fastrmemory 0.3.0 → 0.3.1

package/README.md

@@ -1,729 +1,727 @@
-<div align="center">
-
-# ⚡ FastrMemory
-
-### High-Performance Cognitive Agent Memory Engine
-**Zero Daemon • Native Node 22+ `node:sqlite` • Bi-Temporal Git Sync • Triple-Stream RRF • Official MCP v2**
-
-[![CI](https://github.com/atifjubaer/fastrmemory/actions/workflows/ci.yml/badge.svg)](https://github.com/atifjubaer/fastrmemory/actions)
-[![npm](https://img.shields.io/npm/v/@atifjubaer/fastrmemory?style=flat-square&logo=npm&label=npm)](https://www.npmjs.com/package/@atifjubaer/fastrmemory)
-[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=flat-square)](LICENSE)
-[![Node](https://img.shields.io/badge/Node-%3E%3D22.16.0-339933?style=flat-square&logo=node.js&logoColor=white)](https://nodejs.org)
-[![Protocol](https://img.shields.io/badge/Protocol-MCP%20v2-7C3AED?style=flat-square)](https://modelcontextprotocol.io)
-[![Tests](https://img.shields.io/badge/Tests-276%20Passed-brightgreen?style=flat-square)](tests/)
-[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](CONTRIBUTING.md)
-[![Architecture](https://img.shields.io/badge/Architecture-Zero--Daemon%20WAL-orange?style=flat-square)](#-architecture)
-
-> **Status (2026-10-23):** The published release is `@atifjubaer/fastrmemory@0.2.1`; `npm view @atifjubaer/fastrmemory version` returns `0.2.1`. The unreleased **0.3.0** branch renames the canonical package to unscoped **`fastrmemory`** and pins generated MCP/hook configs to `fastrmemory@0.3.0`; do not publish from this branch until the release gate passes. The latest GitHub release is **v0.2.1**. This README tracks **0.3.0**, so features marked **0.3.0** are not in the v0.2.1 package. Install `@0.2.1` for the current release; use the **v0.2.1 GitHub Release tarball** as a byte-verified fallback. The exact release surface is in [CHANGELOG.md](CHANGELOG.md); the release post is [docs/blog/2026-10-21-fastrmemory-0.2.1.md](docs/blog/2026-10-21-fastrmemory-0.2.1.md). The headline benchmark uses **240 deterministic synthetic cases with a 20% holdout**, not SWE-bench or LongMemEval. Public LongMemEval, LoCoMo, and self-repository retrieval-only results plus pinned external baselines are in [BENCHMARKS.md](BENCHMARKS.md); no QA-leaderboard parity is claimed. Performance, packaging, and retrieval claims are tracked in [CLAIMS.md](CLAIMS.md); every README section is mapped to claim IDs in the README claim trace at the end of that ledger. Methodology, caveats, and raw JSON are in [BENCHMARKS.md](BENCHMARKS.md).
-
-<p align="center">
-  <a href="#-overview">Overview</a> &bull;
-  <a href="#-design-principles">Design Principles</a> &bull;
-  <a href="#-retrieval-benchmark-240-synthetic-cases">Benchmarks</a> &bull;
-  <a href="#-local-web-dashboard">Web UI</a> &bull;
-  <a href="#-works-with-mcp--and-http-compatible-agents">Supported Agents</a> &bull;
-  <a href="#-quick-start">Quick Start</a> &bull;
-  <a href="#-mcp-server-tools--resources">MCP Tools</a> &bull;
-  <a href="#-architecture">Architecture</a> &bull;
-  <a href="ROADMAP.md">Roadmap</a> &bull;
-  <a href="MIGRATION.md">Migration</a> &bull;
-  <a href="SECURITY.md">Security</a> &bull;
-  <a href="SCORECARD.md">Scorecard</a> &bull;
-  <a href="#-contributing">Contributing</a>
-</p>
-
-</div>
-
----
-
-## Launch Status at a Glance
-
-| Claim | Current result | Evidence |
-|---|---|---|
-| Install path | Published `@atifjubaer/fastrmemory@0.2.1`; the 0.3.0 branch package is unscoped `fastrmemory` (unreleased) | `npm view @atifjubaer/fastrmemory version` -> `0.2.1`; `node -p "require('./package.json').name + ' ' + require('./package.json').version"` -> `fastrmemory 0.3.0` |
-| Synthetic retrieval | Holdout `95.8%` Hit@1, `100%` Hit@5, MRR `0.969` | `npx tsx scripts/eval-bench.ts --split all --embeddings minilm --out bench/results/minilm.json` |
-| Test suite | `276` tests across `51` files on the `0.3.0` branch; v0.2.1 is `235` / `43` | `npm test` |
-| Crash safety | 10/10 runs, 0 lost, 0 duplicate ids/titles | `npm run test:crash`; `bench/results/crash-test.json` |
-| Public retrieval (0.3.0 branch) | LongMemEval `+10.4pp` / `+11.0pp` Hit@5; LoCoMo `+4.4pp` / `+2.3pp` (target missed) | [docs/EXTERNAL_BASELINE.md](docs/EXTERNAL_BASELINE.md) |
-| Release score | Provisional `9.4 / 10`; `9.2` target met; Retrieval remains Partial | [SCORECARD.md](SCORECARD.md) |
-
-The synthetic table is not SWE-bench or LongMemEval. Public numbers are retrieval-only and are not QA-leaderboard results. Full provenance is in [CLAIMS.md](CLAIMS.md).
-
----
-
-## 💡 Overview
-
-AI coding agents (Claude Code, Cursor, Windsurf, Codex, Antigravity) degrade on long-running codebases when project memory is lossy or operationally heavy. Common designs make one of three trade-offs:
-- **Decay and merge** old episodes to keep the store small, which can lose exact file paths, stack traces, and edge cases.
-- **Run a daemon or external database**, which adds ports, containers, and setup failure modes.
-- **Dump a static context file**, which grows without bound and is not queryable.
-
-**FastrMemory** keeps a verbatim event log, bi-temporal memory history, and a replayable Git mirror in a **single in-process TypeScript engine** (3 runtime dependencies; local embeddings and the daemon are optional):
-
-<table>
-<tr>
-<td width="33%" align="center">
-
-### ⚡ Zero Daemon Overhead
-Pure Node 22+ built-in `node:sqlite` in WAL mode. On the 240-case suite, engine-level recall is **0.95 ms p50 / 1.60 ms p95** with hash embeddings and **3.30 ms p50 / 5.11 ms p95** with MiniLM on the train split (CLI startup measured separately). The default CLI/MCP path has no background daemon and no open port; `daemon start` is optional. Native on Windows, macOS, and Linux (the current CI matrix uses Intel macOS; Apple Silicon is not covered); CI matrix status is reported in [Actions](https://github.com/atifjubaer/fastrmemory/actions).
-
-</td>
-<td width="33%" align="center">
-
-### 🔀 Bi-Temporal Git Sync
-Never deletes facts during consolidation (there is no destructive sleep step). Replaces half-life decay with `valid_from` / `valid_to` timestamps and auto-mirrors human-readable `.fastr/pages/*.md` files into Git.
-
-</td>
-<td width="33%" align="center">
-
-### 🎯 Triple-Stream RRF ($k=20$)
-Fuses FTS5 BM25 + optional local embeddings + file-graph links. Error traps receive a **conditional 2.0x boost** only for trap-intent or file-scoped queries, with per-ID outcome feedback (+0.2 / -0.5). Three consecutive bad outcomes move a memory to dormant; confidence tiers are `high`, `medium`, `low`, `dormant`, and `superseded`.
-
-</td>
-</tr>
-</table>
-
----
-
-## 🧭 Design Principles
-
-| Principle | Implementation |
-| :--- | :--- |
-| **Lossless by default** | Raw events, bi-temporal `valid_from` / `valid_to`, and supersession chains are retained. Nothing is destroyed by consolidation. |
-| **Zero daemon by default** | One Node 22+ process uses built-in `node:sqlite` in WAL mode. The default CLI/MCP path opens no ports or background services; `daemon start` is optional. |
-| **Replayable** | Git-diffable Markdown mirrors plus snapshots and rollback keep history inspectable. |
-| **Measured, not asserted** | Public claims are tied to committed benchmark JSON with a 20% holdout; simulated baselines are labeled as simulations. |
-
----
-
----
-
-## 🤖 Works With MCP- and HTTP-Compatible Agents
-
-FastrMemory exposes one stdio MCP server and optional local HTTP services (dashboard and daemon). **Native installers wire Claude Code (MCP config plus lifecycle hooks), Cursor (MCP config plus skills), and, on 0.3.0, Gemini CLI, GitHub Copilot CLI, and OpenCode V2** (`fastrmemory hook install`); `fastrmemory setup` also writes MCP configs for Antigravity, Claude Desktop, and Windsurf. Every other client connects through its own MCP configuration or the REST API. Integration depth varies by client - only the native installers are covered by tests in this repository.
-
-Clients commonly used with FastrMemory include Codex CLI, Gemini CLI, OpenCode, GitHub Copilot CLI, Antigravity, Claude Desktop, Cline, Continue, Roo Code, Goose, Zed, Warp, and Aider. Listing a client does **not** imply a tested native integration.
-
----
-
-## 🚀 Quick Start
-
-### ⚡ Run Without a Global Install
-
-The 0.3.0 branch package is unscoped `fastrmemory`. It is not on the registry until the 0.3.0 release gate passes; the published 0.2.1 package remains available under its scoped name.
-
-```bash
-# 0.3.0 command (after release):
-npx -y fastrmemory@0.3.0 setup
-
-# Published 0.2.1 release:
-npx -y @atifjubaer/fastrmemory@0.2.1 setup
-
-# Or launch the local Web UI:
-npx -y fastrmemory@0.3.0 ui
-```
-
-The GitHub source path remains available for development only: `npx github:atifjubaer/fastrmemory setup`. Do not use it in generated MCP or hook configs; those must pin the npm package version.
-
----
-
-### Install from npm
-
-```bash
-# 0.3.0 branch (after release):
-npm install -g fastrmemory@0.3.0
-
-# Current published release:
-npm install -g @atifjubaer/fastrmemory@0.2.1
-fastr --version
-```
-
-For a one-shot run without a global install:
-
-```bash
-npx -y fastrmemory@0.3.0 --version
-```
-
-The 0.2.1 package is public. The first `npm view` after the 2026-10-22 publish returned E404 for about two minutes during registry propagation; use the exact `0.2.1` version for reproducibility. The 0.3.0 package is unreleased; do not treat the `fastrmemory` install command as available until the release gate passes.
-
-### Install the v0.2.1 GitHub Release Tarball
-
-```bash
-# Local project install from the release asset (verified with the 0.2.1 tarball):
-npm install https://github.com/atifjubaer/fastrmemory/releases/download/v0.2.1/atifjubaer-fastrmemory-0.2.1.tgz
-npx fastr --version
-```
-
-For a global CLI:
-
-```bash
-npm install -g https://github.com/atifjubaer/fastrmemory/releases/download/v0.2.1/atifjubaer-fastrmemory-0.2.1.tgz
-fastr --version
-```
-
-Or install the current default branch for development (not the frozen release tag):
-
-```bash
-npm install -g git+https://github.com/atifjubaer/fastrmemory.git
-```
-
-> Both `fastrmemory` and `fastr` (short alias) are executable after installation. The 0.3.0 branch renames the package to `fastrmemory`; the bin names stay the same. The GitHub asset is the byte-verified fallback for the v0.2.1 release and is not byte-identical to the registry tarball. The release tarball SHA-256 is recorded in [CLAIMS.md](CLAIMS.md).
-
-### 2. Verify Database Health
-
-```bash
-fastrmemory status
-```
-
-Output:
-```text
-=== FastrMemory Health (my-project) ===
-- Project ID:          proj_1cce2a654e3a
-- Active Memories:     2
-- Staging Memories:    0
-- Superseded History:  0
-- Ingested Events:     0
-- Pending Spool:       Clear (0)
-- Database File:       .fastr/fastr.db
-```
-
-### 3. Record & Recall a Memory
-
-```bash
-# Record an error trap linked to an exact file:
-fastrmemory remember "Never Use Date.now() Milliseconds for JWT Expiration" \
-  -c "JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000)." \
-  -m auth -k error_trap -f "src/auth/jwt.ts" --verified
-
-# Recall with conditional 2.0x trap boost & file-graph matching:
-fastrmemory recall "JWT expiration" -f "src/auth/jwt.ts"
-```
-
-Output:
-```text
-=== Recalled Memories (1 results, ~46 tokens) ===
-
-[mem_009e4a7d] [TRAP] [verified] Never Use Date.now() Milliseconds for JWT Expiration (Score: 0.08)
-JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000).
-```
-
-Open contradictions are marked on both sides of the recall result instead of being silently mixed into context (**0.3.0**):
-
-```bash
-# Inspect unresolved contradictions:
-fastrmemory conflict list
-
-# Keep the rule that matches the project and supersede the loser:
-fastrmemory conflict resolve 1 --keep mem_009e4a7d --forget --reason "Seconds are the project standard"
-```
-
-#### Import Existing Local Rules (**0.3.0**)
-
-Bring `AGENTS.md`, `CLAUDE.md`, or `.cursor/rules/*.mdc` content into memory without hand-copying every section. Level 2+ headings become memories; bullet lists and paragraphs are fallbacks. Re-importing the same file skips exact duplicates.
-
-```bash
-# Preview the parsed sections without writing:
-fastrmemory import AGENTS.md --from agents-md --module rules --dry-run
-
-# Import as staging memories for review, or verify them immediately:
-fastrmemory import AGENTS.md --from agents-md --module rules
-fastrmemory import AGENTS.md --from agents-md --module rules --verified
-
-# JSONL snapshots use the same entry point:
-fastrmemory import snapshot.jsonl --from jsonl
-```
-
-### 4. Cognitive Git Blame & Memory-Aware Commit
-
-```bash
-# Cognitive Git Blame linking lines directly to commit, author, and governing error traps (conditional 2.0x boost):
-fastrmemory blame src/auth/jwt.ts:42
-
-# Pre-commit error trap validation & conventional commit synthesis:
-fastrmemory commit
-```
-
-### 5. Git Snapshots, Branches, Rollback & Background Daemon (branches are **0.3.0**)
-
-```bash
-# Point-in-time memory snapshot (Git for Agent Memory):
-fastrmemory snapshot create "pre-refactor-checkpoint"
-fastrmemory snapshot list
-fastrmemory snapshot rollback "pre-refactor-checkpoint"
-
-# 0.3.0: Portable backup with a sidecar provenance manifest:
-fastrmemory backup backups/pre-upgrade.jsonl
-fastrmemory backup --verify backups/pre-upgrade.jsonl
-fastrmemory backup --restore backups/pre-upgrade.jsonl --dry-run
-
-# Immutable memory branch and one-way merge with a conflict report:
-fastrmemory branch create feature/auth
-fastrmemory branch list
-fastrmemory merge feature/auth
-fastrmemory merge feature/auth --force --strategy branch
-
-# Hybrid Background Daemon (Optional HTTP/SSE service for cross-process tools):
-fastrmemory daemon start
-fastrmemory daemon status
-fastrmemory daemon stop
-
-# Auto-wire MCP configs, lifecycle hooks, and Planetary Skills into Claude Code, Cursor,
-# Gemini CLI, GitHub Copilot CLI, and OpenCode; setup also wires Antigravity, Claude Desktop, and Windsurf:
-fastrmemory hook install
-fastrmemory setup
-
-# Mine past Git bug fixes directly into staging error traps:
-fastrmemory learn -n 30 --days 90
-```
-
-Branches are immutable snapshot pointers. `merge` is one-way into the current active set: branch-only memories are added, target-only memories are preserved, and same-identity changes are reported as conflicts. Conflicts block writes by default; `--force` applies non-conflicting additions, and `--force --strategy branch` supersedes the target while keeping old rows in history. Branch checkout or a mutable branch working tree is not implemented.
-
-`backup` writes the portable JSONL snapshot plus `<file>.manifest.json` with the file SHA-256, content hash, record counts, tool version, environment, and source integrity. `--restore` verifies both hashes before importing; `--dry-run` reports counts without writing. The backup scope is memories, raw events, file links, and conflicts, not a physical SQLite/WAL copy. See [MIGRATION.md](MIGRATION.md) for the full backup and rollback path.
-
-### 6. Token Compression, Database Doctor & Vision Search
-
-```bash
-# Compress markdown docs & LLM prompt context to reduce token usage:
-fastrmemory compress docs/architecture.md --dry-run
-
-# Run deep health check across SQLite, FTS5 indices, file links, and task DAGs:
-fastrmemory diagnose
-
-# Auto-repair FTS5 indices, orphaned file links, and WAL fragmentation:
-fastrmemory heal
-
-# 0.3.0: Report orphaned records, duplicate active memories, and stale rows:
-fastrmemory hygiene
-fastrmemory hygiene --stale-days 30 --json --fail-on-issues
-
-# Tag a UI screenshot or architecture diagram with OCR & 384-dim vector indexing:
-fastrmemory vision tag screenshots/modal-error.png --desc "Modal error 401 alert" --ocr "HTTP 401"
-
-# Semantic search across tagged screenshots and visual diagrams:
-fastrmemory vision search "modal error 401"
-
-# Pre-merge CI/CD gate checking PR diffs against active error traps:
-fastrmemory guard --strict
-```
-
-`fastrmemory hygiene` reports orphaned file links, conflict rows, and feedback rows; duplicate active memories by normalized title or exact content; and stale unpinned active memories (default 90 days since the last recall or creation). `npm run check:hygiene` runs the same inspector against a deterministic fixture inside `check:ci`; it does not mutate a project database. Use `--fail-on-issues` when a script should exit nonzero on findings.
-
----
-
-## 🔌 One-Click Agent MCP Configuration
-
-Add this JSON block to your agent's MCP settings to enable autonomous memory:
-
-### Claude Code (`~/.claude.json`)
-```json
-{
-  "mcpServers": {
-    "fastrmemory": {
-      "command": "fastrmemory",
-      "args": ["mcp"]
-    }
-  }
-}
-```
-
-### Cursor (`.cursor/mcp.json`)
-```json
-{
-  "mcpServers": {
-    "fastrmemory": {
-      "command": "fastrmemory",
-      "args": ["mcp"]
-    }
-  }
-}
-```
-
-### Gemini CLI (`.gemini/settings.json`, 0.3.0)
-```json
-{
-  "mcpServers": {
-    "fastrmemory": {
-      "command": "fastrmemory",
-      "args": ["mcp"]
-    }
-  }
-}
-```
-
-`fastrmemory hook install` also merges `SessionStart`, `BeforeTool` (`write_file|replace`), `PreCompress`, and `SessionEnd` hooks into the same project settings file. Gemini CLI requires strict JSON on hook stdout, so the generated commands pass `--format gemini`. Google is transitioning users from Gemini CLI to Antigravity CLI; this integration targets the still-documented `.gemini/settings.json` contract.
-
-### GitHub Copilot CLI (`.github/mcp.json`, 0.3.0)
-```json
-{
-  "mcpServers": {
-    "fastrmemory": {
-      "type": "local",
-      "command": "fastrmemory",
-      "args": ["mcp"]
-    }
-  }
-}
-```
-
-`fastrmemory hook install` also merges `.github/hooks/fastrmemory.json` with `sessionStart`, `preToolUse` (`edit|create|str_replace_editor|apply_patch`), `preCompact`, and `sessionEnd` hooks. Copilot has no model-facing advisory field for `preToolUse`, so an active trap returns `permissionDecision: "ask"` with the warning; autopilot/non-interactive mode treats `ask` as deny. The shared `AGENTS.md` written by the installer supplies repository instructions.
-
-### OpenCode V2 (`opencode.json`, 0.3.0)
-```json
-{
-  "mcp": {
-    "servers": {
-      "fastrmemory": {
-        "type": "local",
-        "command": ["fastrmemory", "mcp"]
-      }
-    }
-  }
-}
-```
-
-`fastrmemory hook install` also writes `.opencode/plugins/fastrmemory/index.ts`, which injects the session-start handoff and critical rules into model context and captures a snapshot before compaction. Existing `opencode.json(c)` settings are preserved; JSONC configs are left untouched and reported for manual wiring.
-
----
-
-## 🛠️ MCP Server: Tools & Resources
-
-Built using the official **v2 `@modelcontextprotocol/server`** SDK. The tool list below describes the **0.3.0** branch; the v0.2.1 release has 4 resources.
-
-### 41 MCP Tools
-
-The default **full profile** exposes all 41 tools. For a smaller schema, start the **core profile** with `fastrmemory mcp --profile core` or `FASTR_MCP_PROFILE=core`; it exposes the 12-tool daily loop: `fastr_recall`, `fastr_remember`, `fastr_handoff`, `fastr_trap_recall`, `fastr_trap_log`, `fastr_status`, `fastr_get`, `fastr_timeline`, `fastr_diff`, `fastr_replay`, `fastr_compress`, and `fastr_diagnose`. Resources and prompts are the same in both profiles.
-
-#### Cognitive Retrieval & Memory Core
-1. `fastr_recall`: Triple-stream hybrid search (BM25 + Vector + Spreading Activation Graph) with progressive L0–L3 token budgeting and air-gapped offline vector fallback.
-2. `fastr_get`: Retrieves complete memory details (including status, timestamps, reward scores, and full content) by memory ID.
-3. `fastr_list`: Lists memories with bounded filtering by module, kind, status, limit, and offset.
-4. `fastr_drill`: Resolves `source_event_ids` to retrieve untruncated verbatim stack traces, diffs, and tool outputs from `raw_events`.
-5. `fastr_file_history`: Returns active rules, `[TRAP]` warnings, and past supersessions for a specific file path.
-6. `fastr_remember`: Records new rules, decisions, or traps. Automatically extracts NER entities, scrubs secrets, and re-renders Markdown mirrors. Supports `scope: 'project' | 'global'`.
-7. `fastr_pin`: Pins critical rules so they are permanently preserved and prioritized in L0 assembly without time decay.
-8. `fastr_forget`: Tombstones and deactivates an outdated memory cleanly with audit logging.
-9. `fastr_supersede`: Retires an outdated rule (`valid_to = now`), records the rationale, and inserts a replacement verified rule.
-10. `fastr_feedback`: Updates `reward_score` and the confidence tier on one memory ID (+0.2 good, -0.5 bad). Three consecutive bad outcomes make it dormant; never penalizes innocent memories.
-11. `fastr_handoff`: Saves or retrieves cross-agent session milestones and promotes staging memories to verified.
-12. `fastr_status`: Returns active/staging counts, spool health, and embedding coverage %.
-13. `fastr_graph_query`: Explores 1-hop and 2-hop structural file-link dependencies, entity links, and connected error traps.
-14. `fastr_timeline`: Chronological audit trail of memory events, newly verified rules, error traps, and historical supersessions.
-
-#### Versioning & Error Traps
-15. `fastr_snapshot`: Creates named point-in-time memory snapshots for branch tracking and experiment safety.
-16. `fastr_rollback`: Instant Git-like rollback to any previous memory snapshot.
-17. `fastr_trap_log`: One-line rapid logging of error traps and bug solutions with a conditional 2.0x recall boost.
-18. `fastr_trap_recall`: Targeted lookup of high-priority error traps protecting specific target files before editing.
-
-#### Proactive Contradiction Detection & Resolution
-19. `fastr_conflicts`: Proactive contradiction detection using Jaccard token overlap (minimum 0.35) and 50-word opposing-polarity analysis.
-20. `fastr_resolve`: Resolves contradictions by keeping preferred rule and superseding or weakening the loser.
-
-#### Kahneman Planning Fallacy & Base-Rate Calibrator
-21. `fastr_predict`: Records effort/time/risk predictions and closes predictions with actual empirical outcomes.
-22. `fastr_predict_baserate`: Computes historical reference-class statistics (Mean, Median p50 ratio, MAE) to debias agent estimates.
-
-#### Multi-Agent Action DAG & Frontier
-23. `fastr_action_create`: Creates structured work item actions with prerequisite (`requires`) and conflict (`conflicts_with`) constraints.
-24. `fastr_action_update`: Updates task lifecycle (`pending`, `active`, `done`, `blocked`), assignments, and memory crystallization.
-25. `fastr_frontier`: Computes unblocked, ready-to-execute frontier actions with satisfied dependencies.
-26. `fastr_next`: Atomically claims and returns the highest-priority frontier action for autonomous worker agents.
-
-#### Bounded Working Memory & Obsidian Vault Export
-27. `fastr_slot_get`: Retrieves bounded working memory slot (e.g. `current_goal`, `user_preferences`, `active_hypothesis`).
-28. `fastr_slot_set`: Updates working memory slot with hard character ceiling enforcement to prevent context bloat.
-29. `fastr_slot_list`: Lists all working memory slots and active character usage.
-30. `fastr_obsidian_export`: Exports all memories, entities, and relationships into an Obsidian-compatible markdown vault with YAML frontmatter, `[[wikilinks]]`, and `MOC.md`.
-
-#### Multi-Repository Federation & Context Assembly
-31. `fastr_federate`: Manages cross-repository organization-wide shared rules and error traps via SQLite native `ATTACH DATABASE` (`~/.fastr/global.db`).
-32. `fastr_assemble`: Dynamically formats and packs high-density structured prompt context (`<fastr_context>`) with token budgeting.
-33. `fastr_risk_predict`: Computes historical failure probability and active trap hazard score for target codebase files.
-34. `fastr_verify_provenance`: Cryptographically verifies SHA-256 provenance hashes for recorded agent attribution.
-
-#### Token Compression & Autonomous Doctor
-35. `fastr_compress`: Compresses markdown files or prompt context while strictly preserving headings, URLs, and code blocks with `.original.md` backup.
-36. `fastr_diagnose`: Deep health audit of SQLite B-Tree integrity, FTS5 BM25 search indices, orphaned file links, and task DAGs.
-37. `fastr_heal`: Automatic repair of database indices, dangling edges, and WAL page reclamation.
-
-#### Memory Replay & Diff
-38. `fastr_replay`: Reconstructs memory state at a timestamp and returns the active snapshot for audit or recovery.
-39. `fastr_diff`: Compares two snapshots and reports added, superseded, and removed memories.
-
-#### Multimodal Visual Memory
-40. `fastr_vision_tag`: Tags screenshots, UI diagrams, and wireframes with OCR and semantic descriptions with 384-dim embeddings.
-41. `fastr_vision_search`: Hybrid vector and keyword search across stored visual assets for multimodal coding agents.
-
-### 2 MCP Prompt Templates
-
-- `pre-edit-check`: Given file paths, instructs the agent to check traps and relevant rules before editing.
-- `session-wrap-up`: End-of-session checklist for logging traps, superseding stale rules, scoring memories, and saving a handoff.
-
-### 5 MCP Resources (0.3.0; v0.2.1 has 4)
-
-- `fastr://project/overview`: L0 project summary containing active counts and storage location.
-- `fastr://project/traps`: All active `[TRAP]` warnings for immediate bug avoidance.
-- `fastr://session/handoff`: Latest cross-agent handoff milestone.
-- `fastr://memory/{id}` (resource template): Full JSON for a single memory, including linked files and its validity window.
-- `fastr://memory/{id}/envelope` (resource template): Metadata, cryptographic provenance, file/graph links, and open/resolved conflict state for one memory.
-
----
-
-## 📄 Two-Zone Git-Diffable Mirror
-
-Every write to the local SQLite database automatically synchronizes human-readable markdown files in `.fastr/pages/<module>.md`. This allows developers to review AI memories directly in GitHub Pull Requests:
-
-```markdown
-# Module: auth
-
-> Auto-generated by FastrMemory. Active rules are at the top; superseded history is preserved below for Git diffs.
-
----
-
-## Compiled Truth (Active Rules & Traps)
-
-### [mem_009e4a7d] [TRAP] Never Use Date.now() Milliseconds for JWT Expiration
-- **Kind**: `error_trap`
-- **Status**: `verified` (Reward Score: 1)
-- **Linked Files**: `src/auth/jwt.ts`
-- **Active Since**: `2026-10-18T21:46:20Z`
-
-JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000).
-
----
-
-## Append-Only Timeline (History & Superseded)
-
-### [EXPIRED 2026-10-18T20:00:00Z -> 2026-10-18T21:46:20Z] [mem_abc123] Token Signing
-- **Superseded By**: `[mem_009e4a7d]`
-- **Reason**: Standardized on integer seconds
-- **Historical Status**: `superseded`
-
-> Old implementation used milliseconds which failed expiration validation.
-```
-
----
-
-## 🧠 Planetary Agent Skills Suite
-
-FastrMemory ships 10 Agent Skills (in `skills/`, mirrored to `.cursor/skills/`) that tell agents *when* to use each memory tool. Install them as a Claude Code plugin (`.claude-plugin/`) or copy them with `fastrmemory setup`:
-
-- [fastr-memory](skills/fastr-memory/SKILL.md): At the start of a task and before editing files: `fastr_trap_recall`, then `fastr_recall` / `fastr_assemble`.
-- [fastr-trap-log](skills/fastr-trap-log/SKILL.md): The moment a failure is diagnosed: record it with `fastr_trap_log`.
-- [fastr-session-commit](skills/fastr-session-commit/SKILL.md): When a task is done and tests pass: supersede, rate memories, and `fastr_handoff` with `verifyStaging`.
-- [fastr-curate](skills/fastr-curate/SKILL.md): When storing durable lessons or fixing contradictions: dedupe, remember, supersede, resolve conflicts, snapshot/rollback.
-- [fastr-setup](skills/fastr-setup/SKILL.md): When FastrMemory is not wired into Claude Code: `fastrmemory hook install`, `claude mcp add`, verify with `fastrmemory status`.
-- [fastr-plan-estimate](skills/fastr-plan-estimate/SKILL.md): When estimating effort or risk: base rates, file risk, and closing predictions.
-- [fastr-dag](skills/fastr-dag/SKILL.md): When work has dependent steps or several agents share a backlog.
-- [fastr-doctor](skills/fastr-doctor/SKILL.md): When recall misses memories or the database looks unhealthy: diagnose, then heal.
-- [fastr-compress](skills/fastr-compress/SKILL.md): When a doc or context block exceeds its token budget.
-- [fastr-vision](skills/fastr-vision/SKILL.md): When screenshots or diagrams should be remembered or searched.
-
-Run `npm run check:skills` to validate every tool call in the skills against `src/mcp/server.ts`.
-
----
-
-## 🏗️ Architecture
-
-```mermaid
-flowchart TD
-    subgraph Ingestion["1. Lossless Ingestion & Spool"]
-        Agent["AI Coding Agent\n(Claude Code, Cursor, Antigravity)"] --> Scrubber["Secret Scrubber\n(API Keys, Bearer, PEM)"]
-        Scrubber --> Spool{"SQLite Busy?"}
-        Spool -- Yes --> SpoolFile[".fastr/spool/pending.jsonl\n(async fallback)"]
-        Spool -- No --> DB
-    end
-
-    subgraph Storage["2. Bi-Temporal Storage & Git Mirror"]
-        DB[("Node 22 node:sqlite (WAL)\nraw_events | memories\nfile_links | handoffs")]
-        DB --> Mirror["Markdown Mirror Engine"]
-        Mirror --> Pages[".fastr/pages/<module>.md\nTop: ## Compiled Truth\nBottom: ## Append-Only Timeline"]
-    end
-
-    subgraph Search["3. Triple-Stream Hybrid Retrieval"]
-        Query["Recall / File Query"] --> FTS["Stream A: FTS5 BM25\n(Sub-millisecond)"]
-        Query --> Vec["Stream B: Xenova Vectors\n(all-MiniLM-L6-v2)"]
-        Query --> Graph["Stream C: file_links Graph\n(1-2 Hop Structural Match)"]
-        FTS & Vec & Graph --> RRF["RRF Fusion (k=20)\n+ Conditional 2.0x Error Trap Multiplier\n+ 1.25x Verified Multiplier"]
-        RRF --> Budget["Progressive Token Packer\nL0 (150t) | L1 (500t) | L2 (1500t) | L3 (4000t)"]
-    end
-
-    subgraph Protocol["4. Official MCP Protocol"]
-        Budget --> MCPServer["Official MCP v2 Server\n(@modelcontextprotocol/server)"]
-        MCPServer --> Tools["41 tools • 2 prompts • 5 resources"]
-        Tools --> Agent
-    end
-```
-
----
-
-## 🧪 Testing & Verification
-
-Run the comprehensive unit test suite:
-
-```bash
-npm test
-```
-
-All **276 tests pass** across **51 test files** on the 0.3.0 branch (the v0.2.1 release has **235 tests / 43 files**) covering database schema, WAL locking, offline spooling, bi-temporal supersession, secret scrubbing, two-zone rendering, automated benchmarks, snapshots/rollback, branch merge conflict reports, replay/diff, memory envelopes, confidence tiers and 3-bad dormancy, memory hygiene checks, Memory CI, conflict-aware recall, portable backup manifests and verified restore, local rule import, OpenCode V2, Gemini CLI, and Copilot CLI wiring, git-learner, cognitive blame, commit synthesis, hybrid background daemon, token compression, self-healing doctor, multimodal vision, web dashboard server, pre-merge trap guardian, UI loopback security boundaries, and atomic installer configuration safety.
-
-**CI performance gates:** `check:query-plans`, `check:recall-latency`, and `check:install-size` run inside `check:ci`. CI executes them on the canonical Ubuntu/Node 24 job; other matrix jobs set `FASTR_PERF_GATE=0` because timing is runner-sensitive, while functional tests still run on every matrix entry.
-
-**Crash-safety evidence:** `npm run test:crash` kills the writer at randomized points across 10 runs, then reopens the WAL database. The committed report at [`bench/results/crash-test.json`](bench/results/crash-test.json) records **10,718 acknowledged writes**, **10,727 committed rows**, **0 lost**, **0 duplicate ids/titles**, and `PRAGMA integrity_check = ok`; methodology is in [`docs/audit/2026-10-21-crash-test.md`](docs/audit/2026-10-21-crash-test.md). `npm run check:crash` validates the report during `check:ci`. This is a process-crash test (`taskkill /F`), not a power-loss test; SQLite runs with `synchronous=NORMAL` in WAL mode.
-
----
-
-## Retrieval Benchmark (240 synthetic cases)
-
-Generated from [`bench/results/minilm.json`](bench/results/minilm.json) on **2026-10-20** at benchmark commit `562f461`. The corpus is deterministic: 120 memories and 240 queries, split into **192 train / 48 holdout (20%)**. The holdout was fixed before tuning and is reported separately. Reproduce with:
-
-```bash
-npx tsx scripts/eval-bench.ts --split all --embeddings minilm --out bench/results/minilm.json
-npx tsx scripts/eval-bench.ts --split all --embeddings hash   --out bench/results/hash.json
-```
-
-| Configuration | Split | Cases | Hit@1 | Hit@3 | Hit@5 | MRR | nDCG@10 | Context tokens | p50 |
-| :--- | :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
-| FastrMemory + MiniLM | Train | 192 | 96.4% | 99.0% | 100% | 0.976 | 0.982 | 208 | 3.30 ms |
-| FastrMemory + MiniLM | **Holdout** | 48 | **95.8%** | **97.9%** | **100%** | **0.969** | **0.977** | 209 | 3.41 ms |
-| FastrMemory BM25-only | Train | 192 | 79.7% | 90.6% | 100% | 0.868 | 0.900 | 203 | 0.48 ms |
-| FastrMemory BM25-only | Holdout | 48 | 77.1% | 77.1% | 93.8% | 0.804 | 0.835 | 204 | 0.60 ms |
-| Static dump - simulated baseline | Train | 192 | 2.1% | 6.3% | 8.3% | 0.055 | 0.081 | 3652 | 0.00 ms |
-| Static dump - simulated baseline | Holdout | 48 | 0.0% | 0.0% | 8.3% | 0.025 | 0.056 | 3652 | 0.00 ms |
-
-> **Caveats:** this is a deterministic synthetic corpus, not SWE-bench or LongMemEval. The static-dump row is a simulation implemented in this repository, not an external project. Separate public retrieval-only external baselines are documented in [docs/EXTERNAL_BASELINE.md](docs/EXTERNAL_BASELINE.md); the synthetic table does not measure them. Context tokens are the compact prompt text under a 250-token budget; the ranked result objects retain full memory content. Methodology, per-category breakdowns, ablations, and confidence intervals are in [BENCHMARKS.md](BENCHMARKS.md) and [docs/benchmark-report.md](docs/benchmark-report.md).
-
-## 🖥️ Local Web Dashboard v2 & 3D Brain Observatory
-
-Visualize active rules, error traps, timeline audits, and interactive 3D memory constellations directly in your browser from bundled UI assets (no external service or database):
-
-```bash
-fastrmemory ui
-```
-
-- **Live URL**: `http://localhost:4242`
-- **Dashboard v2 Architecture**: Built with **shadcn/ui**, **Tailwind CSS v4**, and **TanStack Query**, with SSE updates plus version polling for cross-process writes.
-- **12 Focused Route Workspaces (0.3.0 adds `/replay`)**:
-  - `/`: Real-time system vitals, active trap alerts, recent memory feed, and quick-action shortcuts.
-  - `/memories`: Search, filter, and inspect memories with the slide-out **Memory Detail Sheet**, status toggles, pin, and 1-click forget.
-  - `/traps`: Dedicated **Error Trap Quarantine** displaying governing files, conditional boost conditions, and verified mitigation lessons.
-  - `/conflicts`: Proactive bi-temporal contradiction detection with side-by-side **Word Diff** and 1-click resolution (`Keep A`, `Keep B`, `Keep Both`).
-  - `/actions`: Real-time interactive **Action DAG Canvas** tracking task dependencies, worker assignments, and glowing unblocked frontier aura.
-  - `/graph`: Interactive file and entity relationship graph with 1-hop/2-hop inspection and memory drill-down.
-  - `/observatory`: High-performance **Three.js 3D Constellation Galaxy** with a smooth lerp camera, celestial star dust, glowing amber trap halos, and memory inspect modals.
-  - `/treemap`: Interactive high-DPI squarified treemap visualising memory strength bands and module density.
-  - `/search`: **Search Lab** evaluating triple-stream RRF retrieval with latency waterfall breakdown (BM25 vs Vector vs Graph).
-  - `/replay` (**0.3.0**): **Replay & Diff** workspace reconstructing the active set at two timestamps with snapshot metrics and added/superseded/changed/conflict review.
-  - `/health`: Autonomous SQLite self-healing Doctor with 1-click integrity diagnosis, FTS5 rebuild, and vacuum.
-  - `/settings`: Live database path, project configuration, and export controls.
-- **Memory CI**: The PR diff workflow and comment lifecycle are documented in [docs/MEMORY_CI.md](docs/MEMORY_CI.md).
-- **Dual Theme Support**: Light, dark, and system-preference modes.
-- **Default Zero-Daemon Path**: The dashboard is served by the in-process Node.js HTTP server and embedded SQLite WAL mode; `fastrmemory daemon start` is an optional local REST/SSE service.
-
----
-
-## 🧩 Native VS Code & Cursor Extension
-
-Package and install the native FastrMemory Guardian extension for **VS Code** and **Cursor**:
-
-```bash
-# Compile and package extension
-npm run build:extension
-npx @vscode/vsce package --no-dependencies
-
-# Install into Cursor or VS Code
-cursor --install-extension fastrmemory-vscode-0.1.0.vsix
-```
-
-- **⚡ Status Bar Pill**: Displays active trap count in the status bar (`⚡ 3 Traps Active` or `⚡ 1 Trap on File`). Clicking opens an interactive QuickPick listing all active traps.
-- **Amber Underlines**: Trapped files are underlined in amber with full hover mitigation instructions and conditional 2.0x boost conditions.
-- **Problems Tab Integration**: Active error traps populate the IDE Problems panel as non-blocking warning diagnostics.
-- **Zero Daemons**: Reads directly from `.fastr/fastr.db` via `node:sqlite`.
-
----
-
-## 🤝 Contributing & Pull Request Roadmap
-
-We warmly welcome contributions from the open-source community! Whether you are adding a new AI coding agent hook, integrating local embedding backends, or crafting 3D visualizations, your pull requests are valued and reviewed promptly.
-
-### 🏆 Contributor Wall of Fame
-
-Special thanks to **[@the-arizul](https://github.com/the-arizul)** for architecting PRs #1 through #11:
-- **PR #1**: Loopback security boundaries, DNS rebinding lockdown, and `dist-ui` package resolution.
-- **PR #2**: Safe atomic JSON config merges, nested Claude Code hook schemas, and sandboxed installer tests.
-- **PR #3**: Hardened GitHub Actions fork PR comment safety.
-- **PR #4**: Core SQLite B-tree heal, BUSY spool fallback, ATTACH injection prevention, and atomic claim/supersede.
-- **PR #5**: Git security hardening (zero shell interpolation, confined paths, and high-entropy secret scrubbing).
-- **PR #6**: Triple-stream RRF recall ranking calibration, zero irrelevant results, and Unicode query normalization.
-- **PR #7**: MCP server hardening (`isError` handling, bounded inputs, parameter annotations, prompts, and new tools: `fastr_get`, `fastr_list`, `fastr_pin`, `fastr_forget`).
-- **PR #8**: Skills suite consolidation, plugin manifest, and CI validation runner.
-- **PR #9**: VS Code extension headless activation fallback and staging trap decorations.
-- **PR #10**: Isolated benchmark database harnesses and calibrated baselines.
-- **PR #11**: Planetary Dashboard v2 overhaul with shadcn/ui, Tailwind CSS v4, and live cross-process sync.
-
----
-
-### 🗺️ Open Contribution Roadmap
-
-| Domain / Focus Area | What Needs Building | Difficulty | Reference Location | Target PR Scope |
-| :--- | :--- | :--- | :--- | :--- |
-| **Agent Hook Installers** | Auto-wire hooks & skills for Windsurf, Roo Code, Continue, and Warp | `good first issue` | [src/installer/setup.ts](src/installer/setup.ts) | `feat(installer)` |
-| **Local Embedding Providers** | Optional on-device backends (Ollama, llama.cpp, WebGPU) with air-gapped fallback | Intermediate | [src/search/embeddings.ts](src/search/embeddings.ts) | `feat(embeddings)` |
-| **IDE Extensions** | JetBrains (IntelliJ / WebStorm) and Neovim Lua plugin with status bar pill & trap underlines | Advanced | [extensions/vscode/](extensions/vscode/) | `feat(ide)` |
-| **Benchmark Runners** | SWE-bench and additional public QA scenario runners; LongMemEval and LoCoMo retrieval harnesses already exist | `good first issue` | [src/bench/benchmark.ts](src/bench/benchmark.ts) | `feat(bench)` |
-| **UI Visualizations** | Custom Three.js shaders, Treemap color palettes, and SVG/PNG graph exports | Intermediate | [ui/src/components/](ui/src/components/) | `feat(ui)` |
-
----
-
-### 🚀 Pull Request Workflow
-
-1. **Fork & Clone Repository**:
-   ```bash
-   git clone https://github.com/<your-username>/fastrmemory.git
-   cd fastrmemory
-   ```
-
-2. **Install Dependencies & Verify Test Suite (276 Tests Passing)**:
-   ```bash
-   npm install
-   npm test
-   ```
-
-3. **Create a Feature Branch**:
-   ```bash
-   git checkout -b feat/add-windsurf-hooks
-   # or for bug fixes:
-   git checkout -b fix/sqlite-busy-retry
-   ```
-
-4. **Implement Changes & Verify All Packages Compile**:
-   ```bash
-   # Compiles backend, React UI, and VS Code extension
-   npm run build:all
-   npm test
-   ```
-
-5. **Commit with DCO Sign-off (`-s`) & Open Pull Request**:
-   ```bash
-   git commit -s -m "feat(installer): add windsurf auto-hook integration"
-   git push origin feat/add-windsurf-hooks
-   ```
-
----
-
-### 📋 Pull Request Quality Checklist
-
-Before submitting your PR, verify:
-- [ ] **Strict TypeScript**: `npm run build:all` passes without type errors.
-- [ ] **Zero External Daemons**: Engine runs in-process via Node.js WAL SQLite.
-- [ ] **100% Test Green**: `npm test` passes all 276 unit tests across 51 files.
-- [ ] **DCO Sign-off**: All commits signed off using `git commit -s` ([Developer Certificate of Origin](https://developercertificate.org/)).
-- [ ] **Pre-Merge Trap Guardian**: Run `fastrmemory guard --strict` to verify no active error traps are violated.
-
-See [CONTRIBUTING.md](CONTRIBUTING.md) for full architectural guidelines, secret scrubbing rules, and local development environment setup.
-
----
-
-## 📄 License
-
-Apache License 2.0. Built by **Fastrsoft**. Free for personal and commercial use.
+<div align="center">
+
+# ⚡ FastrMemory
+
+### High-Performance Cognitive Agent Memory Engine
+**Zero Daemon • Native Node 22+ `node:sqlite` • Bi-Temporal Git Sync • Triple-Stream RRF • Official MCP v2**
+
+[![CI](https://github.com/atifjubaer/fastrmemory/actions/workflows/ci.yml/badge.svg)](https://github.com/atifjubaer/fastrmemory/actions)
+[![npm](https://img.shields.io/npm/v/fastrmemory?style=flat-square&logo=npm&label=npm)](https://www.npmjs.com/package/fastrmemory)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=flat-square)](LICENSE)
+[![Node](https://img.shields.io/badge/Node-%3E%3D22.16.0-339933?style=flat-square&logo=node.js&logoColor=white)](https://nodejs.org)
+[![Protocol](https://img.shields.io/badge/Protocol-MCP%20v2-7C3AED?style=flat-square)](https://modelcontextprotocol.io)
+[![Tests](https://img.shields.io/badge/Tests-282%20Passed-brightgreen?style=flat-square)](tests/)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](CONTRIBUTING.md)
+[![Architecture](https://img.shields.io/badge/Architecture-Zero--Daemon%20WAL-orange?style=flat-square)](#-architecture)
+
+> **Status (2026-10-23):** The canonical release target is **`fastrmemory@0.3.1`**. The release workflow publishes it with npm provenance and a matching GitHub Release tarball; verify with `npm view fastrmemory version` and require `latest` to be `0.3.1`. This release replaces the stale `0.3.0` npm README, fixes Windows MCP commands, pins user-scoped clients to the project root, and adds the Node runtime guard. The old scoped npm entries (`@atifjubaer/fastrmemory` and `fastrmemory@0.0.0-stage`) were removed on 2026-10-23; the GitHub `v0.2.1` tag and release remain as history. This README tracks **0.3.1**. Use the exact `0.3.1` version for reproducibility. The release post for 0.2.1 remains at [docs/blog/2026-10-21-fastrmemory-0.2.1.md](docs/blog/2026-10-21-fastrmemory-0.2.1.md). The exact release surface is in [CHANGELOG.md](CHANGELOG.md). The headline benchmark uses **240 deterministic synthetic cases with a 20% holdout**, not SWE-bench or LongMemEval. Public LongMemEval, LoCoMo, and self-repository retrieval-only results plus pinned external baselines are in [BENCHMARKS.md](BENCHMARKS.md); no QA-leaderboard parity is claimed. Performance, packaging, and retrieval claims are tracked in [CLAIMS.md](CLAIMS.md); every README section is mapped to claim IDs in the README claim trace at the end of that ledger. Methodology, caveats, and raw JSON are in [BENCHMARKS.md](BENCHMARKS.md).
+
+<p align="center">
+  <a href="#-overview">Overview</a> &bull;
+  <a href="#-design-principles">Design Principles</a> &bull;
+  <a href="#-retrieval-benchmark-240-synthetic-cases">Benchmarks</a> &bull;
+  <a href="#-local-web-dashboard">Web UI</a> &bull;
+  <a href="#-works-with-mcp--and-http-compatible-agents">Supported Agents</a> &bull;
+  <a href="#-quick-start">Quick Start</a> &bull;
+  <a href="#-mcp-server-tools--resources">MCP Tools</a> &bull;
+  <a href="#-architecture">Architecture</a> &bull;
+  <a href="ROADMAP.md">Roadmap</a> &bull;
+  <a href="MIGRATION.md">Migration</a> &bull;
+  <a href="SECURITY.md">Security</a> &bull;
+  <a href="SCORECARD.md">Scorecard</a> &bull;
+  <a href="#-contributing">Contributing</a>
+</p>
+
+</div>
+
+---
+
+## Launch Status at a Glance
+
+| Claim | Current result | Evidence |
+|---|---|---|
+| Install path | Canonical release target `fastrmemory@0.3.1`; old scoped npm entries removed | `npm view fastrmemory version` -> `0.3.1`; `npm install -g fastrmemory@0.3.1`; `fastr --version` -> `0.3.1` |
+| Synthetic retrieval | Holdout `95.8%` Hit@1, `100%` Hit@5, MRR `0.969` | `npx tsx scripts/eval-bench.ts --split all --embeddings minilm --out bench/results/minilm.json` |
+| Test suite | `282` tests across `52` files in `0.3.1`; v0.2.1 is `235` / `43` | `npm test` |
+| Crash safety | 10/10 runs, 0 lost, 0 duplicate ids/titles | `npm run test:crash`; `bench/results/crash-test.json` |
+| Public retrieval (0.3.0) | LongMemEval `+10.4pp` / `+11.0pp` Hit@5; LoCoMo `+4.4pp` / `+2.3pp` (target missed) | [docs/EXTERNAL_BASELINE.md](docs/EXTERNAL_BASELINE.md) |
+| Release score | Provisional `9.4 / 10`; `9.2` target met; Retrieval remains Partial | [SCORECARD.md](SCORECARD.md) |
+
+The synthetic table is not SWE-bench or LongMemEval. Public numbers are retrieval-only and are not QA-leaderboard results. Full provenance is in [CLAIMS.md](CLAIMS.md).
+
+---
+
+## 💡 Overview
+
+AI coding agents (Claude Code, Cursor, Windsurf, Codex, Antigravity) degrade on long-running codebases when project memory is lossy or operationally heavy. Common designs make one of three trade-offs:
+- **Decay and merge** old episodes to keep the store small, which can lose exact file paths, stack traces, and edge cases.
+- **Run a daemon or external database**, which adds ports, containers, and setup failure modes.
+- **Dump a static context file**, which grows without bound and is not queryable.
+
+**FastrMemory** keeps a verbatim event log, bi-temporal memory history, and a replayable Git mirror in a **single in-process TypeScript engine** (3 runtime dependencies; local embeddings and the daemon are optional):
+
+<table>
+<tr>
+<td width="33%" align="center">
+
+### ⚡ Zero Daemon Overhead
+Pure Node 22+ built-in `node:sqlite` in WAL mode. On the 240-case suite, engine-level recall is **0.95 ms p50 / 1.60 ms p95** with hash embeddings and **3.30 ms p50 / 5.11 ms p95** with MiniLM on the train split (CLI startup measured separately). The default CLI/MCP path has no background daemon and no open port; `daemon start` is optional. Native on Windows, macOS, and Linux (the current CI matrix uses Intel macOS; Apple Silicon is not covered); CI matrix status is reported in [Actions](https://github.com/atifjubaer/fastrmemory/actions).
+
+</td>
+<td width="33%" align="center">
+
+### 🔀 Bi-Temporal Git Sync
+Never deletes facts during consolidation (there is no destructive sleep step). Replaces half-life decay with `valid_from` / `valid_to` timestamps and auto-mirrors human-readable `.fastr/pages/*.md` files into Git.
+
+</td>
+<td width="33%" align="center">
+
+### 🎯 Triple-Stream RRF ($k=20$)
+Fuses FTS5 BM25 + optional local embeddings + file-graph links. Error traps receive a **conditional 2.0x boost** only for trap-intent or file-scoped queries, with per-ID outcome feedback (+0.2 / -0.5). Three consecutive bad outcomes move a memory to dormant; confidence tiers are `high`, `medium`, `low`, `dormant`, and `superseded`.
+
+</td>
+</tr>
+</table>
+
+---
+
+## 🧭 Design Principles
+
+| Principle | Implementation |
+| :--- | :--- |
+| **Lossless by default** | Raw events, bi-temporal `valid_from` / `valid_to`, and supersession chains are retained. Nothing is destroyed by consolidation. |
+| **Zero daemon by default** | One Node 22+ process uses built-in `node:sqlite` in WAL mode. The default CLI/MCP path opens no ports or background services; `daemon start` is optional. |
+| **Replayable** | Git-diffable Markdown mirrors plus snapshots and rollback keep history inspectable. |
+| **Measured, not asserted** | Public claims are tied to committed benchmark JSON with a 20% holdout; simulated baselines are labeled as simulations. |
+
+---
+
+---
+
+## 🤖 Works With MCP- and HTTP-Compatible Agents
+
+FastrMemory exposes one stdio MCP server and optional local HTTP services (dashboard and daemon). **Native installers wire Claude Code (MCP config plus lifecycle hooks), Cursor (MCP config plus skills), and, since 0.3.0, Gemini CLI, GitHub Copilot CLI, and OpenCode V2** (`fastrmemory hook install`); `fastrmemory setup` also writes MCP configs for Antigravity, Claude Desktop, and Windsurf. Every other client connects through its own MCP configuration or the REST API. Integration depth varies by client - only the native installers are covered by tests in this repository.
+
+Clients commonly used with FastrMemory include Codex CLI, Gemini CLI, OpenCode, GitHub Copilot CLI, Antigravity, Claude Desktop, Cline, Continue, Roo Code, Goose, Zed, Warp, and Aider. Listing a client does **not** imply a tested native integration.
+
+---
+
+## 🚀 Quick Start
+
+### ⚡ Run Without a Global Install
+
+The canonical package target is unscoped `fastrmemory@0.3.1`. The old scoped npm entries were removed on 2026-10-23.
+
+```bash
+# Canonical one-shot (pins the exact release):
+npx -y fastrmemory@0.3.1 setup
+
+# Or launch the local Web UI:
+npx -y fastrmemory@0.3.1 ui
+```
+
+The GitHub source path remains available for development only: `npx github:atifjubaer/fastrmemory setup`. For a reproducible source install, pin the tag: `npx github:atifjubaer/fastrmemory#v0.3.1 setup`. Do not use either GitHub form in generated MCP or hook configs; those must pin the npm package version.
+
+---
+
+### Install from npm
+
+```bash
+# Canonical install (latest is 0.3.1):
+npm install -g fastrmemory
+fastr --version
+
+# Exact release:
+npm install -g fastrmemory@0.3.1
+```
+
+For a one-shot run without a global install:
+
+```bash
+npx -y fastrmemory@0.3.1 --version
+```
+
+`0.3.1` is built from tag `v0.3.1` by `.github/workflows/release.yml`, which runs the full gate, publishes with npm provenance, and attaches the same tarball to the GitHub Release. Verify the registry result with `npm view fastrmemory@0.3.1 version` and `npm view fastrmemory dist-tags --json`; a first E404 for a few minutes is registry propagation, not a failed publish. The old scoped npm entries remain removed. Do not republish `0.3.0`.
+
+### Install from GitHub
+
+For a one-shot source run, pin the release tag:
+
+```bash
+npx --yes github:atifjubaer/fastrmemory#v0.3.1 --version
+npx --yes github:atifjubaer/fastrmemory#v0.3.1 setup
+```
+
+For a global CLI without npm's Git resolver, download the release tarball:
+
+```bash
+curl -L -o fastrmemory-0.3.1.tgz \
+  https://github.com/atifjubaer/fastrmemory/releases/download/v0.3.1/fastrmemory-0.3.1.tgz
+npm install -g ./fastrmemory-0.3.1.tgz
+fastr --version
+```
+
+On Windows, download the same URL with `Invoke-WebRequest` or a browser, then run `npm install -g .\fastrmemory-0.3.1.tgz`. For a local project install, use `npm install --no-save ./fastrmemory-0.3.1.tgz` instead of the global flag.
+
+> Git installs build from source and are slower than the npm tarball; for a global CLI, prefer the npm package or the release tarball above. `npm install -g git+https://...` is not recommended with npm 11 because the `prepare` build does not receive dev dependencies. Both `fastrmemory` and `fastr` (short alias) are executable after installation. The canonical package is unscoped `fastrmemory@0.3.1`; the old scoped npm entries are gone. Use npm for generated MCP and hook configs so installs stay reproducible.
+
+### 2. Verify Database Health
+
+```bash
+fastrmemory status
+```
+
+Output:
+```text
+=== FastrMemory Health (my-project) ===
+- Project ID:          proj_1cce2a654e3a
+- Active Memories:     2
+- Staging Memories:    0
+- Superseded History:  0
+- Ingested Events:     0
+- Pending Spool:       Clear (0)
+- Database File:       .fastr/fastr.db
+```
+
+### 3. Record & Recall a Memory
+
+```bash
+# Record an error trap linked to an exact file:
+fastrmemory remember "Never Use Date.now() Milliseconds for JWT Expiration" \
+  -c "JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000)." \
+  -m auth -k error_trap -f "src/auth/jwt.ts" --verified
+
+# Recall with conditional 2.0x trap boost & file-graph matching:
+fastrmemory recall "JWT expiration" -f "src/auth/jwt.ts"
+```
+
+Output:
+```text
+=== Recalled Memories (1 results, ~46 tokens) ===
+
+[mem_009e4a7d] [TRAP] [verified] Never Use Date.now() Milliseconds for JWT Expiration (Score: 0.08)
+JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000).
+```
+
+Open contradictions are marked on both sides of the recall result instead of being silently mixed into context (**0.3.0**):
+
+```bash
+# Inspect unresolved contradictions:
+fastrmemory conflict list
+
+# Keep the rule that matches the project and supersede the loser:
+fastrmemory conflict resolve 1 --keep mem_009e4a7d --forget --reason "Seconds are the project standard"
+```
+
+#### Import Existing Local Rules (**0.3.0**)
+
+Bring `AGENTS.md`, `CLAUDE.md`, or `.cursor/rules/*.mdc` content into memory without hand-copying every section. Level 2+ headings become memories; bullet lists and paragraphs are fallbacks. Re-importing the same file skips exact duplicates.
+
+```bash
+# Preview the parsed sections without writing:
+fastrmemory import AGENTS.md --from agents-md --module rules --dry-run
+
+# Import as staging memories for review, or verify them immediately:
+fastrmemory import AGENTS.md --from agents-md --module rules
+fastrmemory import AGENTS.md --from agents-md --module rules --verified
+
+# JSONL snapshots use the same entry point:
+fastrmemory import snapshot.jsonl --from jsonl
+```
+
+### 4. Cognitive Git Blame & Memory-Aware Commit
+
+```bash
+# Cognitive Git Blame linking lines directly to commit, author, and governing error traps (conditional 2.0x boost):
+fastrmemory blame src/auth/jwt.ts:42
+
+# Pre-commit error trap validation & conventional commit synthesis:
+fastrmemory commit
+```
+
+### 5. Git Snapshots, Branches, Rollback & Background Daemon (branches are **0.3.0**)
+
+```bash
+# Point-in-time memory snapshot (Git for Agent Memory):
+fastrmemory snapshot create "pre-refactor-checkpoint"
+fastrmemory snapshot list
+fastrmemory snapshot rollback "pre-refactor-checkpoint"
+
+# 0.3.0: Portable backup with a sidecar provenance manifest:
+fastrmemory backup backups/pre-upgrade.jsonl
+fastrmemory backup --verify backups/pre-upgrade.jsonl
+fastrmemory backup --restore backups/pre-upgrade.jsonl --dry-run
+
+# Immutable memory branch and one-way merge with a conflict report:
+fastrmemory branch create feature/auth
+fastrmemory branch list
+fastrmemory merge feature/auth
+fastrmemory merge feature/auth --force --strategy branch
+
+# Hybrid Background Daemon (Optional HTTP/SSE service for cross-process tools):
+fastrmemory daemon start
+fastrmemory daemon status
+fastrmemory daemon stop
+
+# Auto-wire MCP configs, lifecycle hooks, and Planetary Skills into Claude Code, Cursor,
+# Gemini CLI, GitHub Copilot CLI, and OpenCode; setup also wires Antigravity, Claude Desktop, and Windsurf:
+fastrmemory hook install
+fastrmemory setup
+
+# Mine past Git bug fixes directly into staging error traps:
+fastrmemory learn -n 30 --days 90
+```
+
+Branches are immutable snapshot pointers. `merge` is one-way into the current active set: branch-only memories are added, target-only memories are preserved, and same-identity changes are reported as conflicts. Conflicts block writes by default; `--force` applies non-conflicting additions, and `--force --strategy branch` supersedes the target while keeping old rows in history. Branch checkout or a mutable branch working tree is not implemented.
+
+`backup` writes the portable JSONL snapshot plus `<file>.manifest.json` with the file SHA-256, content hash, record counts, tool version, environment, and source integrity. `--restore` verifies both hashes before importing; `--dry-run` reports counts without writing. The backup scope is memories, raw events, file links, and conflicts, not a physical SQLite/WAL copy. See [MIGRATION.md](MIGRATION.md) for the full backup and rollback path.
+
+### 6. Token Compression, Database Doctor & Vision Search
+
+```bash
+# Compress markdown docs & LLM prompt context to reduce token usage:
+fastrmemory compress docs/architecture.md --dry-run
+
+# Run deep health check across SQLite, FTS5 indices, file links, and task DAGs:
+fastrmemory diagnose
+
+# Auto-repair FTS5 indices, orphaned file links, and WAL fragmentation:
+fastrmemory heal
+
+# 0.3.0: Report orphaned records, duplicate active memories, and stale rows:
+fastrmemory hygiene
+fastrmemory hygiene --stale-days 30 --json --fail-on-issues
+
+# Tag a UI screenshot or architecture diagram with OCR & 384-dim vector indexing:
+fastrmemory vision tag screenshots/modal-error.png --desc "Modal error 401 alert" --ocr "HTTP 401"
+
+# Semantic search across tagged screenshots and visual diagrams:
+fastrmemory vision search "modal error 401"
+
+# Pre-merge CI/CD gate checking PR diffs against active error traps:
+fastrmemory guard --strict
+```
+
+`fastrmemory hygiene` reports orphaned file links, conflict rows, and feedback rows; duplicate active memories by normalized title or exact content; and stale unpinned active memories (default 90 days since the last recall or creation). `npm run check:hygiene` runs the same inspector against a deterministic fixture inside `check:ci`; it does not mutate a project database. Use `--fail-on-issues` when a script should exit nonzero on findings.
+
+---
+
+## 🔌 One-Click Agent MCP Configuration
+
+Use the installer when possible. `fastr setup` writes the platform-correct command (`node` with an absolute CLI path, or `cmd /c npx` where needed) and pins user-scoped clients to the project root. `fastr hook install` writes project-scoped configs and lifecycle hooks. The manual snippets below use `npx` for project-scoped clients; for user-scoped clients (Claude Desktop, Antigravity, Windsurf, and the Claude Code entry in `~/.claude.json`), append `--project /absolute/path/to/repo`.
+
+### Claude Code (`~/.claude.json`, user-scoped)
+```json
+{
+  "mcpServers": {
+    "fastrmemory": {
+      "command": "npx",
+      "args": ["-y", "fastrmemory@0.3.1", "mcp", "--project", "/absolute/path/to/your/repo"]
+    }
+  }
+}
+```
+
+### Cursor (`.cursor/mcp.json`, project-scoped)
+```json
+{
+  "mcpServers": {
+    "fastrmemory": {
+      "command": "npx",
+      "args": ["-y", "fastrmemory@0.3.1", "mcp"]
+    }
+  }
+}
+```
+
+### Gemini CLI (`.gemini/settings.json`, project-scoped, 0.3.0)
+```json
+{
+  "mcpServers": {
+    "fastrmemory": {
+      "command": "npx",
+      "args": ["-y", "fastrmemory@0.3.1", "mcp"]
+    }
+  }
+}
+```
+
+`fastrmemory hook install` also merges `SessionStart`, `BeforeTool` (`write_file|replace`), `PreCompress`, and `SessionEnd` hooks into the same project settings file. Gemini CLI requires strict JSON on hook stdout, so the generated commands pass `--format gemini`. Google is transitioning users from Gemini CLI to Antigravity CLI; this integration targets the still-documented `.gemini/settings.json` contract.
+
+### GitHub Copilot CLI (`.github/mcp.json`, project-scoped, 0.3.0)
+```json
+{
+  "mcpServers": {
+    "fastrmemory": {
+      "type": "local",
+      "command": "npx",
+      "args": ["-y", "fastrmemory@0.3.1", "mcp"]
+    }
+  }
+}
+```
+
+`fastrmemory hook install` also merges `.github/hooks/fastrmemory.json` with `sessionStart`, `preToolUse` (`edit|create|str_replace_editor|apply_patch`), `preCompact`, and `sessionEnd` hooks. Copilot has no model-facing advisory field for `preToolUse`, so an active trap returns `permissionDecision: "ask"` with the warning; autopilot/non-interactive mode treats `ask` as deny. The shared `AGENTS.md` written by the installer supplies repository instructions.
+
+### OpenCode V2 (`opencode.json`, project-scoped, 0.3.0)
+```json
+{
+  "mcp": {
+    "servers": {
+      "fastrmemory": {
+        "type": "local",
+        "command": ["npx", "-y", "fastrmemory@0.3.1", "mcp"]
+      }
+    }
+  }
+}
+```
+
+`fastrmemory hook install` also writes `.opencode/plugins/fastrmemory/index.ts`, which injects the session-start handoff and critical rules into model context and captures a snapshot before compaction. Existing `opencode.json(c)` settings are preserved; JSONC configs are left untouched and reported for manual wiring.
+
+> **Native Windows:** clients that cannot launch the `npx.cmd` shim directly should use `"command": "cmd"` and `"args": ["/c", "npx", "-y", "fastrmemory@0.3.1", "mcp"]` (add `--project` for user-scoped clients). `fastr setup` writes the absolute `node` path automatically and is the recommended path.
+
+---
+
+## 🛠️ MCP Server: Tools & Resources
+
+Built using the official **v2 `@modelcontextprotocol/server`** SDK. The tool list below describes **0.3.1** (unchanged from 0.3.0); the v0.2.1 release has 4 resources.
+
+### 41 MCP Tools
+
+The default **full profile** exposes all 41 tools. For a smaller schema, start the **core profile** with `fastrmemory mcp --profile core` or `FASTR_MCP_PROFILE=core`; it exposes the 12-tool daily loop: `fastr_recall`, `fastr_remember`, `fastr_handoff`, `fastr_trap_recall`, `fastr_trap_log`, `fastr_status`, `fastr_get`, `fastr_timeline`, `fastr_diff`, `fastr_replay`, `fastr_compress`, and `fastr_diagnose`. Resources and prompts are the same in both profiles. Pass `--project /absolute/path/to/repo` when the host starts the server outside the repository, so memory is written to the intended `.fastr/fastr.db`.
+
+#### Cognitive Retrieval & Memory Core
+1. `fastr_recall`: Triple-stream hybrid search (BM25 + Vector + Spreading Activation Graph) with progressive L0–L3 token budgeting and air-gapped offline vector fallback.
+2. `fastr_get`: Retrieves complete memory details (including status, timestamps, reward scores, and full content) by memory ID.
+3. `fastr_list`: Lists memories with bounded filtering by module, kind, status, limit, and offset.
+4. `fastr_drill`: Resolves `source_event_ids` to retrieve untruncated verbatim stack traces, diffs, and tool outputs from `raw_events`.
+5. `fastr_file_history`: Returns active rules, `[TRAP]` warnings, and past supersessions for a specific file path.
+6. `fastr_remember`: Records new rules, decisions, or traps. Automatically extracts NER entities, scrubs secrets, and re-renders Markdown mirrors. Supports `scope: 'project' | 'global'`.
+7. `fastr_pin`: Pins critical rules so they are permanently preserved and prioritized in L0 assembly without time decay.
+8. `fastr_forget`: Tombstones and deactivates an outdated memory cleanly with audit logging.
+9. `fastr_supersede`: Retires an outdated rule (`valid_to = now`), records the rationale, and inserts a replacement verified rule.
+10. `fastr_feedback`: Updates `reward_score` and the confidence tier on one memory ID (+0.2 good, -0.5 bad). Three consecutive bad outcomes make it dormant; never penalizes innocent memories.
+11. `fastr_handoff`: Saves or retrieves cross-agent session milestones and promotes staging memories to verified.
+12. `fastr_status`: Returns active/staging counts, spool health, and embedding coverage %.
+13. `fastr_graph_query`: Explores 1-hop and 2-hop structural file-link dependencies, entity links, and connected error traps.
+14. `fastr_timeline`: Chronological audit trail of memory events, newly verified rules, error traps, and historical supersessions.
+
+#### Versioning & Error Traps
+15. `fastr_snapshot`: Creates named point-in-time memory snapshots for branch tracking and experiment safety.
+16. `fastr_rollback`: Instant Git-like rollback to any previous memory snapshot.
+17. `fastr_trap_log`: One-line rapid logging of error traps and bug solutions with a conditional 2.0x recall boost.
+18. `fastr_trap_recall`: Targeted lookup of high-priority error traps protecting specific target files before editing.
+
+#### Proactive Contradiction Detection & Resolution
+19. `fastr_conflicts`: Proactive contradiction detection using Jaccard token overlap (minimum 0.35) and 50-word opposing-polarity analysis.
+20. `fastr_resolve`: Resolves contradictions by keeping preferred rule and superseding or weakening the loser.
+
+#### Kahneman Planning Fallacy & Base-Rate Calibrator
+21. `fastr_predict`: Records effort/time/risk predictions and closes predictions with actual empirical outcomes.
+22. `fastr_predict_baserate`: Computes historical reference-class statistics (Mean, Median p50 ratio, MAE) to debias agent estimates.
+
+#### Multi-Agent Action DAG & Frontier
+23. `fastr_action_create`: Creates structured work item actions with prerequisite (`requires`) and conflict (`conflicts_with`) constraints.
+24. `fastr_action_update`: Updates task lifecycle (`pending`, `active`, `done`, `blocked`), assignments, and memory crystallization.
+25. `fastr_frontier`: Computes unblocked, ready-to-execute frontier actions with satisfied dependencies.
+26. `fastr_next`: Atomically claims and returns the highest-priority frontier action for autonomous worker agents.
+
+#### Bounded Working Memory & Obsidian Vault Export
+27. `fastr_slot_get`: Retrieves bounded working memory slot (e.g. `current_goal`, `user_preferences`, `active_hypothesis`).
+28. `fastr_slot_set`: Updates working memory slot with hard character ceiling enforcement to prevent context bloat.
+29. `fastr_slot_list`: Lists all working memory slots and active character usage.
+30. `fastr_obsidian_export`: Exports all memories, entities, and relationships into an Obsidian-compatible markdown vault with YAML frontmatter, `[[wikilinks]]`, and `MOC.md`.
+
+#### Multi-Repository Federation & Context Assembly
+31. `fastr_federate`: Manages cross-repository organization-wide shared rules and error traps via SQLite native `ATTACH DATABASE` (`~/.fastr/global.db`).
+32. `fastr_assemble`: Dynamically formats and packs high-density structured prompt context (`<fastr_context>`) with token budgeting.
+33. `fastr_risk_predict`: Computes historical failure probability and active trap hazard score for target codebase files.
+34. `fastr_verify_provenance`: Cryptographically verifies SHA-256 provenance hashes for recorded agent attribution.
+
+#### Token Compression & Autonomous Doctor
+35. `fastr_compress`: Compresses markdown files or prompt context while strictly preserving headings, URLs, and code blocks with `.original.md` backup.
+36. `fastr_diagnose`: Deep health audit of SQLite B-Tree integrity, FTS5 BM25 search indices, orphaned file links, and task DAGs.
+37. `fastr_heal`: Automatic repair of database indices, dangling edges, and WAL page reclamation.
+
+#### Memory Replay & Diff
+38. `fastr_replay`: Reconstructs memory state at a timestamp and returns the active snapshot for audit or recovery.
+39. `fastr_diff`: Compares two snapshots and reports added, superseded, and removed memories.
+
+#### Multimodal Visual Memory
+40. `fastr_vision_tag`: Tags screenshots, UI diagrams, and wireframes with OCR and semantic descriptions with 384-dim embeddings.
+41. `fastr_vision_search`: Hybrid vector and keyword search across stored visual assets for multimodal coding agents.
+
+### 2 MCP Prompt Templates
+
+- `pre-edit-check`: Given file paths, instructs the agent to check traps and relevant rules before editing.
+- `session-wrap-up`: End-of-session checklist for logging traps, superseding stale rules, scoring memories, and saving a handoff.
+
+### 5 MCP Resources (0.3.0; v0.2.1 has 4)
+
+- `fastr://project/overview`: L0 project summary containing active counts and storage location.
+- `fastr://project/traps`: All active `[TRAP]` warnings for immediate bug avoidance.
+- `fastr://session/handoff`: Latest cross-agent handoff milestone.
+- `fastr://memory/{id}` (resource template): Full JSON for a single memory, including linked files and its validity window.
+- `fastr://memory/{id}/envelope` (resource template): Metadata, cryptographic provenance, file/graph links, and open/resolved conflict state for one memory.
+
+---
+
+## 📄 Two-Zone Git-Diffable Mirror
+
+Every write to the local SQLite database automatically synchronizes human-readable markdown files in `.fastr/pages/<module>.md`. This allows developers to review AI memories directly in GitHub Pull Requests:
+
+```markdown
+# Module: auth
+
+> Auto-generated by FastrMemory. Active rules are at the top; superseded history is preserved below for Git diffs.
+
+---
+
+## Compiled Truth (Active Rules & Traps)
+
+### [mem_009e4a7d] [TRAP] Never Use Date.now() Milliseconds for JWT Expiration
+- **Kind**: `error_trap`
+- **Status**: `verified` (Reward Score: 1)
+- **Linked Files**: `src/auth/jwt.ts`
+- **Active Since**: `2026-10-18T21:46:20Z`
+
+JWT exp claims expect integer seconds. Always use Math.floor(Date.now() / 1000).
+
+---
+
+## Append-Only Timeline (History & Superseded)
+
+### [EXPIRED 2026-10-18T20:00:00Z -> 2026-10-18T21:46:20Z] [mem_abc123] Token Signing
+- **Superseded By**: `[mem_009e4a7d]`
+- **Reason**: Standardized on integer seconds
+- **Historical Status**: `superseded`
+
+> Old implementation used milliseconds which failed expiration validation.
+```
+
+---
+
+## 🧠 Planetary Agent Skills Suite
+
+FastrMemory ships 10 Agent Skills (in `skills/`, mirrored to `.cursor/skills/`) that tell agents *when* to use each memory tool. Install them as a Claude Code plugin (`.claude-plugin/`) or copy them with `fastrmemory setup`:
+
+- [fastr-memory](skills/fastr-memory/SKILL.md): At the start of a task and before editing files: `fastr_trap_recall`, then `fastr_recall` / `fastr_assemble`.
+- [fastr-trap-log](skills/fastr-trap-log/SKILL.md): The moment a failure is diagnosed: record it with `fastr_trap_log`.
+- [fastr-session-commit](skills/fastr-session-commit/SKILL.md): When a task is done and tests pass: supersede, rate memories, and `fastr_handoff` with `verifyStaging`.
+- [fastr-curate](skills/fastr-curate/SKILL.md): When storing durable lessons or fixing contradictions: dedupe, remember, supersede, resolve conflicts, snapshot/rollback.
+- [fastr-setup](skills/fastr-setup/SKILL.md): When FastrMemory is not wired into Claude Code: `fastrmemory hook install`, `claude mcp add`, verify with `fastrmemory status`.
+- [fastr-plan-estimate](skills/fastr-plan-estimate/SKILL.md): When estimating effort or risk: base rates, file risk, and closing predictions.
+- [fastr-dag](skills/fastr-dag/SKILL.md): When work has dependent steps or several agents share a backlog.
+- [fastr-doctor](skills/fastr-doctor/SKILL.md): When recall misses memories or the database looks unhealthy: diagnose, then heal.
+- [fastr-compress](skills/fastr-compress/SKILL.md): When a doc or context block exceeds its token budget.
+- [fastr-vision](skills/fastr-vision/SKILL.md): When screenshots or diagrams should be remembered or searched.
+
+Run `npm run check:skills` to validate every tool call in the skills against `src/mcp/server.ts`.
+
+---
+
+## 🏗️ Architecture
+
+```mermaid
+flowchart TD
+    subgraph Ingestion["1. Lossless Ingestion & Spool"]
+        Agent["AI Coding Agent\n(Claude Code, Cursor, Antigravity)"] --> Scrubber["Secret Scrubber\n(API Keys, Bearer, PEM)"]
+        Scrubber --> Spool{"SQLite Busy?"}
+        Spool -- Yes --> SpoolFile[".fastr/spool/pending.jsonl\n(async fallback)"]
+        Spool -- No --> DB
+    end
+
+    subgraph Storage["2. Bi-Temporal Storage & Git Mirror"]
+        DB[("Node 22 node:sqlite (WAL)\nraw_events | memories\nfile_links | handoffs")]
+        DB --> Mirror["Markdown Mirror Engine"]
+        Mirror --> Pages[".fastr/pages/<module>.md\nTop: ## Compiled Truth\nBottom: ## Append-Only Timeline"]
+    end
+
+    subgraph Search["3. Triple-Stream Hybrid Retrieval"]
+        Query["Recall / File Query"] --> FTS["Stream A: FTS5 BM25\n(Sub-millisecond)"]
+        Query --> Vec["Stream B: Xenova Vectors\n(all-MiniLM-L6-v2)"]
+        Query --> Graph["Stream C: file_links Graph\n(1-2 Hop Structural Match)"]
+        FTS & Vec & Graph --> RRF["RRF Fusion (k=20)\n+ Conditional 2.0x Error Trap Multiplier\n+ 1.25x Verified Multiplier"]
+        RRF --> Budget["Progressive Token Packer\nL0 (150t) | L1 (500t) | L2 (1500t) | L3 (4000t)"]
+    end
+
+    subgraph Protocol["4. Official MCP Protocol"]
+        Budget --> MCPServer["Official MCP v2 Server\n(@modelcontextprotocol/server)"]
+        MCPServer --> Tools["41 tools • 2 prompts • 5 resources"]
+        Tools --> Agent
+    end
+```
+
+---
+
+## 🧪 Testing & Verification
+
+Run the comprehensive unit test suite:
+
+```bash
+npm test
+```
+
+All **282 tests pass** across **52 test files** in 0.3.1 (the v0.2.1 release has **235 tests / 43 files**) covering database schema, WAL locking, offline spooling, bi-temporal supersession, secret scrubbing, two-zone rendering, automated benchmarks, snapshots/rollback, branch merge conflict reports, replay/diff, memory envelopes, confidence tiers and 3-bad dormancy, memory hygiene checks, Memory CI, conflict-aware recall, portable backup manifests and verified restore, local rule import, OpenCode V2, Gemini CLI, and Copilot CLI wiring, git-learner, cognitive blame, commit synthesis, hybrid background daemon, token compression, self-healing doctor, multimodal vision, web dashboard server, pre-merge trap guardian, UI loopback security boundaries, and atomic installer configuration safety.
+
+**CI performance gates:** `check:query-plans`, `check:recall-latency`, and `check:install-size` run inside `check:ci`. CI executes them on the canonical Ubuntu/Node 24 job; other matrix jobs set `FASTR_PERF_GATE=0` because timing is runner-sensitive, while functional tests still run on every matrix entry.
+
+**Crash-safety evidence:** `npm run test:crash` kills the writer at randomized points across 10 runs, then reopens the WAL database. The committed report at [`bench/results/crash-test.json`](bench/results/crash-test.json) records **10,718 acknowledged writes**, **10,727 committed rows**, **0 lost**, **0 duplicate ids/titles**, and `PRAGMA integrity_check = ok`; methodology is in [`docs/audit/2026-10-21-crash-test.md`](docs/audit/2026-10-21-crash-test.md). `npm run check:crash` validates the report during `check:ci`. This is a process-crash test (`taskkill /F`), not a power-loss test; SQLite runs with `synchronous=NORMAL` in WAL mode.
+
+---
+
+## Retrieval Benchmark (240 synthetic cases)
+
+Generated from [`bench/results/minilm.json`](bench/results/minilm.json) on **2026-10-20** at benchmark commit `562f461`. The corpus is deterministic: 120 memories and 240 queries, split into **192 train / 48 holdout (20%)**. The holdout was fixed before tuning and is reported separately. Reproduce with:
+
+```bash
+npx tsx scripts/eval-bench.ts --split all --embeddings minilm --out bench/results/minilm.json
+npx tsx scripts/eval-bench.ts --split all --embeddings hash   --out bench/results/hash.json
+```
+
+| Configuration | Split | Cases | Hit@1 | Hit@3 | Hit@5 | MRR | nDCG@10 | Context tokens | p50 |
+| :--- | :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
+| FastrMemory + MiniLM | Train | 192 | 96.4% | 99.0% | 100% | 0.976 | 0.982 | 208 | 3.30 ms |
+| FastrMemory + MiniLM | **Holdout** | 48 | **95.8%** | **97.9%** | **100%** | **0.969** | **0.977** | 209 | 3.41 ms |
+| FastrMemory BM25-only | Train | 192 | 79.7% | 90.6% | 100% | 0.868 | 0.900 | 203 | 0.48 ms |
+| FastrMemory BM25-only | Holdout | 48 | 77.1% | 77.1% | 93.8% | 0.804 | 0.835 | 204 | 0.60 ms |
+| Static dump - simulated baseline | Train | 192 | 2.1% | 6.3% | 8.3% | 0.055 | 0.081 | 3652 | 0.00 ms |
+| Static dump - simulated baseline | Holdout | 48 | 0.0% | 0.0% | 8.3% | 0.025 | 0.056 | 3652 | 0.00 ms |
+
+> **Caveats:** this is a deterministic synthetic corpus, not SWE-bench or LongMemEval. The static-dump row is a simulation implemented in this repository, not an external project. Separate public retrieval-only external baselines are documented in [docs/EXTERNAL_BASELINE.md](docs/EXTERNAL_BASELINE.md); the synthetic table does not measure them. Context tokens are the compact prompt text under a 250-token budget; the ranked result objects retain full memory content. Methodology, per-category breakdowns, ablations, and confidence intervals are in [BENCHMARKS.md](BENCHMARKS.md) and [docs/benchmark-report.md](docs/benchmark-report.md).
+
+## 🖥️ Local Web Dashboard v2 & 3D Brain Observatory
+
+Visualize active rules, error traps, timeline audits, and interactive 3D memory constellations directly in your browser from bundled UI assets (no external service or database):
+
+```bash
+fastrmemory ui
+```
+
+- **Live URL**: `http://localhost:4242`
+- **Dashboard v2 Architecture**: Built with **shadcn/ui**, **Tailwind CSS v4**, and **TanStack Query**, with SSE updates plus version polling for cross-process writes.
+- **12 Focused Route Workspaces (0.3.0 adds `/replay`)**:
+  - `/`: Real-time system vitals, active trap alerts, recent memory feed, and quick-action shortcuts.
+  - `/memories`: Search, filter, and inspect memories with the slide-out **Memory Detail Sheet**, status toggles, pin, and 1-click forget.
+  - `/traps`: Dedicated **Error Trap Quarantine** displaying governing files, conditional boost conditions, and verified mitigation lessons.
+  - `/conflicts`: Proactive bi-temporal contradiction detection with side-by-side **Word Diff** and 1-click resolution (`Keep A`, `Keep B`, `Keep Both`).
+  - `/actions`: Real-time interactive **Action DAG Canvas** tracking task dependencies, worker assignments, and glowing unblocked frontier aura.
+  - `/graph`: Interactive file and entity relationship graph with 1-hop/2-hop inspection and memory drill-down.
+  - `/observatory`: High-performance **Three.js 3D Constellation Galaxy** with a smooth lerp camera, celestial star dust, glowing amber trap halos, and memory inspect modals.
+  - `/treemap`: Interactive high-DPI squarified treemap visualising memory strength bands and module density.
+  - `/search`: **Search Lab** evaluating triple-stream RRF retrieval with latency waterfall breakdown (BM25 vs Vector vs Graph).
+  - `/replay` (**0.3.0**): **Replay & Diff** workspace reconstructing the active set at two timestamps with snapshot metrics and added/superseded/changed/conflict review.
+  - `/health`: Autonomous SQLite self-healing Doctor with 1-click integrity diagnosis, FTS5 rebuild, and vacuum.
+  - `/settings`: Live database path, project configuration, and export controls.
+- **Memory CI**: The PR diff workflow and comment lifecycle are documented in [docs/MEMORY_CI.md](docs/MEMORY_CI.md).
+- **Dual Theme Support**: Light, dark, and system-preference modes.
+- **Default Zero-Daemon Path**: The dashboard is served by the in-process Node.js HTTP server and embedded SQLite WAL mode; `fastrmemory daemon start` is an optional local REST/SSE service.
+
+---
+
+## 🧩 Native VS Code & Cursor Extension
+
+Package and install the native FastrMemory Guardian extension for **VS Code** and **Cursor**:
+
+```bash
+# Compile and package extension
+npm run build:extension
+npx @vscode/vsce package --no-dependencies
+
+# Install into Cursor or VS Code
+cursor --install-extension fastrmemory-vscode-0.1.0.vsix
+```
+
+- **⚡ Status Bar Pill**: Displays active trap count in the status bar (`⚡ 3 Traps Active` or `⚡ 1 Trap on File`). Clicking opens an interactive QuickPick listing all active traps.
+- **Amber Underlines**: Trapped files are underlined in amber with full hover mitigation instructions and conditional 2.0x boost conditions.
+- **Problems Tab Integration**: Active error traps populate the IDE Problems panel as non-blocking warning diagnostics.
+- **Zero Daemons**: Reads directly from `.fastr/fastr.db` via `node:sqlite`.
+
+---
+
+## 🤝 Contributing & Pull Request Roadmap
+
+We warmly welcome contributions from the open-source community! Whether you are adding a new AI coding agent hook, integrating local embedding backends, or crafting 3D visualizations, your pull requests are valued and reviewed promptly.
+
+### 🏆 Contributor Wall of Fame
+
+Special thanks to **[@the-arizul](https://github.com/the-arizul)** for architecting PRs #1 through #11:
+- **PR #1**: Loopback security boundaries, DNS rebinding lockdown, and `dist-ui` package resolution.
+- **PR #2**: Safe atomic JSON config merges, nested Claude Code hook schemas, and sandboxed installer tests.
+- **PR #3**: Hardened GitHub Actions fork PR comment safety.
+- **PR #4**: Core SQLite B-tree heal, BUSY spool fallback, ATTACH injection prevention, and atomic claim/supersede.
+- **PR #5**: Git security hardening (zero shell interpolation, confined paths, and high-entropy secret scrubbing).
+- **PR #6**: Triple-stream RRF recall ranking calibration, zero irrelevant results, and Unicode query normalization.
+- **PR #7**: MCP server hardening (`isError` handling, bounded inputs, parameter annotations, prompts, and new tools: `fastr_get`, `fastr_list`, `fastr_pin`, `fastr_forget`).
+- **PR #8**: Skills suite consolidation, plugin manifest, and CI validation runner.
+- **PR #9**: VS Code extension headless activation fallback and staging trap decorations.
+- **PR #10**: Isolated benchmark database harnesses and calibrated baselines.
+- **PR #11**: Planetary Dashboard v2 overhaul with shadcn/ui, Tailwind CSS v4, and live cross-process sync.
+
+---
+
+### 🗺️ Open Contribution Roadmap
+
+| Domain / Focus Area | What Needs Building | Difficulty | Reference Location | Target PR Scope |
+| :--- | :--- | :--- | :--- | :--- |
+| **Agent Hook Installers** | Auto-wire hooks & skills for Windsurf, Roo Code, Continue, and Warp | `good first issue` | [src/installer/setup.ts](src/installer/setup.ts) | `feat(installer)` |
+| **Local Embedding Providers** | Optional on-device backends (Ollama, llama.cpp, WebGPU) with air-gapped fallback | Intermediate | [src/search/embeddings.ts](src/search/embeddings.ts) | `feat(embeddings)` |
+| **IDE Extensions** | JetBrains (IntelliJ / WebStorm) and Neovim Lua plugin with status bar pill & trap underlines | Advanced | [extensions/vscode/](extensions/vscode/) | `feat(ide)` |
+| **Benchmark Runners** | SWE-bench and additional public QA scenario runners; LongMemEval and LoCoMo retrieval harnesses already exist | `good first issue` | [src/bench/benchmark.ts](src/bench/benchmark.ts) | `feat(bench)` |
+| **UI Visualizations** | Custom Three.js shaders, Treemap color palettes, and SVG/PNG graph exports | Intermediate | [ui/src/components/](ui/src/components/) | `feat(ui)` |
+
+---
+
+### 🚀 Pull Request Workflow
+
+1. **Fork & Clone Repository**:
+   ```bash
+   git clone https://github.com/<your-username>/fastrmemory.git
+   cd fastrmemory
+   ```
+
+2. **Install Dependencies & Verify Test Suite (282 Tests Passing)**:
+   ```bash
+   npm install
+   npm test
+   ```
+
+3. **Create a Feature Branch**:
+   ```bash
+   git checkout -b feat/add-windsurf-hooks
+   # or for bug fixes:
+   git checkout -b fix/sqlite-busy-retry
+   ```
+
+4. **Implement Changes & Verify All Packages Compile**:
+   ```bash
+   # Compiles backend, React UI, and VS Code extension
+   npm run build:all
+   npm test
+   ```
+
+5. **Commit with DCO Sign-off (`-s`) & Open Pull Request**:
+   ```bash
+   git commit -s -m "feat(installer): add windsurf auto-hook integration"
+   git push origin feat/add-windsurf-hooks
+   ```
+
+---
+
+### 📋 Pull Request Quality Checklist
+
+Before submitting your PR, verify:
+- [ ] **Strict TypeScript**: `npm run build:all` passes without type errors.
+- [ ] **Zero External Daemons**: Engine runs in-process via Node.js WAL SQLite.
+- [ ] **100% Test Green**: `npm test` passes all 282 unit tests across 52 files.
+- [ ] **DCO Sign-off**: All commits signed off using `git commit -s` ([Developer Certificate of Origin](https://developercertificate.org/)).
+- [ ] **Pre-Merge Trap Guardian**: Run `fastrmemory guard --strict` to verify no active error traps are violated.
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for full architectural guidelines, secret scrubbing rules, and local development environment setup.
+
+---
+
+## 📄 License
+
+Apache License 2.0. Built by **Fastrsoft**. Free for personal and commercial use.