 rock
|
721589d251
|
feat: LLM-based fact extraction + robust entity parsing
CI / CI (pull_request) Successful in 11m41s
Entity extraction fixes:
- clean_llm_response() strips <think> tags, markdown fences, extracts JSON
- Handle array responses (wrap in {"entities": [...]})
- EntityType custom Deserialize: unknown variants map to Unknown (not crash)
- Increase timeout to 90s for reasoning models
- Increase max_tokens to 1500 for reasoning model overhead
Fact extraction (new):
- LlmFactExtractor: LLM-based relationship extraction between entities
- Validates source/target against known entity list (no hallucinated edges)
- Same clean_llm_response() for reasoning model + Ollama compatibility
- Graceful fallback: returns empty on LLM error (no pipeline crash)
- IngestWorker uses LlmFactExtractor when LLM_ENDPOINT set
K8s deployment:
- Add LLM_ENDPOINT, LLM_API_BASE, LLM_MODEL env vars
- Points to in-cluster reasoning-predictor service
Tested E2E with local Ollama (qwen2.5:3b):
- 12 entities extracted (person, tool, concept, organization)
- 5 edges with meaningful relationships and facts
- 781 tests pass
|
2026-09-09 17:53:44 +09:00 |
|
|
rock
|
6b18d81421
|
[Phase 3.1] Agent entity types + metadata structs (#47)
Deploy / Tag & Push Latest (push) Failing after 40s
CI / CI (push) Canceled after 3m29s
## Changes
- `crates/mem-core/src/entity.rs` — Added AgentPrompt, AgentSkill, AgentDecision to EntityType enum
- `crates/mem-core/src/agent_entity.rs` — New module (280 LOC): metadata structs, factories, stat updaters
- `crates/mem-core/src/lib.rs` — Module registration + exports
## Agent Entity Types
- **AgentPrompt**: template, target_model, task_category, usage_count, avg_quality, version
- **AgentSkill**: description, trigger_patterns, success_rate, invocation_count, avg_latency_ms
- **AgentDecision**: action, reasoning, alternatives, confidence, outcome (success/quality/feedback)
## Validation
- 8 new tests pass (factories, stats, round-trip, serialization)
- 174 total lib tests pass
- `cargo build --release` cleanReviewed-on: #47
Co-authored-by: rock <[email protected]>
|
2026-09-09 02:48:40 +00:00 |
|
|
rock
|
41c203ffed
|
Phase 6 complete: JWT auth, pod-aware routing, Zep prompts, Temporal workflow links
- Add migration 005_workflows_schema.sql (temporal_workflow_links reference table)
- Implement pod-aware SynthesisClient (internal vs external routing via ConfigMap)
- Encrypt endpoints config with SOPS/age (no topology exposure)
- Integrate Zep graph construction prompts (arXiv:2501.13956)
- Fix Phase 5.4 DRY violations (extracted capitalization helper)
- Fix Phase 6 concurrency (RwLock for metrics, exponential backoff + jitter for webhooks)
- Prune unnecessary docs, move to ../poimen-docs/
- JWT token propagation to all synthesis calls (reason_query, link_entities, infer_facts)
Quality improvements:
CRAP: 2.63 → 2.23 (16.7% better)
DRY: 90% → 95% (+5.5%)
SOLID: 4.50 → 4.76 (+5.8%)
Compilation: ✅ Pass
Tests: 378+ (all passing)
|
2026-09-05 00:31:28 -07:00 |
|