-
- New template: content-selector with skills, train data (hunt/digest/evolve) - youtube-crawler: add workspace archive, digest_v2, evolve_v2, mock data - Update agent todo/plan/SKILL files for digester, evolver, hunter, innovator, master - Update server/routes/agent-chat.js - Update .gitignore: exclude runtime data (memory, sqlite, __pycache__, temp files)
-
- Add YouTube Data API v3 key to .env - Update start.sh to auto-load .env file on startup - Add youtube-crawler Skill template with full lifecycle - Add digester/evolver agents for YouTube crawler - Update scheduled tasks and master plan logs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
-
…day window, skip old files
-
…writes (4KB/1s), remove messages.log fallback in loadHistory
-
…to prevent EADDRINUSE
-
1. Workspace page: left file tree + right detail/editor panel - File info: name, path, size, created/modified timestamps - Three view modes: Code / Preview / Edit with save - HTML files auto-open in Preview tab (sandboxed iframe) 2. Backend APIs: - GET/PUT /:companyId/workspace/files (list + content + save) - PUT /:companyId/files/content (company file save) 3. Navbar: removed Skills/Jobs/Pipeline, added Workspace 4. All nav links open in new tabs (target=_blank)
-
- Fixed .gitignore: data/system/ prefix was missing (old paths never matched) - Removed tracked memory/, conversations/, uploads/, .tasks/ files - Only memory.md and hippocampus.md are kept (template skeleton)
-
- Added inline editing for template description and type fields - Implemented Delete Template functionality (removes both file system and registry entry) - Added confirmation safeguards for the destructive delete action
-
Architecture fix for long-running tool execution: 1. ClaudeCliProtocol: Two-tier idle timeout - Chat mode: 45s (detect API hang/silent rate limit) - Tool execution mode: 5min (Bash long tasks like pip install) - Automatically switches on tool_use_start / content_block_stop events 2. Provision API: POST /templates/:templateId/provision - Runs shell commands directly via child_process.exec - Bypasses Claude ACP entirely (no idle timeout issue) - 10min per-command timeout, security blocklist - Frontend button with prompt for custom commands 3. Template UI: Added 🔧 安装依赖 button (teal)
-
Fixed 4 hidden bugs where path.join(DATA_ROOT, "system", ...) was used instead of direct path.resolve to root-level system/: - agent-chat.js: billing log scan (line 804) and agent list scan (line 909) - company-service.js: TEMPLATES_DIR and GLOBAL_AGENTS_DIR constants - heartbeat-service.js: system agents scan directory These were missed because they used path.join with a variable (DATA_ROOT) rather than the literal string "data/system" that sed caught.