superlocalmemory 3.8.0 → 3.8.2

package/CHANGELOG.md

@@ -5,6 +5,118 @@ All notable changes to SuperLocalMemory V3 will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.8.2] - 2026-07-24 — Self-healing upgrades & faster, consistent recall
+
+### Added
+
+- **Self-healing on startup.** After an upgrade the daemon quietly repairs its
+  own index in the background — backfilling any missing embeddings and rebuilding
+  vector indexes — with no manual steps and no interruption to recall. Progress
+  is visible in the dashboard. Upgrading is now genuinely zero-touch.
+- **Confidence-aware recall.** Every recall result now carries clear confidence
+  signals (`no_confident_match`, `answer_confidence`, `abstained`). Connected
+  assistants are guided to sharpen and re-run a query when confidence is low
+  rather than guessing — better answers, with no extra server-side wait.
+- **New `client_driven_agentic` setting** controls whether query refinement is
+  delegated to the calling assistant (default) or performed inside the server.
+- **Self-repairing components.** On startup SLM checks that the models and
+  dependencies it needs are present and quietly re-downloads or reinstalls the
+  ones it can, in the background — no commands to run. Anything it can't fix on
+  its own (for example a missing Ollama install) is reported with the exact
+  command to fix it.
+- **Dashboard “System Health” report.** A new panel in the dashboard Help area
+  shows every component as ready / missing / degraded, with copy-paste fixes and
+  a “Retry now” button.
+- **Editable memory settings in the dashboard.** A new “Recall & Memory
+  Behaviour” group lets you tune recall depth, the quality reranker, and memory
+  injection from the UI. Changes apply immediately and persist — no config files
+  to edit by hand.
+- **`slm help` and `slm doctor --fix`.** `slm help` now prints a grouped guide to
+  every command plus focused topics (`slm help modes | config | self-heal`), and
+  `slm doctor --fix` auto-repairs the components it can.
+- **Friendlier first-time setup.** `slm setup` detects a local Ollama and offers
+  Smart-Local mode in one keypress, summarizes what will download and asks before
+  the large optional compression model, can connect all your detected IDEs in one
+  step, and finishes with a health check. Skill Evolution is now off by default.
+
+### Changed
+
+- **Recall is faster and consistent across every surface.** The CLI, MCP, and
+  editor integrations now return the same fast local results (all retrieval
+  channels plus reranking) in about 1–2 seconds and behave identically. The
+  occasional multi-second tail on some queries is gone.
+- **Dashboard search stays snappy.** The search box returns a quick result list;
+  richer synthesis remains available in the memory chat and knowledge-cluster
+  summaries.
+
+### Fixed
+
+- **Large databases no longer produce an occasional multi-second recall spike**
+  (graph bridge discovery is now time-bounded).
+- **Upgrades that only relabel an embedding model no longer trigger a full
+  re-embed** of every stored memory.
+- Dashboard search now reliably reflects the active profile.
+
+## [3.8.1] - 2026-07-23 — Existing-install stability
+
+### Fixed
+
+- **Large existing databases no longer delay daemon readiness for a full tier
+  rebalance.** Startup now initializes bounded backend state and leaves the
+  scheduled full-database tier evaluation to maintenance.
+- **Failed enrichment can no longer retry forever.** Automatic durable-ingestion
+  materialization stops after ten attempts; an operator can still request an
+  explicit retry after correcting the underlying issue.
+- **Background enrichment no longer monopolizes SQLite.** Durable
+  materialization now uses short saga checkpoints instead of holding one
+  database write transaction across model extraction and embedding work, so
+  remember, update, delete, and dashboard actions remain writable while
+  enrichment continues.
+- **Durable enrichment retries are idempotent after partial failure.** Fact,
+  evidence, provenance, graph, temporal, and entity-association effects are
+  checkpointed or keyed so retries and process recovery cannot inflate them.
+- **Entity counts stay O(1) on mature databases.** A normalized, indexed
+  fact/entity association ledger replaces per-entity scans of the full facts
+  table; existing associations are backfilled once during upgrade.
+- **Newly queryable memories are immediately visible to recall.** A strong
+  exact BM25/FTS hit now retains one bounded result slot even when semantic
+  candidates would otherwise fill a small `limit`, preserving the
+  queryable-before-enrichment contract.
+- **Mesh heartbeat writes no longer block the async HTTP event loop.** SQLite
+  work runs in FastAPI's worker thread pool, keeping health, token, dashboard,
+  recall, and remember endpoints responsive during peer activity.
+- **Dashboard navigation preserves mounted pane state.** Brain, Knowledge Graph,
+  Memories, and Entity Explorer do not remount and refetch on every return.
+  Successful writes and configuration changes invalidate pane state once so
+  the next visit refreshes deliberately.
+- **Brain telemetry is historical and provenance-backed.** Existing reward
+  outcomes are repaired into source-quality observations in resumable bounded
+  batches, and transient database errors can no longer be reported as a
+  completed repair.
+- **Company-mode learning controls enforce workspace permissions.** Learning
+  and behavioral reads and mutations now apply the same read, write, delete,
+  and manage gates as the rest of the control plane.
+- **Large graph views have a fixed browser-compute budget.** The dashboard can
+  render the requested graph result while force simulation is bounded, with a
+  short initial settle and finite animation window; selecting a large graph can
+  no longer monopolize the browser main thread.
+- **Interactive model workers stay warm instead of repeatedly cold-starting.**
+  Embedding and reranker workers now remain resident for a 30-minute working
+  session by default, and the embedding peak guard matches the daemon's
+  2.5 GB per-worker watchdog. Low-RAM installations can retain shorter idle
+  windows and stricter recycling through the existing environment overrides.
+- **CLI mutations use the resident daemon as the single database writer.**
+  Exact delete and update commands no longer initialize a competing engine
+  beside a running daemon, preventing lock failures on active existing
+  installations.
+- **Skill Evolution repairs incomplete historical schemas.** The migration
+  runner verifies a completed migration's promised end-state before skipping
+  it and reapplies additive DDL when an older upgrade left a required table
+  missing.
+- **Release packages are deterministic again.** Canonical data-root routing,
+  generated plugin parity checks, truthful integration instructions, and the
+  bounded npm package surface are restored.
+
 ## [3.8.0] - 2026-07-23 — Teams, bounded loops, and nine framework adapters
 
 ### Added

package/README.md

@@ -5,10 +5,10 @@
   </picture>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.8.0</h1>
+<h1 align="center">SuperLocalMemory V3.8.2</h1>
 <p align="center"><strong>Enterprise-grade, local-first memory for AI agents and teams.</strong><br/>
 <em>A persistent, auditable long-term brain for your agents that runs on your own infrastructure — with multi-workspace isolation, role-based access, and GDPR + EU AI Act governance controls built in.</em></p>
-<p align="center"><code>v3.8.0</code> — one control plane: auditable retrieval · multi-scope memory (personal / shared / global) · Cache · Compress · trusted-peer Mesh · bounded loops — across CLI, MCP, dashboard, and the <strong>Claude, Codex, and GitHub Copilot</strong> plugins.<br/>
+<p align="center"><code>v3.8.2</code> — one control plane: auditable retrieval · multi-scope memory (personal / shared / global) · Cache · Compress · trusted-peer Mesh · bounded loops — across CLI, MCP, dashboard, the <strong>Claude plugin</strong>, the <strong>Codex add-on</strong>, and documented IDE integrations.<br/>
 Proxy: <code>slm wrap claude</code> &nbsp;·&nbsp; MCP: add <code>slm_compress</code> to your config &nbsp;·&nbsp; Skill: zero-config</p>
 <p align="center"><strong>3 public research preprints</strong> (arXiv + Zenodo archives) · <a href="https://arxiv.org/abs/2603.02240">arXiv:2603.02240</a> · <a href="https://arxiv.org/abs/2603.14588">arXiv:2603.14588</a> · <a href="https://arxiv.org/abs/2604.04514">arXiv:2604.04514</a></p>
 
@@ -34,11 +34,14 @@ SuperLocalMemory is an enterprise-grade, local-first memory control plane for AI
 
 Agent-memory systems make different storage, model-provider, and deployment trade-offs. SuperLocalMemory starts with a local runtime and makes provider-backed enrichment, cloud backup, connectors, and proxy use explicit choices.
 
+Different products solve different boundaries. The published benchmark evidence carried into V3.8.0 is protocol-scoped evidence from the published V3 research, not a claim of a newly rerun V3.8.0 package benchmark.
+
 SuperLocalMemory V3 combines conventional dense and lexical retrieval with graph, temporal, associative, and statistical relevance scoring. The default local runtime does not require Docker, a separately operated graph database, or an API key.
 
 **Memory with a sense of time.** SLM does not only store *what* an agent learned — it records *when*. Every fact carries ingestion timing and provenance; recall runs a dedicated temporal candidate channel alongside semantic, lexical, and associative retrieval; scenes and entity timelines reconstruct sequence; and the lifecycle lets neglected memory decay and self-archive instead of growing without bound. Time is a first-class ranking and lifecycle signal rather than a timestamp column an agent never reads — which is what lets a long-lived agent reason about how its context changed, not only what it currently holds.
 
-**What V3.8.0 adds.** This release is a reliability and governance pass on that foundation, not one feature:
+**What V3.8.0 added.** The 3.8.0 capability release introduced the following
+foundation; 3.8.1 is the existing-install stability patch for it:
 
 - **Temporal depth** — the time-aware retrieval and lifecycle described above.
 - **Governance & EU compliance** — [team roles, workspace isolation, a login gate, multi-scope memory, GDPR access/erasure/portability rights, a hash-chained audit trail, and per-mode EU AI Act self-assessment](#teams-and-enterprise-memory-v380).
@@ -49,7 +52,7 @@ SuperLocalMemory V3 combines conventional dense and lexical retrieval with graph
 
 SLM is one strand of Qualixar's work on AI reliability engineering: making agent behavior observable, bounded, and reproducible instead of best-effort.
 
-**Published benchmark evidence carried into V3.8.0:** the architecture evaluated in the V3 paper remains the foundation of this release. The figures below keep their original LoCoMo protocol, answer-construction, model, and sample scope; they are not a claim of a newly rerun V3.8.0 package benchmark.
+The architecture evaluated in the V3 paper remains the foundation of this release. The figures below keep their original LoCoMo protocol, answer-construction, model, and sample scope.
 
 ### How SLM fits beside other memory systems
 
@@ -82,7 +85,7 @@ memory, retrieve bounded evidence for an agent, and expose cache, compression,
 and peer-coordination controls through a CLI, MCP, dashboard, and supported
 IDE integrations.
 
-![SuperLocalMemory V3.7 capability architecture: modes, seven operating layers, Scale Engine, Mesh, delivery surfaces, and opt-in adapters](docs/assets/slm-v37-capability-architecture.png)
+![SuperLocalMemory V3 capability architecture: modes, seven operating layers, Scale Engine, Mesh, delivery surfaces, and opt-in adapters](docs/assets/slm-v37-capability-architecture.png)
 
 *Architecture boundary: SQLite + sqlite-vec remain canonical; CozoDB and
 LanceDB are parity-gated projections; Mesh coordinates trusted peers rather
@@ -464,27 +467,21 @@ not a byte-preserving operation; use it only when you want the MCP server
 configured. Check the result with `slm codex status`; undo SLM-owned add-ons
 with `slm codex remove`.
 
-## GitHub Copilot plugin
+## GitHub Copilot integration
 
-GitHub Copilot gets SuperLocalMemory as its long-term brain — at parity with the
-Claude and Codex plugins — across VS Code, Visual Studio, JetBrains, Eclipse, and
-the Copilot CLI:
+The shipped installer configures the SuperLocalMemory MCP server and additive
+agent instructions for VS Code with GitHub Copilot:
 
 ```bash
-slm connect copilot
+slm connect vscode-copilot --here
 ```
 
-A non-destructive merge into your existing project (nothing is overwritten):
-
-- **`.vscode/mcp.json`** — the SLM MCP server, GA on every Copilot IDE (the reliable baseline).
-- **`.github/copilot-instructions.md`** — SLM agent rules, merged inside `<!-- SLM-START -->` / `<!-- SLM-END -->` markers.
-- **`.github/prompts/*.prompt.md`** — 12 slash-command skills: `slm-cache`, `slm-compress`, `slm-governance`, `slm-graph`, `slm-loop`, `slm-mesh`, `slm-profile`, `slm-recall`, `slm-remember`, `slm-scope`, `slm-session`, `slm-status`.
-- **`.github/agents/*.agent.md`** — memory, optimize, and governance advisors.
-- **`.github/hooks/slm-hooks.json`** — session lifecycle (stable on Copilot CLI and cloud agents; VS Code Preview as of 2026).
-
-MCP works on every Copilot IDE at GA; prompts, agents, and hooks are additive and
-degrade gracefully where an IDE does not yet support them. An instruction-level
-fallback in `copilot-instructions.md` keeps memory working even without hooks.
+Run it from the project root. It semantically merges the SLM server into
+`.vscode/mcp.json` and adds SLM-owned guidance inside
+`.github/copilot-instructions.md`, preserving unrelated servers and existing
+instructions. The generated `copilot-plugin/` source bundle is maintained for
+parity checks, but v3.8.1 does not claim that `slm connect` installs its prompt,
+agent, or hook files.
 
 ---
 
@@ -670,84 +667,19 @@ configuration for that framework.
 | Retrieval score contract | [docs/retrieval-score-contract.md](docs/retrieval-score-contract.md) |
 | Wiki | [github.com/qualixar/superlocalmemory/wiki](https://github.com/qualixar/superlocalmemory/wiki) |
 
-**Web dashboard:**
-```bash
-slm dashboard    # Opens at http://localhost:8765
-```
-The dashboard includes Dashboard, Brain, Knowledge Graph, Memories, Health,
-Operations, Entity Explorer, Skill Evolution, Multi-Agent Memory, Mesh Peers,
-Settings, and Optimize workspaces. Features are populated only when their
-corresponding runtime capability is enabled and healthy.
-
-**Release history:**
-
-| Version | Codename | Key Features |
-|---|---|---|
-| **v3.8.0** | Teams & Bounded Loops | Team/role/GDPR controls, bounded loops with gate-verified iteration (`slm loop`, MCP tools `slm_loop_run/history/show`, `/slm-loop` skill), nine framework adapters (LangGraph · Semantic Kernel · Microsoft Agent Framework · LangChain · LlamaIndex · CrewAI · AutoGen · Google ADK · OpenAI Agents), multi-agent memory dashboard |
-| **v3.7.x** | Security & Stability | Profile-isolation leak fix, loopback auth opt-in, Scale Engine parity promotion, skill-evolution cost caps, dashboard landing page fixes, auth hardening across MCP/API/dashboard |
-| **v3.6.23** | Cross-platform Patch | Windows doctor/cache stats fixes (#65), neutral SLM hook guidance (#64), pi.dev MCP docs (#31), contributor fixes for dashboard profile path resolution (#63) and tz-naive Langevin maintenance backfill (#66) |
-| **v3.6.22** | Stability | backbone.py JSONDecodeError on empty HTTP 200 body (issue #62) — retries 3× then returns "" gracefully; remaining dashboard UI audit: clusters/compliance/entities r.ok guards, math-health status badge colors |
-| **v3.6.21** | Dashboard Audit | Full UI audit across all 7 dashboard tabs — auth fix for mesh panel (issue #60 frontend), Quick Store endpoint, timeline endpoint, r.ok guards, SSE \r fix, event delegation for lazy tabs, optimize toggle revert |
-| **v3.6.20** | Mesh Auth | Remote mesh auth fix (issue #60) — `_get_broker` now accepts Bearer + X-Mesh-Secret from non-loopback callers; config settings preservation on hot reload |
-| **v3.6.17** | Community | 8 contributor PRs (observability events, marker-bounded adapter writes, daemon port discovery, anthropic `api_base`, OpenMP workers, atomic-write rehash, `_jl` sentinel, LFS pointer); dashboard-feedback fix (#53/#59); env-tunable SQLite knobs + idle backoff; remote LLM test-probe (#40) |
-| **v3.6.16** | Docs | Corrected Claude Code plugin install — adds the required `/plugin marketplace add` step; clarifies plugin vs pip/npm delivery |
-| **v3.6.15** | Multi-scope | **Opt-in [shared memory](docs/shared-memory.md)** (personal/shared/global, off by default), default-deny scope at every read path, recall scope-race fix, contributor PRs #42/#43/#44, fixes #46–#49 |
-| **v3.6.14** | Plugin-native | Claude Code Plugin (WP-06), MCP profiles (WP-01), IDE connect (WP-08), asset consolidation, UI polish (WP-12) |
-| **v3.6.x** | Optimize Everywhere / Distributed-ready | Three surfaces (proxy/MCP/skill), `SLM_REMOTE=1` LAN mode, remote dashboard, custom LLM endpoints |
-| **v3.5.0** | Historical scale work | Early CozoDB/LanceDB projection paths, retrieval additions, Core Memory Block, context injection v2, score normalization |
-| **v3.4.x** | Scale-Ready (foundation) | Tiered storage, graph pruning, Hopfield channel, LightGBM ranking, mDNS mesh discovery |
-| **v3.3.x** | Foundation | BM25Plus, Fisher-Rao, sqlite-vec, RRF fusion, cross-encoder rerank. 3 published papers |
-
----
+Open the web dashboard with `slm dashboard`; workspaces appear only when their
+runtime capability is enabled and healthy. See [CHANGELOG.md](CHANGELOG.md) for
+the complete release history.
 
 ## Research Papers
 
-SuperLocalMemory is backed by three published research papers (arXiv preprints + Zenodo DOIs). These are preprints — not conference-accepted or journal-published yet.
-
-### Paper 3: The Living Brain (V3.3)
-> **SuperLocalMemory V3.3: The Living Brain — Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems**
-> Varun Pratap Bhardwaj (2026)
-> [arXiv:2604.04514](https://arxiv.org/abs/2604.04514) · [Zenodo DOI: 10.5281/zenodo.19435120](https://zenodo.org/records/19435120)
-
-### Paper 2: Information-Geometric Foundations (V3)
-> **SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory**
-> Varun Pratap Bhardwaj (2026)
-> [arXiv:2603.14588](https://arxiv.org/abs/2603.14588) · [Zenodo DOI: 10.5281/zenodo.19038659](https://zenodo.org/records/19038659)
-
-### Paper 1: Trust & Behavioral Foundations (V2)
-> **SuperLocalMemory: A Structured Local Memory Architecture for Persistent AI Agent Context**
-> Varun Pratap Bhardwaj (2026)
-> [arXiv:2603.02240](https://arxiv.org/abs/2603.02240) · [Zenodo DOI: 10.5281/zenodo.18709670](https://zenodo.org/records/18709670)
-
-### Cite This Work
-
-```bibtex
-@article{bhardwaj2026slmv33,
-  title={SuperLocalMemory V3.3: The Living Brain — Biologically-Inspired
-         Forgetting, Cognitive Quantization, and Multi-Channel Retrieval
-         for Zero-LLM Agent Memory Systems},
-  author={Bhardwaj, Varun Pratap},
-  journal={arXiv preprint arXiv:2604.04514},
-  year={2026},
-  url={https://arxiv.org/abs/2604.04514}
-}
-
-@article{bhardwaj2026slmv3,
-  title={Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory},
-  author={Bhardwaj, Varun Pratap},
-  journal={arXiv preprint arXiv:2603.14588},
-  year={2026}
-}
-
-@article{bhardwaj2026slm,
-  title={A Structured Local Memory Architecture for Persistent AI Agent Context},
-  author={Bhardwaj, Varun Pratap},
-  journal={arXiv preprint arXiv:2603.02240},
-  year={2026}
-}
-```
+SuperLocalMemory is backed by three preprints by Varun Pratap Bhardwaj (2026):
 
----
+- **The Living Brain (V3.3):** [arXiv:2604.04514](https://arxiv.org/abs/2604.04514) · [Zenodo 19435120](https://zenodo.org/records/19435120)
+- **Information-Geometric Foundations (V3):** [arXiv:2603.14588](https://arxiv.org/abs/2603.14588) · [Zenodo 19038659](https://zenodo.org/records/19038659)
+- **Trust & Behavioral Foundations (V2):** [arXiv:2603.02240](https://arxiv.org/abs/2603.02240) · [Zenodo 18709670](https://zenodo.org/records/18709670)
+
+Use the citation metadata on the linked arXiv or Zenodo records.
 
 ## Support / License / Qualixar
 
@@ -763,34 +695,14 @@ Part of [Qualixar](https://qualixar.com) · Author: [Varun Pratap Bhardwaj](http
 
 ### Acknowledgments
 
-- **[Everything Claude Code (ECC)](https://github.com/affaan-m/everything-claude-code)** — SLM's skill observation patterns were inspired by ECC's continuous learning architecture. SLM supports direct ingestion of ECC observations via `slm ingest --source ecc`. We recommend ECC for Claude Code users who want the deepest learning experience alongside SLM.
-- **[HKUDS/OpenSpace](https://github.com/HKUDS/OpenSpace)** — The skill evolution research in SLM draws from the EvoSkills co-evolutionary verification concepts (arXiv:2604.01687). We adopted their 3-trigger evolution system and anti-loop guard patterns.
+- **[Everything Claude Code (ECC)](https://github.com/affaan-m/everything-claude-code)** inspired SLM's skill-observation patterns; SLM can ingest ECC observations with `slm ingest --source ecc`.
+- **[HKUDS/OpenSpace](https://github.com/HKUDS/OpenSpace)** informed the skill-evolution verification design (arXiv:2604.01687).
 
 ### Qualixar AI Agent Reliability Platform
 
-Qualixar is building the open-source infrastructure for AI agent reliability engineering. Seven products, one coherent platform:
-
-| Product | Purpose | Install |
-|---------|---------|---------|
-| **[SuperLocalMemory](https://github.com/qualixar/superlocalmemory)** | Persistent memory + learning | `npm install -g superlocalmemory` |
-| **[Qualixar OS](https://github.com/qualixar/qualixar-os)** | Universal agent runtime | `npx qualixar-os` |
-| **[SLM Mesh](https://github.com/qualixar/slm-mesh)** | P2P coordination across sessions | `npm i slm-mesh` |
-| **[SLM MCP Hub](https://github.com/qualixar/slm-mcp-hub)** | Federate 430+ MCP tools | `pip install slm-mcp-hub` |
-| **[AgentAssay](https://github.com/qualixar/agentassay)** | Token-efficient agent testing | `pip install agentassay` |
-| **[AgentAssert](https://github.com/qualixar/agentassert-abc)** | Behavioral contracts + drift detection | `pip install agentassert-abc` |
-| **[SkillFortify](https://github.com/qualixar/skillfortify)** | Formal verification for agent skills | `pip install skillfortify` |
-
-**Local-first architecture. Deployment-specific privacy and compliance controls.**
-
-Start here → **[qualixar.com](https://qualixar.com)** · [All papers on Qualixar HuggingFace](https://huggingface.co/Qualixar)
-
----
-
-<p align="center">
-  <sub>Built with mathematical rigor. Not in the race — here to help everyone build better AI memory systems.</sub>
-</p>
-
----
+Qualixar builds open-source infrastructure for AI reliability engineering.
+Start at **[qualixar.com](https://qualixar.com)** or browse the
+[Qualixar research archive](https://huggingface.co/Qualixar).
 
 ## Star This Project
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.8.0",
+  "version": "3.8.2",
   "description": "Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.",
   "keywords": [
     "ai-memory",
@@ -79,7 +79,14 @@
     "scripts/preuninstall.js",
     ".claude-plugin/",
     "plugin/",
-    "plugin-src/",
+    "plugin-src/skills/slm-cache/SKILL.md",
+    "plugin-src/skills/slm-compress/SKILL.md",
+    "plugin-src/skills/slm-graph/SKILL.md",
+    "plugin-src/skills/slm-recall/SKILL.md",
+    "plugin-src/skills/slm-remember/SKILL.md",
+    "plugin-src/skills/slm-session/SKILL.md",
+    "plugin-src/skills/slm-status/SKILL.md",
+    "plugin-src/rules/AGENTS.md",
     "docs/pi-dev-integration.md",
     "pyproject.toml",
     "README.md",

package/plugin/.claude-plugin/plugin.json

@@ -5,7 +5,6 @@
   },
   "description": "Local-first agent memory + reversible context compression and KV cache, as an MCP server. 21-tool code profile with graph intelligence.",
   "displayName": "SuperLocalMemory",
-  "hooks": "./hooks/hooks.json",
   "keywords": [
     "memory",
     "mcp",
@@ -16,5 +15,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "3.8.0"
+  "version": "3.8.2"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.8.0 -->
+<!-- BEGIN SuperLocalMemory v3.8.2 -->
 
 ## SuperLocalMemory (SLM) — Agent Rules
 
@@ -39,6 +39,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
 ### Subagents
 slm-memory-advisor (memory decisions, session hygiene, scope/profile guidance) · slm-optimize-advisor (context compression + KV cache) · slm-governance-advisor (scope/roles/compliance/GDPR)
 
-<!-- END SuperLocalMemory v3.8.0 -->
+<!-- END SuperLocalMemory v3.8.2 -->
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-governance-advisor.md

@@ -77,4 +77,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-loop-runner.md

@@ -68,4 +68,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-memory-advisor.md

@@ -17,7 +17,7 @@ When the main agent: starts a session and hasn't loaded project context; is abou
 
 # Tools you may use (real SLM MCP tools, core profile)
 - `session_init(project_path, query, max_results, max_age_days)` — ONCE at session start; returns recent decisions + relevant memories.
-- `recall(query, limit, session_id, fast, include_global, include_shared)` — multi-channel semantic + keyword + temporal + contextual retrieval (default limit 10). Leave `include_global`/`include_shared` unset — recall is private-by-default (v3.6.15).
+- `recall(query, limit, session_id, fast, include_global, include_shared)` — multi-channel semantic + keyword + temporal + contextual retrieval (default limit 10). Leave `include_global`/`include_shared` unset — recall is private-by-default (v3.6.15). Returns fast local results (~1–2s, no server-side LLM round) plus confidence signals: if `no_confident_match` is true or `answer_confidence` is low, advise the main agent to rewrite into 1–3 sharper sub-queries and recall again rather than treating the memory as absent.
 - `search(query, limit, profile_id)` — exact keyword / FTS5 BM25.
 - `remember(content, tags, project, importance, session_id, scope, shared_with)` — store atomic fact; importance 1-10. Leave `scope` unset (defaults to `personal`/private).
 - `update_memory(fact_id, content)` — correct by exact id.
@@ -46,4 +46,4 @@ slm-recall · slm-remember · slm-session · slm-scope · slm-profile · slm-gov
 # What NOT to do
 Never session_init twice; never forget dry_run=False without reporting preview; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit; never bypass scope or governance restrictions.
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/agents/slm-optimize-advisor.md

@@ -41,4 +41,4 @@ slm-compress · slm-cache · slm-status · slm-profile
 # What NOT to do
 Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %; never carry ccr_ids across profile switches.
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.8.0
+superlocalmemory==3.8.2

package/plugin/skills/slm-cache/SKILL.md

@@ -145,4 +145,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-compress/SKILL.md

@@ -147,4 +147,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-governance/SKILL.md

@@ -245,4 +245,4 @@ Before running any destructive operation (`forget`, `compact_memories`):
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-graph/SKILL.md

@@ -311,4 +311,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-loop/SKILL.md

@@ -96,4 +96,4 @@ paused, name the approval needed; when errored, quote the short detail.
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin/skills/slm-mesh/SKILL.md

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-profile/SKILL.md

@@ -145,4 +145,4 @@ Name them differently in your MCP config (e.g. `superlocalmemory-personal` and
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-recall/SKILL.md

@@ -87,9 +87,7 @@ Real response shape (`--json` equivalent):
 }
 ```
 
-**Always check `no_confident_match`.** When `true`, no result cleared the
-evidence floor. Do not invent a memory — tell the user nothing was found and
-offer to search more broadly or store a new fact.
+**Refine on low confidence.** `recall` returns confidence signals with every result. If `no_confident_match` is `true` (or `answer_confidence` is low / `abstained` is `true`), do NOT invent a memory — rewrite the query into 1–3 more specific sub-queries (split multi-hop questions; try entity names, synonyms, or broader phrasing) and call `recall` again before concluding nothing was found. A confident match → use it directly. SLM returns fast local results (~1–2s, no server-side LLM round on the hot path) and lets you, the calling model, drive this refinement.
 
 ### 2. Passing session_id
 
@@ -196,7 +194,7 @@ Flags verified in source (main.py):
 
 ## Never fabricate a memory
 
-If `results` is empty or `no_confident_match` is `true`, report it plainly.
+After re-querying with refined sub-queries (see **Refine on low confidence** above), if `no_confident_match` is still `true` or results are empty, report it plainly.
 Never construct a response as if a memory was found when it was not. The user
 trusts that what you surface came from the store.
 
@@ -238,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-remember/SKILL.md

@@ -238,4 +238,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-scope/SKILL.md

@@ -173,4 +173,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-session/SKILL.md

@@ -227,4 +227,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin/skills/slm-status/SKILL.md

@@ -163,4 +163,4 @@ multi-profile setup. To switch the active profile, see `slm-profile`.
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/AGENTS.md

@@ -28,6 +28,7 @@ Call `session_init(project_path, query, max_results, max_age_days)` **once** at
 - **Concept phrasing** — phrase queries as concepts, not vague words ("database migration strategy" not "database").
 - **Pass session_id** when available to narrow results to the current session.
 - **Empty / low results** — broaden the query, try `search`, or fall back to `list_recent`. Never fabricate a memory.
+- **Refine on low confidence** — if `no_confident_match` is `true` (or `answer_confidence` is low / `abstained` is `true`), rewrite the query into 1–3 more specific sub-queries (split multi-hop questions; try entity names, synonyms, or broader phrasing) and call `recall` again before concluding nothing was found. SLM returns fast local results (~1–2s, no server-side LLM round on the hot path) — you, the calling model, drive refinement.
 
 ---
 
@@ -127,4 +128,4 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 - **slm-optimize-advisor** — context compression and KV cache
 - **slm-governance-advisor** — scope/role compliance, retention policies, GDPR
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-cache/SKILL.md

@@ -145,4 +145,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-compress/SKILL.md

@@ -147,4 +147,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-graph/SKILL.md

@@ -311,4 +311,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later

package/plugin-src/skills/slm-recall/SKILL.md

@@ -87,9 +87,7 @@ Real response shape (`--json` equivalent):
 }
 ```
 
-**Always check `no_confident_match`.** When `true`, no result cleared the
-evidence floor. Do not invent a memory — tell the user nothing was found and
-offer to search more broadly or store a new fact.
+**Refine on low confidence.** `recall` returns confidence signals with every result. If `no_confident_match` is `true` (or `answer_confidence` is low / `abstained` is `true`), do NOT invent a memory — rewrite the query into 1–3 more specific sub-queries (split multi-hop questions; try entity names, synonyms, or broader phrasing) and call `recall` again before concluding nothing was found. A confident match → use it directly. SLM returns fast local results (~1–2s, no server-side LLM round on the hot path) and lets you, the calling model, drive this refinement.
 
 ### 2. Passing session_id
 
@@ -196,7 +194,7 @@ Flags verified in source (main.py):
 
 ## Never fabricate a memory
 
-If `results` is empty or `no_confident_match` is `true`, report it plainly.
+After re-querying with refined sub-queries (see **Refine on low confidence** above), if `no_confident_match` is still `true` or results are empty, report it plainly.
 Never construct a response as if a memory was found when it was not. The user
 trusts that what you surface came from the store.
 
@@ -238,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-remember/SKILL.md

@@ -238,4 +238,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*

package/plugin-src/skills/slm-session/SKILL.md

@@ -227,4 +227,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v3.8.0 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.2 · Qualixar · AGPL-3.0-or-later*