ruvnet-brain 4.3.20 → 4.3.25

package/README.md

@@ -1,4 +1,4 @@
-Updated: 2026-09-07 11:22:00 EDT | Version 4.3.10
+Updated: 2026-09-11 08:00:00 EDT | Version 4.3.21
 Created: 2026-06-29 22:36:38 EDT
 
 <div align="center">
@@ -7,7 +7,7 @@ Created: 2026-06-29 22:36:38 EDT
 
 # 🧠 RuvNet Brain
 
-### 🧠 RuvNet Brain — [![RuvNet Brain version 4.3.20 — updated 2026-07-30 03:24 EDT](https://img.shields.io/badge/version_4.3.20-updated_2026--07--30_03:24_EDT-1E90FF?style=for-the-badge&labelColor=0757BA)](https://github.com/stuinfla/ruvnet-brain/blob/main/plugin/.claude-plugin/plugin.json)
+### 🧠 RuvNet Brain — [![RuvNet Brain version 4.3.25 — updated 2026-07-30 03:24 EDT](https://img.shields.io/badge/version_4.3.25-updated_2026--07--30_03:24_EDT-1E90FF?style=for-the-badge&labelColor=0757BA)](https://github.com/stuinfla/ruvnet-brain/blob/main/plugin/.claude-plugin/plugin.json)
 
 **A portable, source-grounded brain over Reuven Cohen's (rUv's) RuvNet stack — delivered as a Claude Code plugin that makes Claude _use_ the stack instead of fighting it.**
 
@@ -47,7 +47,7 @@ safe inverse must not be advertised as a one-click undo. See the
 [![explainer](https://img.shields.io/badge/▶%20see%20it%20live-isovision.ai%2Fruvnet--brain-e8a13a?style=flat-square)](https://isovision.ai/ruvnet-brain/)
 [![license](https://img.shields.io/badge/license-MIT-8ecae6?style=flat-square)](LICENSE)
 [![grounded](https://img.shields.io/badge/answers-cited%20rUv%20source-333?style=flat-square)](#testing--proof)
-[![coverage](https://img.shields.io/badge/coverage-41%25%20of%20ALL%20source%20·%20honest-b58900?style=flat-square)](#testing--proof)
+[![coverage](https://img.shields.io/badge/coverage-42%25%20of%20ALL%20source%20·%20honest-b58900?style=flat-square)](#testing--proof)
 
 > **One Brain generation everywhere.** npm, the GitHub tag/release, bundle manifests, source metadata, and checksum-bound RVF generations must share the same product version. Headline claims are regenerated and checked by the claims ledger (`scripts/claims-verify.mjs`); other numbers below are hand-stamped and dated:
 > - **`plugin`** (badge above) — the Claude Code plugin itself: SKILL.md, the grounding hooks, the MCP server. Read live from [`plugin/.claude-plugin/plugin.json`](plugin/.claude-plugin/plugin.json). Updates often — this is where behavior fixes land.
@@ -525,7 +525,7 @@ node plugin/test/run-tests.mjs                    # full plugin QA over real JSO
 | **L4 "orchestrate"** | **downgraded — measures speech, not obedience** | L4 asserts the hook's own injected prose contains required words (`must: ['take the wheel','SPARC','swarm',…]`). That proves **the brain spoke**. It cannot fail when the advice is read and ignored — which is the failure this product exists to prevent. Counterfactual replay against a brain-off control (ADR-058 §D4) is what will earn this row back |
 | **Plugin QA** | **60 / 60** | manifests, hook firing, MCP `initialize`/`tools/list`, capability battery |
 | **Clean-room install** | **3 / 3** | download the published bundle fresh → unzip → query → grounded, cited answers |
-| **Unit tests** | **3,035 passing, 161 todo** · 41% of ALL source covered | `npm run test:cov` regenerates both — the coverage floor fails CI if it slips (`claims:verify` re-derives the %, it is not a hand-typed badge). 41% is the honest number over every shipped file; the previous "75%" measured a hand-picked 8-file subset |
+| **Unit tests** | **3,035 passing, 161 todo** · 42% of ALL source covered | `npm run test:cov` regenerates both — the coverage floor fails CI if it slips (`claims:verify` re-derives the %, it is not a hand-typed badge). 42% is the honest number over every shipped file; the previous "75%" measured a hand-picked 8-file subset |
 | **Grounding proof** | `npx ruvnet-brain --doctor` | asks a real question, then checks the cited path really exists in the on-disk store; a citation that doesn't resolve is reported as **NOT grounded** |
 | **Held-out eval** | **grounded 100/100** · routed 63/80 | `npm run eval` — 120 frozen, hash-pinned questions across 5 strata, never used for tuning, graded on ground truth, never by a model |
 
@@ -562,7 +562,7 @@ node forge-ask-all.mjs --dir . --q "How does RuVector implement HNSW vector sear
 
 This project versions in the open (see the live badge up top for the exact plugin version; the downloadable knowledge bundle is a separate track) — we don't claim “done,” “complete,” or “zero hallucinations.” Where it stands:
 
-- ✅ **The grounding brain is real and proven** — 184 public stores · 146,970 public source chunks, dual embeddings, cross-encoder rerank, plugin (MCP tool + explicit skills; automatic hooks retired), all re-runnable.
+- ✅ **The grounding brain is real and proven** — 182 public stores · 143,719 public source chunks, dual embeddings, cross-encoder rerank, plugin (MCP tool + explicit skills; automatic hooks retired), all re-runnable.
 - ✅ **Code-level depth** — the code-rich repos are indexed to full function bodies; “how is it implemented?” returns the implementation. Verified in the shipped bundle (clean-room 3/3).
 - ✅ **Routing holds** — named 47/48, described 26/28, scenario 7/8; behavioral L1–L3 all pass (**L4 downgraded — it measures that the brain spoke, not that anything listened**); private stores fenced out of the public bundle (zero-leak verified).
 - ⚠️ **Two routing residuals** (above) — surfaced, not hidden.