The script expected field names (team_status, modules, next_step, waiting_for,
last_synced) that didn't match the actual Notion-synced data (team, module,
current, waiting, last_sync). Added a data normalization step after reading
JSON files to bridge the gap. Also handles nested collaborators.json format
and missing tech_routing/server_info/os fields gracefully.
Co-authored-by: qinfendebingshuo <207279273+qinfendebingshuo@users.noreply.github.com>
- Require PALACE_SAVE_KEY env var in production (fail-fast)
- Add try-catch to deleteSave for robustness
Co-authored-by: qinfendebingshuo <207279273+qinfendebingshuo@users.noreply.github.com>
- Fix email validation JSDoc comment in chat.js
- Add explicit format validation for devId/project in preview routes
- Sanitize contact field input in build route
- Add detailed token estimation comment in memory-injector
- Add warning log when ws module is not available
Co-authored-by: qinfendebingshuo <207279273+qinfendebingshuo@users.noreply.github.com>
- chat.html: Enhanced modal with email+contact fields, split-screen HTML structure,
resizer divider, preview panel with status bar and iframe
- chat.js: Email validation (frontend regex), email prefill on repeat visits,
split-screen enterDevMode(), draggable resizer with touch support,
preview panel status updates, WebSocket connection for build progress
- style.css: Split-screen dev-mode layout, resizer styles, preview panel styles
with status indicators (waiting/building/done/error), modal field styles
- backend: Preview API route, WebSocket server for progress push,
enhanced build route with email validation and broadcast,
enhanced email template with file list and brand signature
Co-authored-by: qinfendebingshuo <207279273+qinfendebingshuo@users.noreply.github.com>
- Add profile-learner.js for auto user profile learning
- Add knowledge-extractor.js for knowledge auto-extraction
- Add pattern-analyzer.js for pattern recognition
- Add evolution-logger.js for evolution event logging
- Add memory-injector.js with 5-layer system prompt
- Update model-config.json with context_window_target: 200000
- Update model-router.js to prioritize 200k+ models
- Update persona-engine.js with knowledge/pattern queries
- Update code-generator.js with post-build evolution triggers
- Update memory-manager.js with updateProfile/autoExtractKnowledge
- Update chat route with auto profile update after each conversation
- Add brain JSON structures for knowledge-base, pattern-library, evolution-log, quality-scores
Co-authored-by: qinfendebingshuo <207279273+qinfendebingshuo@users.noreply.github.com>
github-actions[bot]
铸渊 (ZhùYuān)
bingshuo-neural-system
冰朔
Awen
zhuyuan-bot
copilot-swe-agent[bot]
飞毛嘴帅气爱