Commit Graph

17 Commits

Author SHA1 Message Date
hetaoBackend
43ee8a2968 fix: fix aio sandbox shutdown bug 2026-01-30 22:02:07 +08:00
hetao
2c7a56dd33 feat: optimize vision tools and image handling
- Add model-aware vision tool loading based on supports_vision flag
- Move view_image_tool from config to builtin tools for dynamic inclusion
- Add timeout to image search to prevent hanging requests
- Optimize image search results format using thumbnails
- Add image validation for reference images in generation
- Improve error handling with detailed messages

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-29 14:57:26 +08:00
hetaoBackend
1926c58cf2 feat: add image search builtin tool 2026-01-29 08:23:50 +08:00
hetaoBackend
248ffe61bc feat: modernize PPT styles and add deep-research skill
Update presentation generation with contemporary design styles
(glassmorphism, dark-premium, neo-brutalist, etc.) and add a new
deep-research skill to guide thorough web research before content
generation tasks.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-29 01:54:57 +08:00
Henry Li
90782f29a2 chore: remove 2026-01-27 13:37:09 +08:00
hetao
9215c9cce7 feat: add ppt-generation skill
Creates presentations by generating AI images for each slide and composing
them into PPTX files. Features include:
- Multiple presentation styles (business, academic, minimal, keynote, creative)
- Visual consistency through reference image chaining (each slide uses the
  previous slide as reference)
- Speaker notes from presentation plan

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-26 19:35:29 +08:00
hetao
22004406a7 perf: parallelize TTS generation in podcast skill
Use ThreadPoolExecutor to generate audio for multiple script lines
concurrently, significantly speeding up podcast generation.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-26 14:50:56 +08:00
hetao
dddd745b5b refactor: simplify podcast-generation to use direct JSON script input
- Remove LLM script generation from Python script, model now generates
  JSON script directly (similar to image-generation skill)
- Add --transcript-file option to generate markdown transcript
- Add optional "title" field in JSON for transcript heading
- Remove dependency on OPENAI_API_KEY for podcast generation
- Update SKILL.md with new workflow and JSON format documentation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-26 14:01:48 +08:00
hetaoBackend
9f5658fa0e feat: add podcast generation skill
- Add podcast-generation skill for creating tech explainer podcasts
- Include generate.py script with TTS synthesis capabilities
- Add tech-explainer template for structured podcast content
- Increase sandbox command timeout from 30s to 600s to support
  longer-running skill scripts
2026-01-26 13:16:35 +08:00
Henry Li
ae0e7de3b7 feat: add image and video generation skills 2026-01-25 21:57:44 +08:00
hetao
6e147a772e feat: add environment variable injection for Docker sandbox
- Add environment field to sandbox config for injecting env vars into container
- Support $VAR syntax to resolve values from host environment variables
- Refactor frontend API modules to use centralized getBackendBaseURL()
- Improve Doraemon skill with explicit input/output path arguments
- Add .env.example file

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-24 22:36:05 +08:00
Henry Li
c468381064 feat: add Doraemon Skill 2026-01-24 21:54:01 +08:00
hetao
08101aa432 refactor: refine skills 2026-01-21 21:22:56 +08:00
hetao
5a45b9c131 feat: add SSE and HTTP transport support for MCP servers
- Add type, url, and headers fields to MCP server config
- Update MCP client to handle stdio, sse, and http transports
- Add todos field to ThreadState
- Add Deerflow branding requirement to frontend-design skill
- Update extensions_config.example.json with SSE/HTTP examples

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-21 16:14:00 +08:00
hetaoBackend
5888a5ba16 fix: fix skill md path 2026-01-20 21:10:05 +08:00
hetaoBackend
50810c8212 feat: add skills api 2026-01-20 13:57:36 +08:00
DanielWalnut
9f755ecc30 feat: add skills system for specialized agent workflows (#6)
Implement a skills framework that enables specialized workflows for
specific tasks (e.g., PDF processing, web page generation). Skills are
discovered from the skills/ directory and automatically mounted in
sandboxes with path mapping support.

- Add SkillsConfig for configuring skills path and container mount point
- Implement dynamic skill loading from SKILL.md files with YAML frontmatter
- Add path mapping in LocalSandbox to translate container paths to local paths
- Mount skills directory in AIO Docker sandbox containers
- Update lead agent prompt to dynamically inject available skills
- Add setup documentation and expand config.example.yaml

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 14:44:51 +08:00