only subtle focus outlines to preserve premium look while improving mechanism clarity.\\\",\\n \\\"approval_commands\\\": [\\n \\\"APPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.3.0-b1-visible-invite-ai-only\\\",\\n \\\"APPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.3.0-b2-visible-invite-minimal-focus\\\",\\n \\\"REVISE_PROOF_SHORT calendar-invite-login-trap-30s \\\\\\\"...\\\\\\\"\\\"\\n ]\\n}\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_SQliPZ0789n0v4XbKhL1IbTq" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_d8SJMfavpp2MAiMXpDC8bNSw", "call_id": "call_d8SJMfavpp2MAiMXpDC8bNSw", "response_item_id": "fc_051a8a0b2fb58918016a14b6f38bcc8191a6c7b1546c8288dc", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/b1_contact_sheet_v1.jpg\",\"question\":\"QA B1 contact sheet: AI-visible invite only + subtitles. Are captions readable and safe? Is calendar invite/login situation visible enough? Any problematic text/logos/QR/people/hands? Does it carry the story without focus overlays?\"}" } }, { "id": "call_HgsmAzgwMkfTJPvN9CCIlsDM", "call_id": "call_HgsmAzgwMkfTJPvN9CCIlsDM", "response_item_id": "fc_051a8a0b2fb58918016a14b6f38be08191a288b117b0fcf42a", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/b2_contact_sheet_v1.jpg\",\"question\":\"QA B2 contact sheet: visible invite + minimal focus outlines + subtitles. Are captions readable? Are focus outlines too PowerPoint-like or acceptable? Is mechanism clearer than B1? Any problematic text/logos/QR/people/hands?\"}" } }, { "id": "call_GTICBQYhFBefoQqML0tNMyJ3", "call_id": "call_GTICBQYhFBefoQqML0tNMyJ3", "response_item_id": "fc_051a8a0b2fb58918016a14b6f38bf48191afcdec59e3267862", "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/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4; sha256sum /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4\",\"timeout\":30}" } } ], "finish_reason": "tool_calls", "reasoning": "**Planning QA for Outputs**\n\nI'm thinking I need to ensure quality assurance (QA) with a focus on b1, b2, and also using ffprobe’s output, if that's ready. It seems like I could employ a parallel approach to streamline the process. This might help me manage the tasks more efficiently and gather all necessary information in one go. I should clarify the specifics and see how best to implement this. Let’s keep it organized!", "reasoning_content": "**Planning QA for Outputs**\n\nI'm thinking I need to ensure quality assurance (QA) with a focus on b1, b2, and also using ffprobe’s output, if that's ready. It seems like I could employ a parallel approach to streamline the process. This might help me manage the tasks more efficiently and gather all necessary information in one go. I should clarify the specifics and see how best to implement this. Let’s keep it organized!", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFLbzc3T5uA8eUwGjqiAgCjWw28m_K4c9rBdUCLSo9uqjsaNoevARZryeyodublf9rBZ0__p2oisKETAuqpgYBPMgHaSLFHV6cHDlScx8iRtLnvdTdCdXOQQs9ZAyRC4mmdWV0wS1QaeYtWhJFCWsAPo-c3didArwPh-v7gUG5wzCJ8mB2gtoayCLOV3ecXaCuC_DEwJA9Y-KOKam-jULOuGl26p7tpc1QBIYb89MAa9DRJDXmmSVZ6Bn0x4TLbQig6dr40umyPcFhPeW03jUUto-F9qAbXHrLXp3o-APkpADQsgqwdFGT8nqgFs4PIMjlzkgsAKpnnVsG-vL_ZuhJTAe3Hx0yLfRVmhygjcNIGgcL6zhxsv8SGEXkudwvijcd5BJZ1ekf_Bi27ZTfJLJksGZcbNYmKIAdWiDma6lA3hS1ebSyajtGOdwCNb25tuGfBh_9gWehO35678UWNY8DGOmQjG1E9lBU3CsepIwoFXXNw_B3hZa3fe2Qsg_JG9sq_cjAa6ufR5Ho5eaDO-MviHez-VrFaFAFZw4uJ76Hqn8zd2y2oLoIHw9L1Yw2xXrKqZQPho4a5EIx0SGB9jvNFFzdbm6VZy9E7LxQ7ZNU98fJUYXORCmKz05Xz3hTK-blfoSRhk4WPU0Yw68uzNtzv-gepnQt9zAFnjk9zlSY6tB170A9fvnUcV7ptI47553K8lHnmi6vIFMqoWFQuyo7-Z4rDzlhVRbLAFcjY-ClLlw6RlV3ZmzGn3BxBqu3c7yQaUtsjkngVBJ5CZH7CDg_0oMeuAfUDKKx2CTBKKK2KAtFpY7PmrDz1D_ziivg1dq-uy7PTYzpwMdPCcZ6oxKbzcnAIYZlL-nVF33EPQwaTABlozdvwS15IC3LJe-c6d1PbS9WSo3SlXYL-axj-uKaYNHZlbsdw_v4v9FvApb9ANE0AHq0Zo238UBQ3S5f9lG9iyS7lPral0PIEIa3ofGq_2RfWrcVvrZI38YRJ33BIV8dzGW7o71Oz9ERqvkAOflUqbB", "id": "rs_051a8a0b2fb58918016a14b6eac8e0819195577232fa9a159f", "summary": [ { "type": "summary_text", "text": "**Planning QA for Outputs**\n\nI'm thinking I need to ensure quality assurance (QA) with a focus on b1, b2, and also using ffprobe’s output, if that's ready. It seems like I could employ a parallel approach to streamline the process. This might help me manage the tasks more efficiently and gather all necessary information in one go. I should clarify the specifics and see how best to implement this. Let’s keep it organized!" } ] } ] }, { "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: QA B1 contact sheet: AI-visible invite only + subtitles. Are captions readable and safe? Is calendar invite/login situation visible enough? Any problematic text/logos/QR/people/hands? Does it carry the story without focus overlays?\n[screenshot]", "tool_call_id": "call_d8SJMfavpp2MAiMXpDC8bNSw" }, { "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: QA B2 contact sheet: visible invite + minimal focus outlines + subtitles. Are captions readable? Are focus outlines too PowerPoint-like or acceptable? Is mechanism clearer than B1? Any problematic text/logos/QR/people/hands?\n[screenshot]", "tool_call_id": "call_HgsmAzgwMkfTJPvN9CCIlsDM" }, { "role": "tool", "content": "{\"output\": \"Argument '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4' provided as input filename, but '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4' was already specified.\\n04d26c5eff645ec852755f072695693c3f862232ad9e49b891656054933ab16e /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4\\n63d8cdd8347f27b86ed4e03046160a1d19e10491ad747b0c1df72fa0897480b7 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_GTICBQYhFBefoQqML0tNMyJ3" }, { "role": "user", "content": "[Your active task list was preserved across context compression]\n- [>] render-b1. Variant B1 rendern: AI-visible invite only + Voiceover + Subtitles (in_progress)\n- [ ] render-b2. Variant B2 rendern: AI-visible invite + minimaler Fokus-Layer + Subtitles (pending)\n- [ ] qa-deliver. A/B QA, Manifest, SHA256 und Lieferung mit Empfehlung (pending)" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_e4qjI7gBbIjeU8j8y4hMmqA7", "call_id": "call_e4qjI7gBbIjeU8j8y4hMmqA7", "response_item_id": "fc_0684ad9be089992d016a14b774cc908191b363ab37107fe401", "type": "function", "function": { "name": "skill_view", "arguments": "{\"name\":\"social-media-shorts-automation\"}" } } ], "finish_reason": "tool_calls", "reasoning": "**Finalizing media tasks**\n\nI need to continue with the project. It looks like I have to finalize the media delivery, but first, I should verify ffprobe separately. I also need to update my to-do list. There's a thought about creating relevant social shorts, which could be useful. I should load the necessary elements because this task is about automating shorts. But wait, I realize I didn't do that yet! So, I must load it now.", "reasoning_content": "**Finalizing media tasks**\n\nI need to continue with the project. It looks like I have to finalize the media delivery, but first, I should verify ffprobe separately. I also need to update my to-do list. There's a thought about creating relevant social shorts, which could be useful. I should load the necessary elements because this task is about automating shorts. But wait, I realize I didn't do that yet! So, I must load it now.", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFLd0xV3P5aecbEZ2IGJJ3yZWCLFU335ZvljmfCTMGtb160uYW6X0LEThwPy4Sh2DXR9rjF7FLY6GEMyHezOnPaDhCLyGk7tPTG98RdS8wAn4GZIBs8eyaOC0dJDveOgdge3l023-HldjRDOKCdvAUzM1NMbuWFbmLPcsbevKk8CTNRiG8rFpVOxTyNXvCVlLOiLelD_02r8zX6oOgrWM6DTPGsz6U5qiOf9mKljgl35JbmssIUz87GOz7YCp65I8GTIb22NClzPIqYtNh4jRCIMAzYL1Y1U_eQxtbZcBPRedwjZWV_tmcJn9R9UzptA7wFuu5O5jdrK_JOaMeL-OJB29XhxdmqopxA0jiEjCQrFvM7GD1EsNpLjmi411lpqVqqO3ZX2Y3MUZAyNc3_LZmOoClkM0d17B5KT8pIxbKPAHLNOxbFYAiHeyIDBXfkbMjXlnt1creFHORCsXYRZADMm8yl5nKTGB7RZJAh-k_FU3VQlKtZI1OfL6ouxmUJZf5AvxvivEadIqWwvHbKUe7kLGWiSmb1QCwlrDhulhephrIJDB0NQYFiiSWq2cRrSPGn7bATjmCMsvBtcD3CuhpdbKSy9RNXPFN2LU8XnTgPdiOsNRLtwysj-sj6k1GOLger2YjB3H0KwDIBBrKwzRnTLca6DNEhT155vKbwBWCg7jtC1uurJdtiYEZ4q0QSPkDUNvE-rJSfe1yQcCrl7rSzSWXo-I4A-wmAPALnnZZEi9FniozBrjDLaUXNWGDViPsQgjBvPpLZOChSm6u1R9M1Tlkopn-ViI73EUixLjQpv4mGNb5kBTqaZCZqn10T4S39sjQqZRfKFUCEsZypUvmcCJvvRiGyYGDHpUuExmbKuUFgHQfj7SLOT8r7IQBKbCOUAJ-tkifS0nQFBJxxLWUg-jgLaUwAjhaR9BiofvIJgjacVoQptsNG26D9otMMdBWdYlC3uE1qsweeZbGklQlAWPB1U9Bi6StvrQv6HezTrJ92P-rQynClWczxTOnLAhMFfYm6PkFXQlzzVOMT0g4jjfGisiHeGbe3pnhv_b8mTBSdLtZ5LdUV7fl6yA8VSwwxiJrtUb6q9ASkpojPOxhj8RzUJJBUiaqtIWnfs_XklS0rtgR_BQdoGrU2umP6B7JJZhGcp0qW0ABUivgwzZ0KHle0Pw6pKTa7Ow2J6oKSPkshyCG23f7aWJAa_NBozdjga2", "id": "rs_0684ad9be089992d016a14b770cc3c8191ab0cbdfebef11416", "summary": [ { "type": "summary_text", "text": "**Finalizing media tasks**\n\nI need to continue with the project. It looks like I have to finalize the media delivery, but first, I should verify ffprobe separately. I also need to update my to-do list. There's a thought about creating relevant social shorts, which could be useful. I should load the necessary elements because this task is about automating shorts. But wait, I realize I didn't do that yet! So, I must load it now." } ] } ] }, { "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`. For the follow-up A/B test where the user asks whether pure KI images can match or beat hybrid mockups, see `references/clean-ai-cut-vs-hybrid-mechanism.md`: compare clean image-only premium feel against mechanism clarity, keep word-aligned subtitles, and consider `90% clean AI images + 10% minimal deterministic mechanism` as the likely next style.\\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 provider word-boundary events before sending another final-near clip. For EdgeTTS previews, request `boundary='WordBoundary'` and render active-word highlights from those offsets; do not merely distribute words evenly over sentence SRT durations. 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.\\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`.\\nIf the user rejects the 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`. If the user then asks whether pure KI-Bilder can achieve the same or better effect, run an A/B proof against the hybrid version and assess premium look vs mechanism clarity; the likely final style may be `90% clean AI images + 10% minimal renderer-owned mechanism`. See `references/clean-ai-cut-vs-hybrid-mechanism.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. See `references/word-boundary-caption-sync-and-solution-gate.md` for the stronger EdgeTTS `WordBoundary` timing pattern and the explicit solution/fazit gate for Proof Shorts.\\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/word-boundary-caption-sync-and-solution-gate.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/clean-ai-cut-vs-hybrid-mechanism.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_e4qjI7gBbIjeU8j8y4hMmqA7" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_c30AC9rxnEEK48ISPlCWBSXS", "call_id": "call_c30AC9rxnEEK48ISPlCWBSXS", "response_item_id": "fc_030089ba91e8432c016a14b776d18c819186c840575cbb985c", "type": "function", "function": { "name": "skill_view", "arguments": "{\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/clean-ai-cut-vs-hybrid-mechanism.md\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/clean-ai-cut-vs-hybrid-mechanism.md\", \"content\": \"# Clean AI Cut vs Hybrid Mechanism — session learning\\n\\nUse this when comparing a pure premium AI-image sequence against a proof short with deterministic mechanism/UI overlays.\\n\\n## Session-derived pattern\\n\\nFor a scam/cybersecurity proof short, a clean image sequence can look significantly more premium and native to TikTok/Reels, but it often weakens immediate mechanism clarity.\\n\\nObserved comparison:\\n\\n```text\\nClean AI Cut = premium mood, calmer, less explainer-board\\nHybrid = clearer mechanism, more immediately useful\\nBest likely final direction = mostly clean images + one minimal deterministic mechanism moment\\n```\\n\\nRecommended framing:\\n\\n```text\\n90% Clean AI Images\\n10% precise renderer-owned mechanism\\n```\\n\\nExamples of acceptable minimal mechanism moments:\\n\\n- one brief `suspicious link/domain` reveal\\n- one brief `close invite -> open trusted app/bookmark` action moment\\n- one simple before/after state, not a full checklist board\\n\\nAvoid returning to:\\n\\n- checklist-heavy UI cards\\n- boxed explainer overlays\\n- arrows/circles/diagram markers\\n- repeated labels and decision-target graphics\\n\\n## Viewer explanation rule\\n\\nWhen the viewer is not technical, do not use shorthand such as `open the service yourself` without explanation. Spell out the exact action:\\n\\n```text\\nClose the invite.\\nOpen your calendar or work app from the normal icon/bookmark.\\nIf the meeting is real, it will still be there.\\nTrust the path you chose, not the button that chose you.\\n```\\n\\nThis converts a security maxim into a concrete next action.\\n\\n## Caption synchronization rule\\n\\nFor final-near shorts where the user complains that subtitles do not match voiceover exactly, use actual word-boundary/forced-alignment timing rather than distributing words evenly across sentence SRT blocks. For EdgeTTS previews, request `boundary='WordBoundary'`, store word cues, then render static phrase segments where only the active spoken word highlights.\\n\\nKeep the established caption policy:\\n\\n- static phrase segment, usually 3–7 words\\n- active spoken word highlighted in yellow\\n- inactive words white\\n- no subtitle box/bar\\n- bottom mobile-safe position\\n\\n## A/B decision criteria\\n\\nAfter rendering both versions, explicitly answer:\\n\\n1. Which version looks more premium?\\n2. Which version explains the mechanism faster without audio?\\n3. Does the clean cut rely too much on VO/subtitles?\\n4. Would one minimal deterministic mechanism moment recover clarity without killing the premium look?\\n5. Is Wan/I2V worth testing, or is image-sequence motion enough for this stage?\\n\\nDefault recommendation: do not jump to full Wan/I2V after this test. If clean images work visually, test exactly one short motion micro-proof only after approval.\", \"file_type\": \".md\"}", "tool_call_id": "call_c30AC9rxnEEK48ISPlCWBSXS" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_hmbB2edC0KVFpTXjG23UvQl5", "call_id": "call_hmbB2edC0KVFpTXjG23UvQl5", "response_item_id": "fc_0d23da4b61c18128016a14b77b8fac81919323dd989aba97b9", "type": "function", "function": { "name": "skill_view", "arguments": "{\"file_path\":\"references/word-boundary-caption-sync-and-solution-gate.md\",\"name\":\"social-media-shorts-automation\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/word-boundary-caption-sync-and-solution-gate.md\", \"content\": \"# Word-boundary caption sync + explicit solution gate\\n\\nSession learning from a TrueTraceShorts Proof Short review where the user found captions irritating because they were not exactly simultaneous with the voiceover, and also noted that the video lacked a real solution/fazit.\\n\\n## Trigger\\n\\nUse this pattern when producing final-near Shorts with voiceover + subtitles, especially Proof Shorts / Digital Red Flags / mechanism reveal videos.\\n\\nUser-visible failure signals:\\n\\n- subtitles lag or lead the voiceover;\\n- captions are approximated by sentence duration and feel “off” while listening/reading;\\n- the video explains a mechanism but the viewer does not leave with a concrete action;\\n- the ending feels like an observation rather than a solution.\\n\\n## Caption timing rule\\n\\nDo not rely on evenly distributing words across sentence SRT durations when a better timing source is available. For EdgeTTS, request word-boundary metadata directly:\\n\\n```python\\ncommunicate = edge_tts.Communicate(\\n script,\\n voice,\\n rate='+0%',\\n boundary='WordBoundary',\\n)\\n\\nasync for chunk in communicate.stream():\\n if chunk['type'] == 'audio':\\n audio_bytes.extend(chunk['data'])\\n elif chunk['type'] == 'WordBoundary':\\n start = chunk['offset'] / 10_000_000\\n duration = chunk['duration'] / 10_000_000\\n word = chunk['text']\\n```\\n\\nBuild `WordCue(start, end, word, sentence)` from those offsets, then feed the existing static active-word caption renderer:\\n\\n```text\\nEdgeTTS WordBoundary cues\\n→ 3–7 word static phrase segments\\n→ active spoken word highlighted/pulsed\\n→ phrase changes only at phrase/sentence boundary\\n```\\n\\nThis gives the Hormozi/TikTok-style feel the user prefers: several words remain stable, while the currently spoken word lights up exactly when spoken.\\n\\n## Caption QA gates\\n\\nBefore delivery, verify and report:\\n\\n- `caption_sync_source = edge_tts_word_boundary_offsets` or another forced-alignment source;\\n- `static_phrase_active_word = true`;\\n- no default one-word-only captions;\\n- no sliding word window where all visible words change each word;\\n- no subtitle box/bar unless explicitly requested;\\n- mobile-safe bottom placement;\\n- contact sheet inspected for clipping/legibility.\\n\\nIf WordBoundary / forced alignment is unavailable, label the render as approximation-only and do not present it as final-near.\\n\\n## Explicit solution/fazit gate\\n\\nEvery Proof Short must answer the viewer’s post-watch question: “What do I do now?” Add a concrete end-state action, not just a clever line.\\n\\nGood ending shape:\\n\\n```text\\nMechanism revealed → simple safe action → memorable rule\\n```\\n\\nExamples:\\n\\n- Calendar login trap: “Open the service yourself. Trust the app you opened, not the button that rushed you.”\\n- Invoice route trap: “Do not pay from the email. Verify route changes through a second channel.”\\n\\nReview-package fields to include:\\n\\n```json\\n{\\n \\\"usefulness_fix\\\": \\\"Concrete action the viewer should take\\\",\\n \\\"takeaway\\\": \\\"Short memorable rule\\\",\\n \\\"summary_fazit_present\\\": true,\\n \\\"final_solution\\\": \\\"...\\\"\\n}\\n```\\n\\n## Pitfall\\n\\nA video can be factually correct and still feel unsatisfying if it only diagnoses the trap. The final beat must solve the viewer’s immediate problem in one simple action.\", \"file_type\": \".md\"}", "tool_call_id": "call_hmbB2edC0KVFpTXjG23UvQl5" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_g9iQJLVvEyDlntwyaZTJfUSK", "call_id": "call_g9iQJLVvEyDlntwyaZTJfUSK", "response_item_id": "fc_08b0b81e026c222b016a14b78457608191bde9b35f7ec272f5", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from hermes_tools import terminal\\nimport json, subprocess, os\\npaths=['/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4','/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4']\\nfor p in paths:\\n cmd=f\\\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json {p!r}\\\"\\n res=terminal(cmd, timeout=30)\\n print('---', os.path.basename(p), '---')\\n print(res['output'])\"}" } } ], "finish_reason": "tool_calls", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFLeE8hYuwu2Jcjs3SnesRn1IIf2pDvSz0Uf8rcnhOzl1un8sGlYwxBEzu6KiA2BzQrc8wRPzy76yFzMii1rJcPYFRVrLMFxP0mSY0ZYyyFcGPQNteXaRHNfhbh2U1pDfmmOiOrgzQRi2XXIOZGdrq6Afwv0rQ7WEiWRm8_tJFHKQsRFEfztvmWiRyYtrNY6ziQvQ0YChx6_qzOFsVRK6ZW7MHKS1vb7NNlsYzD88M0bJEdU5J34OCc8AsKQZN1jzWRYaw0vp2rNv8uA0Jfh3IWZrJ_nRvNZ8B4saXg6oOCB8dSitzXlOZj3K7QLzCcPOUYvJKnf-7SksKYbKQxIvDP07wJPr608t7g_G27Kb9-XLPFMZPP1h1r_DhoWHPaTzC2Ujs7KqN0h5JFibtGjKhplqsBGHjFrI5kh37HJesE0B1N689hcweEG4TFD2AmRXE1q9pSKAQ9YwSX_1MUBqGhqyzkhw26-9dk4CHGQ9FIzRvF6LUcDbgBdB-zgA2tGrA-Qw8Un-Q-S77Svb0bBmj8oro8Rlfou6gZb4VL-Lxw5slKlxkQm_GFfm-53Z6dB5yo0PUq6J5BOW8EP6eEuIqrX0SjzLY7_gcN9CAf1-xmdzptyqwpmKKuu4wTAQt7KRvlkBpRwgi2jfawdhLPsxx2H0Rw-2YBnMN_abI_if_padoI2lA0KPFtZYzO9QtPu8WhFfA9MKyQES7-S-ci87ps_1Dw3XP1fE6GPKI7uKi6TEqcxXEIwJBUrHK8jAClq-8BX3DC5yKV9Qg_kZ2B7AwrhAkDrkE_KxKGuZpKM_GADGyc9-DTdCsRVkdAYUWWePqJGI38ixb3J-mdvnV5A5xV1mHad2cvaY4vpKeJp1hEqIfT8DjQZD-CVYfV0DDHHD-DK1kuxBQB7sQL48p26kUIdxXnzuTaDkJn1ZmJL7kQ72VhyiiLWjv1aB84CSMDxHfF62xKHlYIzmM91jfvRhMhyN7VkDKYnf54q--sbWw6f4rQpf9-YYVQOxPt0AhYcT_S4mnRdoGfYbLQiixfZqLQSaaHURcKEGuVFO7CKPWV5Sp3V0dOmMoKz_mcP8lpQsHhPVtN67NNaf8G3iDeOapFwU9bzvG8GmmNhpKFQg9EoZYEWkbePcdLBylmWhFOLpYzhpKScO7ZIHUYYNsDsO4fxKAJpQaa3Vj_pOkKOaPF7kpV3pY8qofYlnrBT_KXWz_LauQ1H7ecMW-aUqzRw2MP8-xGVOVjQ-1vY4Dm5QwYQjBs7FBiU1NWcPqbsMH4J7T8c9BhsFOm2K8YdzvJzharWpWfpW2q2cSl2Zq917P9X9o6Vldy6oDueErERL5CbHZYFvl4KoFkaPyJkbxHyKElArMrKsXBnOtBX3vpXugwqJVuoY9HtjRvpRTUm8IJW_yRLAXIkT75zD7NF5ohyE-Z0avppzBFYSbn5YUL3he7Bz0l9omRmevDDDPtT5FB2_nm6BGLNwHX9EkTqFe3NlEai1pYxBDy01r_qRE7yUL9YD9Ip_dK5bth8d9FIOLj-eb49Tfy2TjWeSOiaeuddSsLOcY9OvUGnGnvcQtPJu6RrjPvCxktVwbd1r4IxD1wgD1OuYnyMM3pKOHZ2XxJGYmB0hmWnV_u-U0gDYQ8hw-Zm4TmMDs9NC3CDb-R6qMfttlaTxXBAEShFPGGGgArouehIOFsULvRhMOrGyNZaQhbyzxZVzWYrFLqyM5a8KbxgHfUCa4h3c0X4Ey-fsJfbMjetk01Zpx3iW0ohbPprCSXmgUYZVHw6sIXjQc0IHktBG2iFDe-aMJBCPTGLbGUh5p6xVSoySSZFs3pE9OPyGz13a___81nYn0uIin8hF71DAEi3Z", "id": "rs_08b0b81e026c222b016a14b77fbf6481919df9000bfb6f350e", "summary": [] } ] }, { "role": "tool", "content": "{\"status\": \"success\", \"output\": \"--- calendar-invite-login-trap-30s_b1.mp4 ---\\n{\\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\\\": \\\"12551970\\\"\\n }\\n}\\n--- calendar-invite-login-trap-30s_b2.mp4 ---\\n{\\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\\\": \\\"12650916\\\"\\n }\\n}\\n\", \"tool_calls_made\": 2, \"duration_seconds\": 0.86}", "tool_call_id": "call_g9iQJLVvEyDlntwyaZTJfUSK" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_Ud7HXgSIYXot9OpJbVZNb1Zb", "call_id": "call_Ud7HXgSIYXot9OpJbVZNb1Zb", "response_item_id": "fc_069d8218d149e21f016a14b78a39408191b3efc24cb57486ed", "type": "function", "function": { "name": "todo", "arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Variant B1 rendern: AI-visible invite only + Voiceover + Subtitles\",\"id\":\"render-b1\",\"status\":\"completed\"},{\"content\":\"Variant B2 rendern: AI-visible invite + minimaler Fokus-Layer + Subtitles\",\"id\":\"render-b2\",\"status\":\"completed\"},{\"content\":\"A/B QA, Manifest, SHA256 und Lieferung mit Empfehlung\",\"id\":\"qa-deliver\",\"status\":\"completed\"}]}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"todos\": [{\"id\": \"gen\", \"content\": \"6 konkrete Visible-Invite-Cinematic KI-Keyframes erzeugen\", \"status\": \"completed\"}, {\"id\": \"qaimg\", \"content\": \"Keyframes prüfen: sichtbare Einladung, kein lesbarer Text/Logo/QR/People\", \"status\": \"completed\"}, {\"id\": \"render-b1\", \"content\": \"Variant B1 rendern: AI-visible invite only + Voiceover + Subtitles\", \"status\": \"completed\"}, {\"id\": \"render-b2\", \"content\": \"Variant B2 rendern: AI-visible invite + minimaler Fokus-Layer + Subtitles\", \"status\": \"completed\"}, {\"id\": \"qa-deliver\", \"content\": \"A/B QA, Manifest, SHA256 und Lieferung mit Empfehlung\", \"status\": \"completed\"}], \"summary\": {\"total\": 5, \"pending\": 0, \"in_progress\": 0, \"completed\": 5, \"cancelled\": 0}}", "tool_call_id": "call_Ud7HXgSIYXot9OpJbVZNb1Zb" }, { "role": "assistant", "content": "Erledigt, Sir. Zwei sauber gelabelte A/B-Previews — **nicht gepostet**, nur Review.\n\n## A/B Preview\n\n**B1 — Clean AI Visible Invite**\n- Nur KI-Bilder + Voiceover + aktive Wort-Subtitles\n- Premium/Cinematic wirkt ruhiger\n- Mechanismus ist sichtbar, aber etwas stärker abhängig von Voiceover/Subtitles\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4\n\n**B2 — Visible Invite + minimaler Fokus-Layer**\n- Gleiche KI-Bilder + sehr dezente Fokus-Outlines\n- Mechanismus ist schneller verständlich\n- Minimal mehr „explainer“, aber noch nicht PowerPoint-Hölle. Ein kleiner Sieg der Zivilisation.\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4\n\n## QA / Fakten\n\n- Format: 1080×1920, 24 fps\n- Länge: 41.875 s\n- Audio: enthalten\n- Caption-Sync: Word-boundary/aktive Wort-Hervorhebung verwendet\n- Ende/Fazit: konkret ergänzt:\n - Close the invite\n - Open calendar/work app via normal icon/bookmark\n - If real, it will still be there\n - Rule: trust the path you chose, not the button that chose you\n- Kein Wan/I2V\n- Kein Platform-Posting\n- Keine Menschen/Hände/Gesichter/QRs/Logos in den geprüften Keyframes\n\n## Hashes\n\n- B1 SHA256: `04d26c5eff645ec852755f072695693c3f862232ad9e49b891656054933ab16e`\n- B2 SHA256: `63d8cdd8347f27b86ed4e03046160a1d19e10491ad747b0c1df72fa0897480b7`\n\n## Meine Empfehlung\n\n**B2 gewinnt für diesen Proof Short.** \nB1 sieht cleaner aus, aber B2 erklärt den Scam schneller — und genau das war der Kernkritikpunkt: Der Zuschauer muss nach dem Video denken: *„Ah, ich weiss jetzt konkret, was ich tun soll.“*\n\nWenn du freigeben willst:\n\n`APPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.3.0-b2-visible-invite-minimal-focus`\n\nOder Revision:\n\n`REVISE_PROOF_SHORT calendar-invite-login-trap-30s \"...\"`", "codex_message_items": [ { "type": "message", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Erledigt, Sir. Zwei sauber gelabelte A/B-Previews — **nicht gepostet**, nur Review.\n\n## A/B Preview\n\n**B1 — Clean AI Visible Invite**\n- Nur KI-Bilder + Voiceover + aktive Wort-Subtitles\n- Premium/Cinematic wirkt ruhiger\n- Mechanismus ist sichtbar, aber etwas stärker abhängig von Voiceover/Subtitles\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b1/calendar-invite-login-trap-30s_b1.mp4\n\n**B2 — Visible Invite + minimaler Fokus-Layer**\n- Gleiche KI-Bilder + sehr dezente Fokus-Outlines\n- Mechanismus ist schneller verständlich\n- Minimal mehr „explainer“, aber noch nicht PowerPoint-Hölle. Ein kleiner Sieg der Zivilisation.\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b2/calendar-invite-login-trap-30s_b2.mp4\n\n## QA / Fakten\n\n- Format: 1080×1920, 24 fps\n- Länge: 41.875 s\n- Audio: enthalten\n- Caption-Sync: Word-boundary/aktive Wort-Hervorhebung verwendet\n- Ende/Fazit: konkret ergänzt:\n - Close the invite\n - Open calendar/work app via normal icon/bookmark\n - If real, it will still be there\n - Rule: trust the path you chose, not the button that chose you\n- Kein Wan/I2V\n- Kein Platform-Posting\n- Keine Menschen/Hände/Gesichter/QRs/Logos in den geprüften Keyframes\n\n## Hashes\n\n- B1 SHA256: `04d26c5eff645ec852755f072695693c3f862232ad9e49b891656054933ab16e`\n- B2 SHA256: `63d8cdd8347f27b86ed4e03046160a1d19e10491ad747b0c1df72fa0897480b7`\n\n## Meine Empfehlung\n\n**B2 gewinnt für diesen Proof Short.** \nB1 sieht cleaner aus, aber B2 erklärt den Scam schneller — und genau das war der Kernkritikpunkt: Der Zuschauer muss nach dem Video denken: *„Ah, ich weiss jetzt konkret, was ich tun soll.“*\n\nWenn du freigeben willst:\n\n`APPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.3.0-b2-visible-invite-minimal-focus`\n\nOder Revision:\n\n`REVISE_PROOF_SHORT calendar-invite-login-trap-30s \"...\"`" } ], "id": "msg_0d4a723b463df28d016a14b78dd034819188f9513f54855c73", "phase": "final_answer" } ], "finish_reason": "stop" }, { "role": "user", "content": "[M G] B2 bringt keinen mehrwert mit den linien im bild… versuche die KI bilder mit mehr details zu füllen (sichtbare outlookeinladung mit text usw). Das Image-modell ist hier ziemlich zuverlässig; du musst nur den prompt sehr detailiert formulieren." }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_hbGGgR5cZ1eqBq8rnzc6DJjt", "call_id": "call_hbGGgR5cZ1eqBq8rnzc6DJjt", "response_item_id": "fc_0d4a723b463df28d016a14ba59385c8191a3040a22d073188e", "type": "function", "function": { "name": "todo", "arguments": "{\"todos\":[{\"id\":\"b3-gen\",\"content\":\"Neue B3-KI-Keyframes mit detaillierter sichtbarer Outlook-artiger Einladung/Text erzeugen\",\"status\":\"in_progress\"},{\"id\":\"b3-qaimg\",\"content\":\"Keyframes auf Lesbarkeit, Details und Artefakte prüfen\",\"status\":\"pending\"},{\"id\":\"b3-render\",\"content\":\"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\",\"status\":\"pending\"},{\"id\":\"b3-qa-deliver\",\"content\":\"B3 technisch prüfen, Hash/Manifest erstellen und liefern\",\"status\":\"pending\"}]}" } } ], "finish_reason": "tool_calls", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFLpZGKy1zLHChhgBViZ_cPL42JtsUtUi74ukhIFZG-5RKAVbWxcjpWutrgiPmM-Tw6KelQdq_R05yRYpArfmUV5miJA1vUTv9ZXQxNXgA9Pidn8UtfELHEta1ccLcrAWRILXxbWE5-6HFcJQBdU2PNioOJaQ9pHfcgWbPHDUlA_dToiGngV1R-4ylv8tcS4OPmg6WrWCczZvFIMkoZ6r-C7HE1RvEdYQn2d9XLIUyAjLJd1J5I_FMLuv-5jPzk70CH-Lhv9RpA3t-bs_mPI4NiNV-mQ_V0XA8JqnrM0s48LK1heJgoxcRSFQQg53a-tm3ieiU3JBJxI3UOSSyRF-lhiFsCLKodQyolsbdY6kQBR0SLcwdQvhWPL3OejuJK7fVriSGnChKjdeZPOHH4j5XtBXATx1TpYOe0DodL56KCKNWPnLt9aUdhnCTZAK-iOqQqYC10nCfvpMt1kmJqS5l9TSPjWvKBDk1aIohs7Djgs0kwPbBUYS03Zsy8XEQJZZeL_ykMzD_Eg6QEktRCa5z9h0oEFPx-fJ2Dj2bEtaOPIyDuK3vijmA5TmFCysfq3NPxdddS5tCIagjgFtESOPYsxq0eVvVk9tkUvIunw9xKJpakMATtj6CKqbOib_CYLWE3nRHHu0kFIp5LS2H6TxgBEMs08sZnAj9XpV5-xqNst2udgy3ogwceYmQnYEmPIoN4ToKYFssS7aNCuo0KPwL9kO3DkwuhjUuWsWQlTYbOXI86e5p3D2CsRggXEBM3yG4HTIPv2DHkthnhxHaN7meo5N54qPnjjN9tT7sJKKM9CqxKFDVoYBzb5TSPHkfCxY4WSTA79Iq_69cZynfLyhZlZkcgXt51E_nLmmHg-RYx4K4Ny2TRcS3uaNF2fhObo2dNfZ-ohcVBdqQIF7BkKVBCs6GmGgdHn7B25xvd7RAW-2pnm_srUaiaoxFPXzZIgBg-8gN-DIe0kYjHm_lFKpvR5Q-xX2SG3jdCO3bADy8mYlmMeL1IvwbQAn3wBVOVYzwbd7oGBnD0QnDcVqbuTm2310AChE8DHHnvVGyHFDTCFb0J7LqfTxZIIfVs-f6czBUv1CGXUcb6xYks9zbPXYKp85cHP79NiNQnSupAxF5RWWQRZzgSvy9s7jMmYSewGG0rRmRl_u4X2MbZ20hp4mfl9XL3dOmk_yySRIPUW3Q2SPJWhYFwKWUR6FjaRJRAKwP1b2impPm1_SXLt070OeWd-Qi8Hhp4JSu2WyLbWpgbHoLEwIOL8uM_1vBrWtxslSh7_FUwhFxtJUPN9xhlpwcLawJrbd-2UlOB6CrMEfA3dDCcTfYuRwOlyap5zZnQOoIR9FfuRNc2ZCCe4r60Uo_UFLg7duX_gGKyuU0-ScRTy9jeCEeWU8dTNJ5RLDG6J14PYsSR1cbwyFHQRMgy060UUjbsntNrPZ4znmr4LE1d_lhtiG06VV_k_pjBmcZsXr3r8bGUUYiPGWHTPEoc5KpOduroSg1Wgne6ZU0Mvo6zGvHUmph-mbX4MN_CW-WYRXg_SMUjE6aT9lKsxnui-QwPPaWU7i9OCuiCBOo60cvzAwi3R_95RiSjplDX69F_uXeOI23fcjI1iT0KcyDAzToaXo5v0J-z4_1cTfHCXICxgeXO4a5LHWOdhL3PP4mnyL9nS4aW5bO_M1SVNBuXXLjdvURfmsE1mfQJxHG4xkZOMH6mYey6GlI4WovXLPcTtRmArvaUKD4PPP6nKzBywHx6XjS-eh1-XTmUXu5YU9WjOnJ75E23wWcEblM-bZCR3hLPyps2fD6n93LKt7wCfe15-VzQwR69E2vT9kg60vNhx07x7B-LyEVwYunVdMqOiGchFeOmZ20AnmsZdk26UwBFgMB6sImjteLn9pj3y7RHufCW1mhg8k3IghC3sYWp5vFsYZp6QtrNhJEiiYQR0Q3H8dYw-UKWC_AMFYJtpG9PiV7dES_f5uB4tDY-AFx-l9vdI3PRDHe6Emc41ajHd0x11GVaiSVkf5JUwxMffc9h-dinDokCh9qJ2r0jJPIhArgUfForFEm3yf_KvgbMoysO-mOyQxgRmCs88JUsOPlwMfizeRvYUD8LMVM8A3a55mR2QXpIDcXzjHRil7uFoI3eMZsf6Lfb4SIboFG_fYr9l-TqIGlzgjgIfP9B6Y8VaQr03aZR1jppJnpWlN-ylISUHx1cjBGE0J_-ZIhfHjEXxKGS37A-REx8VkzKjGVypIrJPcJ7x7yYXYg01GJ41KKkbiu5ZpI_H-ui6a3H32wgF_n3ILK6c4RQzlPnAr6IlNhbJrrAIfHQ0-XCKgP3faDzlk7LP9ICWCzzVuxRCHuq3pz8ruC5XEUjgL3EYnXMrqWQhrrbnf2VIji5-3jxF9g-QPMeOLQiVJe3aiLW6FoG_7RYBtYOM3m2AY1Hij0IxCe3uONSHgecIWmXEtso3sXEBS9MJurRPOzH2kdiy45qVrDiSbRxTNRzQhNtn1Dw8HE8KbHqXmWgiI2vYrNSxdAX6zIANBBGSPK4P-6PQr4QIbKDwS7PO0e5d3aVjaneZP4DnlNhNhZpJSOnrXGyItXsYdmIAoD6RFL4w2cE3mt1h1od2i67T4ctLpS88DMlPQCQ9VsTFK_fuE-Wt0y97KT2xSUb3-DQBGBBaR6VgQrNQeaZbRaguQ35sM0K-vHTqy2J4FG055KxKbXU8CJdAoLFI2Z8NBJqyxMwdAvr72Bz7FgGVkcIB0_SqglXpT863lCdJxl4EqlorqNuLr9rO5isjwk8kZGZv8I8EpJh0Exh62wVSE8Y2H2y-4_UH9mEd-eAdJ0G_uV_kWRc0Rkirjw8fhqU4q7Ig00Fe_8iReZccWtzb8K17q3kFuRBCJNaLbhwEjRqEDto2R6u_NHTyT5ZIEnGzk7mkoo3vlBLn8CD9scEmw2qE8TPaeklhsLRiAuDoSD3rp4rnfGiaMIrdFnVRfe9kpCEzO24okMgTuYAF6SfXEneAbBooze6Z1kq6ZFQMGCvyKnJBxThPVJdAwPQmhN-HlakQBhEroq4E7GKONK9yLun6UO-QQ7B2Wzi2T0dU-WZrOtR-DbrGMCJCtENvWEjb_lUiX9xPGf5SaqVQpnzo=", "id": "rs_0d4a723b463df28d016a14ba528064819194ff74486964a7ba", "summary": [] } ] }, { "role": "tool", "content": "{\"todos\": [{\"id\": \"b3-gen\", \"content\": \"Neue B3-KI-Keyframes mit detaillierter sichtbarer Outlook-artiger Einladung/Text erzeugen\", \"status\": \"in_progress\"}, {\"id\": \"b3-qaimg\", \"content\": \"Keyframes auf Lesbarkeit, Details und Artefakte prüfen\", \"status\": \"pending\"}, {\"id\": \"b3-render\", \"content\": \"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\", \"status\": \"pending\"}, {\"id\": \"b3-qa-deliver\", \"content\": \"B3 technisch prüfen, Hash/Manifest erstellen und liefern\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 3, \"in_progress\": 1, \"completed\": 0, \"cancelled\": 0}}", "tool_call_id": "call_hbGGgR5cZ1eqBq8rnzc6DJjt" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_SlmGghi25e8HolypQnaijNC0", "call_id": "call_SlmGghi25e8HolypQnaijNC0", "response_item_id": "fc_0d4a723b463df28d016a14ba672bf48191a33f460bea619941", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic social-video keyframe, realistic modern desk with laptop screen in sharp focus. The laptop shows a detailed Outlook-style calendar invitation email UI, but no Microsoft logo and no brand logo. Use clean readable English text on the invite only. Exact visible UI text: Title line: “Quarterly Review Meeting”; sender: “Alex Morgan”; time row: “Today, 10:00 AM”; location row: “Online meeting”; large blue button text: “Join meeting”; smaller link line below: “Sign in to continue”. Add attendee avatars, calendar icon, email header bars, sidebar folders, and realistic UI details. The visual problem must be instantly clear: a normal-looking meeting invite asks for login. No people, no hands, no faces, no QR codes, no watermarks. Premium navy/amber lighting, shallow depth of field, clean lower safe space for subtitles.\"}" } }, { "id": "call_12nNiCGlgalW4Bnhxtaupc8H", "call_id": "call_12nNiCGlgalW4Bnhxtaupc8H", "response_item_id": "fc_0d4a723b463df28d016a14ba672c248191b8bfa8efbe29e41b", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic close-up of a smartphone on a desk, screen sharp and readable. The phone displays a detailed Outlook-style calendar invite notification/email, no logo or brand mark. Exact visible text: “Quarterly Review Meeting”; “Today 10:00 AM”; “Organizer: Alex Morgan”; “Join meeting”; “Sign in to continue”; “This meeting starts soon”. Include realistic message rows, attendee circles, a blue join button, small calendar header, and subtle warning red/amber glow around the sign-in area. No people, no hands, no faces, no QR codes, no watermark. High-end social video style, clean bottom safe zone for subtitles.\"}" } }, { "id": "call_mK1TuNSCGEOWqa84p7x69dcL", "call_id": "call_mK1TuNSCGEOWqa84p7x69dcL", "response_item_id": "fc_0d4a723b463df28d016a14ba672c308191a9b06640a0eaec0f", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cybersecurity keyframe, laptop screen close-up showing an Outlook-style meeting invitation with many believable UI details, no logo. The invite should be readable and concrete. Exact text on screen: “Quarterly Review Meeting”; “Today, 10:00 AM”; “Join meeting”; “Sign in to continue”; “meeting-login.example-security.com”. Show a suspicious login prompt panel opening after the invite button, with fields labeled “Email” and “Password” and button “Sign in”. The login panel should look slightly suspicious but still professional. No people, no hands, no faces, no QR/barcodes, no watermarks. Cinematic dark desk lighting, premium, subtitles-safe lower area.\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_230948_055dd350.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic social-video keyframe, realistic modern desk with laptop screen in sharp focus. The laptop shows a detailed Outlook-style calendar invitation email UI, but no Microsoft logo and no brand logo. Use clean readable English text on the invite only. Exact visible UI text: Title line: \\u201cQuarterly Review Meeting\\u201d; sender: \\u201cAlex Morgan\\u201d; time row: \\u201cToday, 10:00 AM\\u201d; location row: \\u201cOnline meeting\\u201d; large blue button text: \\u201cJoin meeting\\u201d; smaller link line below: \\u201cSign in to continue\\u201d. Add attendee avatars, calendar icon, email header bars, sidebar folders, and realistic UI details. The visual problem must be instantly clear: a normal-looking meeting invite asks for login. No people, no hands, no faces, no QR codes, no watermarks. Premium navy/amber lighting, shallow depth of field, clean lower safe space for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_SlmGghi25e8HolypQnaijNC0" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231101_a6d41601.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic close-up of a smartphone on a desk, screen sharp and readable. The phone displays a detailed Outlook-style calendar invite notification/email, no logo or brand mark. Exact visible text: \\u201cQuarterly Review Meeting\\u201d; \\u201cToday 10:00 AM\\u201d; \\u201cOrganizer: Alex Morgan\\u201d; \\u201cJoin meeting\\u201d; \\u201cSign in to continue\\u201d; \\u201cThis meeting starts soon\\u201d. Include realistic message rows, attendee circles, a blue join button, small calendar header, and subtle warning red/amber glow around the sign-in area. No people, no hands, no faces, no QR codes, no watermark. High-end social video style, clean bottom safe zone for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_12nNiCGlgalW4Bnhxtaupc8H" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231303_bdbc188f.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cybersecurity keyframe, laptop screen close-up showing an Outlook-style meeting invitation with many believable UI details, no logo. The invite should be readable and concrete. Exact text on screen: \\u201cQuarterly Review Meeting\\u201d; \\u201cToday, 10:00 AM\\u201d; \\u201cJoin meeting\\u201d; \\u201cSign in to continue\\u201d; \\u201cmeeting-login.example-security.com\\u201d. Show a suspicious login prompt panel opening after the invite button, with fields labeled \\u201cEmail\\u201d and \\u201cPassword\\u201d and button \\u201cSign in\\u201d. The login panel should look slightly suspicious but still professional. No people, no hands, no faces, no QR/barcodes, no watermarks. Cinematic dark desk lighting, premium, subtitles-safe lower area.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_mK1TuNSCGEOWqa84p7x69dcL" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_cuotyaiqzG28GoTJ0qYBeVZy", "call_id": "call_cuotyaiqzG28GoTJ0qYBeVZy", "response_item_id": "fc_0d4a723b463df28d016a14bb6ace188191a5e0e2dfaa5257e3", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cinematic keyframe, realistic laptop on desk, screen sharp. Show a detailed email/calendar invite UI like Outlook, no brand logo. This is the safe action beat: the suspicious email invite is minimized in the background and a clean calendar app window is open in front. Exact readable text in the calendar window: “Calendar”; “Quarterly Review Meeting”; “Today 10:00 AM”; “Online meeting”; “Open from calendar”. The suspicious invite in background can show “Sign in to continue” dimmed. Add realistic panes, event list, calendar grid, attendee dots. No people, no hands, no faces, no QR codes, no watermarks. Premium blue secure lighting, lower safe space for subtitles.\"}" } }, { "id": "call_DpkRakvk9kOd1jsHr37gS48I", "call_id": "call_DpkRakvk9kOd1jsHr37gS48I", "response_item_id": "fc_0d4a723b463df28d016a14bb6ace2c8191b52f136cf1f6dd6a", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 cybersecurity social-video keyframe. Detailed close-up of laptop and phone together on a modern desk. Laptop shows a browser/email invite UI, phone shows calendar app. Both screens have readable text, no logos. Exact visible text on laptop: “Quarterly Review Meeting”, “Join meeting”, “Sign in to continue”. Exact visible text on phone: “Calendar”, “Quarterly Review Meeting”, “Today 10:00 AM”. The contrast should explain the safe rule: do not trust the button; open your own calendar. Make it cinematic and realistic, with many small UI details but no extra gibberish text. No people, no hands, no faces, no QR/barcodes, no watermarks. Clean lower subtitle-safe area.\"}" } }, { "id": "call_AnhTg3kOT3AmNMVqfmfPNb65", "call_id": "call_AnhTg3kOT3AmNMVqfmfPNb65", "response_item_id": "fc_0d4a723b463df28d016a14bb6ace3481918939450118d01d8e", "type": "function", "function": { "name": "image_generate", "arguments": "{\"aspect_ratio\":\"portrait\",\"prompt\":\"Premium vertical 9:16 final resolution keyframe for a cybersecurity short. A calm modern desk with laptop screen showing a detailed clean calendar event page, no logo. Exact readable text: “Calendar”; “Quarterly Review Meeting”; “Today, 10:00 AM”; “Meeting verified”; “Open meeting from calendar”. In the corner/background, a dim email invite card says “Sign in to continue” but it is visually ignored. Add realistic UI details: sidebar, calendar grid, attendee circles, blue meeting card, subtle secure glow. No people, no hands, no faces, no QR codes, no watermarks. Premium cinematic look, bottom safe area for subtitles.\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231408_c83f61fc.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cinematic keyframe, realistic laptop on desk, screen sharp. Show a detailed email/calendar invite UI like Outlook, no brand logo. This is the safe action beat: the suspicious email invite is minimized in the background and a clean calendar app window is open in front. Exact readable text in the calendar window: \\u201cCalendar\\u201d; \\u201cQuarterly Review Meeting\\u201d; \\u201cToday 10:00 AM\\u201d; \\u201cOnline meeting\\u201d; \\u201cOpen from calendar\\u201d. The suspicious invite in background can show \\u201cSign in to continue\\u201d dimmed. Add realistic panes, event list, calendar grid, attendee dots. No people, no hands, no faces, no QR codes, no watermarks. Premium blue secure lighting, lower safe space for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_cuotyaiqzG28GoTJ0qYBeVZy" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231615_47b2fd03.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 cybersecurity social-video keyframe. Detailed close-up of laptop and phone together on a modern desk. Laptop shows a browser/email invite UI, phone shows calendar app. Both screens have readable text, no logos. Exact visible text on laptop: \\u201cQuarterly Review Meeting\\u201d, \\u201cJoin meeting\\u201d, \\u201cSign in to continue\\u201d. Exact visible text on phone: \\u201cCalendar\\u201d, \\u201cQuarterly Review Meeting\\u201d, \\u201cToday 10:00 AM\\u201d. The contrast should explain the safe rule: do not trust the button; open your own calendar. Make it cinematic and realistic, with many small UI details but no extra gibberish text. No people, no hands, no faces, no QR/barcodes, no watermarks. Clean lower subtitle-safe area.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_DpkRakvk9kOd1jsHr37gS48I" }, { "role": "tool", "content": "{\"success\": true, \"image\": \"/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231708_8f122fd9.png\", \"model\": \"gpt-image-2-high\", \"prompt\": \"Premium vertical 9:16 final resolution keyframe for a cybersecurity short. A calm modern desk with laptop screen showing a detailed clean calendar event page, no logo. Exact readable text: \\u201cCalendar\\u201d; \\u201cQuarterly Review Meeting\\u201d; \\u201cToday, 10:00 AM\\u201d; \\u201cMeeting verified\\u201d; \\u201cOpen meeting from calendar\\u201d. In the corner/background, a dim email invite card says \\u201cSign in to continue\\u201d but it is visually ignored. Add realistic UI details: sidebar, calendar grid, attendee circles, blue meeting card, subtle secure glow. No people, no hands, no faces, no QR codes, no watermarks. Premium cinematic look, bottom safe area for subtitles.\", \"aspect_ratio\": \"portrait\", \"provider\": \"openai-codex\", \"size\": \"1024x1536\", \"quality\": \"high\"}", "tool_call_id": "call_AnhTg3kOT3AmNMVqfmfPNb65" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_CIoaxe7HM1PGpmVVXEBIK6ZK", "call_id": "call_CIoaxe7HM1PGpmVVXEBIK6ZK", "response_item_id": "fc_0d4a723b463df28d016a14bc59b12481918d3fd7d23068e66b", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from pathlib import Path\\nimport shutil, json, hashlib\\nfrom PIL import Image, ImageDraw, ImageFont\\nsrcs=['/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_230948_055dd350.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231101_a6d41601.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231303_bdbc188f.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231408_c83f61fc.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231615_47b2fd03.png','/home/agent/.hermes/cache/images/openai_codex_gpt-image-2-high_20260525_231708_8f122fd9.png']\\nbase=Path('/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1')\\nai=base/'ai_keyframes_b3_text_detail'; ai.mkdir(parents=True, exist_ok=True)\\nitems=[]\\nfor i,s in enumerate(srcs,1):\\n dst=ai/f'b3_text_detail_keyframe_{i:02d}_openai_codex_gpt-image-2-high.png'\\n shutil.copy2(s,dst)\\n im=Image.open(dst)\\n items.append({'index':i,'path':str(dst),'sha256':hashlib.sha256(dst.read_bytes()).hexdigest(),'resolution':f'{im.width}x{im.height}'})\\nsheet=Image.new('RGB',(1080,1120),(12,16,24)); d=ImageDraw.Draw(sheet)\\ntry: f=ImageFont.truetype('/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf',28)\\nexcept: f=None\\nfor idx,item in enumerate(items):\\n im=Image.open(item['path']).convert('RGB'); im.thumbnail((330,495))\\n cell=Image.new('RGB',(360,560),(12,16,24)); cd=ImageDraw.Draw(cell)\\n cell.paste(im,((360-im.width)//2,42)); cd.text((14,14),f\\\"B3 KF {item['index']:02d}\\\",font=f,fill=(247,202,76)); cd.text((14,525),item['resolution'],fill=(220,225,235))\\n x=(idx%3)*360; y=(idx//3)*560\\n sheet.paste(cell,(x,y)); d.rectangle((x,y,x+359,y+559),outline=(55,65,90),width=2)\\ncontact=base/'b3_text_detail_keyframes_contact_sheet_v1.jpg'; sheet.save(contact,quality=92)\\nmanifest={'generated_keyframes':items,'contact_sheet':str(contact),'purpose':'B3 no focus lines: detailed AI-generated Outlook-style visible invite/login/safe-calendar images with readable text.'}\\n(base/'b3_text_detail_keyframes_manifest_v1.json').write_text(json.dumps(manifest,indent=2),encoding='utf-8')\\nprint(contact)\"}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"status\": \"success\", \"output\": \"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3_text_detail_keyframes_contact_sheet_v1.jpg\\n\", \"tool_calls_made\": 0, \"duration_seconds\": 0.44}", "tool_call_id": "call_CIoaxe7HM1PGpmVVXEBIK6ZK" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_RaHqfybf4FFNqKJK17JBpZ39", "call_id": "call_RaHqfybf4FFNqKJK17JBpZ39", "response_item_id": "fc_0d4a723b463df28d016a14bc6e4b948191beaf051ebbef35da", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3_text_detail_keyframes_contact_sheet_v1.jpg\",\"question\":\"QA the six B3 keyframes. Need detailed visible Outlook-style calendar invite/login/safe-calendar screens with readable text. Identify which frames are usable, weak, or problematic. Check for gibberish text, logos, QR, people/hands/faces, and whether the core scam mechanism is clearer without added focus lines.\"}" } } ], "finish_reason": "tool_calls" }, { "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: QA the six B3 keyframes. Need detailed visible Outlook-style calendar invite/login/safe-calendar screens with readable text. Identify which frames are usable, weak, or problematic. Check for gibberish text, logos, QR, people/hands/faces, and whether the core scam mechanism is clearer without added focus lines.\n[screenshot]", "tool_call_id": "call_RaHqfybf4FFNqKJK17JBpZ39" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_upI8A67Oa7tsfEFAD5rE40nE", "call_id": "call_upI8A67Oa7tsfEFAD5rE40nE", "response_item_id": "fc_0d4a723b463df28d016a14bc8161508191a9e6d06648ec7a69", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from pathlib import Path\\nold=Path('/tmp/autoshorts_proof_short_sprint31/render_visible_invite_cinematic_ab_v1.py').read_text()\\nnew=old\\nnew=new.replace(\\\"OUT = BASE / 'visible_invite_cinematic_ab_v1'\\\", \\\"OUT = BASE / 'visible_invite_cinematic_ab_v1'\\\")\\nold_key=\\\"KEYFRAMES = [OUT/'ai_keyframes'/f'visible_invite_keyframe_{i:02d}_openai_codex_gpt-image-2-high.png' for i in range(1,7)]\\\"\\nnew_key=\\\"KEYFRAMES = [OUT/'ai_keyframes_b3_text_detail'/f'b3_text_detail_keyframe_{i:02d}_openai_codex_gpt-image-2-high.png' for i in range(1,7)]\\\"\\nnew=new.replace(old_key,new_key)\\nnew=new.replace(\\\"'mode':'visible_invite_cinematic_'+('ai_only' if variant=='b1' else 'minimal_focus_layer')\\\", \\\"'mode': ('visible_invite_cinematic_ai_only' if variant in ('b1','b3') else 'visible_invite_cinematic_minimal_focus_layer')\\\")\\nnew=new.replace(\\\"'NoOverlayPolicy':{'result':'pass' if variant=='b1' else 'modified_for_B2_minimal_focus','allowed':['subtitles_only'] if variant=='b1' else ['subtitles','subtle_focus_outline_no_text_no_labels_no_arrows']}\\\", \\\"'NoOverlayPolicy': {'result': 'pass' if variant in ('b1','b3') else 'modified_for_B2_minimal_focus', 'allowed': ['subtitles_only'] if variant in ('b1','b3') else ['subtitles','subtle_focus_outline_no_text_no_labels_no_arrows']}\\\")\\nstart=new.index('def main():')\\nnew=new[:start]+\\\"def main():\\\\n b3=render_variant('b3','v1.4.0-b3-text-detail-ai-only')\\\\n review={'candidate_id':CANDIDATE,'version':'v1.4.0-b3-text-detail-ai-only','status':'review_preview_only_not_posted','variant':b3,'assessment':'B3 removes B2 focus lines and relies on more detailed AI-generated Outlook-style invite/login/calendar screens with readable UI text.','approval_commands':[f'APPROVED_PROOF_SHORT {CANDIDATE} v1.4.0-b3-text-detail-ai-only', f'REVISE_PROOF_SHORT {CANDIDATE} \\\\\\\\\\\\\\\"...\\\\\\\\\\\\\\\"']}\\\\n (OUT/'review_package_b3_text_detail_v1.json').write_text(json.dumps(review,indent=2),encoding='utf-8')\\\\n print(json.dumps(review,indent=2))\\\\nif __name__=='__main__': main()\\\\n\\\"\\nPath('/tmp/autoshorts_proof_short_sprint31/render_b3_text_detail_v1.py').write_text(new)\\nprint('/tmp/autoshorts_proof_short_sprint31/render_b3_text_detail_v1.py')\"}" } } ], "finish_reason": "tool_calls", "reasoning": "**Considering script modifications**\n\nI need to focus on modifying the script for b3. Currently, the script renders both b1 and b2 when set to main, and I’m wondering if we could create the b3 script by programmatically changing KEYFRAMES and the render functionality. The b3 variant should choose between modes based on whether it's b1 or not. It looks like I'd need to manage output paths carefully so they don't overwrite each other. I might script these changes to streamline the process.\n**Modifying output paths**\n\nI'm considering creating a new version from the previous file and adjusting the output path to 'visible_invite_cinematic_ab_v1/b3_text_detail_v1'. However, the function seems to expect a specific OUT/ai_keyframes setup, and I need to set KEYFRAMES as absolute. I might use render_variant('b1', 'v1.4.0-b3-text-detail-ai-only') initially, but ideally, I want to call render_variant('b3') directly. There shouldn’t be any focus because it will only draw when variant == 'b2'. It's a bit messy, but it’s manageable.\n**Fixing variant issues**\n\nIt looks like the current variant isn't matching b1, which is incorrect. I think it's important to patch the ternary function to handle b3 properly. I'll write out the necessary Python transformations and run them. I also wonder if lowering subtitles might help obscure the screen better since there's already a safe black veil at the bottom. After rendering, I definitely need to consider doing a contact sheet quality assurance check. I'll utilize the available tools for this.", "reasoning_content": "**Considering script modifications**\n\nI need to focus on modifying the script for b3. Currently, the script renders both b1 and b2 when set to main, and I’m wondering if we could create the b3 script by programmatically changing KEYFRAMES and the render functionality. The b3 variant should choose between modes based on whether it's b1 or not. It looks like I'd need to manage output paths carefully so they don't overwrite each other. I might script these changes to streamline the process.\n**Modifying output paths**\n\nI'm considering creating a new version from the previous file and adjusting the output path to 'visible_invite_cinematic_ab_v1/b3_text_detail_v1'. However, the function seems to expect a specific OUT/ai_keyframes setup, and I need to set KEYFRAMES as absolute. I might use render_variant('b1', 'v1.4.0-b3-text-detail-ai-only') initially, but ideally, I want to call render_variant('b3') directly. There shouldn’t be any focus because it will only draw when variant == 'b2'. It's a bit messy, but it’s manageable.\n**Fixing variant issues**\n\nIt looks like the current variant isn't matching b1, which is incorrect. I think it's important to patch the ternary function to handle b3 properly. I'll write out the necessary Python transformations and run them. I also wonder if lowering subtitles might help obscure the screen better since there's already a safe black veil at the bottom. After rendering, I definitely need to consider doing a contact sheet quality assurance check. I'll utilize the available tools for this.", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFLyB3JimtyVEHyi0oc1pegwm4GF-mqoSqcjlK1FVyrSqdqpKdAK_XzrJ8JQO5-P7zaGGmSHoJZ8BJ-EEjIt_1jxyr_J08rKpVvKI4hgQ3gUFMQKBc38aZaK2nktbvDUitiazbkNvy8nWQBvjTY3kPcxJPOyLeNvVt6BexeZggu9-jvw66xPIG0NooN_nMoxaRmDMe1GvopqA1A_TuMPOA5BioU1NK5O17cPZuD0heaX_LdBHJw7ub7bv4w7Kp8TkfTcjVStxYcRVKzZkbHBU3kGIBOm2plpLhmd04RnPldaM8RrTqYnvKeRTQnz7YGhMgbthylx4EqkS1oLqMHJJni4Eij8MQE0AfbTu9kYFpHUr3VKdoWksbqOafAoFHMfAgbk-ta1tyPIEH6Gtnl6kKjnIMdgT1yY-lS0V6RdLbytMK5_xwHs-1AGbWq8KqO6yt0BlZ3p-_jBOR3aMmXLSxU6kLcgHMtid7SyfV27b_OutgK3AYF7Lxu76CThE9q6okikqsiwot4kWyDd8q4qv78BdG_IA-Oi4EoyuzyPW_g2bxFh-iNNyBu7Oe9hFG8aT4SvoLRAP0FrHGhzyoBqIcUANcqXkq7ENbw79sqc7nHx7Pzn7rOVjxDaCarG715xQejxzMrPD4xiQ-Axl0-LQUjzm3BcvYysOXwt9uGnAFwOIDMvCxZ0SAV0Y6IBe954CeXeIneJWwwb32gCuYx1hwYOEgusG52bzcUYOlPohjn0Fi_0MICFFk8_8PIWR8IcsdzrMkO-rq033JASwHjsqAEg-ZcPt4DG86vX9428XUDy3_59WMAjlTgCpD5EUVfFGDf6dpNoVtTOH8-4DHCE3xQg91Hm99j65_0z8FyQ1MOqEDrpOZ5EBPuL5TE-b4BZzCpeL0GvhEzg94RD4uOcHggi3zVmYYLanMUQTdgwc61KZ8yqrIVF5BvGYEH6PV2T2RWz9FGS05QPulW1cY9yqECKSNtBO1p_vvhZf1rAP-9reSmtuCcVWogQcVovJgKNxvBBmCtZjG5Lz8ne_7URbWhG4xn-kG_FWP__V7DxGv-B8eCzRJtkSFJFJZ9Kjxw7prgTXhdVJxGNieNPmPpGE_GHPMfRpB7tY-CgJl7ibJg1enieJHB0tz0XuWna4L3a12vJd1DQ6stTKHgfCZlWjzNAo8pF3VwUALYaAez3vmcJ0K1LuXhq2Z_A4E88H35YuuHebQKyU4yjTIl-Lv-oOBJxvy3SgnirBbGX0NrwgmiUd5jF0lpwkWtzeoOv30zw3uNTseyx-5Y-jkuO3IHASLZr2lkE6lHTSfNAdizd7NE0BGsUnjSCXiTQTIS3zxUSKrFIlSsDuNdMubnScKr7HWEp1SSn-MrVFl2MppEUm12EohU9DW6SUGZ9t8oehrInTp1Pf23IjqQbHaanKQ_bCxcGw3Nut3Um3tSdy2yW2ApyBFwz9JCdlDqhDBeLMDkpYjsc_I-iG2RIbjs4oQwF_ZFq8Ty1s1rJvpLIO2MTWdAfQHKDflMrIOh9ReBzSVDeOYxJfNCUy-4dZXcCsjBErykjWqeZchA1OKO4L-AC5iU_WiwhQ7GaDexJjGE_nuLiw_230yFBowc3kJK-v_fwmptOEW3lXkjFlS7HeX5rDyTfp55T3GclGwtGSC9ogw7cnsDeDWNpx-kH3g1UKZSn_R7dlIKkeHXchNpT81q9u4AxYrQ7s24ZEn046mxxUiT_jaGfNkTOvvLqxROCIB46uprxeW5gVICRx-inqgguA_H_8FldVoxNEyQwfUlSQoddBZvbvGfINm55zQPxZ2fEbkXmochdDS4cPu-OOiWzeMvSnsRNJNq1g_bITbwvYP_PH7hYUoWNZ5IfCH3wFtBunZU6nE1lPcMOJ8hmn3POsOC_pYrkfP1M6If-Y-dU_00sw62aWMs00vt9T_t-fSJekATOhRcdMHi5k-STcdmEdSnXy8IXE2jMhJ6I67v50aLzC4mMrYoA-XUL0sXOpK-DYBECVq-VwZ-OG03nAz48hrO6xNMJOtsJl0o29WeQYGI0o9R47sFsCiLJJNSwuwVwPJVP4Xg0jrheXUQHLZrsRV8RGk7rowA8NWzH322Oxa977aP3Niu9s25gbAgZK2lXypttewJALHRt85xmQwiZ2Pn789ECXuHthV9WD-TEgyKsojdDsuX7DUn2E6Ka8kFE42_QHSd3y7Wj9zVHiaOuLzryCKr52JQYeA5QSPGj4VjhT7h8EGvcaiCaF_XT9TYNRtXYS_IQAHkASoPPScnBLjJo2U1uomZygySiTpUYOQzun96x0xWrxNoUFFxFHHPLx1lmi-dHyUhf_RuEXJFejhk__iy7RUfdupPiYmQLXEzpfJ0BQnv21UHoQGm5xS3h3Bt89_EKjfpHopx9juxeETurZBhcqlbd7E4hDPf4lMnyFT-OWA8w3PewUgZjdS2YNfuMhv6GKaN7tuNjXNE7v3AVEMWFM1Ethdsl1-dwV5oz8mUeZI3S9m1zhWLJ8oiNZMiiyHqW3AwGVjd9PH0ywVVrworAdBqDB7etwTNlmzFjwkkz0hOpx-8mmM5UwY87r6r0thZ_4DbSIixGeCANf-57BfQOwQqKtbZEB4VCcVnWoJBMu7lJLRacfyisUTAUWEE75rHz4U6RUh6kSja0HDqnTvD1rbc0BR-UBzTZww2C7PUJXe9X94S0nmlqrR5gg7V-u0DiWqMmCaPCXgxzrVhN0DF_nRdzA-Fxix6YM9Ik4KboL1uQaVfqRqbzqCbSgMy6G57mgO4ZoRoUlouE9z7mkVRjTdk1dKxtFF3dlEYT3zzg7KkgsmXUePopf_VXon2i0YLkXe4EorvkrxceK-PqYh0iBycommhKF0XFa4nwEPzhl8U1YAwP2QIhgrmCQ5y3CBDxdhlqyBWHhDsPuHFl5Wrd-T36V8xUb45zGAVyEdvSRT116O8vy3OcTOcxeXJGwKRMaDzUiN74o8GKUjHes2QTvbN7p31baVaTj-_cABqRmR7C7gRV5LoS42yJ3cBj-SQWVEK-4Au4psnUtAXZ_hss3tzAgzY2vnKnZrny0Is2bVHtfcYD6gVto9iUhZjlfUqqW66oq5ByCGl6cbIy6w-kjez_4p1ltRDw7qh1LONOzGMLs9n6Aoh7fcTEaUpR6em2AZKpMD0UO_JG6CtF_VY0xlS-HTdSruHK_o-JyMfKccj-DqFlS-4Duhy2fIV3EAfALAd5yaLa3NLzOrrWKncIfQRcI6jkFuQxps08_dH7ddIPryZIvwmL1SAWou72EvSSrEiBdk6xp64-57ncS0tvZsHIOdHod4q-iaos9X6xg7BLWW9yryL6at90gS8AR9eZr2JQG_OpjFLee6bkAiU-wCYorR4PEQ1LpLcnvOgkT0y6wCgqUP2YdloiIqF3LYoHUeMqfz_Mx_97vbXtAQAqweKm7HsCLD1jtfTshc5rJe3F59h4bAga-jmEwKI4eJsPJ40cXJARU4RriUJZawCFm7SDVhwkEa3o-milz3YZDgrZCu_Jhm97RNx_YHsBK0Pv5qQviRwCLySUDPALQI6P990dTEvB-4Hrd7_XEyT0FDsIvYOkgc75lCz1J8XopsZhC6mkuxdPAxKUOxaa06YMwFzA3zcm9FqxPJXrLpZykE53bP4mna624Tz4lldHOYa-ojYzmaYWvvJWXI5rfn6kcbprnzPIlD3a9G6qxl_DNyfx4bE1kOM1etxVc_6ZI2JV6mfqTFajZFRMmEh4VohaSilOIMRez9H-QPiJka8C5UK5V15NyQHjpk0UVYwuag8MtSeucPhOH3cz7jfgGmLex2MPXd4rY4kkFhJejKWgktuOOavwCmaASkIK4jqFv7pI3CO-THfJH-oLupqWCH0JwgZ6CQFan9elgDik7NSysY256DmeKPVHjPpb1-CZC40Oms1WGhHb-WeBAehkSjjbgpuadAATneowUmK6Edp0zLuqHYMamo8uiIJholFVJT-4ln-FtrGNKCSqxIXFl90e1vlHVTPMYV534dV-UZ-KED0isM6ZcsotWmhxjmphsab_lAiB_6C2_wffMtFogKF_P0q2Ba9RB_n_Rt_ycy8wA0KMit3VwtlSFruincYPppwE5ZnpI8g3nahAbSm7Qd5EAizqUWV1bCQO5WzZkS4tChg9vuyUV9z_s_s59jmC1a2dWCDB4C5ODnzO2LYRZjcrOG38uE0OgQgHaX0l0nspGdCeTkwpRETLtaIynr5bHxaPmCC_gTLvfI8dXd-hCGrUvSs9nHZ464UqqdlyiViEKc5Ff3MlCqEd_6QO0TKMkGjeLq343E_CFRBwcYhyw9gd6HenGQLmWTdsZh6ZUFLu5ACz_cOvyc9s2_iDKrzrEF1ot4_HwvJBLWqTHTorKzRy2zU1yXvDW6Yivts9hRtzuHkWo9GuSTAmS1sOrng9xANwlzUoazfc8M1Gy0Rfa5CWAU-RMzuhIU-BrssPCnoQP5XNSXJ70f3aAFR4bKlghu8R025aMCU5G3DBMlRCvH8VPk3uU6bw326Yggw_vZzXw-rK1fTTel2Wnhxr6KpPzUIv8619TiGh_jVRUCu_JvTkFxt4fx758OZs2bV3BzYeWXm1LRjv1ubfFSVuKh67WYm-0674bed6q1_P2L5ZZ9BIArDkbK1tcV4HKYBl8oEgs", "id": "rs_0d4a723b463df28d016a14bc73407c8191904a1dcfbef6cf6f", "summary": [ { "type": "summary_text", "text": "**Considering script modifications**\n\nI need to focus on modifying the script for b3. Currently, the script renders both b1 and b2 when set to main, and I’m wondering if we could create the b3 script by programmatically changing KEYFRAMES and the render functionality. The b3 variant should choose between modes based on whether it's b1 or not. It looks like I'd need to manage output paths carefully so they don't overwrite each other. I might script these changes to streamline the process." }, { "type": "summary_text", "text": "**Modifying output paths**\n\nI'm considering creating a new version from the previous file and adjusting the output path to 'visible_invite_cinematic_ab_v1/b3_text_detail_v1'. However, the function seems to expect a specific OUT/ai_keyframes setup, and I need to set KEYFRAMES as absolute. I might use render_variant('b1', 'v1.4.0-b3-text-detail-ai-only') initially, but ideally, I want to call render_variant('b3') directly. There shouldn’t be any focus because it will only draw when variant == 'b2'. It's a bit messy, but it’s manageable." }, { "type": "summary_text", "text": "**Fixing variant issues**\n\nIt looks like the current variant isn't matching b1, which is incorrect. I think it's important to patch the ternary function to handle b3 properly. I'll write out the necessary Python transformations and run them. I also wonder if lowering subtitles might help obscure the screen better since there's already a safe black veil at the bottom. After rendering, I definitely need to consider doing a contact sheet quality assurance check. I'll utilize the available tools for this." } ] } ] }, { "role": "tool", "content": "{\"status\": \"success\", \"output\": \"/tmp/autoshorts_proof_short_sprint31/render_b3_text_detail_v1.py\\n\", \"tool_calls_made\": 0, \"duration_seconds\": 0.24}", "tool_call_id": "call_upI8A67Oa7tsfEFAD5rE40nE" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_Sdbk719HxcxuqRqzYOCBLBEu", "call_id": "call_Sdbk719HxcxuqRqzYOCBLBEu", "response_item_id": "fc_0d4a723b463df28d016a14bc8f8c7881919f83e7d3021610d7", "type": "function", "function": { "name": "todo", "arguments": "{\"merge\":true,\"todos\":[{\"content\":\"Neue B3-KI-Keyframes mit detaillierter sichtbarer Outlook-artiger Einladung/Text erzeugen\",\"id\":\"b3-gen\",\"status\":\"completed\"},{\"content\":\"Keyframes auf Lesbarkeit, Details und Artefakte prüfen\",\"id\":\"b3-qaimg\",\"status\":\"completed\"},{\"content\":\"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\",\"id\":\"b3-render\",\"status\":\"in_progress\"}]}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"todos\": [{\"id\": \"b3-gen\", \"content\": \"Neue B3-KI-Keyframes mit detaillierter sichtbarer Outlook-artiger Einladung/Text erzeugen\", \"status\": \"completed\"}, {\"id\": \"b3-qaimg\", \"content\": \"Keyframes auf Lesbarkeit, Details und Artefakte prüfen\", \"status\": \"completed\"}, {\"id\": \"b3-render\", \"content\": \"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\", \"status\": \"in_progress\"}, {\"id\": \"b3-qa-deliver\", \"content\": \"B3 technisch prüfen, Hash/Manifest erstellen und liefern\", \"status\": \"pending\"}], \"summary\": {\"total\": 4, \"pending\": 1, \"in_progress\": 1, \"completed\": 2, \"cancelled\": 0}}", "tool_call_id": "call_Sdbk719HxcxuqRqzYOCBLBEu" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_vsaqUPVd327o0PH1Zidgs25W", "call_id": "call_vsaqUPVd327o0PH1Zidgs25W", "response_item_id": "fc_0d4a723b463df28d016a14bc93b66c8191b6b3d87e442019c4", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"python /tmp/autoshorts_proof_short_sprint31/render_b3_text_detail_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 @ 0x64f9dd5343c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x64f9dd5343c0] profile High, level 4.0, 4:2:0, 8-bit\\n[libx264 @ 0x64f9dd5343c0] 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=18.0 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/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_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= 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=0.7 q=23.0 size= 0kB time=00:00:00.08 bitrate= 4.6kbits/s speed=0.015x \\rframe= 10 fps=1.6 q=23.0 size= 256kB time=00:00:00.33 bitrate=6292.6kbits/s speed=0.0542x \\rframe= 15 fps=2.2 q=23.0 size= 256kB time=00:00:00.54 bitrate=3872.4kbits/s speed=0.0811x \\rframe= 20 fps=2.8 q=23.0 size= 256kB time=00:00:00.75 bitrate=2796.7kbits/s speed=0.104x \\rframe= 25 fps=3.3 q=23.0 size= 256kB time=00:00:00.95 bitrate=2188.7kbits/s speed=0.125x \\rframe= 30 fps=3.7 q=23.0 size= 256kB time=00:00:01.16 bitrate=1797.9kbits/s speed=0.142x \\rframe= 35 fps=4.0 q=23.0 size= 512kB time=00:00:01.37 bitrate=3050.7kbits/s speed=0.157x \\rframe= 41 fps=4.4 q=23.0 size= 512kB time=00:00:01.62 bitrate=2581.3kbits/s speed=0.174x \\rframe= 46 fps=4.6 q=23.0 size= 512kB time=00:00:01.83 bitrate=2288.0kbits/s speed=0.185x \\rframe= 51 fps=4.9 q=23.0 size= 768kB time=00:00:02.04 bitrate=3081.7kbits/s speed=0.196x \\rframe= 56 fps=5.1 q=23.0 size= 768kB time=00:00:02.25 bitrate=2796.4kbits/s speed=0.205x \\rframe= 61 fps=5.3 q=23.0 size= 768kB time=00:00:02.45 bitrate=2559.4kbits/s speed=0.213x \\rframe= 66 fps=5.4 q=23.0 size= 768kB time=00:00:02.66 bitrate=2359.4kbits/s speed=0.22x \\rframe= 71 fps=5.6 q=23.0 size= 1024kB time=00:00:02.87 bitrate=2917.9kbits/s speed=0.227x \\rframe= 76 fps=5.8 q=23.0 size= 1024kB time=00:00:03.08 bitrate=2720.8kbits/s speed=0.235x \\rframe= 80 fps=5.8 q=23.0 size= 1024kB time=00:00:03.25 bitrate=2581.2kbits/s speed=0.238x \\rframe= 84 fps=5.9 q=23.0 size= 1024kB time=00:00:03.41 bitrate=2455.3kbits/s speed=0.239x \\rframe= 88 fps=5.9 q=23.0 size= 1280kB time=00:00:03.58 bitrate=2926.4kbits/s speed=0.24x \\rframe= 92 fps=5.9 q=23.0 size= 1280kB time=00:00:03.75 bitrate=2796.3kbits/s speed=0.241x \\rframe= 96 fps=5.9 q=23.0 size= 1280kB time=00:00:03.91 bitrate=2677.3kbits/s speed=0.242x \\rframe= 101 fps=6.0 q=23.0 size= 1280kB time=00:00:04.12 bitrate=2542.1kbits/s speed=0.247x \\rframe= 107 fps=6.2 q=23.0 size= 1536kB time=00:00:04.37 bitrate=2876.2kbits/s speed=0.253x \\rframe= 112 fps=6.3 q=23.0 size= 1536kB time=00:00:04.58 bitrate=2745.4kbits/s speed=0.258x \\rframe= 118 fps=6.4 q=23.0 size= 1536kB time=00:00:04.83 bitrate=2603.4kbits/s speed=0.264x \\rframe= 124 fps=6.6 q=23.0 size= 1536kB time=00:00:05.08 bitrate=2475.4kbits/s speed=0.269x \\rframe= 129 fps=6.6 q=23.0 size= 1792kB time=00:00:05.29 bitrate=2774.3kbits/s speed=0.272x \\rframe= 135 fps=6.7 q=23.0 size= 1792kB time=00:00:05.54 bitrate=2649.1kbits/s speed=0.277x \\rframe= 141 fps=6.8 q=23.0 size= 2048kB time=00:00:05.79 bitrate=2896.9kbits/s speed=0.281x \\rframe= 146 fps=6.9 q=23.0 size= 2304kB time=00:00:06.00 bitrate=3145.8kbits/s speed=0.284x \\rframe= 151 fps=7.0 q=23.0 size= 2560kB time=00:00:06.20 bitrate=3378.0kbits/s speed=0.286x \\rframe= 156 fps=7.0 q=23.0 size= 2560kB time=00:00:06.41 bitrate=3268.3kbits/s speed=0.289x \\rframe= 163 fps=7.2 q=23.0 size= 2816kB time=00:00:06.66 bitrate=3460.4kbits/s speed=0.293x \\rframe= 168 fps=7.2 q=23.0 size= 2816kB time=00:00:06.91 bitrate=3335.3kbits/s speed=0.297x \\rframe= 173 fps=7.3 q=23.0 size= 2816kB time=00:00:07.12 bitrate=3237.8kbits/s speed=0.299x \\rframe= 178 fps=7.3 q=23.0 size= 3072kB time=00:00:07.33 bitrate=3431.8kbits/s speed=0.301x \\rframe= 183 fps=7.3 q=23.0 size= 3072kB time=00:00:07.54 bitrate=3337.0kbits/s speed=0.302x \\rframe= 188 fps=7.4 q=23.0 size= 3072kB time=00:00:07.75 bitrate=3247.3kbits/s speed=0.303x \\rframe= 193 fps=7.4 q=23.0 size= 3328kB time=00:00:07.95 bitrate=3425.8kbits/s speed=0.305x \\rframe= 198 fps=7.4 q=23.0 size= 3328kB time=00:00:08.16 bitrate=3338.4kbits/s speed=0.307x \\rframe= 203 fps=7.5 q=23.0 size= 3328kB time=00:00:08.37 bitrate=3255.3kbits/s speed=0.308x \\rframe= 208 fps=7.5 q=23.0 size= 3584kB time=00:00:08.58 bitrate=3420.6kbits/s speed=0.31x \\rframe= 213 fps=7.5 q=23.0 size= 3584kB time=00:00:08.79 bitrate=3339.6kbits/s speed=0.311x \\rframe= 218 fps=7.5 q=23.0 size= 3584kB time=00:00:09.00 bitrate=3262.3kbits/s speed=0.312x \\rframe= 223 fps=7.6 q=23.0 size= 3840kB time=00:00:09.20 bitrate=3416.2kbits/s speed=0.312x \\rframe= 228 fps=7.6 q=23.0 size= 3840kB time=00:00:09.41 bitrate=3340.6kbits/s speed=0.313x \\rframe= 234 fps=7.7 q=23.0 size= 3840kB time=00:00:09.62 bitrate=3268.3kbits/s speed=0.315x \\rframe= 238 fps=7.6 q=23.0 size= 4096kB time=00:00:09.83 bitrate=3412.4kbits/s speed=0.316x \\rframe= 243 fps=7.7 q=23.0 size= 4096kB time=00:00:10.04 bitrate=3341.6kbits/s speed=0.317x \\rframe= 248 fps=7.7 q=23.0 size= 4096kB time=00:00:10.25 bitrate=3273.6kbits/s speed=0.319x \\rframe= 253 fps=7.7 q=23.0 size= 4608kB time=00:00:10.45 bitrate=3609.5kbits/s speed=0.319x \\rframe= 257 fps=7.7 q=23.0 size= 4608kB time=00:00:10.62 bitrate=3552.9kbits/s speed=0.318x \\rframe= 261 fps=7.7 q=23.0 size= 4608kB time=00:00:10.79 bitrate=3498.0kbits/s speed=0.317x \\rframe= 264 fps=7.6 q=23.0 size= 4608kB time=00:00:10.91 bitrate=3457.9kbits/s speed=0.316x \\rframe= 268 fps=7.6 q=23.0 size= 4608kB time=00:00:11.08 bitrate=3405.9kbits/s speed=0.315x \\rframe= 273 fps=7.6 q=23.0 size= 4864kB time=00:00:11.29 bitrate=3528.8kbits/s speed=0.316x \\rframe= 279 fps=7.7 q=23.0 size= 4864kB time=00:00:11.54 bitrate=3452.4kbits/s speed=0.317x \\rframe= 285 fps=7.7 q=23.0 size= 4864kB time=00:00:11.79 bitrate=3379.2kbits/s speed=0.319x \\rframe= 291 fps=7.8 q=23.0 size= 5120kB time=00:00:12.00 bitrate=3495.3kbits/s speed=0.32x \\rframe= 295 fps=7.8 q=23.0 size= 5120kB time=00:00:12.20 bitrate=3435.6kbits/s speed=0.321x \\rframe= 301 fps=7.8 q=23.0 size= 5120kB time=00:00:12.45 bitrate=3366.7kbits/s speed=0.323x \\rframe= 306 fps=7.8 q=23.0 size= 5376kB time=00:00:12.66 bitrate=3476.9kbits/s speed=0.324x \\rframe= 312 fps=7.9 q=23.0 size= 5376kB time=00:00:12.91 bitrate=3409.6kbits/s speed=0.325x \\rframe= 318 fps=7.9 q=23.0 size= 5632kB time=00:00:13.16 bitrate=3504.1kbits/s speed=0.327x \\rframe= 325 fps=8.0 q=23.0 size= 5888kB time=00:00:13.41 bitrate=3595.1kbits/s speed=0.329x \\rframe= 330 fps=8.0 q=23.0 size= 5888kB time=00:00:13.66 bitrate=3529.4kbits/s speed=0.331x \\rframe= 336 fps=8.0 q=23.0 size= 6144kB time=00:00:13.91 bitrate=3616.7kbits/s speed=0.332x \\rframe= 341 fps=8.0 q=23.0 size= 6144kB time=00:00:14.12 bitrate=3563.3kbits/s speed=0.333x \\rframe= 347 fps=8.1 q=23.0 size= 6144kB time=00:00:14.37 bitrate=3501.4kbits/s speed=0.334x \\rframe= 352 fps=8.1 q=23.0 size= 6144kB time=00:00:14.58 bitrate=3451.3kbits/s speed=0.335x \\rframe= 358 fps=8.1 q=23.0 size= 6400kB time=00:00:14.83 bitrate=3534.6kbits/s speed=0.337x \\rframe= 364 fps=8.2 q=23.0 size= 6400kB time=00:00:15.08 bitrate=3476.0kbits/s speed=0.338x \\rframe= 369 fps=8.2 q=23.0 size= 6400kB time=00:00:15.29 bitrate=3428.6kbits/s speed=0.338x \\rframe= 375 fps=8.2 q=23.0 size= 6656kB time=00:00:15.50 bitrate=3517.8kbits/s speed=0.339x \\rframe= 379 fps=8.2 q=23.0 size= 6656kB time=00:00:15.70 bitrate=3471.2kbits/s speed=0.34x \\rframe= 384 fps=8.2 q=23.0 size= 6656kB time=00:00:15.91 bitrate=3425.7kbits/s speed=0.34x \\rframe= 389 fps=8.2 q=23.0 size= 6656kB time=00:00:16.12 bitrate=3381.5kbits/s speed=0.341x \\rframe= 395 fps=8.3 q=23.0 size= 6656kB time=00:00:16.37 bitrate=3329.9kbits/s speed=0.342x \\rframe= 401 fps=8.3 q=23.0 size= 6912kB time=00:00:16.62 bitrate=3405.9kbits/s speed=0.343x \\rframe= 406 fps=8.3 q=23.0 size= 6912kB time=00:00:16.83 bitrate=3363.8kbits/s speed=0.344x \\rframe= 411 fps=8.3 q=23.0 size= 6912kB time=00:00:17.04 bitrate=3322.6kbits/s speed=0.344x \\rframe= 416 fps=8.3 q=23.0 size= 7168kB time=00:00:17.25 bitrate=3404.1kbits/s speed=0.345x \\rframe= 421 fps=8.3 q=23.0 size= 7168kB time=00:00:17.45 bitrate=3363.5kbits/s speed=0.345x \\rframe= 427 fps=8.3 q=23.0 size= 7168kB time=00:00:17.66 bitrate=3323.8kbits/s speed=0.345x \\rframe= 430 fps=8.3 q=23.0 size= 7168kB time=00:00:17.83 bitrate=3292.7kbits/s speed=0.345x \\rframe= 433 fps=8.3 q=23.0 size= 7424kB time=00:00:17.95 bitrate=3386.6kbits/s speed=0.344x \\rframe= 437 fps=8.3 q=23.0 size= 7424kB time=00:00:18.12 bitrate=3355.5kbits/s speed=0.343x \\rframe= 441 fps=8.2 q=23.0 size= 7424kB time=00:00:18.29 bitrate=3324.9kbits/s speed=0.342x \\rframe= 445 fps=8.2 q=23.0 size= 7424kB time=00:00:18.45 bitrate=3294.9kbits/s speed=0.341x \\rframe= 450 fps=8.2 q=23.0 size= 7424kB time=00:00:18.62 bitrate=3265.4kbits/s speed=0.341x \\rframe= 455 fps=8.2 q=23.0 size= 7424kB time=00:00:18.87 bitrate=3222.1kbits/s speed=0.342x \\rframe= 461 fps=8.3 q=23.0 size= 7680kB time=00:00:19.12 bitrate=3289.7kbits/s speed=0.343x \\rframe= 467 fps=8.3 q=23.0 size= 7680kB time=00:00:19.33 bitrate=3254.2kbits/s speed=0.343x \\rframe= 471 fps=8.3 q=23.0 size= 7680kB time=00:00:19.54 bitrate=3219.5kbits/s speed=0.343x \\rframe= 476 fps=8.3 q=23.0 size= 7936kB time=00:00:19.75 bitrate=3291.8kbits/s speed=0.344x \\rframe= 481 fps=8.3 q=23.0 size= 7936kB time=00:00:19.95 bitrate=3257.4kbits/s speed=0.344x \\rframe= 486 fps=8.3 q=23.0 size= 7936kB time=00:00:20.16 bitrate=3223.7kbits/s speed=0.345x \\rframe= 491 fps=8.3 q=23.0 size= 8192kB time=00:00:20.37 bitrate=3293.7kbits/s speed=0.345x \\rframe= 497 fps=8.3 q=23.0 size= 8448kB time=00:00:20.62 bitrate=3355.5kbits/s speed=0.346x \\rframe= 504 fps=8.4 q=23.0 size= 8704kB time=00:00:20.87 bitrate=3415.7kbits/s speed=0.347x \\rframe= 508 fps=8.4 q=23.0 size= 8704kB time=00:00:21.08 bitrate=3382.0kbits/s speed=0.347x \\rframe= 514 fps=8.4 q=23.0 size= 8704kB time=00:00:21.29 bitrate=3348.9kbits/s speed=0.348x \\rframe= 518 fps=8.4 q=23.0 size= 8704kB time=00:00:21.50 bitrate=3316.4kbits/s speed=0.348x \\rframe= 524 fps=8.4 q=23.0 size= 8704kB time=00:00:21.70 bitrate=3284.6kbits/s speed=0.348x \\rframe= 528 fps=8.4 q=23.0 size= 8960kB time=00:00:21.91 bitrate=3349.1kbits/s speed=0.349x \\rframe= 533 fps=8.4 q=23.0 size= 8960kB time=00:00:22.12 bitrate=3317.5kbits/s speed=0.349x \\rframe= 538 fps=8.4 q=23.0 size= 8960kB time=00:00:22.33 bitrate=3286.6kbits/s speed=0.35x \\rframe= 543 fps=8.4 q=23.0 size= 9216kB time=00:00:22.54 bitrate=3349.3kbits/s speed=0.35x \\rframe= 548 fps=8.4 q=23.0 size= 9216kB time=00:00:22.75 bitrate=3318.6kbits/s speed=0.351x \\rframe= 553 fps=8.5 q=23.0 size= 9216kB time=00:00:22.95 bitrate=3288.5kbits/s speed=0.351x \\rframe= 558 fps=8.5 q=23.0 size= 9216kB time=00:00:23.16 bitrate=3258.9kbits/s speed=0.351x \\rframe= 563 fps=8.5 q=23.0 size= 9216kB time=00:00:23.37 bitrate=3229.9kbits/s speed=0.352x \\rframe= 568 fps=8.5 q=23.0 size= 9472kB time=00:00:23.58 bitrate=3290.2kbits/s speed=0.352x \\rframe= 574 fps=8.5 q=23.0 size= 9472kB time=00:00:23.83 bitrate=3255.7kbits/s speed=0.353x \\rframe= 581 fps=8.5 q=23.0 size= 9472kB time=00:00:24.08 bitrate=3221.9kbits/s speed=0.353x \\rframe= 587 fps=8.5 q=23.0 size= 9728kB time=00:00:24.33 bitrate=3275.0kbits/s speed=0.354x \\rframe= 593 fps=8.6 q=23.0 size= 9728kB time=00:00:24.58 bitrate=3241.7kbits/s speed=0.355x \\rframe= 598 fps=8.6 q=23.0 size= 9728kB time=00:00:24.83 bitrate=3209.1kbits/s speed=0.355x \\rframe= 603 fps=8.6 q=23.0 size= 9728kB time=00:00:25.04 bitrate=3182.4kbits/s speed=0.355x \\rframe= 609 fps=8.6 q=23.0 size= 9984kB time=00:00:25.29 bitrate=3233.8kbits/s speed=0.356x \\rframe= 614 fps=8.6 q=23.0 size= 9984kB time=00:00:25.50 bitrate=3207.4kbits/s speed=0.356x \\rframe= 619 fps=8.6 q=23.0 size= 9984kB time=00:00:25.70 bitrate=3181.4kbits/s speed=0.357x \\rframe= 623 fps=8.6 q=23.0 size= 9984kB time=00:00:25.87 bitrate=3160.9kbits/s speed=0.356x \\rframe= 627 fps=8.6 q=23.0 size= 10240kB time=00:00:26.04 bitrate=3221.2kbits/s speed=0.356x \\rframe= 631 fps=8.5 q=23.0 size= 10240kB time=00:00:26.20 bitrate=3200.8kbits/s speed=0.355x \\rframe= 635 fps=8.5 q=23.0 size= 10240kB time=00:00:26.37 bitrate=3180.5kbits/s speed=0.354x \\rframe= 639 fps=8.5 q=23.0 size= 10240kB time=00:00:26.54 bitrate=3160.6kbits/s speed=0.353x \\rframe= 645 fps=8.5 q=23.0 size= 10240kB time=00:00:26.79 bitrate=3131.1kbits/s speed=0.354x \\rframe= 650 fps=8.5 q=23.0 size= 10496kB time=00:00:27.00 bitrate=3184.6kbits/s speed=0.354x \\rframe= 656 fps=8.5 q=23.0 size= 10496kB time=00:00:27.20 bitrate=3160.2kbits/s speed=0.354x \\rframe= 660 fps=8.5 q=23.0 size= 10496kB time=00:00:27.41 bitrate=3136.2kbits/s speed=0.355x \\rframe= 665 fps=8.5 q=23.0 size= 10496kB time=00:00:27.62 bitrate=3112.5kbits/s speed=0.355x \\rframe= 670 fps=8.5 q=23.0 size= 10752kB time=00:00:27.83 bitrate=3164.6kbits/s speed=0.355x \\rframe= 676 fps=8.6 q=23.0 size= 10752kB time=00:00:28.08 bitrate=3136.4kbits/s speed=0.356x \\rframe= 682 fps=8.6 q=23.0 size= 11008kB time=00:00:28.33 bitrate=3182.8kbits/s speed=0.356x \\rframe= 689 fps=8.6 q=23.0 size= 11008kB time=00:00:28.58 bitrate=3154.9kbits/s speed=0.357x \\rframe= 694 fps=8.6 q=23.0 size= 11264kB time=00:00:28.83 bitrate=3200.3kbits/s speed=0.357x \\rframe= 699 fps=8.6 q=23.0 size= 11264kB time=00:00:29.04 bitrate=3177.3kbits/s speed=0.358x \\rframe= 704 fps=8.6 q=23.0 size= 11264kB time=00:00:29.25 bitrate=3154.7kbits/s speed=0.358x \\rframe= 709 fps=8.6 q=23.0 size= 11264kB time=00:00:29.45 bitrate=3132.4kbits/s speed=0.358x \\rframe= 714 fps=8.6 q=23.0 size= 11520kB time=00:00:29.66 bitrate=3181.1kbits/s speed=0.359x \\rframe= 720 fps=8.6 q=23.0 size= 11520kB time=00:00:29.91 bitrate=3154.5kbits/s speed=0.359x \\rframe= 725 fps=8.6 q=23.0 size= 11520kB time=00:00:30.12 bitrate=3132.7kbits/s speed=0.359x \\rframe= 731 fps=8.7 q=23.0 size= 11776kB time=00:00:30.37 bitrate=3175.9kbits/s speed=0.36x \\rframe= 737 fps=8.7 q=23.0 size= 11776kB time=00:00:30.62 bitrate=3150.0kbits/s speed=0.36x \\rframe= 743 fps=8.7 q=23.0 size= 11776kB time=00:00:30.87 bitrate=3124.5kbits/s speed=0.361x \\rframe= 749 fps=8.7 q=23.0 size= 11776kB time=00:00:31.12 bitrate=3099.4kbits/s speed=0.361x \\rframe= 754 fps=8.7 q=23.0 size= 12032kB time=00:00:31.33 bitrate=3145.7kbits/s speed=0.362x \\rframe= 759 fps=8.7 q=23.0 size= 12032kB time=00:00:31.54 bitrate=3125.0kbits/s speed=0.362x \\rframe= 765 fps=8.7 q=23.0 size= 12032kB time=00:00:31.79 bitrate=3100.4kbits/s speed=0.362x \\rframe= 771 fps=8.7 q=23.0 size= 12288kB time=00:00:32.04 bitrate=3141.6kbits/s speed=0.363x \\rframe= 777 fps=8.7 q=23.0 size= 12288kB time=00:00:32.29 bitrate=3117.3kbits/s speed=0.363x \\rframe= 783 fps=8.8 q=23.0 size= 12288kB time=00:00:32.54 bitrate=3093.4kbits/s speed=0.364x \\rframe= 787 fps=8.7 q=23.0 size= 12288kB time=00:00:32.70 bitrate=3077.6kbits/s speed=0.363x \\rframe= 791 fps=8.7 q=23.0 size= 12288kB time=00:00:32.87 bitrate=3062.0kbits/s speed=0.363x \\rframe= 794 fps=8.7 q=23.0 size= 12544kB time=00:00:33.00 bitrate=3114.0kbits/s speed=0.362x \\rframe= 798 fps=8.7 q=23.0 size= 12544kB time=00:00:33.16 bitrate=3098.3kbits/s speed=0.361x \\rframe= 802 fps=8.7 q=23.0 size= 12544kB time=00:00:33.33 bitrate=3082.8kbits/s speed=0.361x \\rframe= 808 fps=8.7 q=23.0 size= 12544kB time=00:00:33.54 bitrate=3063.7kbits/s speed=0.361x \\rframe= 813 fps=8.7 q=23.0 size= 12544kB time=00:00:33.75 bitrate=3044.8kbits/s speed=0.361x \\rframe= 818 fps=8.7 q=23.0 size= 12800kB time=00:00:34.00 bitrate=3084.1kbits/s speed=0.362x \\rframe= 824 fps=8.7 q=23.0 size= 12800kB time=00:00:34.25 bitrate=3061.5kbits/s speed=0.362x \\rframe= 830 fps=8.7 q=23.0 size= 12800kB time=00:00:34.45 bitrate=3043.0kbits/s speed=0.362x \\rframe= 836 fps=8.7 q=23.0 size= 12800kB time=00:00:34.70 bitrate=3021.1kbits/s speed=0.363x \\rframe= 841 fps=8.7 q=23.0 size= 13056kB time=00:00:34.91 bitrate=3063.2kbits/s speed=0.363x \\rframe= 846 fps=8.7 q=23.0 size= 13056kB time=00:00:35.12 bitrate=3045.0kbits/s speed=0.363x \\rframe= 851 fps=8.7 q=23.0 size= 13312kB time=00:00:35.33 bitrate=3086.4kbits/s speed=0.363x \\rframe= 856 fps=8.8 q=23.0 size= 13312kB time=00:00:35.54 bitrate=3068.3kbits/s speed=0.363x \\rframe= 860 fps=8.7 q=23.0 size= 13568kB time=00:00:35.75 bitrate=3109.1kbits/s speed=0.363x \\rframe= 866 fps=8.8 q=23.0 size= 13568kB time=00:00:35.95 bitrate=3091.1kbits/s speed=0.364x \\rframe= 870 fps=8.8 q=23.0 size= 13568kB time=00:00:36.16 bitrate=3073.3kbits/s speed=0.364x \\rframe= 876 fps=8.8 q=23.0 size= 13824kB time=00:00:36.37 bitrate=3113.3kbits/s speed=0.364x \\rframe= 880 fps=8.8 q=23.0 size= 13824kB time=00:00:36.58 bitrate=3095.6kbits/s speed=0.364x \\rframe= 886 fps=8.8 q=23.0 size= 13824kB time=00:00:36.83 bitrate=3074.6kbits/s speed=0.365x \\rframe= 891 fps=8.8 q=23.0 size= 13824kB time=00:00:37.04 bitrate=3057.3kbits/s speed=0.365x \\rframe= 897 fps=8.8 q=23.0 size= 14080kB time=00:00:37.29 bitrate=3093.0kbits/s speed=0.365x \\rframe= 903 fps=8.8 q=23.0 size= 14080kB time=00:00:37.54 bitrate=3072.4kbits/s speed=0.365x \\rframe= 909 fps=8.8 q=23.0 size= 14080kB time=00:00:37.79 bitrate=3052.1kbits/s speed=0.366x \\rframe= 915 fps=8.8 q=23.0 size= 14336kB time=00:00:38.04 bitrate=3087.2kbits/s speed=0.366x \\rframe= 921 fps=8.8 q=23.0 size= 14336kB time=00:00:38.29 bitrate=3067.0kbits/s speed=0.367x \\rframe= 927 fps=8.8 q=23.0 size= 14336kB time=00:00:38.54 bitrate=3047.1kbits/s speed=0.367x \\rframe= 934 fps=8.9 q=23.0 size= 14592kB time=00:00:38.79 bitrate=3081.5kbits/s speed=0.368x \\rframe= 939 fps=8.9 q=23.0 size= 14592kB time=00:00:39.04 bitrate=3061.8kbits/s speed=0.368x \\rframe= 945 fps=8.9 q=23.0 size= 14592kB time=00:00:39.29 bitrate=3042.3kbits/s speed=0.369x \\rframe= 951 fps=8.9 q=23.0 size= 14848kB time=00:00:39.54 bitrate=3076.1kbits/s speed=0.369x \\r[out#0/mp4 @ 0x64f9dd532d00] video:15675kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.079204%\\nframe= 1005 fps=9.3 q=-1.0 Lsize= 15687kB time=00:00:41.75 bitrate=3078.1kbits/s speed=0.385x \\n[libx264 @ 0x64f9dd5343c0] frame I:5 Avg QP:12.45 size:199983\\n[libx264 @ 0x64f9dd5343c0] frame P:347 Avg QP:14.80 size: 33671\\n[libx264 @ 0x64f9dd5343c0] frame B:653 Avg QP:17.37 size: 5155\\n[libx264 @ 0x64f9dd5343c0] consecutive B-frames: 9.3% 8.0% 13.1% 69.7%\\n[libx264 @ 0x64f9dd5343c0] mb I I16..4: 10.0% 67.1% 23.0%\\n[libx264 @ 0x64f9dd5343c0] mb P I16..4: 1.6% 2.5% 1.6% P16..4: 40.8% 14.5% 9.1% 0.0% 0.0% skip:29.9%\\n[libx264 @ 0x64f9dd5343c0] mb B I16..4: 0.2% 0.1% 0.0% B16..8: 35.2% 1.2% 0.1% direct: 1.6% skip:61.7% L0:47.6% L1:47.3% BI: 5.1%\\n[libx264 @ 0x64f9dd5343c0] 8x8 transform intra:47.4% inter:84.2%\\n[libx264 @ 0x64f9dd5343c0] coded y,uvDC,uvAC intra: 52.0% 46.8% 25.2% inter: 12.5% 8.0% 1.6%\\n[libx264 @ 0x64f9dd5343c0] i16 v,h,dc,p: 29% 49% 5% 17%\\n[libx264 @ 0x64f9dd5343c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 24% 26% 30% 3% 4% 3% 4% 3% 4%\\n[libx264 @ 0x64f9dd5343c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 35% 30% 16% 3% 4% 3% 4% 2% 2%\\n[libx264 @ 0x64f9dd5343c0] i8c dc,h,v,p: 51% 29% 17% 3%\\n[libx264 @ 0x64f9dd5343c0] Weighted P-Frames: Y:3.7% UV:3.5%\\n[libx264 @ 0x64f9dd5343c0] ref P L0: 60.9% 3.4% 20.8% 14.7% 0.1%\\n[libx264 @ 0x64f9dd5343c0] ref B L0: 80.9% 11.9% 7.2%\\n[libx264 @ 0x64f9dd5343c0] ref B L1: 94.3% 5.7%\\n[libx264 @ 0x64f9dd5343c0] kb/s:3066.31\\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/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_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: 3068 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 3066 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 @ 0x5db964ddc2c0] 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/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.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, 3066 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= 14336kB time=00:00:37.50 bitrate=3131.8kbits/s speed=74.9x \\r[out#0/mp4 @ 0x5db964dfb040] video:15675kB audio:321kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.154325%\\nsize= 16020kB time=00:00:41.75 bitrate=3143.4kbits/s speed=76.3x \\n[aac @ 0x5db964d4d900] Qavg: 17882.781\\n{\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.4.0-b3-text-detail-ai-only\\\",\\n \\\"status\\\": \\\"review_preview_only_not_posted\\\",\\n \\\"variant\\\": {\\n \\\"candidate_id\\\": \\\"calendar-invite-login-trap-30s\\\",\\n \\\"version\\\": \\\"v1.4.0-b3-text-detail-ai-only\\\",\\n \\\"variant\\\": \\\"b3\\\",\\n \\\"mode\\\": \\\"visible_invite_cinematic_ai_only\\\",\\n \\\"preview_mp4_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4\\\",\\n \\\"preview_sha256\\\": \\\"4fb33b4201e9253ff39072fb175b40415d96d40db71e8051cd741c0193a1a9b8\\\",\\n \\\"duration_seconds\\\": 41.852,\\n \\\"resolution\\\": \\\"1080x1920\\\",\\n \\\"fps\\\": 24,\\n \\\"audio_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/audio/voiceover_word_boundary.mp3\\\",\\n \\\"script_hash\\\": \\\"0e9ec7f162b69573\\\",\\n \\\"contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_contact_sheet_v1.jpg\\\",\\n \\\"keyframes_contact_sheet_path\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/visible_invite_keyframes_contact_sheet_v1.jpg\\\",\\n \\\"keyframes\\\": [\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_01_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_02_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_03_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_04_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_05_openai_codex_gpt-image-2-high.png\\\",\\n \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/ai_keyframes_b3_text_detail/b3_text_detail_keyframe_06_openai_codex_gpt-image-2-high.png\\\"\\n ],\\n \\\"NoOverlayPolicy\\\": {\\n \\\"result\\\": \\\"pass\\\",\\n \\\"allowed\\\": [\\n \\\"subtitles_only\\\"\\n ]\\n },\\n \\\"blocked\\\": {\\n \\\"wan_used\\\": false,\\n \\\"i2v_used\\\": false,\\n \\\"t2v_used\\\": false,\\n \\\"platform_api_used\\\": false,\\n \\\"posting\\\": false\\n }\\n },\\n \\\"assessment\\\": \\\"B3 removes B2 focus lines and relies on more detailed AI-generated Outlook-style invite/login/calendar screens with readable UI text.\\\",\\n \\\"approval_commands\\\": [\\n \\\"APPROVED_PROOF_SHORT calendar-invite-login-trap-30s v1.4.0-b3-text-detail-ai-only\\\",\\n \\\"REVISE_PROOF_SHORT calendar-invite-login-trap-30s \\\\\\\"...\\\\\\\"\\\"\\n ]\\n}\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_vsaqUPVd327o0PH1Zidgs25W" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_xe4FlyBB7fX3Pn20Zl3vs9FF", "call_id": "call_xe4FlyBB7fX3Pn20Zl3vs9FF", "response_item_id": "fc_0d4a723b463df28d016a14bd0c68388191a3721e6373915a91", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_contact_sheet_v1.jpg\",\"question\":\"QA B3 rendered contact sheet. It should have no focus lines/boxes/arrows except subtitles, detailed AI-generated Outlook-style invite/login/calendar screens, readable captions, no people/hands/faces/QR/watermark. Assess if it is clearer than B2 and if any generated screen text looks harmful/gibberish.\"}" } }, { "id": "call_xBrG8SPBhm2l2zS2hgkMaWCk", "call_id": "call_xBrG8SPBhm2l2zS2hgkMaWCk", "response_item_id": "fc_0d4a723b463df28d016a14bd0c68648191a2ab2b83ce0c52b1", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from hermes_tools import terminal\\np='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4'\\nprint(terminal(f\\\"ffprobe -v error -show_entries format=duration,size:stream=codec_type,width,height,r_frame_rate -of json {p!r}\\\", timeout=30)['output'])\\nprint(terminal(f\\\"sha256sum {p!r}\\\", timeout=30)['output'])\"}" } } ], "finish_reason": "tool_calls", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFL0MDSyG12d2n2ol-_B_HSjLyP95B9SbbJ5Vjur43AG5xtdWmSxGpvnhAZ42DT4gNO-azcOL2WTTnJHbuOi-dfVzbpa5fIFBHhuOCi1eqBz7MHX55pK5KVw4kxlXkrYbJ4chAwP6R9sG4dbCz0Rtt9pqiN0DegeXXu8DcmlksZCsA3qvnydkHbkJ1FcxWs_rmlWP3pb0dhZcaMeEpo3XGOMWN6Uo7F-marw1FA4bcuFn0O0fndMhYWRfxaSPRyHFECLs2R1CmKEoN_Fd0zoaUDZZ1nR4fYlTOshyrMk-B--6YDKmj8VfTwHAO0VPhJrIn8vKkpS8KZyDFc7dIhCWPmgjjCJ34W8kWnZZX2Ap3gExlEo9TGeT0LcqomeMmRbqiNxUPeXIYHE7DYnfHfPTAKfZxNGoBrzDLFSbvZZZnuIBIJEyHfnfHQqViX3ssdSR_oEm9u3edYU0LGiHriIIfDREoSS-HQIMbI5hXm2I7B6m9-DSAwsbf9nrX7ru2FeGQVIGelfOHQsuWDX-9AUjcXfBmZV5T2kYc1D12JcZDZyNGzY-7wqsrotN89RYkGaDHyTYEuC3MeT3Y7PglP0i8BRfXCdJOvRC6NA18pP5MErKAgUeX61W1IVo-K3UUv8w37qZaTWmdLxZGx4mf1X5NrjBJLg_bG0Iqn8IPTU3PnROQkdgv-yr9s4uXUaP5BjHqGe34oNS3jyGqdqDvehn8ASsxfN1fwUJeGWNNIaY3l5nicMym-HZhcTPxZOBGLLdxe3B3gP-lvIQksIXQttM0kQaCMwpNdbgbvUvn1v8GXv6bevRYjRtdGFkZfMTdKqeqIpBHRwvEdGoWWGSCWUAqc6q4zgmRckbk9tupRuCWOkMS-KEByEmXf_r9-QIGW5ryRiSc_eSWbHkXVIW0-dVjdsV7hsGW-rQZuq3w2Grxbm8cyI-zUNTBpsE8PHChWeuRFzPSVOIC_3h1AbpUBcW1WeGOw==", "id": "rs_0d4a723b463df28d016a14bd073a8c81918310ccdf95ed546f", "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: QA B3 rendered contact sheet. It should have no focus lines/boxes/arrows except subtitles, detailed AI-generated Outlook-style invite/login/calendar screens, readable captions, no people/hands/faces/QR/watermark. Assess if it is clearer than B2 and if any generated screen text looks harmful/gibberish.\n[screenshot]", "tool_call_id": "call_xe4FlyBB7fX3Pn20Zl3vs9FF" }, { "role": "tool", "content": "{\"status\": \"success\", \"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\\\": \\\"16404399\\\"\\n }\\n}\\n4fb33b4201e9253ff39072fb175b40415d96d40db71e8051cd741c0193a1a9b8 /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4\\n\", \"tool_calls_made\": 2, \"duration_seconds\": 0.84}", "tool_call_id": "call_xBrG8SPBhm2l2zS2hgkMaWCk" }, { "role": "assistant", "content": "", "tool_calls": [ { "id": "call_k6pXr37l7plvhTaGOmsxKjv3", "call_id": "call_k6pXr37l7plvhTaGOmsxKjv3", "response_item_id": "fc_0d4a723b463df28d016a14bd10ab64819180885295f74ba632", "type": "function", "function": { "name": "todo", "arguments": "{\"merge\":true,\"todos\":[{\"content\":\"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\",\"id\":\"b3-render\",\"status\":\"completed\"},{\"content\":\"B3 technisch prüfen, Hash/Manifest erstellen und liefern\",\"id\":\"b3-qa-deliver\",\"status\":\"completed\"}]}" } } ], "finish_reason": "tool_calls" }, { "role": "tool", "content": "{\"todos\": [{\"id\": \"b3-gen\", \"content\": \"Neue B3-KI-Keyframes mit detaillierter sichtbarer Outlook-artiger Einladung/Text erzeugen\", \"status\": \"completed\"}, {\"id\": \"b3-qaimg\", \"content\": \"Keyframes auf Lesbarkeit, Details und Artefakte prüfen\", \"status\": \"completed\"}, {\"id\": \"b3-render\", \"content\": \"B3 ohne Linien/Fokus-Overlay rendern, nur KI-Bilder + Voiceover + aktive Wort-Subtitles\", \"status\": \"completed\"}, {\"id\": \"b3-qa-deliver\", \"content\": \"B3 technisch prüfen, Hash/Manifest erstellen und liefern\", \"status\": \"completed\"}], \"summary\": {\"total\": 4, \"pending\": 0, \"in_progress\": 0, \"completed\": 4, \"cancelled\": 0}}", "tool_call_id": "call_k6pXr37l7plvhTaGOmsxKjv3" }, { "role": "assistant", "content": "Verstanden — du hattest recht. Die Linien in B2 bringen kaum Mehrwert und beschädigen eher den Premium-Look.\n\nIch habe deshalb **B3** gebaut:\n\n## B3 — Detailed AI Invite Cut\n\n- Keine Linien\n- Keine Pfeile\n- Keine Boxen\n- Keine Fokus-Markierungen\n- Nur KI-Bilder + Voiceover + aktive Wort-Subtitles\n- Dafür deutlich detailliertere, sichtbare Outlook-artige Einladung:\n - `Quarterly Review Meeting`\n - `Join meeting`\n - `Sign in to continue`\n - Login-Panel\n - Kalender-App als sichere Alternative\n - Meeting verified / Open meeting from calendar\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4\n\n## QA\n\n- Länge: 41.875 s\n- Format: 1080×1920, 24 fps\n- Audio: enthalten\n- Caption-Sync: aktive Wort-Hervorhebung bleibt erhalten\n- NoOverlayPolicy: pass — nur Subtitles\n- Keine Menschen/Hände/Gesichter/QR/Watermark sichtbar\n- Die Bild-Story ist jetzt klarer als B1/B2, weil der Scam visuell wirklich im Screen stattfindet — nicht mehr nur durch Voiceover erklärt wird.\n\n## Hash\n\n`4fb33b4201e9253ff39072fb175b40415d96d40db71e8051cd741c0193a1a9b8`\n\nMeine Einschätzung: **B3 ist klar die bessere Richtung.** \nDas wirkt mehr wie ein echter Social-Short über einen konkreten Scam und weniger wie ein hübsches Moodboard mit Sicherheits-Predigt.", "codex_message_items": [ { "type": "message", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Verstanden — du hattest recht. Die Linien in B2 bringen kaum Mehrwert und beschädigen eher den Premium-Look.\n\nIch habe deshalb **B3** gebaut:\n\n## B3 — Detailed AI Invite Cut\n\n- Keine Linien\n- Keine Pfeile\n- Keine Boxen\n- Keine Fokus-Markierungen\n- Nur KI-Bilder + Voiceover + aktive Wort-Subtitles\n- Dafür deutlich detailliertere, sichtbare Outlook-artige Einladung:\n - `Quarterly Review Meeting`\n - `Join meeting`\n - `Sign in to continue`\n - Login-Panel\n - Kalender-App als sichere Alternative\n - Meeting verified / Open meeting from calendar\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4\n\n## QA\n\n- Länge: 41.875 s\n- Format: 1080×1920, 24 fps\n- Audio: enthalten\n- Caption-Sync: aktive Wort-Hervorhebung bleibt erhalten\n- NoOverlayPolicy: pass — nur Subtitles\n- Keine Menschen/Hände/Gesichter/QR/Watermark sichtbar\n- Die Bild-Story ist jetzt klarer als B1/B2, weil der Scam visuell wirklich im Screen stattfindet — nicht mehr nur durch Voiceover erklärt wird.\n\n## Hash\n\n`4fb33b4201e9253ff39072fb175b40415d96d40db71e8051cd741c0193a1a9b8`\n\nMeine Einschätzung: **B3 ist klar die bessere Richtung.** \nDas wirkt mehr wie ein echter Social-Short über einen konkreten Scam und weniger wie ein hübsches Moodboard mit Sicherheits-Predigt." } ], "id": "msg_0d4a723b463df28d016a14bd1578d881918b4ffbf62754e958", "phase": "final_answer" } ], "finish_reason": "stop" }, { "role": "user", "content": "[M G] Sehr gut. Das ist nun unser neuer standard! Nur eine korrektur: das videoformat stimmt nicht. Es ist quadratisch wenn ich es abspiele (in der höhe zusammengestaucht). Bitte noch korrigieren und dann weiterbauen." }, { "role": "assistant", "content": "", "reasoning": "**Addressing memory and format updates**\n\nI need to respond and possibly save a memory or skill update since there's a new standard for durability. I also have to fix the format and inspect the video for any display issues, possibly due to SAR on Telegram. I think I should use ffprobe for that. The skill is already loaded, but I need to scan it. It might be relevant for social media shorts automation, so I need to check the files too.", "finish_reason": "tool_calls", "reasoning_content": "**Addressing memory and format updates**\n\nI need to respond and possibly save a memory or skill update since there's a new standard for durability. I also have to fix the format and inspect the video for any display issues, possibly due to SAR on Telegram. I think I should use ffprobe for that. The skill is already loaded, but I need to scan it. It might be relevant for social media shorts automation, so I need to check the files too.", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFL8WprebAKtAizNsW4VWY2-gzMsnToK-hxr55fHjFeYGh6O5JtgMUxxnaCWQca7LOlzaRFo0LhMJFzzC2Gno6yMEJDA7eiwvhpweTrNNVUk1FBJtWwS2pxj-zvV2Kvev3TQIwlwpYWYQCzW-gL--Y_dMYCB8c33u3mvLixLh1sjEXrrM2pqSlCf_CwCUgwUrcg037ZCPK58TMajL4VVocWK0frJYJc403ZBYCD9crNnBTM7-IhqEmJeD5CcZjIUG8ckMbBnVhs27kkYNGUNkZ_abgsedUxLoqaANrCPGMF5jjt_2JkI7esN1wuMPAVz7bc8Xl5NltRJvk-pN0oTiYjJbTuN3etbRvcVPKR982imnv4Cf1DJtBleDyt00oZBJQdrB3greu0ZcfDj4y85UJKJ-3oVxjkPxrjhnXIC19oI_Lw1pKjosds-sMwxhSYA5NI0tZNvd8Owu_TpG7cJCcT4FOHR6aHu01CgzradQlx2ehihUVcX-GmxCBJRQUV9kl0RReL69895U0RC2zsqfNHI10R3hUpVXXCi1xyHymGb4KLwSILk9dmQ_0Gx1lmp5XW85xvukqOLmx319LvhxxTeykFmc39Dniu8Cq1vRKSJtnTSNciTNHMErSpr7OTAwXQ8jrxK8R6GWafEoQXntOxIieZsd8ayvj95O8oYM52fvvDoZTHm3yiJxNZ_j-ZRhshLr10ckxoL7jUXXQWadwUV5ArYPFbKmnkvHq3iZMEg1llYTfIgsEYWoDLOdmR1u76u7YzSp2uCJiAZU9TvI-wZoWus5eC7le8aP-CnRSWUaSjcecFT2tz2N6dWpA9_B0XAN8Q6BJ9u2hdwxIaZC-yKmxbJxhJEsxeCjxHs1cOzWA5l4RleU5UW4KsvQaeIvsytOk8axsUk7u4GVm_WXlXKJEQ_UMmBfkx8FTXsSmZh1LpVhB0VxoTMHHH431yMQqpAZHO5Ypweoe1XasKdRF9_K3Sjdms0Oi9EnZIq_FUsa6LdTwB74ykAErjb-IqbGrHbk13S1XhqwonbLttDZdd1nJ5gzlEiDflJkWJutxdZi2IUG9SQ1QdGz_gM6DvfgisUBptceiy7SbBM2WwDK0hvpL3RzRbVT8jje8S09NOb6w4qTnjtW5LCnRfb-u-finyryeHJDbT36Cuj1QYA9fHKe7cOytp9YMbWGNEf7gWpbgL8P0ypQIGH2h-H7TCubDWjbUGUWv9V9V7-eTlKSINftQcMpOIWG4mmAYFeqxMphs99dVE2ThNcPA1vMo2LE0Ek92zot0BHexkzM2CtHssf3IQgVg9AKlXYnWjnhnH1sBLTCNDy75_ljrAYvfl1FtFecsnNepT80hm2EVSSDwT32vA==", "id": "rs_0d4a723b463df28d016a14bf10f42481918b4154d8c126c4c6", "summary": [ { "type": "summary_text", "text": "**Addressing memory and format updates**\n\nI need to respond and possibly save a memory or skill update since there's a new standard for durability. I also have to fix the format and inspect the video for any display issues, possibly due to SAR on Telegram. I think I should use ffprobe for that. The skill is already loaded, but I need to scan it. It might be relevant for social media shorts automation, so I need to check the files too." } ] } ], "tool_calls": [ { "id": "call_5sRFstFJfVxhEo5JOJh0mtp3", "call_id": "call_5sRFstFJfVxhEo5JOJh0mtp3", "response_item_id": "fc_0d4a723b463df28d016a14bf162204819191f9be260461f888", "type": "function", "function": { "name": "todo", "arguments": "{\"todos\":[{\"id\":\"fmt-inspect\",\"content\":\"B3 MP4-Format/Metadata prüfen: Pixelgröße, SAR/DAR, Rotation, Stream-Tags\",\"status\":\"in_progress\"},{\"id\":\"fmt-fix\",\"content\":\"B3 als echtes 9:16 Telegram-kompatibles MP4 neu muxen/encoden\",\"status\":\"pending\"},{\"id\":\"fmt-verify\",\"content\":\"Korrigierte Datei mit ffprobe + Screenshot/Frame-QA verifizieren\",\"status\":\"pending\"},{\"id\":\"standard-save\",\"content\":\"Neuen visuellen Standard als Skill/Memory verankern\",\"status\":\"pending\"},{\"id\":\"continue-build\",\"content\":\"Nach Formatfix nächsten Build-Schritt vorbereiten/ausführen\",\"status\":\"pending\"}]}" } } ] }, { "role": "tool", "name": "todo", "content": "{\"todos\": [{\"id\": \"fmt-inspect\", \"content\": \"B3 MP4-Format/Metadata prüfen: Pixelgröße, SAR/DAR, Rotation, Stream-Tags\", \"status\": \"in_progress\"}, {\"id\": \"fmt-fix\", \"content\": \"B3 als echtes 9:16 Telegram-kompatibles MP4 neu muxen/encoden\", \"status\": \"pending\"}, {\"id\": \"fmt-verify\", \"content\": \"Korrigierte Datei mit ffprobe + Screenshot/Frame-QA verifizieren\", \"status\": \"pending\"}, {\"id\": \"standard-save\", \"content\": \"Neuen visuellen Standard als Skill/Memory verankern\", \"status\": \"pending\"}, {\"id\": \"continue-build\", \"content\": \"Nach Formatfix nächsten Build-Schritt vorbereiten/ausführen\", \"status\": \"pending\"}], \"summary\": {\"total\": 5, \"pending\": 4, \"in_progress\": 1, \"completed\": 0, \"cancelled\": 0}}", "tool_call_id": "call_5sRFstFJfVxhEo5JOJh0mtp3" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "tool_calls": [ { "id": "call_drhj5wnJKO23tDJu83QbuzHY", "call_id": "call_drhj5wnJKO23tDJu83QbuzHY", "response_item_id": "fc_0d4a723b463df28d016a14bf18fd5c8191980038263a892e70", "type": "function", "function": { "name": "skill_view", "arguments": "{\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/clean-ai-cut-vs-hybrid-mechanism.md\"}" } } ] }, { "role": "tool", "name": "skill_view", "content": "{\"success\": true, \"name\": \"social-media-shorts-automation\", \"file\": \"references/clean-ai-cut-vs-hybrid-mechanism.md\", \"content\": \"# Clean AI Cut vs Hybrid Mechanism — session learning\\n\\nUse this when comparing a pure premium AI-image sequence against a proof short with deterministic mechanism/UI overlays.\\n\\n## Session-derived pattern\\n\\nFor a scam/cybersecurity proof short, a clean image sequence can look significantly more premium and native to TikTok/Reels, but it often weakens immediate mechanism clarity.\\n\\nObserved comparison:\\n\\n```text\\nClean AI Cut = premium mood, calmer, less explainer-board\\nHybrid = clearer mechanism, more immediately useful\\nBest likely final direction = mostly clean images + one minimal deterministic mechanism moment\\n```\\n\\nRecommended framing:\\n\\n```text\\n90% Clean AI Images\\n10% precise renderer-owned mechanism\\n```\\n\\nExamples of acceptable minimal mechanism moments:\\n\\n- one brief `suspicious link/domain` reveal\\n- one brief `close invite -> open trusted app/bookmark` action moment\\n- one simple before/after state, not a full checklist board\\n\\nAvoid returning to:\\n\\n- checklist-heavy UI cards\\n- boxed explainer overlays\\n- arrows/circles/diagram markers\\n- repeated labels and decision-target graphics\\n\\n## Viewer explanation rule\\n\\nWhen the viewer is not technical, do not use shorthand such as `open the service yourself` without explanation. Spell out the exact action:\\n\\n```text\\nClose the invite.\\nOpen your calendar or work app from the normal icon/bookmark.\\nIf the meeting is real, it will still be there.\\nTrust the path you chose, not the button that chose you.\\n```\\n\\nThis converts a security maxim into a concrete next action.\\n\\n## Caption synchronization rule\\n\\nFor final-near shorts where the user complains that subtitles do not match voiceover exactly, use actual word-boundary/forced-alignment timing rather than distributing words evenly across sentence SRT blocks. For EdgeTTS previews, request `boundary='WordBoundary'`, store word cues, then render static phrase segments where only the active spoken word highlights.\\n\\nKeep the established caption policy:\\n\\n- static phrase segment, usually 3–7 words\\n- active spoken word highlighted in yellow\\n- inactive words white\\n- no subtitle box/bar\\n- bottom mobile-safe position\\n\\n## A/B decision criteria\\n\\nAfter rendering both versions, explicitly answer:\\n\\n1. Which version looks more premium?\\n2. Which version explains the mechanism faster without audio?\\n3. Does the clean cut rely too much on VO/subtitles?\\n4. Would one minimal deterministic mechanism moment recover clarity without killing the premium look?\\n5. Is Wan/I2V worth testing, or is image-sequence motion enough for this stage?\\n\\nDefault recommendation: do not jump to full Wan/I2V after this test. If clean images work visually, test exactly one short motion micro-proof only after approval.\\n\\n## Visible-problem keyframe A/B pattern\\n\\nWhen the user asks whether pure KI images can carry a Proof Short, do not generate generic premium atmosphere. The first image batch must make the real viewer problem literally visible without text:\\n\\n- show the concrete object/situation (e.g. a calendar invite card on laptop/phone, a join/login button shape, attendee dots, blank time rows);\\n- keep all generated UI text-free: no letters, pseudo-letters, numbers, logos, QR/barcodes, watermarks, people, hands, or faces;\\n- use contact-sheet QA before rendering and discard frames that only look like generic laptop/desk B-roll;\\n- expect later safe/resolution frames to be less semantically explicit, but the first half must visually anchor the trap.\\n\\nFor the calendar-invite login-trap proof, the session result was:\\n\\n```text\\nB1 = clean visible-invite AI images only + voiceover + active-word subtitles\\nB2 = same images + very subtle focus outlines, no labels/arrows/checklists\\nOutcome = B2 recommended: slightly less pure, but the scam mechanism is understood faster while still avoiding PowerPoint/explainer-board look.\\n```\\n\\nUse this as the default next-step bias: if clean images are beautiful but semantically weak, add exactly one or two subtle focus moments around the suspicious invite/button/app path rather than returning to labels, arrows, boxes, or checklist UI cards.\", \"file_type\": \".md\"}", "tool_call_id": "call_drhj5wnJKO23tDJu83QbuzHY" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "tool_calls": [ { "id": "call_LBz3w9D1U4NCjVkyohu08gsL", "call_id": "call_LBz3w9D1U4NCjVkyohu08gsL", "response_item_id": "fc_0d4a723b463df28d016a14bf1cf11c8191a869a1546ba3e3e0", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from hermes_tools import terminal\\np='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4'\\nfor cmd in [\\n f\\\"ffprobe -v error -show_streams -show_format -of json {p!r}\\\",\\n f\\\"mediainfo {p!r} || true\\\"\\n]:\\n print('CMD',cmd)\\n print(terminal(cmd, timeout=60)['output'][:12000])\"}" } } ] }, { "role": "tool", "name": "execute_code", "content": "{\"status\": \"success\", \"output\": \"CMD ffprobe -v error -show_streams -show_format -of json '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4'\\n{\\n \\\"streams\\\": [\\n {\\n \\\"index\\\": 0,\\n \\\"codec_name\\\": \\\"h264\\\",\\n \\\"codec_long_name\\\": \\\"H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10\\\",\\n \\\"profile\\\": \\\"High\\\",\\n \\\"codec_type\\\": \\\"video\\\",\\n \\\"codec_tag_string\\\": \\\"avc1\\\",\\n \\\"codec_tag\\\": \\\"0x31637661\\\",\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"coded_width\\\": 1080,\\n \\\"coded_height\\\": 1920,\\n \\\"closed_captions\\\": 0,\\n \\\"film_grain\\\": 0,\\n \\\"has_b_frames\\\": 2,\\n \\\"pix_fmt\\\": \\\"yuv420p\\\",\\n \\\"level\\\": 40,\\n \\\"chroma_location\\\": \\\"left\\\",\\n \\\"field_order\\\": \\\"progressive\\\",\\n \\\"refs\\\": 1,\\n \\\"is_avc\\\": \\\"true\\\",\\n \\\"nal_length_size\\\": \\\"4\\\",\\n \\\"id\\\": \\\"0x1\\\",\\n \\\"r_frame_rate\\\": \\\"24/1\\\",\\n \\\"avg_frame_rate\\\": \\\"24/1\\\",\\n \\\"time_base\\\": \\\"1/12288\\\",\\n \\\"start_pts\\\": 0,\\n \\\"start_time\\\": \\\"0.000000\\\",\\n \\\"duration_ts\\\": 514560,\\n \\\"duration\\\": \\\"41.875000\\\",\\n \\\"bit_rate\\\": \\\"3066439\\\",\\n \\\"bits_per_raw_sample\\\": \\\"8\\\",\\n \\\"nb_frames\\\": \\\"1005\\\",\\n \\\"extradata_size\\\": 47,\\n \\\"disposition\\\": {\\n \\\"default\\\": 1,\\n \\\"dub\\\": 0,\\n \\\"original\\\": 0,\\n \\\"comment\\\": 0,\\n \\\"lyrics\\\": 0,\\n \\\"karaoke\\\": 0,\\n \\\"forced\\\": 0,\\n \\\"hearing_impaired\\\": 0,\\n \\\"visual_impaired\\\": 0,\\n \\\"clean_effects\\\": 0,\\n \\\"attached_pic\\\": 0,\\n \\\"timed_thumbnails\\\": 0,\\n \\\"non_diegetic\\\": 0,\\n \\\"captions\\\": 0,\\n \\\"descriptions\\\": 0,\\n \\\"metadata\\\": 0,\\n \\\"dependent\\\": 0,\\n \\\"still_image\\\": 0\\n },\\n \\\"tags\\\": {\\n \\\"language\\\": \\\"und\\\",\\n \\\"handler_name\\\": \\\"VideoHandler\\\",\\n \\\"vendor_id\\\": \\\"[0][0][0][0]\\\",\\n \\\"encoder\\\": \\\"Lavc60.31.102 libx264\\\"\\n }\\n },\\n {\\n \\\"index\\\": 1,\\n \\\"codec_name\\\": \\\"aac\\\",\\n \\\"codec_long_name\\\": \\\"AAC (Advanced Audio Coding)\\\",\\n \\\"profile\\\": \\\"LC\\\",\\n \\\"codec_type\\\": \\\"audio\\\",\\n \\\"codec_tag_string\\\": \\\"mp4a\\\",\\n \\\"codec_tag\\\": \\\"0x6134706d\\\",\\n \\\"sample_fmt\\\": \\\"fltp\\\",\\n \\\"sample_rate\\\": \\\"24000\\\",\\n \\\"channels\\\": 1,\\n \\\"channel_layout\\\": \\\"mono\\\",\\n \\\"bits_per_sample\\\": 0,\\n \\\"initial_padding\\\": 0,\\n \\\"id\\\": \\\"0x2\\\",\\n \\\"r_frame_rate\\\": \\\"0/0\\\",\\n \\\"avg_frame_rate\\\": \\\"0/0\\\",\\n \\\"time_base\\\": \\\"1/24000\\\",\\n \\\"start_pts\\\": 0,\\n \\\"start_time\\\": \\\"0.000000\\\",\\n \\\"duration_ts\\\": 992448,\\n \\\"duration\\\": \\\"41.352000\\\",\\n \\\"bit_rate\\\": \\\"63433\\\",\\n \\\"nb_frames\\\": \\\"971\\\",\\n \\\"extradata_size\\\": 5,\\n \\\"disposition\\\": {\\n \\\"default\\\": 1,\\n \\\"dub\\\": 0,\\n \\\"original\\\": 0,\\n \\\"comment\\\": 0,\\n \\\"lyrics\\\": 0,\\n \\\"karaoke\\\": 0,\\n \\\"forced\\\": 0,\\n \\\"hearing_impaired\\\": 0,\\n \\\"visual_impaired\\\": 0,\\n \\\"clean_effects\\\": 0,\\n \\\"attached_pic\\\": 0,\\n \\\"timed_thumbnails\\\": 0,\\n \\\"non_diegetic\\\": 0,\\n \\\"captions\\\": 0,\\n \\\"descriptions\\\": 0,\\n \\\"metadata\\\": 0,\\n \\\"dependent\\\": 0,\\n \\\"still_image\\\": 0\\n },\\n \\\"tags\\\": {\\n \\\"language\\\": \\\"und\\\",\\n \\\"handler_name\\\": \\\"SoundHandler\\\",\\n \\\"vendor_id\\\": \\\"[0][0][0][0]\\\"\\n }\\n }\\n ],\\n \\\"format\\\": {\\n \\\"filename\\\": \\\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4\\\",\\n \\\"nb_streams\\\": 2,\\n \\\"nb_programs\\\": 0,\\n \\\"format_name\\\": \\\"mov,mp4,m4a,3gp,3g2,mj2\\\",\\n \\\"format_long_name\\\": \\\"QuickTime / MOV\\\",\\n \\\"start_time\\\": \\\"0.000000\\\",\\n \\\"duration\\\": \\\"41.875000\\\",\\n \\\"size\\\": \\\"16404399\\\",\\n \\\"bit_rate\\\": \\\"3133974\\\",\\n \\\"probe_score\\\": 100,\\n \\\"tags\\\": {\\n \\\"major_brand\\\": \\\"isom\\\",\\n \\\"minor_version\\\": \\\"512\\\",\\n \\\"compatible_brands\\\": \\\"isomiso2avc1mp41\\\",\\n \\\"encoder\\\": \\\"Lavf60.16.100\\\"\\n }\\n }\\n}\\nCMD mediainfo '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4' || true\\n/usr/bin/bash: Zeile 3: mediainfo: Befehl nicht gefunden\\n\", \"tool_calls_made\": 2, \"duration_seconds\": 1.04}", "tool_call_id": "call_LBz3w9D1U4NCjVkyohu08gsL" }, { "role": "assistant", "content": "", "reasoning": "**Considering video format compatibility**\n\nI’m thinking about creating videos in both 720x1280 with an explicit display aspect ratio and a fixed 1080 version for compatibility. The error \"videoformat stimmt nicht\" likely indicates an issue with display metadata, which I need to correct using ffmpeg and verify with ffprobe. Once that's done, I should consider developing a standard template for future videos, especially since the user mentioned a “new standard.” I'll need to update my memory with this new information as well.", "finish_reason": "tool_calls", "reasoning_content": "**Considering video format compatibility**\n\nI’m thinking about creating videos in both 720x1280 with an explicit display aspect ratio and a fixed 1080 version for compatibility. The error \"videoformat stimmt nicht\" likely indicates an issue with display metadata, which I need to correct using ffmpeg and verify with ffprobe. Once that's done, I should consider developing a standard template for future videos, especially since the user mentioned a “new standard.” I'll need to update my memory with this new information as well.", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFL8scckNuNqqKvYcmZbSBmPrcLEbO4ARCJpECOGlekt7-VyO8d9LGHrsNySmN1jSb4oQ1QGTqkUsnPbi5XUmo5GwCFgId_mz5SlRJkuUOO-zSIF4D_gW0SqfZKeGmnMqXIuWU-1s9fbTTS9KwPV2cqd2tRgg0VJMphs42swWVh-MMspiNwnZ_NOb4xmslO_SBfqVI1DiNRl2Q-kV2thy7QTc1wFmF01UyzWkO_FB2jjB_NKhEn3kej9KZtvbBMXXQDGGkapfywXZzpGCKFHmQL9TzWUfxAcTVMRM9W2sxm1Wus8G5VLqISXJqQ7vqoVfMcRDS9qkp07S5fT9g-uulyUVptHiudDOhbAUyaw-jz64vja0NERRMkJLzPB-bAT0O4j3mdxPxqxX-odMAoz0cglmF3zB3lzYmk2SRjsrzWImLhW86-EE3hFHRj1KXAp0UB8miQe6DUuQauxVLezwfRQxSxL5SsQolfUVg5Wxte0KwJwEZq5_nRe8AVDX4lR_L7m8R3SV0fMXc7ONqWBg9AYaQMMe5dda2S4g-a3yrKgLdgi_Cfpf-RdS4oZZ-IiBS8UtBiv3tnbHQn56pf_NgTd6cZwfYyBOuP5AlCwmsPB__TBPR6QQH5E6lKvobKUloSGDve5bZ3AKFIxCRORCBf9C0lXavBQ524DHY6hRsS-NKlSWHyU0Ay3Stb7HdDiG4kJacpnqVj5UhpgDnsTuJQAxvoXL51Ois_Wb4io8gU7z4D41De2pzs-my7Y5k0K-taXBAOAN-bqo3d_yTkS-bz1jQ7SvYwM5P2QpNOx7N8jNgcW_o-5y6QUWTSmVFzS6vGL3EzXjb9n-LloD79pbqL5kddIM-AGFjDFWly9NiVEWvjxkM5xpOTT97__MB3uu4IKmg8wPaIkl5JpQdAk8-ZkW0AGq-Er8D6itufCUpJgHUANf2wWZmiQixzE_NoBj2N5RsHWcRmNqtPNJaZBomU4Xk-uon3NudwAFIViLdyb5ZSbEdl6dQQpzYUPET28isuEZ8YS07rWLArvvOFoDkTnUMaotJ0dkFmIcblC1rObkiiOdVxZa0qZlgOzsA84XD7YWq4txGBoSFKF7CiJGk4rhkubAMUFdENlRVYbeqcavlZNLWkRPtkC2JK9JBGy7nht6gq_l8wrp6l8dhGZSn2I8BGbh7u6ZJGnIoiTf67yk8gCLFlK1anfIxpTQWsSi8pm3SxEOtkEfoiHT-P12GncaE7Oq8gEt0LgwQrxk3dGM6BwBAOAFnrhFxGtl9P2KP9-ah_aMXNx70A4F4gtBEJSnM58ajyZNCg9Pnli-Ze3kJETV1WhlcPVEvI4c6cb9RbSZnMTW4VeWTquHyPgm0gOtuEZE4EE4kapM8SVXcdahf9vGoA8s7TMXUZNI6t36cJnXM6gw0_-C-b--2Nb_Ti4933R_yKFfiGmTkRAgcLuyyBTJvNkdnxdKHVl8-6OBPal07BGuckczco4mzyQufsRYNHDQf1etTOM7c-rOMTfP2pB6fSVHhGyIbg4CA22TLPvsbucNW2eNEDmNEqrnLDziD0eNt-oSQEtODqF0KVvEtCCkjuNb8WSNNrII_umbQn8gKh-f39z_h2aWEp_XUcOrjzgyPMfc1kpK-6vS5Ilg6KEYRUXK83A31VmlfAsxaITTJHGjSfewMelG1umIPC2ZqXy9cswBD6x9oypciDBlFAE4IgR_cRKZr1tTYrjBEIiV-5IMwmrOCBTk9JpsK5QnDZ0HdEHHt0pZEwFwQu61DcQGVvFDPP70wX7QJD-hX2XlICR8xJODy77BoElJ2vEaxlUT5WxmdruSucw_GQKdvJwFerGIxjGxJW25aVMSmHo3SYDDi1rlorq0ZydC48S0Wa0JOSFNYDWUuOHHMVaNobnlfMcS8oXpL7RABDXpj-JLQK8AElBZwqr4WU4BxJDp9a-mwGvh8gVGnNsBdofXokXlV-hSSoOFb0e5RiD-EyRskVQE5GnFxcy8fPVCopJPQ6bZQ0XiUdfU8IRyaAXswqY5KljL3101aour518uMSgvQ4SZZR0P6R07-h_Upev_lzip1w5pXlR2J6woZBxKd1zlDQpejI8NJfRH9zQABeVdsY_pzKSQJ0hZjLfZuI_BR9z3MPPZEY7jyYbuvui5DDP5a4mFp3Qzm5aQBeUBCOgfjnLC92dwG7x7L0koVCx4DACsEM_JInednQHxjty_8qt6ZiRalglkjdIY4UNrHwvPpfsvyYvBtLpjzm0wznXyGDYq-7FYpmDaPYxrRXvUjXAdvBokDIC4Hscz-1EByz6hT5W7LiGNh8D7p-Njo_d3bn0fjnmqvhJrRv-fzBJDSxYiZ3wAEpzM6-wo0VWfIzF3ip42G15KDKyR94Hnpx9inLDAEbX_30I_G76ODpYJMMNIEMz_V_2UbOdOTfBDqIGheq4_loHxGd4QlF93mKbMEWcKzi899AcngE5sSSHW5BtwVkGgFF4MQC9oC5yZo1ndBd6dAOB2frWIfu20cyRZq64W8I6x5Pe_iavw0nSgZ-AcIF-hYJ8YKidi8wY2zMPqQnh6AA-9iIJ9hDOGblmVcZ2FK1ZATm15kL5xjIje-VyB1gSYAARHa9cKD7df04yZRvHJ6_ScxTOSbmSb_UuxRS158TNptpikdk_U_K-jr3hzU36tsQtvQJOQ9GSRgIsuAngR0Xaw_yN80OdzJFZFfyS2qOxTUQQ07woJLBP-tHdmO3zci4xz-K3GF4iZiZGhsjRltP3hoc8xHhNWPIErSsdme243vja17v_mzK_IjxFZHmbzQCO-ONKpQ3KXoy4jtO8FZmtxo2prrRljo5Km-u7oerA_T9JX1Ng7eGUWVjx_ZW8MYarcWkEromRPWhHQW-ZKDBObW5mRnsQsAlPvx75uNSddrhO0hCFpf00yRdIrjJ-O6hB-Ni7jq5_2WLz8F8S5jsYtUvt5dtHYiP0bQ8_0pmYRemK2M-HzPMP6RqBrc8ZQu8ANNsvRijH0bltcHDmQat_N9W5-n692H2VrBfvPLi0YFAJJvTFMHx6QuffwGVNrAJLqQY7LWHp7f3D8hxWVFp3oQzk3LaRSH1UtF1vJGirJRv56Z_AGaLJJG8lw7vILNCpK8pdH3rgflDahZIPnuDMDVycls57JNvGRJQ8_g7rsNmCkIH5_W-Cc4H7VddJVm7uHxWIFXrGSpFP5cePf-kPR3pIv3FshoC5hHFY0RA0za_lcsmccJOG5Fks_IrgR6pXWPLM7Hj58yIKwjRwtlv4RgB6JGWK6h2vFeqayfYuC1TTDl-B6X8LKIoOS0SnBpG0wKwuqVNoMrVTDSLWPjCqs42VyRMuGQFByEIx6MvNSwp1HQAyukSE2PPCd0n3QGxw8-ZksKXaa-KC9XWvdUcReWNDfo7XT1PA9xyQx9HpSXbglABCFiacJ0uRV4CqMV6uc8uHmUtiWRWVCp0e9Q_jzjo2QFhklCryHPrLorHv3vavSQ6_IVoCLZgM36lmeXkI8Ayt_Uukoj9UXxMUpZ8zi2pjTJFwsdktJfn7mujPZO6L3HbO747guAYgJOeEXS1OfCpQqI8YNoOfp", "id": "rs_0d4a723b463df28d016a14bf2277a8819194b6d545eea4ec0d", "summary": [ { "type": "summary_text", "text": "**Considering video format compatibility**\n\nI’m thinking about creating videos in both 720x1280 with an explicit display aspect ratio and a fixed 1080 version for compatibility. The error \"videoformat stimmt nicht\" likely indicates an issue with display metadata, which I need to correct using ffmpeg and verify with ffprobe. Once that's done, I should consider developing a standard template for future videos, especially since the user mentioned a “new standard.” I'll need to update my memory with this new information as well." } ] } ], "tool_calls": [ { "id": "call_K8VMlhbfrV9xHUfzxmbylNwF", "call_id": "call_K8VMlhbfrV9xHUfzxmbylNwF", "response_item_id": "fc_0d4a723b463df28d016a14bf2c8ee08191978521758af35599", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"IN='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.mp4'; OUT='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4'; ffmpeg -y -i \\\"$IN\\\" -vf \\\"scale=1080:1920:flags=lanczos,setsar=1,setdar=9/16\\\" -c:v libx264 -profile:v high -level:v 4.2 -pix_fmt yuv420p -r 24 -crf 18 -movflags +faststart -metadata:s:v:0 rotate=0 -c:a aac -ar 44100 -ac 1 -b:a 96k -shortest \\\"$OUT\\\" && ffprobe -v error -select_streams v:0 -show_entries stream=width,height,sample_aspect_ratio,display_aspect_ratio,avg_frame_rate,level,pix_fmt:format=duration,size -of json \\\"$OUT\\\" && sha256sum \\\"$OUT\\\"\",\"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, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3.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: 3133 kb/s\\n Stream #0:0[0x1](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1080x1920, 3066 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[0x2](und): Audio: aac (LC) (mp4a / 0x6134706D), 24000 Hz, mono, fltp, 63 kb/s (default)\\n Metadata:\\n handler_name : SoundHandler\\n vendor_id : [0][0][0][0]\\n[vost#0:0/libx264 @ 0x594edc5ad900] Conversion of a 'rotate' metadata key to a proper display matrix rotation is deprecated. See -display_rotation for setting rotation instead.Stream mapping:\\n Stream #0:0 -> #0:0 (h264 (native) -> h264 (libx264))\\n Stream #0:1 -> #0:1 (aac (native) -> aac (native))\\nPress [q] to stop, [?] for help\\n[libx264 @ 0x594edc60a440] using SAR=1/1\\n[libx264 @ 0x594edc60a440] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512\\n[libx264 @ 0x594edc60a440] profile High, level 4.2, 4:2:0, 8-bit\\n[libx264 @ 0x594edc60a440] 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=18.0 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/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.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 (avc1 / 0x31637661), yuv420p(progressive), 1080x1920 [SAR 1:1 DAR 9:16], q=2-31, 24 fps, 12288 tbn (default)\\n Metadata:\\n handler_name : VideoHandler\\n vendor_id : [0][0][0][0]\\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\\n Stream #0:1(und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, mono, fltp, 96 kb/s (default)\\n Metadata:\\n handler_name : SoundHandler\\n vendor_id : [0][0][0][0]\\n encoder : Lavc60.31.102 aac\\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=00:00:01.83 bitrate= 0.2kbits/s speed=3.16x \\rframe= 17 fps= 14 q=23.0 size= 256kB time=00:00:02.83 bitrate= 740.4kbits/s speed= 2.4x \\rframe= 38 fps= 23 q=23.0 size= 512kB time=00:00:03.66 bitrate=1143.4kbits/s speed=2.18x \\rframe= 54 fps= 24 q=23.0 size= 768kB time=00:00:04.41 bitrate=1426.1kbits/s speed= 2x \\rframe= 76 fps= 27 q=23.0 size= 1024kB time=00:00:05.29 bitrate=1584.6kbits/s speed=1.89x \\rframe= 96 fps= 28 q=23.0 size= 1280kB time=00:00:06.13 bitrate=1710.6kbits/s speed=1.79x \\rframe= 117 fps= 30 q=23.0 size= 1536kB time=00:00:07.01 bitrate=1794.4kbits/s speed=1.78x \\rframe= 133 fps= 29 q=23.0 size= 2048kB time=00:00:07.66 bitrate=2189.5kbits/s speed=1.65x \\rframe= 151 fps= 29 q=23.0 size= 2560kB time=00:00:08.42 bitrate=2488.1kbits/s speed=1.63x \\rframe= 167 fps= 29 q=23.0 size= 2816kB time=00:00:09.12 bitrate=2528.0kbits/s speed=1.61x \\rframe= 187 fps= 30 q=23.0 size= 3072kB time=00:00:09.86 bitrate=2550.2kbits/s speed= 1.6x \\rframe= 207 fps= 30 q=23.0 size= 3584kB time=00:00:10.75 bitrate=2731.0kbits/s speed=1.58x \\rframe= 231 fps= 31 q=23.0 size= 3840kB time=00:00:11.74 bitrate=2677.4kbits/s speed=1.59x \\rframe= 253 fps= 32 q=23.0 size= 4608kB time=00:00:12.63 bitrate=2988.5kbits/s speed= 1.6x \\rframe= 274 fps= 32 q=23.0 size= 4864kB time=00:00:13.53 bitrate=2943.5kbits/s speed= 1.6x \\rframe= 295 fps= 33 q=23.0 size= 5120kB time=00:00:14.41 bitrate=2908.8kbits/s speed= 1.6x \\rframe= 307 fps= 32 q=23.0 size= 5376kB time=00:00:14.90 bitrate=2954.3kbits/s speed=1.57x \\rframe= 325 fps= 32 q=23.0 size= 5888kB time=00:00:15.62 bitrate=3086.6kbits/s speed=1.56x \\rframe= 347 fps= 33 q=23.0 size= 6144kB time=00:00:16.57 bitrate=3035.9kbits/s speed=1.57x \\rframe= 367 fps= 33 q=23.0 size= 6400kB time=00:00:17.41 bitrate=3010.6kbits/s speed=1.56x \\rframe= 388 fps= 33 q=23.0 size= 6656kB time=00:00:18.34 bitrate=2972.5kbits/s speed=1.56x \\rframe= 409 fps= 33 q=23.0 size= 6912kB time=00:00:19.17 bitrate=2952.3kbits/s speed=1.56x \\rframe= 428 fps= 33 q=23.0 size= 7168kB time=00:00:19.99 bitrate=2937.2kbits/s speed=1.56x \\rframe= 448 fps= 34 q=23.0 size= 7424kB time=00:00:20.80 bitrate=2923.2kbits/s speed=1.56x \\rframe= 470 fps= 34 q=23.0 size= 7680kB time=00:00:21.71 bitrate=2897.9kbits/s speed=1.56x \\rframe= 485 fps= 34 q=23.0 size= 8192kB time=00:00:22.33 bitrate=3004.3kbits/s speed=1.55x \\rframe= 503 fps= 34 q=23.0 size= 8704kB time=00:00:23.08 bitrate=3089.3kbits/s speed=1.54x \\rframe= 525 fps= 34 q=23.0 size= 8960kB time=00:00:24.00 bitrate=3057.2kbits/s speed=1.55x \\rframe= 545 fps= 34 q=23.0 size= 9216kB time=00:00:24.84 bitrate=3038.7kbits/s speed=1.55x \\rframe= 567 fps= 34 q=23.0 size= 9472kB time=00:00:25.75 bitrate=3013.3kbits/s speed=1.56x \\rframe= 585 fps= 34 q=23.0 size= 9728kB time=00:00:26.49 bitrate=3007.9kbits/s speed=1.55x \\rframe= 603 fps= 34 q=23.0 size= 9984kB time=00:00:27.26 bitrate=3000.3kbits/s speed=1.55x \\rframe= 622 fps= 34 q=23.0 size= 10240kB time=00:00:28.04 bitrate=2990.6kbits/s speed=1.55x \\rframe= 642 fps= 35 q=23.0 size= 10496kB time=00:00:28.88 bitrate=2976.7kbits/s speed=1.55x \\rframe= 658 fps= 34 q=23.0 size= 10752kB time=00:00:29.51 bitrate=2984.5kbits/s speed=1.55x \\rframe= 674 fps= 34 q=23.0 size= 11008kB time=00:00:30.20 bitrate=2985.1kbits/s speed=1.53x \\rframe= 693 fps= 34 q=23.0 size= 11520kB time=00:00:30.99 bitrate=3044.4kbits/s speed=1.53x \\rframe= 709 fps= 34 q=23.0 size= 11520kB time=00:00:31.62 bitrate=2984.0kbits/s speed=1.53x \\rframe= 729 fps= 34 q=23.0 size= 11776kB time=00:00:32.46 bitrate=2971.8kbits/s speed=1.53x \\rframe= 743 fps= 34 q=20.0 size= 12032kB time=00:00:33.08 bitrate=2978.9kbits/s speed=1.52x \\rframe= 765 fps= 34 q=23.0 size= 12288kB time=00:00:33.99 bitrate=2961.2kbits/s speed=1.53x \\rframe= 786 fps= 34 q=23.0 size= 12544kB time=00:00:34.87 bitrate=2946.4kbits/s speed=1.53x \\rframe= 802 fps= 34 q=23.0 size= 12800kB time=00:00:35.54 bitrate=2949.6kbits/s speed=1.52x \\rframe= 819 fps= 34 q=23.0 size= 13056kB time=00:00:36.24 bitrate=2950.8kbits/s speed=1.52x \\rframe= 838 fps= 34 q=23.0 size= 13056kB time=00:00:37.03 bitrate=2887.9kbits/s speed=1.52x \\rframe= 853 fps= 34 q=23.0 size= 13568kB time=00:00:37.66 bitrate=2951.2kbits/s speed=1.52x \\rframe= 871 fps= 34 q=23.0 size= 13824kB time=00:00:38.42 bitrate=2946.9kbits/s speed=1.52x \\rframe= 888 fps= 34 q=23.0 size= 14080kB time=00:00:39.12 bitrate=2948.0kbits/s speed=1.51x \\rframe= 908 fps= 34 q=23.0 size= 14336kB time=00:00:39.96 bitrate=2938.8kbits/s speed=1.51x \\rframe= 925 fps= 34 q=23.0 size= 14592kB time=00:00:40.65 bitrate=2940.1kbits/s speed=1.51x \\rframe= 940 fps= 34 q=23.0 size= 14848kB time=00:00:41.30 bitrate=2944.6kbits/s speed=1.51x \\r[mp4 @ 0x594edc6c22c0] Starting second pass: moving the moov atom to the beginning of the file\\n[out#0/mp4 @ 0x594edc5475c0] video:15326kB audio:409kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.204582%\\nframe= 993 fps= 35 q=-1.0 Lsize= 15767kB time=00:00:41.37 bitrate=3121.5kbits/s speed=1.44x \\n[libx264 @ 0x594edc60a440] frame I:4 Avg QP:11.56 size:213272\\n[libx264 @ 0x594edc60a440] frame P:330 Avg QP:14.33 size: 34584\\n[libx264 @ 0x594edc60a440] frame B:659 Avg QP:17.72 size: 5200\\n[libx264 @ 0x594edc60a440] consecutive B-frames: 7.3% 9.1% 11.2% 72.5%\\n[libx264 @ 0x594edc60a440] mb I I16..4: 11.3% 65.7% 23.1%\\n[libx264 @ 0x594edc60a440] mb P I16..4: 1.9% 3.7% 1.4% P16..4: 38.4% 14.7% 8.4% 0.0% 0.0% skip:31.5%\\n[libx264 @ 0x594edc60a440] mb B I16..4: 0.2% 0.1% 0.0% B16..8: 37.1% 1.6% 0.1% direct: 1.7% skip:59.1% L0:48.4% L1:46.7% BI: 4.9%\\n[libx264 @ 0x594edc60a440] 8x8 transform intra:54.3% inter:76.5%\\n[libx264 @ 0x594edc60a440] coded y,uvDC,uvAC intra: 43.9% 45.2% 21.6% inter: 8.5% 8.6% 1.3%\\n[libx264 @ 0x594edc60a440] i16 v,h,dc,p: 29% 50% 7% 13%\\n[libx264 @ 0x594edc60a440] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 30% 27% 28% 2% 3% 2% 3% 2% 3%\\n[libx264 @ 0x594edc60a440] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 37% 32% 12% 3% 4% 3% 4% 2% 2%\\n[libx264 @ 0x594edc60a440] i8c dc,h,v,p: 51% 28% 18% 3%\\n[libx264 @ 0x594edc60a440] Weighted P-Frames: Y:4.8% UV:4.2%\\n[libx264 @ 0x594edc60a440] ref P L0: 61.5% 4.9% 20.0% 13.5% 0.1%\\n[libx264 @ 0x594edc60a440] ref B L0: 81.5% 12.3% 6.3%\\n[libx264 @ 0x594edc60a440] ref B L1: 94.3% 5.7%\\n[libx264 @ 0x594edc60a440] kb/s:3034.23\\n[aac @ 0x594edc62d780] Qavg: 16314.597\\n{\\n \\\"programs\\\": [\\n\\n ],\\n \\\"streams\\\": [\\n {\\n \\\"width\\\": 1080,\\n \\\"height\\\": 1920,\\n \\\"sample_aspect_ratio\\\": \\\"1:1\\\",\\n \\\"display_aspect_ratio\\\": \\\"9:16\\\",\\n \\\"pix_fmt\\\": \\\"yuv420p\\\",\\n \\\"level\\\": 42,\\n \\\"avg_frame_rate\\\": \\\"24/1\\\"\\n }\\n ],\\n \\\"format\\\": {\\n \\\"duration\\\": \\\"41.386009\\\",\\n \\\"size\\\": \\\"16145292\\\"\\n }\\n}\\ndc764bcb70d5c32783caa49b25e1bf44cafd14b25dc265bc44e2b8661149f66f /tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_K8VMlhbfrV9xHUfzxmbylNwF" }, { "role": "assistant", "content": "", "reasoning": "**Considering video formats**\n\nI'm analyzing the audio and video lengths—41.37 seconds for audio versus 41.875 for video. Maybe I don't need to shorten it, just trim the 0.5 seconds of silence at the end. Verifying the visuals is important, so I'll likely extract frames to check them. I’m thinking about creating a 720p version since Telegram uses a square format, but I should stick to delivering the fixed 1080p one. Still, it might be worth producing a 720 version, considering user experience and video formats.\n**Updating user memory**\n\nI'm considering how to use memory for the user effectively, especially regarding content strategy. The user's profile already has AutoShorts preferences, which means I might need to replace the existing line since memory is almost full. I want to update the AutoShorts/TrueTraceShorts description to include new details about B3 without overloading it. It seems best to replace the old text about manual approval and posting with a more compact version. After that, I’ll patch the skill!", "finish_reason": "tool_calls", "reasoning_content": "**Considering video formats**\n\nI'm analyzing the audio and video lengths—41.37 seconds for audio versus 41.875 for video. Maybe I don't need to shorten it, just trim the 0.5 seconds of silence at the end. Verifying the visuals is important, so I'll likely extract frames to check them. I’m thinking about creating a 720p version since Telegram uses a square format, but I should stick to delivering the fixed 1080p one. Still, it might be worth producing a 720 version, considering user experience and video formats.\n**Updating user memory**\n\nI'm considering how to use memory for the user effectively, especially regarding content strategy. The user's profile already has AutoShorts preferences, which means I might need to replace the existing line since memory is almost full. I want to update the AutoShorts/TrueTraceShorts description to include new details about B3 without overloading it. It seems best to replace the old text about manual approval and posting with a more compact version. After that, I’ll patch the skill!", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFL9Z-6qsz__q6mCGDXJHljxht7UY3GrJOeQgUpobID43dA06BJxVrwUv33Yo72QSZUwLTT5MFJatwLgaS3jQ6MDhGimmfL1e2OCQa2-0j9E06Nqt7VHSgTWBmdmjBZIYmHk0W7-_iOxgL11Sn4gdlnt09aQCv1Bkrk0TX-dcy79yXpCjE1b6fzOzxQAL5rE5b-ETWzizIZkEtPNqc3sEoVBF3pjb4y_-RWOxUxZ-xitJGOnpBXT6_xNxWLkPovc45GcyM7LrLxTRVOtTa0vD2wciBm9U11u4NTam_8MtBvwK8M_OSyz3ZWUa7zJslrG05sXpJQZX72rXUwRugARN9uaBzvirjZ_fIsLo25qTE0x7JRzgZDhfVxBejBuqIRIP3aJGrhCSofiI_R7dNV-xqCnFyTPA1Zn9Z6V458fWuqYNeVpCaw6LeGP-nr5H52SfkdmN5T5n6zz-GGs2G4AlHYi1rgfojZsLfq5SEMwEfm6EKAI0AJwyamIq81nTk7_CLC6YhS1VjFnKueA-SijkZcHfI26PsRFO-f1R7RYGzDaUDPqDTvHT8wdB_ClHqMKqLmV2_9tAswmWOvkD66R97cOg4HhzfU6pyHkOd2hf-vWv_CmX7XyTnhwTTADqnmEYElBw6-EkV3qoh_5GJxI6pT64ZedjebztCR58W0LH6JDMWfYhk6CsXCPw-OpJGbi3MTNOS6X7QQUGgX49StIIYyBdkRPTKOofCept8qP7fIDJkmjgwNxfHcg3T4nr-jd0AgS3MjD3pJMngos7ksF76-k270IfasJlIdrhYA9ZGQn4ptN4aWDGJhzFLHg6BTG5ruuX9Gg8O2K_XDeoOMOvPQOrwvaWBQFyc7tEEdgK1YfaJWLAeVW4F__fMwlYKzPOBAwm8p7lexW6Zz3Yx--RKplkmJ_J6LCBYf3RAX4cC8G0iWL1RCbrp5uIIRHF-IwrFNKFgiV_V8gSiv41asfZuErA-JwQ6AN72WcwPmXSAngkMCiDgZEL1fwp1nPKlrNqFEq5zCNv5hIMKC_qbhlkujBgSRc0qLI2sEB03PTGyFmFaBHKB4NdiSBxnzBHIlo8nw-Yjxp2Bt530ec7GeYTXJtf13hoxL2Oxa5U0ktl0CWWPWITm_q4tiPn2Vg2DkEq6mC1H-OvI1Vr8eRGdmKme3er3r8RAQoljUrfbPji6pWJuowBt-RklryxgIQWM909T-C6oHmwpJwQbHJmZkhycExb3hVZc9OrivfGY2Cx_30D6FX8GXaKg8CCp9M51GnRbfR4vp0z8V7P1LkpDe9tx74BGbP13hvOv-MhTIIahuPZN00lo32sGsaalWAdjBDKVYmKiWQGpwKFWtWRtNX3AAPdGR07-zSU914RLVEepBXvIC9nJRyXZy-03y9m5-ZZ8zuHITOgowHicYJJlMvZ_nJhXy7nE3XfQU4gG7JwlULOr2TU4SG-dCF83SlbeZPIzuw10x1H8IBkq6pCpw5VpDnnv-xSKhC7EE9sWJGF_l4CKRT9QKpC2QEzyzx_YNhrozYotW1Uy8fL7oWde7ced4fKy4Kn8ZWyMEYklsa-UnXjV6EEvgweavcmdfx24TPHoTe2c-30uy5JqbeY5EGggmvs21yXycI-LqbLjbkLCJUWoArcDCc7zxzCoeMg33mKlSEMhHlLJv5hcTrLaonhTkZZwPBQG1J1jKznH3SNE8_DI9wqyr2u53NFAABEytbDdrk5BswiLQfiUrp83qEQIp7BVq7sqYdCipxJFPf_BcoPb8qlFXxnd6A94mITu9Ke5Zl9A1OePPhBVAUJTGKDM5Inw-6v3W5npHcHE0ICmm7wAQlW4pqBS7lNAqs_4kdW1MCrFdlBM4nKYVjWxlE5V_JqKDUGQOJaKapQcoTjwYQaM7sx-zQTF0IYWzp6Dkb48_iTl3DsYxY9c97PLjvAWupCSR3VqoXU-KjWxZCOREOETZVT4wpTAnG2LXqR9t0klWEkx-uVuMzwSNP1lMM7KRLJkDjd7v4x8_cSf7Hu6XbR5Wo5Yi1bMUuHKrRGt90dpR9jrCK_Frj9ilPDjKY46KQrLDYLiBuKg6A8XSf_6I7IjKv1kjKc3kk_lLW6phgMnVFI-jGKMobVWr1GFvXtGYhWTvUCcMGOo8e2sK9sOUU2t7suxchHdtYLdYrK6fQdJ94E9659ZRp7F9MHGduO6SIxNUIuIvgEiNfzNkLBSRJYq3Z2Sg8s_-4_4kVol940Twh5-Ok5-7KkHlXYfrd9fitmFUjTjIQVOqu9RT976UYDcPH7IiCg-ZqxNzEd0Pl_Syl9xCq3N3LslBEYYZnGktjwT4fC9w2Dy23h8IdqpZSmHnZKQK9cZBP9stTLP5T5QLiguLs_epgWUgYptHweoTzJ778YsSLoUXV--gcGWuQWk9ywSpO8vOLoIHkS18cDqvowe5e889xMCm_xNZLrbnOpeWiCpGa_Zu7mWxpi0Kl0-7pT9r0bkAHDgSF5YGmNMlXmcmTvLQQa9XVjpue3crdpAgS_EbmK3t_1EJT_6YWYIfRYf-9LMYYEdymEm4w_Yb5Yo-xZ07FzTEpb6d_uaOpJnb3CDBp2cgHUlCpPafsICAHc7NF1gzQkEY6syB8Ft8fxQitZ0GMxWISXg6E8xY1gjMEqwpr-TyIEtyepI2lRcPJi3BEDgXHVCHNwXhD3mx0m6llgRBRaNHqF-gdfGFsMoIPJY_I7kvZLRVc6psWqkTyL3iV7WLKfaBMAdJc6bhpYX5MmxZm85y7v_35jKmISRTxSejuXmryObLzLE7fFvD0=", "id": "rs_0d4a723b463df28d016a14bf51e11481918b722baf2815849b", "summary": [ { "type": "summary_text", "text": "**Considering video formats**\n\nI'm analyzing the audio and video lengths—41.37 seconds for audio versus 41.875 for video. Maybe I don't need to shorten it, just trim the 0.5 seconds of silence at the end. Verifying the visuals is important, so I'll likely extract frames to check them. I’m thinking about creating a 720p version since Telegram uses a square format, but I should stick to delivering the fixed 1080p one. Still, it might be worth producing a 720 version, considering user experience and video formats." }, { "type": "summary_text", "text": "**Updating user memory**\n\nI'm considering how to use memory for the user effectively, especially regarding content strategy. The user's profile already has AutoShorts preferences, which means I might need to replace the existing line since memory is almost full. I want to update the AutoShorts/TrueTraceShorts description to include new details about B3 without overloading it. It seems best to replace the old text about manual approval and posting with a more compact version. After that, I’ll patch the skill!" } ] } ], "tool_calls": [ { "id": "call_JPWgFFCZq612M5JX9YnVW2jb", "call_id": "call_JPWgFFCZq612M5JX9YnVW2jb", "response_item_id": "fc_0d4a723b463df28d016a14bf592c048191b1e7aa64382d860f", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_contact_sheet_v1.jpg\",\"question\":\"Re-check the rendered B3 contact sheet for shape/format: it should be vertical 9:16, not square or horizontally squeezed, with readable subtitles and detailed screen visuals. Note any obvious issue.\"}" } } ] }, { "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: Re-check the rendered B3 contact sheet for shape/format: it should be vertical 9:16, not square or horizontally squeezed, with readable subtitles and detailed screen visuals. Note any obvious issue." }, { "type": "image_url", "image_url": { "url": "data:image/jpeg;base64,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" } } ], "tool_call_id": "call_JPWgFFCZq612M5JX9YnVW2jb" }, { "role": "assistant", "content": "", "reasoning": "**Clarifying frame extraction**\n\nI'm thinking about how the vision shows a contact sheet in a grid format, which seems to be square. It's not a fixed video, so I need to verify the actual dimensions of the first frame. I might use ffmpeg to extract this frame and verify its details. The contact sheet being square doesn't help, and I should focus on extracting a potentially taller image. I should use the terminal to execute the frame extraction.", "finish_reason": "tool_calls", "reasoning_content": "**Clarifying frame extraction**\n\nI'm thinking about how the vision shows a contact sheet in a grid format, which seems to be square. It's not a fixed video, so I need to verify the actual dimensions of the first frame. I might use ffmpeg to extract this frame and verify its details. The contact sheet being square doesn't help, and I should focus on extracting a potentially taller image. I should use the terminal to execute the frame extraction.", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFL9grYG1c8dyZBh2lKcMz8WsIOwuMA4AZI4AKyYGuQHVZyMt9Ia68mfCFNJCw6dKPkA8pXTxnUx_iKz9xgNBuqHK22zIjxJi_JIdhpgTQ8R2K6gnGtC7uQS5a2dVMdA_8WDAe6PKhSAg2Od3QEaIGvo0lcZ5qEnwCO8D5GJbasye-1b3i5BCkwhiTPY5wgGFKg4rV2Ob-B2UoZQomW-XvIaab0R5oMI6HPygMeU_GPiMvaVZBYuqOLciY1JUt9n8ah30WxXclx4I_COBiIVdlTqcUzNS68EU49xsX_d9WbZqDDyNzqbSctKKxUlMav1s39AZQY3bS7sNyUQkhFQLRKcgjIpcD46Uls9W0w6WAqFyV7CFfViv-9pExSQjBHViybt6PGg4EvM8b-kIj2L66XPjvxcmV30l1fb5inW6OmK-IkRwYp4CgZerz7CVzIe_eB4lTBzZbgZv7J5RIPB-2Ebw7_I8EDPFeKWihiPv9Xs19_ibMbtj3MFg_8t1EmO7t_iDmiFccyk1teMF_PBTySQs48SbN4KRBIQ-N9BvWwDZLgfcXnd5QfZCiH9TXib5VCfhrdLFbmbm9IYQY4_ns9Fn7SXpeJnHBpdO4317TKBAgCt1Y0P15dujr5qxPczFUirXrZHAzLTMLzjFFp7dd456s3_TWYCIwqPhJMYZGiaiph9rVIFRWpRQDQmu0Ysnb4eJp7KyyGfOfbTf-UxD8yp0jgoXQa4YwDoxRE2oODdDWOXG_0NwOKAGwsjZ4MsHY4UG5B_AHkHH8Q4BIkjy-jm2Be68mEbsm96Xa4XzMcEOIZIFzUp8GUHAWj7I1eCJSlFLXq-b3pWTxBv2lQL0kDZhZVR-h8FXmXy1JDUfAq2YNeRwW3unmL401oR48MNqYsCTjciZ7BV59fRG1EYG6cJYAoPGoL5MQdwU3EbosEk2qA3vtUrmgs7MAB0fTQdqGnvSW6VEHla-T78R8P45Eu10AIQ6swd2o9jSqgWS5j5Fv69AfYkUzW_6_nLuAaw6KUAiR6styPtVKPn_00XDcz-NhnVZQmviRWX-ZTOMaK9mWudxBRyW6cEydPzXCac8z9qS5LL2YdPWOTERrHCV3RuKdRK0WrEIwyGbMC073e1gQ4l0DKol9uTAga6HDRPlT_K065Qhbt9Uidj_baxVXfOpZ88zdM-hnoaTS1TssmWKW7_vNUSUGrKYfOO9hhrOVK_JScXHI4qReTvGGoj6VgR8w_vAhtG_FfOQUPzAgbe5DYBzRN2msoRuYd_aIJNgTPlnQ0FeoS_Xk3GV2WZfA_ttu2PKtFPFrYyVU7UTYl8CTfo=", "id": "rs_0d4a723b463df28d016a14bf5d80908191a31957c76cfb7b79", "summary": [ { "type": "summary_text", "text": "**Clarifying frame extraction**\n\nI'm thinking about how the vision shows a contact sheet in a grid format, which seems to be square. It's not a fixed video, so I need to verify the actual dimensions of the first frame. I might use ffmpeg to extract this frame and verify its details. The contact sheet being square doesn't help, and I should focus on extracting a potentially taller image. I should use the terminal to execute the frame extraction." } ] } ], "tool_calls": [ { "id": "call_I3I5JZZyyLkza806A9LE1pJX", "call_id": "call_I3I5JZZyyLkza806A9LE1pJX", "response_item_id": "fc_0d4a723b463df28d016a14bf60a53c819189ddf9d077dd1227", "type": "function", "function": { "name": "terminal", "arguments": "{\"command\":\"OUT='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4'; FRAME='/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_9x16_fixed_frame_5s.jpg'; ffmpeg -y -ss 5 -i \\\"$OUT\\\" -frames:v 1 \\\"$FRAME\\\" >/dev/null 2>&1 && identify \\\"$FRAME\\\" && printf '\\\\n%s\\\\n' \\\"$FRAME\\\"\",\"timeout\":30}" } } ] }, { "role": "tool", "name": "terminal", "content": "{\"output\": \"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_9x16_fixed_frame_5s.jpg JPEG 1080x1920 1080x1920+0+0 8-bit sRGB 81870B 0.000u 0:00.000\\n\\n/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_9x16_fixed_frame_5s.jpg\", \"exit_code\": 0, \"error\": null}", "tool_call_id": "call_I3I5JZZyyLkza806A9LE1pJX" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "tool_calls": [ { "id": "call_sMSCKZ2443dwdcUhmfqdsMt2", "call_id": "call_sMSCKZ2443dwdcUhmfqdsMt2", "response_item_id": "fc_0d4a723b463df28d016a14c0d46d508191a72f42725376bd4c", "type": "function", "function": { "name": "vision_analyze", "arguments": "{\"image_url\":\"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/b3_9x16_fixed_frame_5s.jpg\",\"question\":\"Verify this extracted frame is vertical 9:16 and not squeezed or square. Also check the subtitle is readable.\"}" } } ] }, { "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: Verify this extracted frame is vertical 9:16 and not squeezed or square. Also check the subtitle is readable." }, { "type": "image_url", "image_url": { "url": "data:image/jpeg;base64,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" } } ], "tool_call_id": "call_sMSCKZ2443dwdcUhmfqdsMt2" }, { "role": "assistant", "content": "", "reasoning": "**Considering patch updates**\n\nI need to implement a patch for my skills. Maybe I should create a 720 fallback? Right now, the extracted image is 1080x1920, which our interface shows as 1080x1920 too. That seems fine. For the patch skill text, I will replace the previous B1/B2 outcome section with the new one. I'll just need to use the skill_manage patch. It sounds straightforward!", "finish_reason": "tool_calls", "reasoning_content": "**Considering patch updates**\n\nI need to implement a patch for my skills. Maybe I should create a 720 fallback? Right now, the extracted image is 1080x1920, which our interface shows as 1080x1920 too. That seems fine. For the patch skill text, I will replace the previous B1/B2 outcome section with the new one. I'll just need to use the skill_manage patch. It sounds straightforward!", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFMDb0JtOPUtaS-f9Ff9FFIxvhKMpD04Dv2ina8IRl48jQhywH_I_g83VEzooRbHP8ODL6NwPrtkxA_ZuGl7yNWEWaUvMUszPpWatWhqMTwnVKcQ60zJn_JC6m72BrSOd-1BC9TG4j-Lbw8RzZibQ6zZHwGjuPqXBpxNCwyxBN9MDJQLGW-NwZeZ3U7y-SHaIXOrv_25EhHJDwPPvesuf3EFdDwUh9E1sx_2AQb91xwUoAPXOYq4RJTX4RUiPTSaRXGb-OetBJH9CKNqDeuTpPn4i6jPE8lOfnVYTtIny5TRB27p2OW6timJg9FBt_JxfSG8Bj8VFM29jh551fkVIJrI4FAKm6ouLUZ3kOLZEch2Ihqe4RAZ6_syyeeI1cZCslt6UkoVeXTeMBXA6qLLRUrXemhmIPEli5s37zFtiRhkDgTlJxAyX9ioiKQTYEJIvMky5UYlSP7hxTO1nUHuWSupa9pEnv0WcnyVQmGQc9idPxIPAWCH_IU0w3NJ3EtR2EWstH3-XT4I2EDcL2AAq7fB7QbBogfn9JJyuYL14KXJi0xEOc_zUoUv1Nu4NtlrmXp-lLoKwrlYG9_D03qQJkF3e6CXyEaWBB5gHG_hZo2FMG6gu4ukfB_NM3elzHOpGXF8ljWnZOP2OuR69gnL1zR_yPFVEIa1zETHmzOMvX1xZKIf88LgC8Zk0RhdR-yhalzhnVTeeaWUg-yqYAXO80WEhXR1Eu_g3rpVKhcosMEXQhQx4TGQcjsj0eMjIoBUZQxwO-dUf4x4of_EhWimhFz8BNfgG4Ys-NkC88pmzsEazbh4M_yGZtsWcq77AF8uRrYJvfNENzD-vtimePxvoQxbQSF4I5DMXuIapIw0Wzdc2gE-KiPIx-8OVFDt4lY9dwbqiJr3Bm3OSG3ggDBOHuxwAg1GZVIiC01n_6KdKGU_QjH7O0JFQPHHiGCknop3p-uxeCUyD6Gae7xUoIKBI5I79-XZIneNeXLYVLlAbsOOEWlJuUJr7S6Y1zUcxmUN7DUDYLIbdybzHFn5eYzneJmOcYr11_fNc7UqLnazIBe56aMCpYCvNw0V6aUneX8FGMNlyVjX5tD093ChpD2QlJEUQuiZmJ_WrbQwiLWKkiNRACqvPssYAIr9FpnnH7_29eg7H75SMy22KjHTLRpnVCI0z3uYNhrCltLw7lRf3HmkJNP5NrCvaKgYikjTEvf05yR_TguKgN5TmSpxA4kTnQbJj1vJxWrlvo4Apk8au2pgY37A=", "id": "rs_0d4a723b463df28d016a14c0d89f7c8191870ae0ae7e91a403", "summary": [ { "type": "summary_text", "text": "**Considering patch updates**\n\nI need to implement a patch for my skills. Maybe I should create a 720 fallback? Right now, the extracted image is 1080x1920, which our interface shows as 1080x1920 too. That seems fine. For the patch skill text, I will replace the previous B1/B2 outcome section with the new one. I'll just need to use the skill_manage patch. It sounds straightforward!" } ] } ], "tool_calls": [ { "id": "call_3nCRKscWwoEfFlSZg67uot39", "call_id": "call_3nCRKscWwoEfFlSZg67uot39", "response_item_id": "fc_0d4a723b463df28d016a14c0dbaa20819194da3655265e3b5c", "type": "function", "function": { "name": "skill_manage", "arguments": "{\"action\":\"patch\",\"name\":\"social-media-shorts-automation\",\"file_path\":\"references/clean-ai-cut-vs-hybrid-mechanism.md\",\"old_string\":\"For the calendar-invite login-trap proof, the session result was:\\n\\n```text\\nB1 = clean visible-invite AI images only + voiceover + active-word subtitles\\nB2 = same images + very subtle focus outlines, no labels/arrows/checklists\\nOutcome = B2 recommended: slightly less pure, but the scam mechanism is understood faster while still avoiding PowerPoint/explainer-board look.\\n```\\n\\nUse this as the default next-step bias: if clean images are beautiful but semantically weak, add exactly one or two subtle focus moments around the suspicious invite/button/app path rather than returning to labels, arrows, boxes, or checklist UI cards.\",\"new_string\":\"For the calendar-invite login-trap proof, the updated session result was:\\n\\n```text\\nB1 = clean visible-invite AI images only + voiceover + active-word subtitles; premium but still a bit VO-dependent.\\nB2 = same images + subtle focus outlines; rejected because the lines added little value and reduced the premium look.\\nB3 = detailed AI-generated Outlook-style invite/login/calendar screens with readable UI text + voiceover + active-word subtitles; accepted as the new standard.\\nOutcome = B3 recommended/default: no renderer-added lines/arrows/boxes, but prompt the image model with very detailed, concrete, readable screen/UI content so the problem and safe action are visible in the image itself.\\n```\\n\\nUse this as the default next-step bias: if clean images are beautiful but semantically weak, first make the AI keyframes themselves more specific and content-rich (visible app/email/invite/login/calendar screens, exact readable text, realistic UI details) rather than adding focus lines, arrows, circles, labels, or checklist cards. Deterministic renderer text remains appropriate for captions; visible screen text may be AI-generated when the user explicitly wants detailed realistic UI images and the keyframes pass visual QA.\\n\\nExport QA pitfall: Telegram/mobile playback may misinterpret vertical files if aspect metadata is weak. For final/review MP4s, explicitly encode with `setsar=1,setdar=9/16`, `yuv420p`, `-profile:v high -level:v 4.2`, `-movflags +faststart`, and verify `ffprobe` reports `width=1080 height=1920 sample_aspect_ratio=1:1 display_aspect_ratio=9:16` before delivery.\"}" } } ] }, { "role": "tool", "name": "skill_manage", "content": "{\"success\": true, \"message\": \"Patched references/clean-ai-cut-vs-hybrid-mechanism.md in skill 'social-media-shorts-automation' (1 replacement).\"}", "tool_call_id": "call_3nCRKscWwoEfFlSZg67uot39" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "tool_calls": [ { "id": "call_rxLH4lUjEpYeagXQpuZ2AO9p", "call_id": "call_rxLH4lUjEpYeagXQpuZ2AO9p", "response_item_id": "fc_0d4a723b463df28d016a14c0e7b53881918c69902475003c92", "type": "function", "function": { "name": "memory", "arguments": "{\"action\":\"replace\",\"target\":\"user\",\"old_text\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN.\",\"content\":\"AutoShorts/TrueTraceShorts: manual approval/posting; previews DE, finals EN. New visual standard for proof shorts: detailed AI-generated real UI/screen images with readable concrete text (e.g. Outlook-style invite/login/calendar), no extra focus lines/arrows/boxes; active-word subtitles; export MP4 with explicit 9:16 SAR/DAR.\"}" } } ] }, { "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. New visual standard for proof shorts: detailed AI-generated real UI/screen images with readable concrete text (e.g. Outlook-style invite/login/calendar), no extra focus lines/arrows/boxes; active-word subtitles; export MP4 with explicit 9:16 SAR/DAR.\"], \"usage\": \"98% — 1,349/1,375 chars\", \"entry_count\": 10, \"message\": \"Entry replaced.\"}", "tool_call_id": "call_rxLH4lUjEpYeagXQpuZ2AO9p" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "codex_reasoning_items": [ { "type": "reasoning", "encrypted_content": "gAAAAABqFMDvs1DkIr0uImorJiqWOoFQjtwG3S4EmM9gdmsjoZedgOWD9DvsL-EE_ht1gF2lM-b6kYkonj23phEMCE86x3fk9AU-CQ0vFNT8X-iD1d3ILQ2Yy66SklNNfh4N3Pv0qVRhhNDyHLY2405okQuDbIKH_qf33UYc9LofzZHQ-O2a9jzvsniI0rWXcbP-uRpuXUBNPZ4WczqoW2uJsMdeuH2e8sEkQ1BCyWR5zHkiG9RDcZcWFNm0J3MYKgR3iLZEjx8Q84llTqY0Ydyo33p7rz9xCrKmKjnTnaHLB9uleLKRL_0kvzHFyZGCE711p-IKfwEIYJJ-nOnARsb8r3lhogaTTTmS5xrrPoUEajubojig4pX81r1CaYqamfZFPPSELKsZu5yfq5yAMMxcYCUDFH4oWfu1Ezqf58B3JAW4xnGHUg_DyEBkd_k2uH4F0qzuYVscNdn4bx9tcgi7KazQ6wu0G1G-R-o4Npn942mdfUTxTzPFNS8dSKU8SjPCC-sv9_bVxfP_2NrBicCS-ibyC6SD_PchI39vGTT9F34mvpeU8dNBjIO9E8ajvlreJcpiFsarpDSD3wvOmNydtubHs4nQ3Th92okeRBObJu8ZkGxyPyaw-6L6Nm2O5FcaCHQ4J1RPYjTpQkw_hRofRxwL6Y9Ied9SWx-pyMBXi06oYgGbZ-duLN8qJ4B1sd8GtBHrb0icUjLyTvup4LwLwHHac49mukrk5C-Y7FMs2_6MXCBO38Kd_epNTZjMJu0xwqUn2ewEWq5wp5lNMftEPW8Xo2SMcRTt4xPhYukIBDdrSBCBh6vPfd0nIxTHEvT1smOrVj-u3awVal_WMeExqc7J4M18qe_GFLmZigj4mtQvbB9wMRgBn47QRUX4pAIrBrRrBqa7C2XojCbjMyCbpMc4CHG7rtfVfgS47723jy7N4RW2ABUZhqJ3--X5HZojubH7_5yKuwBEh5Vjeu5TG0izUf0dnf29f1m_xbcumsX0ELE3Cjcg6vmE_VP-bxgeV1BDNkp6S-5dIGE9_Kmc7jaVCH2mnB4SYeWf3tsssO8VnfhO-0-ova4W5RY7Veux3ogLzObnA1bzwG-2MfJAt5bQrq32C9vrLdNHLh7x3ARC7Bdkab_Awvanh7dLVeQKEKOSMUxcwXRB-5_lX3q1Szzjs8ZPp-VCIxreqGi6NIV3mQt7ojzIyOycNvXT8ldao91_9V3Ta3-GQjADiHreEO1pyHbsNh0eU05rHZ6fHb8ZNrATmRyVSLlAAJ4_eP9AOkf7z3VzcWs7WFFJkzJJLvkOmtPMXeiybrhL78ViYIgNY0DvNz3Tr5b9YcJ8BHTDhPIYTrPSK4pbMeJgIDFgxTlbY2NaBz69R6FOVUSnSCtluaUArW6nFNWAIW5qUQ4e6cYwG_8mYx1bCdYnVIUrTpXDYqyPNPAtBOexEafzOurSO06vDc-ogzGcH29p-G5QRdm9VDImhAGmNNT3fA3seutdzUG_oTgzHQKMoj2DWykf8Fg2I9lgKC3LJlqhhrWrzyLpJutjosRKKBkN18YQejQPch01cmo0dDETBdS-gJJHFe43IDfH2X0XDUmHPLV2wnKzK6wNrW_gK5qJhTfX1Ti948L8UczHaT0wl4IiJSyFiPeEITDTSNnO8E0oQw4MyP9VJhKB6DlFoYfI-SNuSDupNY5C9akx6QZThzzyR_k9QheeAt43-ZJAk0h-rJD-vnIVpnysbtbbwmRhzqILkWaaNN2syeLi2Pl_nz3D1wvPh7VYTx8YKFoE9-yrO940jl6o7BkaOueZnKhUgAnBWBHrDVr9czB32y_Myax7FX_N2NpGbHc4CnPBh9p2xbv1Rr565fhoL6QtZHb4s-Q5JBN3YuwZw-rO5UOhAhTFqlMWJw42eiIO0QzMr3HgAZrHlX6DVcEEg7QNcfshwzED7VpyBMEckpCoz0vdfNtA95c0PF7oFEA=", "id": "rs_0d4a723b463df28d016a14c0ec060c8191af92a8bcf7adb5d0", "summary": [] } ], "tool_calls": [ { "id": "call_kQ0iPeqP08emM2wM9Ol3flRn", "call_id": "call_kQ0iPeqP08emM2wM9Ol3flRn", "response_item_id": "fc_0d4a723b463df28d016a14c0ef7a64819183015615912fca56", "type": "function", "function": { "name": "execute_code", "arguments": "{\"code\":\"from pathlib import Path\\nimport json, hashlib\\np=Path('/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4')\\nmanifest={\\n 'candidate_id':'calendar-invite-login-trap-30s',\\n 'version':'v1.4.1-b3-text-detail-ai-only-9x16-fixed',\\n 'status':'review_preview_only_not_posted',\\n 'preview_mp4_path':str(p),\\n 'preview_sha256':hashlib.sha256(p.read_bytes()).hexdigest(),\\n 'format_fix':{'width':1080,'height':1920,'sample_aspect_ratio':'1:1','display_aspect_ratio':'9:16','h264_level':'4.2','pix_fmt':'yuv420p','movflags':'faststart'},\\n 'visual_standard':'detailed AI-generated real UI/screen images with readable concrete text; no focus lines/arrows/boxes; active-word subtitles only',\\n 'blocked':{'posting':False,'platform_api_used':False,'wan_used':False,'i2v_used':False}\\n}\\nout=p.parent/'manifest_b3_9x16_fixed_v1.json'\\nout.write_text(json.dumps(manifest,indent=2),encoding='utf-8')\\nprint(out)\\nprint(manifest['preview_sha256'])\"}" } } ] }, { "role": "tool", "name": "execute_code", "content": "{\"status\": \"success\", \"output\": \"/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/manifest_b3_9x16_fixed_v1.json\\ndc764bcb70d5c32783caa49b25e1bf44cafd14b25dc265bc44e2b8661149f66f\\n\", \"tool_calls_made\": 0, \"duration_seconds\": 0.26}", "tool_call_id": "call_kQ0iPeqP08emM2wM9Ol3flRn" }, { "role": "assistant", "content": "", "reasoning": null, "finish_reason": "tool_calls", "tool_calls": [ { "id": "call_qEIhz8Pci1gsfAR5txmN0Aoj", "call_id": "call_qEIhz8Pci1gsfAR5txmN0Aoj", "response_item_id": "fc_0d4a723b463df28d016a14c0fa8c84819190eed59aec66c37d", "type": "function", "function": { "name": "todo", "arguments": "{\"merge\":true,\"todos\":[{\"content\":\"B3 MP4-Format/Metadata prüfen: Pixelgröße, SAR/DAR, Rotation, Stream-Tags\",\"id\":\"fmt-inspect\",\"status\":\"completed\"},{\"content\":\"B3 als echtes 9:16 Telegram-kompatibles MP4 neu muxen/encoden\",\"id\":\"fmt-fix\",\"status\":\"completed\"},{\"content\":\"Korrigierte Datei mit ffprobe + Screenshot/Frame-QA verifizieren\",\"id\":\"fmt-verify\",\"status\":\"completed\"},{\"content\":\"Neuen visuellen Standard als Skill/Memory verankern\",\"id\":\"standard-save\",\"status\":\"completed\"},{\"content\":\"Nach Formatfix nächsten Build-Schritt vorbereiten/ausführen\",\"id\":\"continue-build\",\"status\":\"completed\"}]}" } } ] }, { "role": "tool", "name": "todo", "content": "{\"todos\": [{\"id\": \"fmt-inspect\", \"content\": \"B3 MP4-Format/Metadata prüfen: Pixelgröße, SAR/DAR, Rotation, Stream-Tags\", \"status\": \"completed\"}, {\"id\": \"fmt-fix\", \"content\": \"B3 als echtes 9:16 Telegram-kompatibles MP4 neu muxen/encoden\", \"status\": \"completed\"}, {\"id\": \"fmt-verify\", \"content\": \"Korrigierte Datei mit ffprobe + Screenshot/Frame-QA verifizieren\", \"status\": \"completed\"}, {\"id\": \"standard-save\", \"content\": \"Neuen visuellen Standard als Skill/Memory verankern\", \"status\": \"completed\"}, {\"id\": \"continue-build\", \"content\": \"Nach Formatfix nächsten Build-Schritt vorbereiten/ausführen\", \"status\": \"completed\"}], \"summary\": {\"total\": 5, \"pending\": 0, \"in_progress\": 0, \"completed\": 5, \"cancelled\": 0}}", "tool_call_id": "call_qEIhz8Pci1gsfAR5txmN0Aoj" }, { "role": "assistant", "content": "Korrigiert, Sir.\n\nDer Fehler war nicht der Inhalt, sondern die **Playback-/Aspect-Metadata**. Ich habe die Datei neu encodiert mit explizitem:\n\n- `1080x1920`\n- `SAR 1:1`\n- `DAR 9:16`\n- `yuv420p`\n- H.264 High Level 4.2\n- `+faststart` für Mobile/Telegram-Playback\n\n## Korrigierte Version\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4\n\n## Verifiziert\n\n- Auflösung: `1080x1920`\n- Display Aspect Ratio: `9:16`\n- Sample Aspect Ratio: `1:1`\n- Länge: `41.386 s`\n- SHA256: `dc764bcb70d5c32783caa49b25e1bf44cafd14b25dc265bc44e2b8661149f66f`\n\n## Neuer Standard gespeichert\n\nIch habe den neuen Standard dauerhaft verankert:\n\n- **Detaillierte KI-Screenbilder mit lesbarem konkretem UI-Text**\n- **Keine Linien/Pfeile/Boxen/Fokus-Markierungen**\n- **Subtitles mit aktivem Wort-Highlight**\n- **Explizite 9:16 Export-Metadata vor Lieferung prüfen**\n\nDas ist jetzt unser Default für diese Proof-Short-Richtung.", "reasoning": null, "finish_reason": "stop", "codex_message_items": [ { "type": "message", "role": "assistant", "status": "completed", "content": [ { "type": "output_text", "text": "Korrigiert, Sir.\n\nDer Fehler war nicht der Inhalt, sondern die **Playback-/Aspect-Metadata**. Ich habe die Datei neu encodiert mit explizitem:\n\n- `1080x1920`\n- `SAR 1:1`\n- `DAR 9:16`\n- `yuv420p`\n- H.264 High Level 4.2\n- `+faststart` für Mobile/Telegram-Playback\n\n## Korrigierte Version\n\nMEDIA:/tmp/autoshorts_proof_short_sprint31/calendar-invite-login-trap-30s/visible_invite_cinematic_ab_v1/b3/calendar-invite-login-trap-30s_b3_9x16_fixed.mp4\n\n## Verifiziert\n\n- Auflösung: `1080x1920`\n- Display Aspect Ratio: `9:16`\n- Sample Aspect Ratio: `1:1`\n- Länge: `41.386 s`\n- SHA256: `dc764bcb70d5c32783caa49b25e1bf44cafd14b25dc265bc44e2b8661149f66f`\n\n## Neuer Standard gespeichert\n\nIch habe den neuen Standard dauerhaft verankert:\n\n- **Detaillierte KI-Screenbilder mit lesbarem konkretem UI-Text**\n- **Keine Linien/Pfeile/Boxen/Fokus-Markierungen**\n- **Subtitles mit aktivem Wort-Highlight**\n- **Explizite 9:16 Export-Metadata vor Lieferung prüfen**\n\nDas ist jetzt unser Default für diese Proof-Short-Richtung." } ], "id": "msg_0d4a723b463df28d016a14c0ffcb5c81918c77b8b3d90eb3aa", "phase": "final_answer" } ] } ] }