Introduces a comprehensive agent management system and a new research interface within the cockpit. This includes backend API endpoints for CRUD operations on agents, a new agent lifecycle manager, and frontend components for managing agents, skills, and research workflows.
- feat(backend): add REST API for agent lifecycle management (list, create, update, delete, import)
- feat(backend): implement `pkg/agent/manager` for agent lifecycle control
- feat(gateway): register agent API routes in the gateway
- feat(frontend): add cockpit tabs for Agents, Skills, and Research
- feat(frontend): implement AgentsPage and ResearchPage components
- feat(frontend): add `use-agents` and `use-cockpit-skills` hooks
- docs: add Agent Management API documentation and update project map
- refactor(tools): update ToolSkill metadata handling and regex parsing
- ToolSkill struct with Name, Description, Tags, UsageCount
- LoadToolSkill() to read and parse tool skill files
- Extract tags from content if not in frontmatter
- Add build-without-make.bat script for Windows builds without make
- Update .gitignore to exclude .gocache and dist directories
- Fix scripts/build-without-make.bat to properly handle repository root resolution
- Add CALL directive for pnpm commands in batch scripts
- Agent system improvements and health server enhancements
- Add agent cockpit UI components and memory graph visualization
- API improvements for PicoClaw web backend
- Update frontend routing and app sidebar
- Add ParseFrontmatter function to extract YAML frontmatter from content
- Add test coverage for valid YAML, no frontmatter, and invalid YAML cases
- Use gopkg.in/yaml.v3 for parsing
Complete end-to-end permission flow for tool execution:
- Add POST /api/permission/grant endpoint with gateway proxy
- Add permission checks for list_dir, edit_file, append_file tools
- Fix frontend PermissionPrompt to call grant API instead of chat messages
- Add grantPermission() to frontend API client
- Expose PermissionCache via AgentInstance for API access
- Wire up permission grant callback through gateway to agent loop
Inspired by opencode's permission system architecture.
Integrate `PermissionCache` into `WriteFileTool`, `EditFileTool`, `AppendFileTool`, and `ListDirTool` to allow user approval for actions outside the workspace.
- Add `PermissionPrompter` interface and `TerminalPrompter` implementation.
- Update `AgentInstance` to initialize and register the permission cache and `RequestPermissionTool`.
- Refactor filesystem tools to support permission checks via a `PermissionChecker` interface.
- Add `plan.md` documenting the multi-wave permission implementation strategy.
* fix(channels): dismiss tool feedback animation when turn ends via ResponseHandled
When a tool sets ResponseHandled=true (e.g., send_file), the turn ends
without producing a final assistant response. This meant no outbound
message triggered FinalizeToolFeedbackMessage, leaving the animation
goroutine running indefinitely — editing the Feishu card every 3 seconds
with "." / ".." suffixes long after the tool had finished.
Fix: call DismissToolFeedback at "Tool output satisfied delivery" so the
tracker is cleared and the animation goroutine is stopped immediately.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(adapters): add DismissToolFeedback to channelManagerAdapter
The adapter must implement the new interface method added in the
previous commit, otherwise the package fails to compile.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(channels): pass InboundContext to DismissToolFeedback for topic-aware keys
Telegram forum topics use scoped tracker keys like "chatID/topicID",
resolved via ToolFeedbackMessageChatID with the InboundContext. The
previous nil context caused the lookup to fall back to the raw chatID,
missing the topic-scoped entry and leaving the animation goroutine
orphaned in forum-topic conversations.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* style: wrap long function signatures for golines
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(feishu): fix image download with API fallback and post image support
- Add Image.Get API fallback when MessageResource.Get fails (different
permission scope: im:resource vs im:message:readonly)
- Extract and download images from post (rich text) messages
- Extract images from interactive card messages
- Deduplicate post image keys across locales
- Add comprehensive tests for new helpers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(media): add image path tags alongside base64 for LLM file access
Images are still base64-encoded into msg.Media for multimodal LLMs,
but now also get [image:path] tags injected into message content so
the LLM knows the local file path for save/forward operations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor(media): only auto-inject images for tool results, not user messages
Channel-received images (role=user) now get path tags only, letting
the LLM decide whether to view via load_image or just operate on
the file. Tool result images (role=tool, e.g. load_image) are
base64-encoded into a synthetic user message appended after the tool
message, since many LLM APIs don't support image_url in tool messages.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(media): preserve tool-message ordering for multi-tool-call scenarios
Move synthetic user message (carrying base64 tool images) to after the
entire contiguous tool-message block instead of immediately after each
tool message. This preserves the assistant→tool→tool ordering required
by OpenAI-compatible APIs.
Also fix load_image to use generic [image: photo] placeholder so
injectPathTags can properly replace it with the actual path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(test): update load_image test for [image: photo] placeholder
The test was checking ForLLM for the media:// ref, but load_image now
emits the generic [image: photo] placeholder instead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(media): match all channel image placeholders in injectPathTags
Different channels emit different placeholder formats — Telegram/Feishu
use [image: photo], WeCom/WeChat/Line use bare [image], QQ/Discord use
[image: <filename>]. The previous string-match code only handled
[image: photo], so for the other channels the path tag was appended as
a duplicate, producing content like "[image] [image:/path]".
Switch to per-type regex that matches all generic placeholder shapes
while leaving path tags ([image:/path]) untouched. Also fixes the same
issue for [audio], [video], [file] tags. Added test coverage for the
various placeholder shapes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(media): skip path tag append for JSON content (Feishu cards/posts)
When content is structured JSON (interactive cards, post messages),
injectPathTags now skips the fallback append — only placeholder
replacement is attempted. This prevents corrupting JSON payloads
like {"schema":"2.0",...} with appended [image:/path] tags.
Adds looksLikeJSON() helper and three test cases covering JSON
objects, arrays, and an end-to-end resolveMediaRefs scenario with
Feishu card content.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(media): prepend path tags for JSON content, narrow looksLikeJSON
Two fixes from code review:
1. looksLikeJSON now only checks for '{' prefix (not '['), avoiding
false positives on regular text like "[update] see attached".
2. For JSON content (Feishu cards/posts), path tags are prepended
before the JSON instead of being silently dropped. This ensures
the LLM can discover attached images via the path tag while the
JSON payload stays valid for downstream parsing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add detection for 'unknown variant' + 'image_url' error pattern used by
DeepSeek and other strict providers when vision is not supported.
These providers reject the image_url field at the JSON schema level
rather than returning a semantic 'not supported' message.
* feat(tools): add cross-platform serial hardware tool
* feat(config): wire serial tool into runtime and dashboard
* hardware/serial: tighten validation and error handling
* hardware/serial: improve unix cancellation and timeout polling
* hardware/serial: improve windows I/O handling
* hardware/serial: fix darwin cross-compilation build
* docs(design): summarize hardware support and serial limits
* build: keep go generate on host during cross builds
* onboard: drop unrelated go generate change from serial work
* style(tools): wrap serial lines for golines
