- Convert 20 tool definition files to import Type/AgentTool from
@openchatlab/node-runtime instead of direct pi-* packages
- Migrate compression, summary, RAG, LLM config, and IPC modules
to use node-runtime re-exports (completeSimple, streamSimple, etc.)
- Remove @mariozechner/pi-agent-core and @mariozechner/pi-ai from
root package.json — now only node-runtime depends on them directly
- Electron is now fully decoupled from pi-* direct imports
- Add session index endpoints (generate-index, clear-index) with writable db
- Add window.sessionApi shims for web mode (getStats, generate, getSessions, etc.)
- Fix CORS: add Vite dev proxy for chatlab.fun, centralize CHATLAB_SITE_BASE
- Guard DemoImportButton: show fallback message in web mode
- Use tsx watch for dev:serve hot-reloading
- Reorganize dev scripts: dev:app (web frontend), dev:serve (backend), dev:web (both)
- dev: Electron only (renderer port 3400, unchanged)
- dev:app: Web frontend only (port 3100)
- dev:serve: Backend only (chatlab serve, default port 3110)
- dev:web: Web frontend + backend auto-start (3100 + 3110)
- Revert electron.vite.config.ts to original (no extra plugins)
- chatlabServePlugin gated by CHATLAB_AUTO_SERVE env var
Phase 3A.2: Create vite.web.config.mts for building the CLI serve
Web SPA independently from the Electron build pipeline.
- __IS_ELECTRON__ = false, __IS_BROWSER_STANDALONE__ = false
- Output to dist-web/ (gitignored)
- Dev proxy: /_web and /api -> localhost:3400 (chatlab serve)
- Resolve aliases for @electron/shared and @electron/preload
(type-only imports, erased at build time)
- npm scripts: dev:web, build:web
- Same manualChunks strategy as Electron renderer build
digua
n-WN