 poimen
|
6ef6663965
|
fix: resolve all 3 critical blockers in PR #13
CI / CI (pull_request) Successful in 4m4s
1. PersistSynthesisActivity - Error propagation (FIXED)
- Was: Swallowed errors, returned success on failure
- Now: Collects errors, returns them (fail-safe semantics)
- Prevents data loss on persistence failures
2. ExtractFactsActivity - Input validation (FIXED)
- Was: No validation on subject/object length
- Now: Validates non-empty, truncates to 500 chars
- Prevents garbage extraction and infinite object sizes
3. DetectContradictionsActivity & PersistSynthesis - Test coverage (FIXED)
- Added tests for validation logic
- TestExtractFacts_WithValidation: Verifies truncation
- TestExtractFacts_SkipsEmpty: Verifies empty skipping
- TestPersistSynthesis_EmptyInput: Verifies structure
All tests passing (10/10 synthesis tests):
✅ Entity extraction (4 tests)
✅ Fact extraction (3 tests)
✅ Helper functions (3 tests)
Fixes:
- PersistSynthesisActivity: errors collected + returned
- ExtractFactsActivity: subject/object validated + truncated
- Tests: Added validation and truncation coverage
No breaking changes. Production-ready after deployment.
|
2026-09-08 17:44:07 -07:00 |
|
|
poimen
|
5342de37cc
|
feat(phase-2.2): synthesis activities (5 activities)
Activities for the synthesis workflow pipeline:
1. ChunkAndEmbedActivity — deterministic chunk ID + ingest via memory service
2. ExtractEntitiesActivity — wiki-link, proper noun, technical term extraction
3. ExtractFactsActivity — verb pattern matching (uses/runs/has/is/depends_on)
4. DetectContradictionsActivity — query existing facts + pre-filter contradictions
5. PersistSynthesisActivity — save entities + facts to memory service
Entity extraction patterns:
- [[WikiLinks]] → 0.95 confidence
- ProperNouns → 0.70 confidence
- TECHNICAL_TERMS/camelCase → 0.65 confidence
- Deduplication across patterns
Fact extraction:
- 6 verb patterns (uses, runs_on, has, is, depends_on, connects_to)
- Confidence boost when subject/object are known entities
Contradiction detection:
- Query memory service for existing facts about same subject
- Pre-filter: subject match + different object
- Severity: low/medium/high based on similarity score
- Auto-resolve low severity, queue review for medium/high
Tests: 10 pass (wiki links, proper nouns, tech terms, dedup,
verb patterns, empty text, contradicts, contains, common, classify)
Build: clean, 35 packages pass
|
2026-09-08 17:38:48 -07:00 |
|