singularity/singularity-forge
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

docs: clarify memory-relations.ts is storage-only today

Browse source 
The architecture.md entry implied memory-relations.ts contributes to
ranking ("knowledge-graph edges between memories"). The read consumer
doesn't exist yet — getRelevantMemoriesRanked uses cosine + static
score, not graph traversal. Relations are written via /sf memory
import / createMemoryRelation but never read for ranking.

Updated the description so a contributor reading this file knows the
graph-traversal pipeline is the next logical extension, not something
that currently runs.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mikael Hugo 2026-05-02 23:52:38 +02:00
parent 0426e61cea
commit 23c5de38bf
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/dev/architecture.md
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) |
| `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-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 |