knit-mcp 0.10.0 → 0.11.2

package/README.md

@@ -3,8 +3,8 @@
   <a href="https://github.com/PDgit12/knit/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/PDgit12/knit/ci.yml?style=for-the-badge&label=CI&color=10b981" alt="CI" /></a>
   <img src="https://img.shields.io/badge/license-MIT-3b82f6?style=for-the-badge" alt="license" />
   <img src="https://img.shields.io/badge/node-%E2%89%A518-339933?style=for-the-badge&logo=node.js&logoColor=white" alt="node" />
-  <img src="https://img.shields.io/badge/tests-492%20passing-22c55e?style=for-the-badge" alt="tests" />
-  <img src="https://img.shields.io/badge/MCP%20tools-43-7c3aed?style=for-the-badge" alt="tools" />
+  <img src="https://img.shields.io/badge/tests-664%20passing-22c55e?style=for-the-badge" alt="tests" />
+  <img src="https://img.shields.io/badge/MCP%20tools-53-7c3aed?style=for-the-badge" alt="tools" />
 </p>
 
 <h1 align="center">🧶 knit</h1>
@@ -18,9 +18,10 @@
 <p align="center">
   <a href="#-quick-start">Quick start</a> ·
   <a href="#-what-knit-is">What it is</a> ·
-  <a href="#-whats-new-in-v090">v0.9</a> ·
-  <a href="#-43-mcp-tools">Tools</a> ·
-  <a href="#-how-its-different">Comparison</a>
+  <a href="#-whats-new-in-v0110">v0.11</a> ·
+  <a href="#-52-mcp-tools">Tools</a> ·
+  <a href="#-how-its-different">Comparison</a> ·
+  <a href="#-honest-comparison-vs-memory-libraries">vs mem0/Letta</a>
 </p>
 
 ---
@@ -410,10 +411,50 @@ Compounding
 
 ---
 
+## 🧭 Honest comparison vs memory libraries
+
+The mem0 / Letta / agentmemory comparison deserves a separate section because they're a different category — **memory-as-a-service libraries**, not MCP-native workflow layers. Reading their published benchmarks side-by-side:
+
+| | mem0 | Letta (MemGPT) | agentmemory | **Knit** |
+|--|---|---|---|---|
+| **Published benchmark** | LOCOMO: 67–92% LLM-as-Judge; ~90% token reduction (1.7K vs 26K per conversation) | No head-to-head token-reduction number; "Letta Leaderboard" benchmarks *LLMs* on agentic memory, not Letta | LongMemEval-S: **95.2% R@5** with BM25+RRF+graph; 86.2% BM25-only | **Not yet measured.** Same architecture as agentmemory; no published number. |
+| **Retrieval architecture** | Vector + graph (Mem0g variant) | OS-inspired tiered memory (core/recall/archival) | BM25 + local vectors + KG fused via RRF (k=60) | BM25 + RRF + graph-traversal (fused via RRF k=60). Per-project + cross-project diversity caps. |
+| **Install shape** | SDK integration; managed cloud or self-hosted | SDK integration; self-hosted server | Python library | **`npx knit-mcp setup` → MCP server, zero glue.** Works with Claude Code / Cursor / Codex / any MCP host. |
+| **Workflow primitive** | None — pure memory | Agent-managed memory operations | None — pure retrieval | **4-tier classifier + plan-mode + protocol guard + parallel team worktrees.** |
+| **Self-calibration** | No | No | No | **Per-project classifier calibration** (v0.11): user FP feedback shifts thresholds; classifier gets less wrong over time. |
+
+### What's honest about this
+
+**Knit's measured retrieval on a 50-question synthetic harness (v0.11.2):**
+
+| Metric | Knit (v0.11.2 synthetic) | agentmemory (LongMemEval-S, published) |
+|---|---|---|
+| Top-1 accuracy | **86.0%** | not published in that form |
+| Recall@5 | **96.0%** | **95.2%** |
+
+Run it yourself: `npm run bench`. Source: [`benchmarks/retrieval-synthetic.ts`](./benchmarks/retrieval-synthetic.ts).
+
+**These numbers are NOT apples-to-apples with agentmemory's.** Their benchmark is 1,500 questions from real long conversations; Knit's is 50 hand-authored questions on a 7KB synthetic corpus. The numbers are close because the architecture is similar (BM25 + RRF), not because we've proven parity at scale. **Real comparison requires running LongMemEval-S on Knit** — on the roadmap for v0.13.
+
+**Knit isn't trying to be a better mem0.** It's a different product:
+- **MCP-native + zero-glue install** — mem0/Letta require SDK integration; Knit drops into any MCP host (Claude Code, Cursor, Codex) with one command.
+- **Workflow primitive** — the 4-tier classifier + plan-mode + protocol guard + team worktrees is what makes Knit a *command layer*, not a memory library.
+- **Per-project classifier calibration** (v0.11 slice 4) — `knit_record_false_positive` with a direction tag shifts thresholds over time. Nobody else does this; nobody else needs to, because they're memory libraries, not workflow routers.
+- **Measurable cheapness** — `knit_compounding_metrics` + `knit_get_metrics_history` make the "cheaper over time" claim *chartable per project*. mem0 publishes aggregate dataset numbers; Knit ships per-user instrumentation.
+
+### What's deferred
+
+LongMemEval-S R@5/R@10 + LOCOMO LLM-as-Judge runs are on the roadmap (v0.13+). Until they're published, treat any cross-system token-savings comparison as architectural-claim-only.
+
+---
+
 ## 📜 Release history
 
 | Version | Headline |
 |---|---|
+| **v0.11.2** | Pre-publish polish · chunk cap (2000) + `errorResponse` envelope across handlers + CLAUDE.md generator surfaces v0.11 tools · new `engram doctor` install health-check CLI · upgrade-path smoke test caught + fixed a data-loss bug in cache.ts (Case B was wiping user permissions on upgrade) · 11 real exploit-payload integration tests prove C1/C2/H1 fixes hold · `npm run bench` ships a synthetic retrieval harness (50 Q&A) measuring 86% top-1 / 96% R@5. 53 tools, 664 tests. |
+| **v0.11.1** | Audit-driven hardening · 3 CRITICAL (source_id path traversal, post-edit tsc shell injection, live calibration bug) + 10 HIGH fixes from a 5-agent audit, implemented in 3 parallel `knit_spawn_team_worktree` teams. HOOKS_VERSION 11 (auto-upgrades existing users). New `knit_delete_requirements` tool. Honest comparison vs mem0/Letta added. 53 tools, 636 tests. |
+| **v0.11.0** | Verify Layer + auto-config foundation · mandatory `knit_verify_claim` REVIEW gate · post-edit diff verify + universal `tsc` check · drift detector · self-healing classifier (per-project calibration) · `knit_index_requirements` + `knit_generate_test_cases` (BM25 over long specs) · `knit_get_fingerprint` + `knit_infer_domains` + `knit_compose_template` (zero-config CLAUDE.md). 52 tools, 625 tests. |
 | **v0.10.0** | Token-economics release · risk × scope × change_kind classifier split · `context_budget_remaining` graceful degradation · per-project diversity cap on cross-project search · 11 new compounding-metrics fields + weekly snapshot persistence + `knit_get_metrics_history`. Makes "Knit makes Claude cheaper" a chartable number from day 1. |
 | **v0.9.0** | Hook-level enforcement · citation rule · `knit_verify_claim` · auto-search in classify · `suggested_reads` · `knit_get_learning` · `knit_consolidate_learnings`. |
 | **v0.8.x** | Vectorless RAG (BM25 + RRF) · graph-traversal retriever · per-project instruction tailoring · `knit_compounding_metrics` · integration scanner. |

package/dist/cache-3LPETDUT.js

@@ -0,0 +1,19 @@
+import {
+  detectProjectRoot,
+  getBrain,
+  refreshBrain
+} from "./chunk-TWHNYJAJ.js";
+import "./chunk-HROSQ5MS.js";
+import "./chunk-RZOVZYTF.js";
+import "./chunk-MOOVNMIN.js";
+import "./chunk-ST4X7LZT.js";
+import "./chunk-M3YZOJNW.js";
+import "./chunk-VB2TIR6L.js";
+import "./chunk-7UFS67HP.js";
+import "./chunk-WKQHCLLO.js";
+import "./chunk-27TA2ZQZ.js";
+export {
+  detectProjectRoot,
+  getBrain,
+  refreshBrain
+};

package/dist/{chunk-BW4JUY74.js → chunk-27TA2ZQZ.js}

@@ -93,6 +93,18 @@ function searchMarkerPath(rootPath) {
 function claimMarkerPath(rootPath) {
   return join2(projectDataDir(rootPath), ".claim-verified-current");
 }
+function turnEditLogPath(rootPath) {
+  return join2(projectDataDir(rootPath), ".turn-edits.jsonl");
+}
+function calibrationPath(rootPath) {
+  return join2(projectDataDir(rootPath), "calibration.json");
+}
+function requirementsDir(rootPath) {
+  return join2(projectDataDir(rootPath), "requirements");
+}
+function requirementSourcePath(rootPath, sourceId) {
+  return join2(requirementsDir(rootPath), `${sourceId}.json`);
+}
 function featuresConfigPath(rootPath) {
   return join2(projectDataDir(rootPath), "features.json");
 }
@@ -150,6 +162,10 @@ export {
   sessionMarkerPath,
   searchMarkerPath,
   claimMarkerPath,
+  turnEditLogPath,
+  calibrationPath,
+  requirementsDir,
+  requirementSourcePath,
   featuresConfigPath,
   integrationsConfigPath,
   metricsHistoryPath,

package/dist/{chunk-KLNUEE3O.js → chunk-7UFS67HP.js}

@@ -53,7 +53,15 @@ function generateSessionStartup() {
 
 First action: call \`knit_load_session\`. One MCP call returns last sessions, handoff, learnings, false positives. If \`handoff.md\` exists at the repo root, resume that work first.
 
-Protocol Guard runs in \`warn\` mode by default \u2014 adjust with \`knit_set_protocol_strictness\`.`;
+Protocol Guard runs in \`warn\` mode by default \u2014 adjust with \`knit_set_protocol_strictness\`.
+
+## v0.11 tool surface (in addition to query/search/record)
+
+- **\`knit_verify_claim\`** \u2014 fact-check one claim against the knowledge graph before LEARN. Stop-hook enforces on standard/complex scope.
+- **\`knit_index_requirements\` + \`knit_generate_test_cases\` + \`knit_list_requirements\` + \`knit_delete_requirements\`** \u2014 long-form spec / RFC ingestion (200KB doc \u2192 relevant 5\u20137KB chunks per feature query).
+- **\`knit_get_fingerprint\` + \`knit_infer_domains\` + \`knit_compose_template\`** \u2014 auto-config primitives: detected stack \u2192 ranked domains \u2192 composed CLAUDE.md sections (preview only; you paste to accept).
+- **\`knit_get_calibration\` + tag your false-positives** (e.g. \`#complex-was-trivial\`) \u2014 the per-project self-healing classifier tunes thresholds after 3 same-direction FPs.
+- **\`knit_brain_status\`** surfaces calibration / requirements / fingerprint state so you can discover all of the above from one health check.`;
 }
 function generateProjectMap(knowledge) {
   const { summary } = knowledge;