superlocalmemory 3.8.3 → 3.8.6

package/CHANGELOG.md

@@ -5,6 +5,82 @@ 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).
 
+## [3.8.6] - 2026-07-27 — Serialized writes and read-only recall
+
+### Fixed
+- Remember requests and dashboard fact mutations now enter one bounded,
+  priority-aware coordinator. Durable idempotency receipts make retries safe,
+  while accepted admissions survive daemon interruption and replay once.
+- Recall paths now use query-only SQLite connections and no longer update
+  diagnostics, bandit state, access counters, or other canonical tables.
+- Dashboard, CLI, and MCP mutations use the running daemon instead of opening
+  competing writable engines. When the daemon is unavailable, writes fail
+  explicitly instead of silently switching to another database path.
+- Mode and profile changes rebind the canonical writer before the new runtime
+  is exposed, and roll back cleanly when persistence fails.
+- Stuck background enrichment work is moved to a bounded failed/dead-letter
+  state instead of retrying forever (#77).
+- Daemon shutdown now closes deferred writers and terminates embedding and
+  reranker workers within bounded time, including Mode B container deployments
+  (#91).
+- CozoDB now installs on Linux ARM64 by using the current embedded wheel series.
+
+### Added
+- A separate authenticated admission journal protects accepted remember
+  requests before canonical SQLite work begins.
+- Runtime readiness now distinguishes full retrieval readiness from degraded
+  or warming operation without breaking existing status clients.
+- Concurrency regression coverage for duplicate remember requests, foreground
+  priority, read-only recall, legacy writer coexistence, mode/profile isolation,
+  and bounded child-process shutdown.
+
+### Notes
+- Upgrades apply automatically on daemon start; no manual migration is needed.
+- Existing memory databases are preserved. The new coordinator ledger and
+  admission journal are additive.
+
+## [3.8.5] - 2026-07-26 — Reliable, full-quality recall
+
+### Fixed
+- Recall now consistently uses full-quality relevance ranking. The ranking model
+  warms up in the background with automatic retries, so recall no longer quietly
+  falls back to basic scoring when the model is slow to load, is recycled, or is
+  restarted. Full ranking resumes on its own within seconds if it is ever interrupted.
+- The first recall after startup is now fast. The memory graph is fully warmed in
+  the background before queries arrive, instead of the first query paying a
+  multi-second load — and the graph no longer reloads on the query path during
+  normal use, so recall latency stays consistent.
+- Recall stays responsive under heavy concurrent load. A startup contention issue
+  that could make the first queries slow on busy multi-agent systems has been removed.
+- The internal recall cache is now cleaned up automatically. It could previously
+  grow without bound over months of use; on upgrade, stale entries are compacted away.
+
+### Added
+- Automatic scale-up for very large memory graphs. A database that grows past
+  millions of connections switches to a high-performance graph backend on its own;
+  smaller databases stay on the fast built-in engine, which is quicker for them. The
+  switch runs in the background, is verified for correctness before it takes effect,
+  and falls back safely to the built-in engine if it cannot complete.
+
+### Notes
+- Upgrades apply automatically on daemon start — no manual migration command needed.
+- Recommended upgrade for all 3.8.x users.
+
+## [3.8.4] - 2026-07-26
+
+### Fixed
+- Frequent "database is locked" errors under heavy or concurrent multi-agent use.
+- MCP connections dropping when idle; connections now stay stable and recover cleanly.
+- A just-saved memory is now instantly findable by meaning, not only by keyword (on a warm instance).
+- HTTP write endpoints (dashboard Save / API) were rejected on some networked/containerized setups (#90).
+- Background ingestion operations that failed no longer retry forever; failures move to a dead-letter queue (#77).
+- Stale agent locks are cleared on restart; daemon shutdown no longer logs spurious import errors; the dashboard UI serves reliably on restricted filesystems.
+### Added
+- A choice of connection transport (stdio or HTTP) when connecting IDEs.
+- Configurable graph-memory pruning (max edges per node, minimum edge weight) (#84).
+### Notes
+- Upgrades apply automatically on daemon start — no manual migration command needed.
+
 ## [3.8.3] - 2026-07-24 — Recall stays responsive under heavy load
 
 ### Fixed

package/README.md

@@ -5,14 +5,15 @@
   </picture>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.8.3</h1>
+<h1 align="center">SuperLocalMemory V3.8.6</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>v3.8.3</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/>
+<p align="center"><code>v3.8.6</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>
 
 <p align="center">
+  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/v3.8.6-Current_Release-2ea44f?style=for-the-badge&logo=checkmarx&logoColor=white" alt="v3.8.6 — Current Release"/></a>
   <a href="https://arxiv.org/abs/2603.14588"><img src="https://img.shields.io/badge/arXiv-2603.14588-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"/></a>
   <a href="#three-surfaces-proxy--mcp-tools--skill"><img src="https://img.shields.io/badge/Proxy_|_MCP_|_Skill-22c55e?style=for-the-badge" alt="Three Surfaces: Proxy, MCP Tools, Skill"/></a>
   <a href="https://pypi.org/project/superlocalmemory/"><img src="https://img.shields.io/pypi/v/superlocalmemory?style=for-the-badge&logo=pypi&logoColor=white" alt="PyPI"/></a>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.8.3",
+  "version": "3.8.6",
   "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": "3.8.3"
+  "version": "3.8.6"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.8.3 -->
+<!-- BEGIN SuperLocalMemory v3.8.6 -->
 
 ## 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 v3.8.3 -->
+<!-- END SuperLocalMemory v3.8.6 -->
 
-SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

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

@@ -68,4 +68,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

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

@@ -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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.8.3
+superlocalmemory==3.8.6

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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

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

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later*

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

@@ -236,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/AGENTS.md

@@ -128,4 +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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

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

@@ -236,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.6 · 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 v3.8.3 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.6 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.8.3"
+version = "3.8.6"
 description = "Local-first agent memory with auditable hybrid retrieval"
 readme = "README.md"
 license = "AGPL-3.0-or-later"
@@ -59,6 +59,10 @@ dependencies = [
     "psutil==7.2.2",
     "structlog==25.5.0",
     "portalocker==3.2.0",
+    # Capture-file ACLs are applied through the verified Windows file handle.
+    # Keep this direct: portalocker also needs pywin32 today, but capture must
+    # not depend on that transitive implementation detail.
+    "pywin32==311; sys_platform == 'win32'",
     "cryptography==48.0.1",
     # Semantic search + cross-encoder reranker. Do NOT use
     # sentence-transformers[onnx] — its extras pull optimum which
@@ -78,7 +82,7 @@ dependencies = [
     # until `slm db scale prepare -> verify -> promote` proves parity with
     # canonical SQLite; dependency installation never migrates user data.
     "lancedb==0.30.2",
-    "pycozo[embedded]==0.3.0",
+    "pycozo[embedded]==0.7.6",
     # v3.6.10: LLMLingua-2 prose compression (aggressive mode, opt-in at runtime).
     # Hard dependency so `pip install superlocalmemory` ships compression-ready;
     # the ~560MB model downloads on first setup/warmup (fail-open). Verified the
@@ -117,13 +121,13 @@ lancedb = [
     "lancedb==0.30.2",
 ]
 cozo = [
-    "pycozo[embedded]==0.3.0",
+    "pycozo[embedded]==0.7.6",
 ]
 # Backwards-compatible explicit install target for automation and docs.  The
 # packages are also base dependencies from v3.7 onward.
 scale = [
     "lancedb==0.30.2",
-    "pycozo[embedded]==0.3.0",
+    "pycozo[embedded]==0.7.6",
 ]
 ingestion = [
     "keyring>=25.0.0",
@@ -227,4 +231,5 @@ dev = [
     "pytest>=9.0.2",
     "pytest-asyncio>=0.21",
     "twine>=6.2.0",
+    "wheel==0.46.3",
 ]

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "3.8.3"
+__version__ = "3.8.6"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",