docs: memory-relations.ts is now ranker-live

Updates 23c5de38b (which flagged the table as storage-only) to reflect
that 55b14c3f7 wired the ranker consumer (graph-boost in
getRelevantMemoriesRanked) and b9bff3762 wired the writer
(co-extraction linkage in applyMemoryActions). The graph-aware
pipeline is now end-to-end live, with named relation types,
auto-linking confidence (0.5), intra-pool boost, and damping (0.4).

Honest description for contributors reading top-down.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mikael Hugo 2026-05-03 00:13:56 +02:00
parent b9bff37623
commit a37737c4af

View file

@ -167,7 +167,7 @@ Phase skipping (from token profile) gates steps 2-3: if a phase is skipped, the
| `memory-store.ts` | Persistent memory store for cross-session knowledge; query-aware ranking |
| `memory-embeddings.ts` | Vector storage + cosine ranking + agent_end backfill driver |
| `memory-embeddings-llm-gateway.ts` | OpenAI-shaped /v1/embeddings + /v1/rerank adapter for the inference-fabric llm-gateway (env-driven; opt-in via `SF_LLM_GATEWAY_KEY`) |
| `memory-relations.ts` | Knowledge-graph edges between memories (typed relations). Storage + import/export wired; no ranker consumer yet — the ranking pipeline currently uses cosine + static score, not graph traversal. |
| `memory-relations.ts` | Knowledge-graph edges between memories (typed relations: `related_to`, `depends_on`, `contradicts`, `elaborates`, `supersedes`). Memory-extraction batches auto-link co-extracted memories with `related_to` (confidence 0.5). `getRelevantMemoriesRanked` walks the cosine top-N's edges and applies a one-pass score boost (intra-pool, damping=0.4) so cohort memories surface together. |
| `memory-source-store.ts` | Raw source rows preserved separately from extracted memories (idempotent re-extraction) |
| `queue-order.ts` | Milestone queue ordering |
| `context-masker.ts` | Context masking for model routing optimization |