## Changes ### Entity Extraction - Switch from WikiLinkFallbackExtractor to LlmEntityExtractor when LLM_ENDPOINT set - `clean_llm_response()`: strips `<think>` tags, markdown fences, extracts JSON - Handle array responses (Ollama returns `[...]` not `{entities: [...]}`) - EntityType custom Deserialize: unknown variants → Unknown (no crash) - Increase timeout 30s→90s, max_tokens 500→1500 for reasoning models - Graceful reflection fallback: keep entities if verification fails ### Fact Extraction (NEW) - LlmFactExtractor: LLM-based relationship extraction between entity pairs - Validates source/target against known entity list (drops hallucinated edges) - Same robust JSON cleaning for reasoning models + Ollama - IngestWorker auto-selects LLM vs Simple based on LLM_ENDPOINT env ### K8s Deployment - Add `command: ["/app/mem"]` (fix args replacing CMD) - Add LLM_ENDPOINT, LLM_MODEL env vars for in-cluster LLM ## E2E Tested (local Ollama qwen2.5:3b) - 12 entities extracted (person, tool, concept, organization) - 5 edges with relationships and facts - 781 tests pass ## Zep Paper Alignment (§2.2) - Entity extraction + resolution (§2.2.1) - Fact extraction between entity pairs (§2.2.2) - Temporal edge invalidation ready (t_valid/t_invalid schema) - Reflection verification (§2.2.1, graceful fallback) --------- Co-authored-by: rock <[email protected]> Reviewed-on: #48 Co-authored-by: poimen <[email protected]>
## Problem 8 integration test files failed to compile due to: 1. Ambiguous float types (Rust 2024+ stricter inference) 2. chrono 0.4 API change (`with_hour` removed) 3. Missing `sqlx` + `base64` in `[dev-dependencies]` 4. `<` parsed as generics instead of comparison 5. Incorrect assertion (3^5=243 > 100) ## Fix - Added `f32`/`f64` type annotations to vec declarations and bindings - Replaced `with_hour(0)` with `date_naive().and_hms_opt(0,0,0).unwrap().and_utc()` - Added `sqlx` + `base64` to `[dev-dependencies]` - Wrapped comparison in parens - Fixed assertion: nodes=100 → nodes=1000 ## Validation - `cargo build --release` clean - `cargo test` — 20 test suites, 0 failures - 10 files changed, 46 insertions, 42 deletionsReviewed-on: #46 Co-authored-by: rock <[email protected]>
- Enable docker build, sha extraction on PRs (validate Dockerfile) - Add SOPS encrypted memory-agent credentials - Plan 15 tasks: 5 memory service + 10 temporal workflow - Milestone: monitoring-agent (due 2025-03-15) - Ready: Forgejo API token needed for PR automation ``` Co-authored-by: rock <[email protected]>