Phase 3 — Tracks
Five execution tracks for the core memory substrate.
Phase 3 — Tracks
Track A — Schema & Migrations
Memory schema with temporal validity, multi-label categories, and HNSW-ready vector columns. Schema details are a planning baseline and may be refined during implementation.
Preferred sequencing within track: single foundation milestone; blocks Tracks B–D. Status: 3.1.1 completed (ADR-0052 / 000017).
- 3.1.1 — Memory Schema v2 (completed)
Track B — Vector Store & Embedding
Pluggable vector store interface with pgvector HNSW as the starting backend preference (replacing the earlier IVFFlat plan). Alternatives can be investigated if latency/recall measurements require it.
Preferred sequencing within track: depends on Track A schema. Status: 3.2.1 complete (ADR-0053).
- 3.2.1 — Vector Store Interface & pgvector HNSW (completed)
Track C — Write Pipeline
Memory write pipeline stages: validate → PII detect/redact → dedup → embed → near-dup → conflict detect → DB write → cache update → index. Stage order is the preferred starting sequence and can be adjusted after integration testing.
| Step | Stage | Owner |
|---|---|---|
| 1 | validate | Seam from 3.C.1 |
| 2 | PII detect/redact | 3.C.1 (ADR-0054) |
| 3 | exact dedup | 3.C.2 (ADR-0055) |
| 4 | embed | Track B client / pipeline |
| 5 | near-dup | 3.C.2 (ADR-0055) |
| 6 | conflict detect | 3.C.3 (ADR-0056) |
| 7 | DB write (+ apply supersessions / escalations) | 3.C.5 (ADR-0057) |
| 8 | cache update | 3.C.5 (write-time; 3.D.3 is read hot cache) |
| 9 | index / vector upsert | 3.C.5 |
Multi-label classification (3.C.4) is write-path logic that runs at insert time and therefore follows 3.C.5. Track C write pipeline is complete (3.C.1–3.C.5 + 3.C.4).
Preferred sequencing within track: 3.C.1 → 3.C.2 → 3.C.3 → 3.C.5 → 3.C.4 after Tracks A/B.
- 3.C.1 — PII Detection & Redaction (completed)
- 3.C.2 — Content Near-Duplicate Detection (completed)
- 3.C.3 — Temporal Conflict Detection (completed)
- 3.C.5 — Write-path Persistence & Orchestration (completed)
- 3.C.4 — Multi-Label Classification (completed)
Track D — Read/Ranking Pipeline
Semantic search read path, composite scoring with category-conditional decay, and Redis sorted-set hot cache.
Preferred sequencing within track: 3.D.1 → 3.D.2 → 3.D.3 after Track B. Status: Track D complete.
- 3.D.1 — Semantic Search Read Path (completed)
- 3.D.2 — Composite Scoring v2 (completed)
- 3.D.3 — Hot Cache (Redis Sorted Set) (completed)
Track E — Exit Gate
Security integration suite, E2E lifecycle test, retrieval-quality benchmark, ADR consolidation, and exit audit.
Preferred sequencing within track: 3.E.1 → 3.E.2 → 3.E.3 → 3.E.4 → 3.E.5 after Tracks A–D.
Status: Track E complete — phase3-exit-audit.
- 3.E.1 — Memory Security Integration Suite (complete)
- 3.E.2 — E2E Memory Lifecycle Test (complete)
- 3.E.3 — Retrieval-Quality Benchmark Sign-Off (complete)
- 3.E.4 — ADR Consolidation and Index Update (complete)
- 3.E.5 — Phase 3 Exit Audit Document (complete)
Last updated on