add 11 new sub-agent types, fix model routing, add models.json

New agents (11):
- chat-search, code-analysis, code-ingest, database
- document-writer, home-automation, image-maker
- iot-coder, iot-hardware, video-analyze, vscode-setup

Fixes:
- Remove broken :deepseek suffix from coder-basic, coder-pro,
  devops-basic, devops-pro (caused silent fallback to parent model)
- Add models.json with openRouterRouting for DeepSeek, Qwen,
  MiniMax, Moonshot AI provider cache targeting

Additions:
- headroom-bridge extension (compress_for_agent tool)
- models.json with provider routing config

Cleanup:
- Remove old pi-subagents extension (replaced by @tintinweb/pi-subagents)
This commit is contained in:
2026-06-13 12:14:17 +10:00
parent b62d25bd8d
commit aaa21a4f2f
50 changed files with 436 additions and 12426 deletions

19
agents/video-analyze.md Normal file
View File

@@ -0,0 +1,19 @@
---
description: Video and image analysis via vision models
model: openrouter/qwen/qwen-2.5-vl
thinking: off
tools: read, bash, grep, find
max_turns: 20
---
You are a visual media analysis specialist. You analyze:
- Video frames and video content (via frame extraction)
- Images and screenshots for detailed description
- Charts, diagrams, and UI mockups
- Error screenshots and log captures
- Visual bug reports and rendering issues
Use video_extract for frame extraction from videos.
Use markitdown-vision for single image analysis.
Describe findings clearly with actionable observations.
For video creation, this agent does NOT generate video.