jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-10-08 16:02:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat(runtime): bind browser resources to authority

Browse Source
This commit is contained in:
Alexandre Teixeira
2026-10-02 18:54:09 +01:00
parent b648f9ddbe
commit e175bea752
27 changed files with 2120 additions and 3153 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/tool_index.py
+2 -2
View File
@@ -111,8 +111,8 @@ BUILTIN_TOOL_DESCRIPTIONS: Dict[str, str] = {
"get_weather": "Get current weather and a three-day forecast for a city or place from Open-Meteo without an API key. Use for weather lookups before web_search.",
"web_fetch": "Fetch and read the text content of a specific URL/website the user names (e.g. 'check example.com', 'open this link'). Use when you have a concrete URL; for open-ended lookups use web_search instead.",
"pdf_extract": "Extract focused, source-attributed passages and exact table values from an online PDF or task-local /workspace/*.pdf. Use for arXiv papers, reports, manuals, PDF tables, evaluation metrics, and multi-document PDF extraction. Prefer this over Python requests, curl, downloading, pdftotext, or guessing. Include target model names, metrics, and table headings in query.",
"youtube_tool": "Read YouTube-specific data without fighting the JS page: video comments, transcripts, metadata, or latest video from a channel. Use for YouTube comments/transcript/channel latest-video tasks; use private_browser only for visual site interaction.",
"private_browser": "Private browser automation through Odysseus' agent-browser wrapper. Use only for specific pages that need JavaScript, login/session state, clicking, filling forms, waiting, screenshots, or rendered DOM inspection. For open-ended search use web_search; for ordinary URL reading use web_fetch.",
"youtube_tool": "Read YouTube-specific data without fighting the JS page: video comments, transcripts, metadata, or latest video from a channel. Use for YouTube comments/transcript/channel latest-video tasks.",
"private_browser": "Trusted metadata for an existing server-registered browser session only. Page/document reads and interactions are unavailable because the configured producer cannot guarantee exact target binding. No model batch or raw browser commands. Use web_search or web_fetch for supported web access.",
"inspect_media": "Inspect local workspace images, SVGs, videos, and PDF pages with the current multimodal model. Samples bounded timestamped video frames uniformly, at scene cuts, or from temporally diverse motion peaks; renders SVG to PNG; exports stills or clips; concatenates ranges; changes clip speed while preserving audio pitch; and renders query-relevant PDF pages. Prefer these native operations over raw ffmpeg. Increase max_dimension only for small visual details; saved exports keep source quality.",
"extract_text": "Extract exact visible text, confidence, and pixel centers from a local workspace image with Odysseus local OCR. Use for screenshots, scans, labels, numbers, receipts, and text-location tasks; use inspect_media for general visual understanding.",
"transcribe_media": "Transcribe dialogue, narration, names, and spoken timing from a local audio or video file with Odysseus local Whisper. Returns [START --> END] TEXT segments and always persists them to a workspace text file. For a named chapter, question, scene, or topic, locate its boundaries and restrict filtering to that interval. This handles audio speech; combine with inspect_media for audiovisual tasks or visually burned-in subtitles.",