daarion-admin/microdao-daarion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
594 Commits 8 Branches 0 Tags
84cb7e51bcebc70cb3f59c0959d939a373de1450
Commit Graph

37 Commits

Author SHA1 Message Date
Apple
fe6e3d30ae feat(matrix-bridge-dagi): add operator allowlist for control commands (M3.0) 
New: app/control.py
  - ControlConfig: operator_allowlist + control_rooms (frozensets)
  - parse_control_config(): validates @user:server + !room:server formats, fail-fast
  - parse_command(): parses !verb subcommand [args] [key=value] up to 512 chars
  - check_authorization(): AND(is_control_room, is_operator) → (bool, reason)
  - Reply helpers: not_implemented, unknown_command, unauthorized, help
  - KNOWN_VERBS: runbook, status, help (M3.1+ stubs)
  - MAX_CMD_LEN=512, MAX_CMD_TOKENS=20

ingress.py:
  - _try_control(): dispatch for control rooms (authorized → audit + reply, unauthorized → audit + optional ⛔)
  - join control rooms on startup
  - _enqueue_from_sync: control rooms processed first, never forwarded to agents
  - on_control_command(sender, verb, subcommand) metric callback
  - CONTROL_UNAUTHORIZED_BEHAVIOR: "ignore" | "reply_error"

Audit events:
  matrix.control.command       — authorised command (verb, subcommand, args, kwargs)
  matrix.control.unauthorized  — rejected by allowlist (reason: not_operator | not_control_room)
  matrix.control.unknown_cmd   — authorised but unrecognised verb

Config + main:
  - bridge_operator_allowlist, bridge_control_rooms, control_unauthorized_behavior
  - matrix_bridge_control_commands_total{sender,verb,subcommand} counter
  - /health: control_channel section (enabled, rooms_count, operators_count, behavior)
  - /bridge/mappings: control_rooms + control_operators_count
  - docker-compose: BRIDGE_OPERATOR_ALLOWLIST, BRIDGE_CONTROL_ROOMS, CONTROL_UNAUTHORIZED_BEHAVIOR

Tests: 40 new → 148 total pass
Made-with: Cursor
 2026-03-05 01:50:04 -08:00
Apple
d40b1e87c6 feat(matrix-bridge-dagi): harden mixed rooms with safe defaults and ops visibility (M2.2) 
Guard rails (mixed_routing.py):
  - MAX_AGENTS_PER_MIXED_ROOM (default 5): fail-fast at parse time
  - MAX_SLASH_LEN (default 32): reject garbage/injection slash tokens
  - Unified rejection reasons: unknown_agent, slash_too_long, no_mapping
  - REASON_REJECTED_* constants (separate from success REASON_*)

Ingress (ingress.py):
  - per-room-agent concurrency semaphore (MIXED_CONCURRENCY_CAP, default 1)
  - active_lock_count property for /health + prometheus
  - UNKNOWN_AGENT_BEHAVIOR: "ignore" (silent) | "reply_error" (inform user)
  - on_routed(agent_id, reason) callback for routing metrics
  - on_route_rejected(room_id, reason) callback for rejection metrics
  - matrix.route.rejected audit event on every rejection

Config + main:
  - max_agents_per_mixed_room, max_slash_len, unknown_agent_behavior, mixed_concurrency_cap
  - matrix_bridge_routed_total{agent_id, reason} counter
  - matrix_bridge_route_rejected_total{room_id, reason} counter
  - matrix_bridge_active_room_agent_locks gauge
  - /health: mixed_guard_rails section + total_agents_in_mixed_rooms
  - docker-compose: all 4 new guard rail env vars

Runbook: section 9 — mixed room debug guide (6 acceptance tests, routing metrics, session isolation, lock hang, config guard)

Tests: 108 pass (94 → 108, +14 new tests for guard rails + callbacks + concurrency)
Made-with: Cursor
 2026-03-05 01:41:20 -08:00
Apple
a85a11984b feat(matrix-bridge-dagi): add mixed-room routing by slash/mention (M2.1) 
- mixed_routing.py: parse BRIDGE_MIXED_ROOM_MAP, route by /slash > @mention > name: > default
- ingress.py: _try_enqueue_mixed for mixed rooms, session isolation {room}:{agent}, reply tagging
- config.py: bridge_mixed_room_map + bridge_mixed_defaults fields
- main.py: parse mixed config, pass to MatrixIngressLoop, expose in /health + /bridge/mappings
- docker-compose: BRIDGE_MIXED_ROOM_MAP / BRIDGE_MIXED_DEFAULTS env vars, BRIDGE_ALLOWED_AGENTS multi-value
- tests: 25 routing unit tests + 10 ingress integration tests (94 total pass)

Made-with: Cursor
 2026-03-05 01:29:18 -08:00
Apple
79db053b38 feat(matrix-bridge-dagi): support N rooms in BRIDGE_ROOM_MAP, reject duplicate room_id (M2.0) 
Made-with: Cursor
 2026-03-05 01:21:07 -08:00
Apple
a24dae8e18 feat(matrix-bridge-dagi): add backpressure queue with N workers (H2) 
Reader + N workers architecture:
  Reader: sync_poll → rate_check → dedupe → queue.put_nowait()
  Workers (WORKER_CONCURRENCY, default 2): queue.get() → invoke → send → audit

Drop policy (queue full):
  - put_nowait() raises QueueFull → dropped immediately (reader never blocks)
  - audit matrix.queue_full + on_queue_dropped callback
  - metric: matrix_bridge_queue_dropped_total{room_id,agent_id}

Graceful shutdown:
  1. stop_event → reader exits loop
  2. queue.join() with QUEUE_DRAIN_TIMEOUT_S (default 5s) → workers finish in-flight
  3. worker tasks cancelled

New config env vars:
  QUEUE_MAX_EVENTS (default 100)
  WORKER_CONCURRENCY (default 2)
  QUEUE_DRAIN_TIMEOUT_S (default 5)

New metrics (H3 additions):
  matrix_bridge_queue_size (gauge)
  matrix_bridge_queue_dropped_total (counter)
  matrix_bridge_queue_wait_seconds histogram (buckets: 0.01…30s)

/health: queue.size, queue.max, queue.workers
MatrixIngressLoop: queue_size + worker_count properties

6 queue tests: enqueue/process, full-drop-audit, concurrency barrier,
graceful drain, wait metric, rate-limit-before-enqueue
Total: 71 passed

Made-with: Cursor
 2026-03-05 01:07:04 -08:00
Apple
a4e95482bc feat(matrix-bridge-dagi): add rate limiting (H1) and metrics (H3) 
H1 — InMemoryRateLimiter (sliding window, no Redis):
  - Per-room: RATE_LIMIT_ROOM_RPM (default 20/min)
  - Per-sender: RATE_LIMIT_SENDER_RPM (default 10/min)
  - Room checked before sender — sender quota not charged on room block
  - Blocked messages: audit matrix.rate_limited + on_rate_limited callback
  - reset() for ops/test, stats() exposed in /health

H3 — Extended Prometheus metrics:
  - matrix_bridge_rate_limited_total{room_id,agent_id,limit_type}
  - matrix_bridge_send_duration_seconds histogram (invoke was already there)
  - matrix_bridge_invoke_duration_seconds buckets tuned for LLM latency
  - matrix_bridge_rate_limiter_active_rooms/senders gauges
  - on_invoke_latency + on_send_latency callbacks wired in ingress loop

16 new tests: rate limiter unit (13) + ingress integration (3)
Total: 65 passed

Made-with: Cursor
 2026-03-05 00:54:14 -08:00
Apple
cad3663508 feat(matrix-bridge-dagi): add egress, audit integration, fix router endpoint (PR-M1.4) 
Closes the full Matrix ↔ DAGI loop:

Egress:
- invoke Router POST /v1/agents/{agent_id}/infer (field: prompt, response: response)
- send_text() reply to Matrix room with idempotent txn_id = make_txn_id(room_id, event_id)
- empty reply → skip send (no spam)
- reply truncated to 4000 chars if needed

Audit (via sofiia-console POST /api/audit/internal):
- matrix.message.received (on ingress)
- matrix.agent.replied (on successful reply)
- matrix.error (on router/send failure, with error_code)
- fire-and-forget: audit failures never crash the loop

Router URL fix:
- DAGI_GATEWAY_URL now points to dagi-router-node1:8000 (not gateway:9300)
- Session ID: stable per room — matrix:{room_localpart} (memory context)

9 tests: invoke endpoint, fallback fields, audit write, full cycle,
dedupe, empty reply skip, metric callbacks

Made-with: Cursor
 2026-03-03 08:06:49 -08:00
Apple
dbfab78f02 feat(matrix-bridge-dagi): add room mapping, ingress loop, synapse setup (PR-M1.2 + PR-M1.3) 
PR-M1.2 — room-to-agent mapping:
- adds room_mapping.py: parse BRIDGE_ROOM_MAP (format: agent:!room_id:server)
- RoomMappingConfig with O(1) room→agent lookup, agent allowlist check
- /bridge/mappings endpoint (read-only ops summary, no secrets)
- health endpoint now includes mappings_count
- 21 tests for parsing, validation, allowlist, summary

PR-M1.3 — Matrix ingress loop:
- adds ingress.py: MatrixIngressLoop asyncio task
- sync_poll → extract → dedupe → _invoke_gateway (POST /v1/invoke)
- gateway payload: agent_id, node_id, message, metadata (transport, room_id, event_id, sender)
- exponential backoff on errors (2s..60s)
- joins all mapped rooms at startup
- metric callbacks: on_message_received, on_gateway_error
- graceful shutdown via asyncio.Event
- 5 ingress tests (invoke, dedupe, callbacks, empty-map idle)

Synapse setup (docker-compose.synapse-node1.yml):
- fixed volume: bind mount ./synapse-data instead of named volume
- added port mapping 127.0.0.1:8008:8008

Synapse running on NODA1 (localhost:8008), bot @dagi_bridge:daarion.space created,
room !QwHczWXgefDHBEVkTH:daarion.space created, all 4 values in .env on NODA1.

Made-with: Cursor
 2026-03-03 07:51:13 -08:00
Apple
d8506da179 feat(matrix-bridge-dagi): add matrix client wrapper and synapse setup (PR-M1.1) 
- adds MatrixClient with send_text/sync_poll/join_room/whoami (idempotent via txn_id)
- LRU dedupe for incoming event_ids (2048 capacity)
- exponential backoff retry (max 3 attempts) for 429/5xx/network errors
- extract_room_messages: filters own messages, non-text, duplicates
- health endpoint now probes matrix_reachable + gateway_reachable at startup
- adds docker-compose.synapse-node1.yml (Synapse + Postgres for NODA1)
- adds ops/runbook-matrix-setup.md (10-step setup: DNS, config, bot, room, .env)
- 19 tests passing, no real Synapse required

Made-with: Cursor
 2026-03-03 07:38:54 -08:00
Apple
129e4ea1fc feat(platform): add new services, tools, tests and crews modules 
New router intelligence modules (26 files): alert_ingest/store, audit_store,
architecture_pressure, backlog_generator/store, cost_analyzer, data_governance,
dependency_scanner, drift_analyzer, incident_* (5 files), llm_enrichment,
platform_priority_digest, provider_budget, release_check_runner, risk_* (6 files),
signature_state_store, sofiia_auto_router, tool_governance

New services:
- sofiia-console: Dockerfile, adapters/, monitor/nodes/ops/voice modules, launchd, react static
- memory-service: integration_endpoints, integrations, voice_endpoints, static UI
- aurora-service: full app suite (analysis, job_store, orchestrator, reporting, schemas, subagents)
- sofiia-supervisor: new supervisor service
- aistalk-bridge-lite: Telegram bridge lite
- calendar-service: CalDAV calendar service with reminders
- mlx-stt-service / mlx-tts-service: Apple Silicon speech services
- binance-bot-monitor: market monitor service
- node-worker: STT/TTS memory providers

New tools (9): agent_email, browser_tool, contract_tool, observability_tool,
oncall_tool, pr_reviewer_tool, repo_tool, safe_code_executor, secure_vault

New crews: agromatrix_crew (10 modules: depth_classifier, doc_facts, doc_focus,
farm_state, light_reply, llm_factory, memory_manager, proactivity, reflection_engine,
session_context, style_adapter, telemetry)

Tests: 85+ test files for all new modules
Made-with: Cursor
 2026-03-03 07:14:14 -08:00
Apple
8879da1e7f feat(sofiia-console): add auto-evidence and post-review generation from runbook runs 
- adds runbook_artifacts.py: server-side render of release_evidence.md and
  post_review.md from DB step results (no shell); saves to
  SOFIIA_DATA_DIR/release_artifacts/<run_id>/
- evidence: auto-fills preflight/smoke/script outcomes, step table, timestamps
- post_review: auto-fills metadata, smoke results, incidents from step statuses;
  leaves [TODO] markers for manual observation sections
- adds POST /api/runbooks/runs/{run_id}/evidence and /post_review endpoints
- updates runbook_runs.evidence_path in DB after render
- adds 11 tests covering file creation, key sections, TODO markers, 404s, API

Made-with: Cursor
 2026-03-03 05:07:52 -08:00
Apple
0603184524 feat(sofiia-console): add safe script executor for allowlisted runbook steps 
- adds safe_executor.py: REPO_ROOT confinement, strict script allowlist,
  env key allowlist (STRICT/SOFIIA_URL/BFF_A/BFF_B/NODE_ID/AGENT_ID),
  stdin=DEVNULL, 8KB output cap, timeout clamp (max 300s), non-root warn
- integrates script action_type into runbook_runner: next_step handles
  http_check and script branches; running_as_root -> step_status=warn
- extends runbook_parser: rehearsal-v1 now includes 3 built-in script steps
  (preflight, idempotency smoke, generate evidence) after http_checks
- adds tests/test_sofiia_safe_executor.py: 12 tests covering path traversal,
  absolute path, non-allowlist, env drop, timeout, exit_code, mocked subprocess

Made-with: Cursor
 2026-03-03 04:57:22 -08:00
Apple
ad8bddf595 feat(sofiia-console): add guided runbook runner with http checks and audit integration 
adds runbook_runs/runbook_steps state machine

parses markdown runbooks into guided steps

supports allowlisted http_check (health/metrics/audit)

integrates runbook execution with audit trail

exposes authenticated runbook runs API

Made-with: Cursor
 2026-03-03 04:49:19 -08:00
Apple
4db1774a34 feat(sofiia-console): rank runbook search results with bm25 
FTS path: score = bm25(docs_chunks_fts), ORDER BY score ASC; LIKE fallback: score null; test asserts score key present

Made-with: Cursor
 2026-03-03 04:36:52 -08:00
Apple
63fec4371a feat(sofiia-console): add runbooks index status endpoint 
GET /api/runbooks/status returns docs_root, indexed_files, indexed_chunks, last_indexed_at, fts_available; docs_index_meta table and set on rebuild

Made-with: Cursor
 2026-03-03 04:35:18 -08:00
Apple
ef3ff80645 feat(sofiia-console): add docs index and runbook search API (FTS5) 
adds SQLite docs index (files/chunks + FTS5) and CLI rebuild

exposes authenticated runbook search/preview/raw endpoints

Made-with: Cursor
 2026-03-03 04:26:34 -08:00
Apple
e2c2333b6f feat(sofiia-console): protect audit endpoint with admin token 
Made-with: Cursor
 2026-03-02 09:42:10 -08:00
Apple
11e0ba7264 feat(sofiia-console): add audit query endpoint with cursor pagination 
Made-with: Cursor
 2026-03-02 09:36:11 -08:00
Apple
3246440ac8 feat(sofiia-console): add audit trail for operator actions 
Made-with: Cursor
 2026-03-02 09:29:14 -08:00
Apple
9b89ace2fc feat(sofiia-console): add rate limiting for chat send (per-chat and per-operator) 
Made-with: Cursor
 2026-03-02 09:24:21 -08:00
Apple
9f085509dd test(sofiia-console): cover redis idempotency backend 
Made-with: Cursor
 2026-03-02 09:08:54 -08:00
Apple
0b30775ac1 feat(sofiia-console): add structured json logging for chat ops 
Made-with: Cursor
 2026-03-02 08:24:54 -08:00
Apple
98555aa483 test(sofiia-console): add multi-node e2e routing test 
Made-with: Cursor
 2026-03-02 08:18:59 -08:00
Apple
e504df7dfa feat(sofiia-console): harden cursor pagination with tie-breaker 
Version cursor payloads and keep backward compatibility while adding dedicated tie-breaker regression coverage for equal timestamps to prevent pagination duplicates and gaps.

Made-with: Cursor
 2026-03-02 08:12:19 -08:00
Apple
0c626943d6 refactor(sofiia-console): extract idempotency store abstraction 
Move idempotency TTL/LRU logic into a dedicated store module with a swap-ready interface and wire chat send flow to use store get/set semantics without changing API behavior.

Made-with: Cursor
 2026-03-02 08:11:13 -08:00
Apple
b9c548f1a6 test(sofiia-console): cover noda2 router_url fallback in legacy local run 
Add regression coverage for router URL resolution when NODE_ID is unset and ROUTER_URL is present, and verify explicit NODES_NODA2_ROUTER_URL keeps higher priority.

Made-with: Cursor
 2026-03-02 08:00:35 -08:00
Apple
93f94030f4 feat(sofiia-console): expose /metrics and add basic ops counters 
Expose Prometheus-style metrics endpoint and add counters for send requests, idempotency replays, and cursor pagination calls, including a safe in-process fallback exposition when prometheus_client is unavailable.

Made-with: Cursor
 2026-03-02 04:52:04 -08:00
Apple
5a886a56ca test(sofiia-console): cover idempotency and cursor pagination contracts 
Add focused API contract tests for chat idempotency, cursor pagination, and node routing behavior using isolated local fixtures and mocked upstream inference.

Made-with: Cursor
 2026-03-02 04:03:30 -08:00
Apple
9a36020316 P3.5-P3.7: 2-layer inventory, capability routing, STT/TTS adapters, Dev Contract 
NCS:
- _collect_worker_caps() fetches capability flags from node-worker /caps
- _derive_capabilities() merges served model types + worker provider flags
- installed_artifacts replaces inventory_only (disk scan with DISK_SCAN_PATHS env)
- New endpoints: /capabilities/caps, /capabilities/installed

Node Worker:
- STT_PROVIDER, TTS_PROVIDER, OCR_PROVIDER, IMAGE_PROVIDER env flags
- /caps endpoint returns capabilities + providers for NCS aggregation
- STT adapter (providers/stt_mlx_whisper.py) — remote + local mode
- TTS adapter (providers/tts_mlx_kokoro.py) — remote + local mode
- OCR handler via vision_prompted (ollama_vision with OCR prompt)
- NATS subjects: node.{id}.stt/tts/ocr/image.request

Router:
- POST /v1/capability/{stt,tts,ocr,image} — capability-based offload routing
- GET /v1/capabilities — global view with capabilities_by_node
- require_fresh_caps(ttl) preflight guard
- find_nodes_with_capability(cap) + load-based node selection

Ops:
- ops/fabric_snapshot.py — full runtime snapshot collector
- ops/fabric_preflight.sh — quick check + snapshot save + diff
- docs/fabric_contract.md — Dev Contract v0.1 (preflight-first)
- tests/test_fabric_contract.py — CI enforcement (6 tests)

Made-with: Cursor
 2026-02-27 05:24:09 -08:00
Apple
a605b8c43e P3.1: GPU/Queue-aware routing — NCS metrics + scoring-based model selection 
NCS (services/node-capabilities/metrics.py):
- NodeLoad: inflight_jobs, queue_depth, concurrency_limit, estimated_wait_ms,
  cpu_load_1m, mem_pressure (macOS + Linux), rtt_ms_to_hub
- RuntimeLoad: per-runtime healthy, p50_ms, p95_ms from rolling 50-sample window
- POST /capabilities/report_latency for node-worker → NCS reporting
- NCS fetches worker metrics via NODE_WORKER_URL

Node Worker:
- GET /metrics endpoint (inflight, concurrency, latency buffers)
- Latency tracking per job type (llm/vision) with rolling buffer
- Fire-and-forget latency reporting to NCS after each successful job

Router (model_select v3):
- score_candidate(): wait + model_latency + cross_node_penalty + prefer_bonus
- LOCAL_THRESHOLD_MS=250: prefer local if within threshold of remote
- ModelSelection.score field for observability
- Structured [score] logs with chosen node, model, and score breakdown

Tests: 19 new (12 scoring + 7 NCS metrics), 36 total pass
Docs: ops/runbook_p3_1.md, ops/CHANGELOG_FABRIC.md

No breaking changes to JobRequest/JobResponse or capabilities schema.

Made-with: Cursor
 2026-02-27 02:55:44 -08:00
Apple
c4b94a327d P2.2+P2.3: NATS offload node-worker + router offload integration 
Node Worker (services/node-worker/):
- NATS subscriber for node.{NODE_ID}.llm.request / vision.request
- Canonical JobRequest/JobResponse envelope (Pydantic)
- Idempotency cache (TTL 10min) with inflight dedup
- Deadline enforcement (DEADLINE_EXCEEDED on expired jobs)
- Concurrency limiter (semaphore, returns busy)
- Ollama + Swapper vision providers

Router offload (services/router/offload_client.py):
- NATS req/reply with configurable retries
- Circuit breaker per node+type (3 fails/60s → open 120s)
- Concurrency semaphore for remote requests

Model selection (services/router/model_select.py):
- exclude_nodes parameter for circuit-broken nodes
- force_local flag for fallback re-selection
- Integrated circuit breaker state awareness

Router /infer pipeline:
- Remote offload path when NCS selects remote node
- Automatic fallback: exclude failed node → force_local re-select
- Deadline propagation from router to node-worker

Tests: 17 unit tests (idempotency, deadline, circuit breaker)
Docs: ops/offload_routing.md (subjects, envelope, verification)
Made-with: Cursor
 2026-02-27 02:44:05 -08:00
Apple
dfc0ef1ceb runtime: sync router/gateway/config policy and clan role registry 2026-02-19 00:14:06 -08:00
Apple
ef3473db21 snapshot: NODE1 production state 2026-02-09 
Complete snapshot of /opt/microdao-daarion/ from NODE1 (144.76.224.179).
This represents the actual running production code that has diverged
significantly from the previous main branch.

Key changes from old main:
- Gateway (http_api.py): expanded from ~40KB to 164KB with full agent support
- Router: new /v1/agents/{id}/infer endpoint with vision + DeepSeek routing
- Behavior Policy: SOWA v2.2 (3-level: FULL/ACK/SILENT)
- Agent Registry: config/agent_registry.yml as single source of truth
- 13 agents configured (was 3)
- Memory service integration
- CrewAI teams and roles

Excluded from snapshot: venv/, .env, data/, backups, .tgz archives

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-09 08:46:46 -08:00
Apple
134c044c21 feat: Behavior Policy v1 - Silent-by-default + Short-first + Media-no-comment 
NODA1 agents now:
- Don't respond to broadcasts/posters/announcements without direct mention
- Don't respond to media (photo/link) without explicit question
- Keep responses short (1-2 sentences by default)
- No emoji, no "ready to help", no self-promotion

Added:
- behavior_policy.py: detect_directed_to_agent(), detect_broadcast_intent(), should_respond()
- behavior_policy_v1.txt: unified policy block for all prompts
- Pre-LLM check in http_api.py: skip Router call if should_respond=False
- NO_OUTPUT handling: don't send to Telegram if LLM returns empty
- Updated all 9 agent prompts with Behavior Policy v1
- Unit and E2E tests for 5 acceptance cases
 2026-02-04 09:03:14 -08:00
Apple
bca81dc719 feat: Node Self-Healing, DAGI Audit, Agent Prompts, Infra Invariants 
### Backend (city-service)
- Node Registry + Self-Healing API (migration 039)
- Improved get_all_nodes() with robust fallback for node_registry/node_cache
- Agent Prompts Runtime API for DAGI Router integration
- DAGI Router Audit endpoints (phantom/stale detection)
- Node Agents API (Guardian/Steward)
- Node metrics extended (CPU/GPU/RAM/Disk)

### Frontend (apps/web)
- Node Directory with improved error handling
- Node Cabinet with metrics cards
- DAGI Router Card component
- Node Metrics Card component
- useDAGIAudit hook

### Scripts
- check-invariants.py - deploy verification
- node-bootstrap.sh - node self-registration
- node-guardian-loop.py - continuous self-healing
- dagi_agent_audit.py - DAGI audit utility

### Migrations
- 034: Agent prompts seed
- 035: Agent DAGI audit
- 036: Node metrics extended
- 037: Node agents complete
- 038: Agent prompts full coverage
- 039: Node registry self-healing

### Tests
- test_infra_smoke.py
- test_agent_prompts_runtime.py
- test_dagi_router_api.py

### Documentation
- DEPLOY_CHECKLIST_2024_11_30.md
- Multiple TASK_PHASE docs
 2025-11-30 13:52:01 -08:00
Apple
1ed1181105 feat: add RAG quality metrics, optimized prompts, and evaluation tools 
Optimized Prompts:
- Create utils/rag_prompt_builder.py with citation-optimized prompts
- Specialized for DAO tokenomics and technical documentation
- Proper citation format [1], [2] with doc_id, page, section
- Memory context integration (facts, events, summaries)
- Token count estimation

RAG Service Metrics:
- Add comprehensive logging in query_pipeline.py
- Log: question, doc_ids, scores, retrieval method, timing
- Track: retrieval_time, total_query_time, documents_found, citations_count
- Add metrics in ingest_pipeline.py: pages_processed, blocks_processed, pipeline_time

Router Improvements:
- Use optimized prompt builder in _handle_rag_query()
- Add graceful fallback: if RAG unavailable, use Memory only
- Log prompt token count, RAG usage, Memory usage
- Return detailed metadata (rag_used, memory_used, citations_count, metrics)

Evaluation Tools:
- Create tests/rag_eval.py for systematic quality testing
- Test fixed questions with expected doc_ids
- Save results to JSON and CSV
- Compare RAG Service vs Router results
- Track: citations, expected docs found, query times

Documentation:
- Create docs/RAG_METRICS_PLAN.md
- Plan for Prometheus metrics collection
- Grafana dashboard panels and alerts
- Implementation guide for metrics
 2025-11-16 05:12:19 -08:00
Apple
382e661f1f feat: complete RAG pipeline integration (ingest + query + Memory) 
Parser Service:
- Add /ocr/ingest endpoint (PARSER → RAG in one call)
- Add RAG_BASE_URL and RAG_TIMEOUT to config
- Add OcrIngestResponse schema
- Create file_converter utility for PDF/image → PNG bytes
- Endpoint accepts file, dao_id, doc_id, user_id
- Automatically parses with dots.ocr and sends to RAG Service

Router Integration:
- Add _handle_rag_query() method in RouterApp
- Combines Memory + RAG → LLM pipeline
- Get Memory context (facts, events, summaries)
- Query RAG Service for documents
- Build prompt with Memory + RAG documents
- Call LLM provider with combined context
- Return answer with citations

Clients:
- Create rag_client.py for Router (query RAG Service)
- Create memory_client.py for Router (get Memory context)

E2E Tests:
- Create e2e_rag_pipeline.sh script for full pipeline test
- Test ingest → query → router query flow
- Add E2E_RAG_README.md with usage examples

Docker:
- Add RAG_SERVICE_URL and MEMORY_SERVICE_URL to router environment
 2025-11-16 05:02:14 -08:00