# ruflo v3.38.7 — v3.38.7 — HNSW status honesty fix, cache-fingerprint follow-up

- Product: ruflo (https://whatsnew.fyi/product/ruflo)
- Vendor: ruflo
- Date: 2026-08-12
- Version: v3.38.7
- Original notes: https://github.com/ruvnet/ruflo/releases/tag/v3.38.7
- Permalink: https://whatsnew.fyi/product/ruflo/releases/v3.38.7

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **fixed** — consolidate()'s graph-state.json write now includes the contentFingerprint stamp so that init()'s cache-hit gate correctly detects cache matches across consolidate/restart boundaries
- **fixed** — getHNSWStatus() and bridgeGetHNSWStatus() now accurately report whether HNSW acceleration is in use instead of unconditionally reporting available: true
- **changed** — Renamed bridgeSearchHNSW, bridgeAddToHNSW, and bridgeGetHNSWStatus to bridgeSearchBruteForceCosine, bridgeAddEmbedding, and bridgeGetVectorSearchStatus to reflect their actual implementations
- **changed** — Vector search status functions now expose an algorithm field indicating 'hnsw' or 'brute-force-cosine'
- **changed** — MCP memory tool responses now report the actual search algorithm in the backend field instead of the hardcoded value 'sql.js + HNSW'

##### Fixes

**#2920 (follow-up) — `consolidate()`'s graph write was missing the `contentFingerprint` stamp that `init()`'s cache-hit gate checks.** The v3.38.6 fix made `consolidate()` (the session-end path) rebuild `graph-state.json` unconditionally, but that write never included `contentFingerprint` — only `init()`'s own write did. So every `init()` immediately following a `consolidate()` saw `nodeCount` match but `contentFingerprint` `undefined !== <real hash>`, missed the cache, and did a full rebuild even with zero content changes. Fail direction was safe (extra rebuilds, never stale data), so it didn't block v3.38.6 — but it meant the 60s graph cache never actually fired across a consolidate/restart boundary.

**#2922 — the memory bridge's brute-force cosine search was misreported as HNSW-accelerated.** `getHNSWStatus()` returned `available: true` whenever the AgentDB v3 bridge was loaded, regardless of whether an HNSW index was actually in the request path — the bridge's default search is a full-table SELECT + brute-force cosine similarity loop that never touches `@ruvector/core`. Same issue in `bridgeGetHNSWStatus` (unconditional `available: true`) and in three misleadingly-named functions that do no HNSW work: `bridgeSearchHNSW`, `bridgeAddToHNSW`, `bridgeGetHNSWStatus` — renamed to `bridgeSearchBruteForceCosine`, `bridgeAddEmbedding`, `bridgeGetVectorSearchStatus`. Both status functions now expose an `algorithm: 'hnsw' | 'brute-force-cosine'` field. The `memory_stats` MCP tool response (and 6 others) previously hardcoded `backend: 'sql.js + HNSW'` regardless of which path ran — now reports the real algorithm.

Note: this changes the *values* returned in the `backend` field of 7 MCP memory tool responses (`memory_store`, `memory_retrieve`, `memory_search`, etc.) from the previous hardcoded `'sql.js + HNSW'` to an accurate value — an observable but non-breaking change (the field's type and presence are unchanged).

Actually wiring `AgentDBBackend`'s real HNSW implementation into the bridge's default search path is a larger architectural question, tracked as the remaining open scope on #2922.

##### Links

- PR: [#3003](https://github.com/ruvnet/ruflo/pull/3003) (#2920 follow-up)
- PR: [#3006](https://github.com/ruvnet/ruflo/pull/3006) (#2922, re-opened after #3004 was auto-closed by a base-branch deletion)
- Filed: [#3005](https://github.com/ruvnet/ruflo/issues/3005) — a suspected root-cause bug in `helper-refresh.ts`'s self-heal path, discovered while working this release
- Previous release: [v3.38.6](https://github.com/ruvnet/ruflo/releases/tag/v3.38.6)