AskaEth/Cyrene_v2
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
38 Commits 7 Branches 0 Tags
dee48b6766df4a0cdd4ea9de5b7aec4ea8ba1539
Commit Graph
21 Commits
Author SHA1 Message Date
Aska dee48b6766 feat: add automation, reminders, notifications, msg search, session export, image analysis, host exec, PWA, Docker, E2E, CI/CD
Cyrene CI / backend (push) Has been cancelled
Details
Cyrene CI / frontend (push) Has been cancelled
Details 
- Automation: rules CRUD (in-memory store + API)
- Reminders: CRUD (in-memory store + API)
- Notifications: push interface for future push server
- Message search: API endpoint with DB-backed query
- Session export: /sessions/:id/export → Markdown
- Image analysis: API stub for multimodal LLM
- Host exec: API stub for Docker sandbox
- PWA: manifest.json + service worker
- Docker: Dockerfile + docker-compose.yml
- E2E: Playwright test scaffold
- CI/CD: GitHub Actions workflow (go test + tsc)
 2026-08-12 19:43:46 +08:00
Aska 3f9c4ca3c3 fix(prompt): prevent LLM from confusing context with user input 
- Context merged into single system message with clear delimiters
- Prefix: 「以下是系统上下文，不是用户说的话」
- Memory → 【相关记忆】, IoT → 【设备状态】
- Filter empty memories, skip raw intent data
- Persona rule: context markers are internal data, not user input
 2026-08-12 19:28:32 +08:00
Aska 585dfa1e38 fix(prompt): clean persona system prompt — remove YAML dump, filter empty subsessions 
- Persona injector: concise natural language rules, not raw YAML
- Context builder: skip empty memory, skip raw intent data
- Prompt reduced from 2000+ tokens to ~500 tokens
- LLM response quality improved (natural tone, no confusion)
 2026-08-12 19:27:12 +08:00
Aska 14a8eecfdb fix(memory): improve dedup thresholds and keyword priority 
- Dedup: OR logic with 28%/0.45 thresholds (was 25%/0.4)
- Keywords: segments first → 3-grams → 2-grams
- False positive: 10% → acceptable level
- Accuracy: 80% correct dedup, 71% real rate
 2026-08-12 19:20:14 +08:00
Aska dc3671eb8d feat(bench): add memory benchmark tool + export keywords 
- tools/memory-bench: 6 metrics (write/search/dedup/keyword/bulk/rate)
- memory: export ExtractKeywordsPublic for benchmarking
- Results: 1000+ 条/秒 write, 380µs search, 80% dedup accuracy, 71% real rate
 2026-08-12 19:15:15 +08:00
Aska 6a4887e52a feat(llm): add LLM call recording with admin panel integration 
- llm.Adapter: SetCallLogger hook for recording every API call
- llm.CallLogger: ring-buffer with Recent+Stats for admin API
- main.go: wire DeepSeek adapter to CallLogger
- Fix: single CallLogger instance for both recording and display
- Metrics: model name, duration, success/fail, tokens
- All 16 packages pass
 2026-08-12 19:10:51 +08:00
Aska 4e2e81f684 feat(trace): waterfall visualization + persona YAML sync 
- trace.Logger: Trace+Span model with 14+ hop tracking
- trace.SpanTimer: convenience API for instrumentation
- trace_adapter.go: serialize Trace+Span for frontend
- Frontend TracePage: colored waterfall bars, expand/collapse, detail popup
- persona.go: full v1 YAML parser (identity/traits/forbidden/sections)
- cyrene_persona.yaml: v1 persona config copied to v2
- Orchestrator: TraceHook + MemoryExtractor injection points
 2026-08-12 18:52:39 +08:00
Aska 47047c903c feat(memory): add LLM-driven memory extraction from conversations 
- memory/extractor: async LLM-based memory extraction from chat history
- Parses JSON lines from LLM response as memory entries
- Wire into orchestrator pipeline via PostProcess hook
- Non-blocking: runs in goroutine with 30s timeout
- Automatic dedup via existing keyword overlap logic
 2026-08-12 18:43:04 +08:00
Aska 886fcf2216 fix(memory): rewrite dedup with n-gram keyword overlap + embedder 
- Keyword extraction: 2-3 char sliding window + segment splitting
- Dedup: keyword overlap (>25%) OR Jaccard (>0.4) triggers merge
- SearchByNGrams: pgvector GIN index on keywords array
- Embedder: n-gram FNV hash (zero dep), OpenAI API with auto-fallback
- GIN index on keywords column for fast overlap search
- All tests pass
 2026-08-12 18:24:04 +08:00
Aska 9eaed2883f feat(bridge): separate bridge config from .env, web panel + hot-reload 
- BridgeConfigStore: file-backed JSON config (configs/bridge.json)
- Auto-creates config file only when user saves via admin panel
- Hot-reload: watches config file every 5s, reloads adapters live
- Admin API: GET/PUT/DELETE /api/v1/admin/bridge/config/:name
- Frontend: full CRUD page with platform type selector + toggle
- Removed bridge env vars from .env.example
 2026-08-12 17:55:15 +08:00
Aska e8b5679cf4 feat(admin): add full-chain trace and performance monitoring 
- Backend: trace.Logger ring-buffer for request chain events
- Backend: perf.Monitor with runtime.MemStats sampling every 10s
- Backend: /api/v1/admin/trace and /api/v1/admin/perf endpoints
- Frontend: TracePage — timeline with hop icons and status dots
- Frontend: PerformancePage — memory/GC bar charts + live stats
- Admin nav expanded to 11 items
 2026-08-12 17:16:33 +08:00
Aska 8420691438 feat(admin): add model config CRUD and platform bridge pages 
- Backend: ModelConfigStore with Provider/Model/Routing CRUD
- Backend: /api/v1/admin/models/config endpoints
- Frontend: ModelsPage with 3-tab editor (providers/models/routing)
- Frontend: BridgePage showing adapter status + group chat rules
- Admin nav expanded to 9 items
 2026-08-12 17:13:29 +08:00
Aska 1a80ac2a00 feat(admin): add LLM call logs, system info, plugin list pages 
- ai-core/llm: ring-buffer call logger with stats
- Gateway: /api/v1/admin/llm-calls, /system, /plugins, /sessions endpoints
- Frontend: LLMCallsPage (table + stats), SystemPage (version/plugins/sessions)
- Admin nav expanded to 7 items
 2026-08-12 16:56:52 +08:00
Aska 17ef73bcbe feat(bridge): add multi-platform bridge — QQ, Telegram, Discord, Webhook 
- platform-bridge: unified message model + Adapter interface
- qq/adapter: OBv11 WebSocket protocol with @mention detection
- telegram/discord: stub adapters with send capability
- webhook: HTTP POST receiver for generic webhook integration
- Router: message routing from platform → AI-Core → back
- Group chat rules: 500 char limit, 3s gap, silence keywords
- main.go: conditional adapter loading via env vars
 2026-08-12 12:30:55 +08:00
Aska fbb331ed4b feat(auth): replace stub auth with real JWT + bcrypt 
- RealAuthManager: JWT signing/validation + bcrypt password hashing
- MemUserStore: in-memory user store with default admin
- Register endpoint: user creation with hashed password
- Login endpoint: bcrypt verification + JWT generation
- AuthManager interface extended with Login/Register methods
 2026-08-12 12:21:36 +08:00
Aska 6811480786 feat(gateway): wire real services into Gateway API handlers 
- Router accepts full Dependencies (memory/voice/orchestrator/WShub)
- Memory API: CRUD + search endpoints with PostgreSQL persistence
- Voice API: STT/TTS endpoints
- Admin dashboard: real uptime + service status
- WebSocket chat: routes to AI-Core orchestrator pipeline
- APIAdapter bridges memory domain model to REST interface
- Smoke test: memory CRUD + session creation verified
 2026-08-12 12:04:31 +08:00
Aska 3b3e5a0697 feat(ai-core): add LLM orchestration engine 
- model: shared data types (Message, Intent, StreamToken, LLMMessage)
- persona: YAML/Raw loading + system prompt injection
- llm: OpenAI-compatible adapter with streaming + semantic cache
- context: sliding window context store with token budgeting
- subsession: parallel provider dispatch + review message parser
- orchestrator: intent analysis pipeline (IoT/greeting/chat/memory)
- background: autonomous thinking engine
- 20+ tests, build + vet clean, ~130 total tests
 2026-08-09 21:21:27 +08:00
Aska 99806fefad feat: add gateway API, voice service, WebSocket hub, and startup entry 
- services/gateway/api: net/http router with JWT auth, stub login, 6 tests
- services/gateway/ws: WebSocket hub with echo support
- services/voice: STT/TTS provider chain with fallback, 6 tests
- cmd/cyrene/main.go: single binary startup, 108 tests total
- Smoke test: health check + login verified on :8080
 2026-08-09 21:09:43 +08:00
Aska 81ebdb910c feat(memory): complete memory service with passing tests 
- model: Memory struct with categories/decay/keywords
- repository: PG CRUD + keyword search + table migration SQL
- service: dedup (Jaccard), keyword extraction, decay formula
- 7 tests (3 DB integration + 4 unit), 96 total, vet clean
 2026-08-09 20:51:01 +08:00
Aska 7295556c59 feat(services): add memory service — model, repository, service layer 
- services/memory/model: Memory struct with categories and decay
- services/memory/repository: PostgreSQL CRUD + keyword search
- services/memory/service: dedup, decay, keyword extraction
- tests coming in follow-up commit
 2026-08-09 20:50:01 +08:00
Aska 14d5d6e555 chore: init Cyrene_v2 project structure and DevDocs 
- Create directory structure for backend, frontend, deployment, tests
- .gitignore with DevDocs/ excluded from version control
- DevDocs: 00-overview, 01-cross-platform, 02-dev-constraints
- DevDocs decisions: 002-communication (NATS), 003-plugin-architecture
- DevDocs modules: ai-core analysis, gateway analysis
 2026-08-09 20:18:56 +08:00