superlocalmemory 3.8.1 → 3.8.3

package/CHANGELOG.md

@@ -5,6 +5,73 @@ 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).
 
+## [3.8.3] - 2026-07-24 — Recall stays responsive under heavy load
+
+### Fixed
+
+- **Recall no longer hangs when the system is busy.** Search and recall now
+  complete within a generous time budget even during background maintenance or
+  when many agents are querying at once. If a query can't finish in that window,
+  SLM returns keyword-matched results and marks them clearly instead of leaving
+  the request to time out. This applies everywhere recall runs — the dashboard
+  search, the CLI, and connected assistants — so results are consistent across
+  every surface.
+- **Dashboard search waits long enough for a real answer.** The dashboard now
+  allows recall the full server-side budget before giving up, so heavy-load
+  queries return results rather than an aborted-request error.
+
+## [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

package/README.md

@@ -5,10 +5,10 @@
   </picture>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.8.1</h1>
+<h1 align="center">SuperLocalMemory V3.8.3</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>v3.8.1</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/>
+<p align="center"><code>v3.8.3</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>
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.8.1",
+  "version": "3.8.3",
   "description": "Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.",
   "keywords": [
     "ai-memory",

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

@@ -15,5 +15,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "3.8.1"
+  "version": "3.8.3"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.8.1 -->
+<!-- BEGIN SuperLocalMemory v3.8.3 -->
 
 ## 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 v3.8.1 -->
+<!-- END SuperLocalMemory v3.8.3 -->
 
-SuperLocalMemory v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later

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

@@ -68,4 +68,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.8.1
+superlocalmemory==3.8.3

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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later

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

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · 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 v3.8.1 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later*

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

@@ -163,4 +163,4 @@ multi-profile setup. To switch the active profile, see `slm-profile`.
 
 ---
 
-SuperLocalMemory v3.8.1 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.8.1"
+version = "3.8.3"
 description = "Local-first agent memory with auditable hybrid retrieval"
 readme = "README.md"
 license = "AGPL-3.0-or-later"

package/scripts/postinstall.js

@@ -200,7 +200,13 @@ function main(argv = process.argv.slice(2)) {
 
   console.log(`SuperLocalMemory ${packageVersion}: isolated runtime verified.`);
   console.log('No memory database, IDE hooks, daemon, configuration, or models were changed.');
-  console.log('Run `slm setup` explicitly when you are ready to configure SLM.');
+  console.log('');
+  console.log('  Next step — run the guided setup (picks your mode, downloads');
+  console.log('  models, connects your IDEs). Takes about a minute:');
+  console.log('');
+  console.log('      slm setup');
+  console.log('');
+  console.log('  Prefer to tune performance profiles? Use:  slm reconfigure');
   console.log('');
   return 0;
 }

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "3.8.1"
+__version__ = "3.8.3"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",