superlocalmemory 4.1.5 → 4.1.7

package/.claude-plugin/marketplace.json

@@ -21,7 +21,7 @@
       "license": "AGPL-3.0-or-later",
       "name": "superlocalmemory",
       "source": "./plugin",
-      "version": "4.1.5"
+      "version": "4.1.7"
     },
     {
       "author": {
@@ -39,7 +39,7 @@
       "license": "AGPL-3.0-or-later",
       "name": "superlocalmemory-codex",
       "source": "./codex-plugin",
-      "version": "4.1.5"
+      "version": "4.1.7"
     }
   ]
 }

package/CHANGELOG.md

@@ -5,6 +5,61 @@ All notable changes to SuperLocalMemory 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).
 
+## [4.1.7] — Recall that improves with use
+
+### Added
+- **Adaptive ranking is on by default.** Recall now learns which memories
+  actually helped and ranks accordingly. Set `SLM_RANKING=off` to opt out.
+
+### Fixed
+- **Ranking never learned anything.** Recalls were not attributed to the
+  conversation they came from, so nothing could tell whether a memory had been
+  useful, and every result was scored the same regardless. Recalls are now
+  attributed correctly and scored from real use.
+- **Unused results are no longer scored as average.** When there is no evidence
+  either way, a result is left unscored instead of being recorded as
+  middling — which had made the ranking progressively harder to change.
+- **Frequently shown memories no longer reinforce themselves.** A memory that
+  was going to be shown regardless now counts for less than one that was not.
+- **Codex subagents install complete.** Installing from a published package
+  produced one-line advisor definitions instead of the full ones.
+
+## [4.1.6] — A learning loop that never learns looks identical to one that works
+
+### Fixed
+- **The engagement-learning loop settled every outcome at neutral, regardless of
+  real usage.** `SESSION_ENV_VARS` checked `SLM_SESSION_ID` and `CLAUDE_SESSION_ID`
+  but not `CLAUDE_CODE_SESSION_ID` — the variable Claude Code's own MCP subprocess
+  actually sets. Every recall from Claude Code fell through to the synthetic
+  `mcp:<agent_id>` id, which step 4 of the resolution ladder deliberately excludes
+  from ever matching a pending outcome, by design — a real session should never be
+  confused with a placeholder. The result: measured on a live store, 6,013 of 6,039
+  settled outcomes carried exactly `reward=0.5`, and all 414 bandit arms held
+  `alpha == beta` at every play count. Adding the missing name is what closes the
+  loop; two test files that had never isolated session resolution from the ambient
+  environment were also hardened, since a live Claude Code session now genuinely
+  satisfies the check they'd only ever run without.
+- **Auto-captured facts could assert a date nothing in the source text contained.**
+  The fact-extraction system prompt taught relative-date resolution with a fixed
+  worked example — `'Yesterday' with session date 2024-01-15 becomes '2024-01-14'`
+  — sent identically on every extraction call. A smaller local model under
+  uncertainty would echo that literal example date back as if it were extracted
+  content, rather than resolving against the real conversation date already present
+  in the same prompt. Reproduced live and fixed by removing the concrete date from
+  the instruction entirely, teaching the same rule without anything to leak.
+  Several existing memories carrying this exact signature — including one date
+  claim accessed 28 times — were identified and quarantined.
+- **A store that drifted from M048's classification rule stayed unready for up to a
+  full maintenance interval (6 hours) after every restart.** The migration itself
+  is idempotent and safe to replay — its own `verify()` docstring says so — but the
+  migration runner never replays a completed migration, and the periodic
+  maintenance cycle that's supposed to reconcile it only runs once every
+  `scheduler_interval_minutes`. A restart landing between cycles reported
+  `ready=false, migrations=false` with "automatic replay is disabled" and stayed
+  that way until the next scheduled tick. A third staggered one-shot startup timer,
+  matching the two that already exist for the same reason (cache GC, graph
+  metrics), now runs the same reconciliation pass within seconds of boot instead.
+
 ## [4.1.5] — Ask whether a feature is working, not whether it is present
 
 ### Added

package/README.md

@@ -5,7 +5,7 @@
   </picture>
 </p>
 
-<h1 align="center">SuperLocalMemory V4.1.5</h1>
+<h1 align="center">SuperLocalMemory V4.1.7</h1>
 
 <h2 align="center">Rent the LLM. Own the memory.</h2>
 
@@ -27,12 +27,12 @@ guarantee here is stated as a falsifiable invariant, tested under an adversarial
 negative control, and shipped with the harness that regenerates the evidence:
 <code>python benchmark/run_all.py --trials 200 --output-dir results/</code>. What each experiment
 does <em>not</em> exercise is stated too.</p>
-<p align="center"><code>v4.1.5</code> — one control plane: <strong>SLM-Mesh</strong> peer coordination · multi-scope memory (personal / shared / global) · profiles · Cache · Compress · 7-layer retrieval · code graph · Entity Explorer · skill evolution · Modes A/B/C · GDPR retention &amp; audit chain · 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>v4.1.7</code> — one control plane: <strong>SLM-Mesh</strong> peer coordination · multi-scope memory (personal / shared / global) · profiles · Cache · Compress · 7-layer retrieval · code graph · Entity Explorer · skill evolution · Modes A/B/C · GDPR retention &amp; audit chain · 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>Four public arXiv preprints</strong> · V4: <a href="https://arxiv.org/abs/2608.08253">arXiv:2608.08253</a> · companion archive: <a href="https://zenodo.org/records/21853302">Zenodo 21853302</a> (<a href="https://doi.org/10.5281/zenodo.21853302">DOI 10.5281/zenodo.21853302</a>) · prior preprints: <a href="https://arxiv.org/abs/2603.02240">2603.02240</a> · <a href="https://arxiv.org/abs/2603.14588">2603.14588</a> · <a href="https://arxiv.org/abs/2604.04514">2604.04514</a>.</p>
 
 <p align="center">
-  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/v4.1.5-Current_Release-2ea44f?style=for-the-badge&logo=checkmarx&logoColor=white" alt="v4.1.5 — Current Release"/></a>
+  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/v4.1.7-Current_Release-2ea44f?style=for-the-badge&logo=checkmarx&logoColor=white" alt="v4.1.7 — Current Release"/></a>
   <a href="https://arxiv.org/abs/2608.08253"><img src="https://img.shields.io/badge/arXiv-2608.08253-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white" alt="SuperLocalMemory 4.0 paper on arXiv:2608.08253"/></a>
   <a href="https://zenodo.org/records/21853302"><img src="https://img.shields.io/badge/Zenodo-10.5281%2Fzenodo.21853302-1682D4?style=for-the-badge&logo=zenodo&logoColor=white" alt="V4 paper on Zenodo: 10.5281/zenodo.21853302"/></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>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "4.1.5",
+  "version": "4.1.7",
   "description": "Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.",
   "keywords": [
     "ai-memory",
@@ -96,6 +96,8 @@
     "plugin-src/skills/slm-scope/SKILL.md",
     "plugin-src/skills/slm-session/SKILL.md",
     "plugin-src/skills/slm-status/SKILL.md",
+    "plugin-src/agents/slm-memory-advisor.md",
+    "plugin-src/agents/slm-optimize-advisor.md",
     "plugin-src/rules/AGENTS.md",
     "docs/pi-dev-integration.md",
     "pyproject.toml",

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

@@ -15,5 +15,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "4.1.5"
+  "version": "4.1.7"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v4.1.5 -->
+<!-- BEGIN SuperLocalMemory v4.1.7 -->
 
 ## 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 v4.1.5 -->
+<!-- END SuperLocalMemory v4.1.7 -->
 
-SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -68,4 +68,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==4.1.5
+superlocalmemory==4.1.7

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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -312,4 +312,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -146,4 +146,4 @@ Name them differently in your MCP config (e.g. `superlocalmemory-personal` and
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -323,4 +323,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -270,4 +270,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -253,4 +253,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -0,0 +1,49 @@
+---
+name: slm-memory-advisor
+description: >
+  Advises the main agent on using SuperLocalMemory well — when to call
+  session_init, remember, recall, and search; how to phrase queries; and how
+  to keep memory clean. Delegate here for any "should I save/recall this?"
+  decision or when memory results look wrong.
+tools: session_init, recall, search, remember, update_memory, forget, list_recent, Read
+model: inherit
+---
+
+# Role
+You are the SuperLocalMemory (SLM) memory advisor. You help the main agent use the local-first memory system correctly across a session. You do not do the user's primary task — you make memory usage disciplined: the right thing saved, the right thing recalled, nothing duplicated, nothing lost between sessions. Core memory tools run against the configured local data root; optional providers, connectors, backup, and downloads have separate network behavior.
+
+# When to act
+When the main agent: starts a session and hasn't loaded project context; is about to or just made a decision worth persisting; asks "what did we decide about X"; gets recall results that look irrelevant/empty; needs advice on scope, profile, or governance.
+
+# 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). 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.
+- `forget(profile_id, dry_run)` — decay cycle; ALWAYS dry_run=True first, report, never apply blind.
+- `list_recent(limit)` — newest first.
+- `Read` — inspect a file before deciding what to remember.
+
+# Decision rules
+1. SESSION_INIT FIRST — once, before any recall/remember in a fresh session. Never skip; never twice.
+2. RECALL BEFORE REMEMBER — if it exists, update_memory instead of duplicating.
+3. REMEMBER ATOMIC DURABLE FACTS ONLY — decisions/conventions/constraints/gotchas/stable prefs; one per call; add tags+project; importance 7-10 for blockers/security/architecture.
+4. QUERY PHRASING — concept phrases not vague words; pass session_id when available.
+5. recall vs search — recall for conceptual; search for literal keyword.
+6. EMPTY/LOW results → broaden, try search, or list_recent; never fabricate.
+7. SESSION END — close_session(session_id) when work meaningfully complete.
+8. SCOPE IS OPT-IN (v3.6.15) — every memory is `personal` (private to this profile) by default, and recall returns only this profile's facts. Do NOT set `scope="shared"/"global"` or `include_global`/`include_shared` on your own. Use them ONLY when the user EXPLICITLY asks to share memories across local profiles or to read other profiles' shared/global facts. Default behaviour is identical to single-profile SLM. See slm-scope for the complete sharing model.
+9. PROFILE CONTEXT (v3.8.0) — session_init and all memory ops use the active profile. If the user needs to work in a different workspace, direct them to switch_profile (requires code/full/power profile). See slm-profile.
+10. GOVERNANCE — in a governed workspace (admin/member/viewer roles), respect role restrictions: viewers must not write, members must not write global scope without authorization. See slm-governance.
+
+# CLI fallback (MCP unavailable)
+recall→`slm recall "<q>" --limit N` (add `--include-global`/`--include-shared` only on explicit user request) · search→`slm search "<q>"` · remember→`slm remember "<c>" --tags a,b` (project/importance are MCP-only, NOT CLI flags; `--scope shared --shared-with a,b` only when the user asks to share) · list→`slm list --limit N` · forget→`slm forget` (preview first) · status→`slm status`. session_init/close_session are daemon-implicit (no CLI verb) — skip on MCP-down.
+
+# Related skills
+slm-recall · slm-remember · slm-session · slm-scope · slm-profile · slm-governance
+
+# 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 v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -0,0 +1,44 @@
+---
+name: slm-optimize-advisor
+description: >
+  Applies SuperLocalMemory's context-optimization rules — reversible
+  compression of large tool output and KV-caching of repeated reads/searches —
+  to stretch the context window with no proxy. Delegate here when context is
+  filling up or the same files/searches are read repeatedly. Strictly advisory
+  and fail-open: optimization must never block the primary task.
+tools: slm_compress, slm_retrieve, slm_cache_set, slm_cache_get, slm_optimize_stats, Read, Bash
+model: inherit
+---
+
+# Role
+You are the SLM optimize advisor. You reduce context-window pressure using Surface-B tools: reversible compression (CCR) and a per-agent KV cache. No proxy; full 1M window preserved on any plan. You apply the same rules as the slm-compress and slm-cache skills. You cannot cache the primary Claude turn (needs a proxy) — only content the agent routes through SLM.
+
+# When to act
+Tool/file read >~2000 chars; same file or bash/web search about to be re-read; user asks how much context saved; context tight with large outputs sitting in window.
+
+# Tools (real SLM MCP tools, core profile)
+slm_compress(content,mode,reversible,ttl_seconds)→compressed,lossy,ccr_id (mode normalize|auto|aggressive); slm_retrieve(ccr_id); slm_cache_set(key,value,ttl_seconds); slm_cache_get(key)→hit,value; slm_optimize_stats(); Read/Bash to fetch content.
+
+# Decision rules (the 8 — apply automatically)
+1. CLAUDE.md >3000 chars → slm_compress(mode="normalize", reversible=False), use compressed IN CONTEXT ONLY; never modify the file.
+2. Tool output >2000 chars → slm_compress(mode="auto", reversible=True); work from compressed; keep ccr_id if lossy.
+3. Repeated file reads → slm_cache_get("file:<path>") first; on miss Read then slm_cache_set("file:<path>", ttl 1800); invalidate on Edit/Write.
+4. Repeated bash/web → slm_cache_set("bash:<cmd[:64]>", ttl 600); web ttl 3600.
+5. Retrieve original only when byte-identical needed.
+6. NEVER compress/cache: code for Edit/Write; JSON to parse; secrets/keys/tokens; ccr_ids; <500 chars.
+7. Stats → slm_optimize_stats() (KV this-session; proxy/compress daemon-persisted).
+8. FAIL-OPEN: ok:false → continue with original, no retry, don't surface unless asked. Never block the task.
+
+# Profile context (v3.8.0)
+Cache entries are namespaced per active profile — if the user switches profiles via switch_profile, the cache is effectively fresh for the new profile. Do not carry ccr_id values across profile switches.
+
+# CLI fallback
+stats→`slm optimize status`/`savings` · compress→`slm compress` · cache→`slm cache ...`. If CLI also fails, drop optimization silently (rule 8).
+
+# Related skills
+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 v4.1.7 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/AGENTS.md

@@ -137,4 +137,4 @@ 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -245,4 +245,4 @@ Before running any destructive operation (`forget`, `compact_memories`):
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -312,4 +312,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -96,4 +96,4 @@ paused, name the approval needed; when errored, quote the short detail.
 
 ---
 
-SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

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

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -146,4 +146,4 @@ Name them differently in your MCP config (e.g. `superlocalmemory-personal` and
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -323,4 +323,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -270,4 +270,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -173,4 +173,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later*

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

@@ -253,4 +253,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v4.1.5 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.1.7 · 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 v4.1.5 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.1.7 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "4.1.5"
+version = "4.1.7"
 description = "Local-first agent memory with auditable hybrid retrieval"
 readme = "README.md"
 license = "AGPL-3.0-or-later"
@@ -186,6 +186,10 @@ superlocalmemory = ["ui/**/*", "optimize/NOTICE", "contracts/schemas/*.json"]
 "share/superlocalmemory/codex/skills/slm-scope" = ["plugin-src/skills/slm-scope/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-session" = ["plugin-src/skills/slm-session/SKILL.md"]
 "share/superlocalmemory/codex/skills/slm-status" = ["plugin-src/skills/slm-status/SKILL.md"]
+"share/superlocalmemory/codex/agents" = [
+    "plugin-src/agents/slm-memory-advisor.md",
+    "plugin-src/agents/slm-optimize-advisor.md",
+]
 "share/superlocalmemory/portable-kit/rules" = ["plugin-src/rules/AGENTS.md"]
 
 [tool.pytest.ini_options]

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "4.1.5"
+__version__ = "4.1.7"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",

package/src/superlocalmemory/cli/host_upgrades.py

@@ -145,13 +145,27 @@ def _upgrade_host(host: str, *, apply: bool, already_integrated: bool) -> dict[s
         if not assets.get("success") or not hooks.get("success"):
             return {"status": "blocked", "detail": "could not refresh SLM-owned Codex assets"}
         action = "would refresh" if not apply else "refreshed"
-        return {
-            "status": "updated" if apply else "preview",
-            "detail": (
-                f"{action} SLM-owned Codex skills, agents, and hooks; "
-                "MCP block preserved"
-            ),
-        }
+        # Name what is actually written.  Saying "refreshed skills" while the
+        # copies under ~/.agents/skills are not what this Codex reads turns a
+        # no-op into a success report.
+        written = assets.get("skills_written") or []
+        agents_written = assets.get("agents_written") or []
+        preserved = assets.get("agents_preserved") or []
+        elsewhere = assets.get("skills_read_elsewhere") or []
+
+        detail = f"{action} {len(written)} skill file(s) and {len(agents_written)} subagent file(s)"
+        if written:
+            detail += f" under {Path(written[0]).parent.parent}"
+        detail += "; hooks refreshed; MCP block preserved"
+        if preserved:
+            names = ", ".join(Path(x).name for x in preserved)
+            detail += f"; preserved {len(preserved)} subagent file(s) not written by SLM ({names})"
+        if elsewhere:
+            detail += (
+                f"; {len(elsewhere)} skill path(s) under ~/.codex/skills resolve outside "
+                f"the written location and were NOT refreshed ({Path(elsewhere[0]).parent})"
+            )
+        return {"status": "updated" if apply else "preview", "detail": detail}
 
     if already_integrated:
         return {

package/src/superlocalmemory/core/engine.py

@@ -24,6 +24,7 @@ import time
 from pathlib import Path
 from typing import Any
 
+from superlocalmemory.core.session_identity import synthetic_session_id
 from superlocalmemory.core.config import CANONICAL_RECALL_LIMIT, SLMConfig
 from superlocalmemory.core.engine_capabilities import Capabilities, CapabilityError
 from superlocalmemory.core.modes import get_capabilities
@@ -138,7 +139,12 @@ class MemoryEngine:
         # one is dropped by the queue, which is how 34 of 35 recall paths came
         # to leave no record at all.
         self._last_session_id: str = ""
-        self._ambient_session_id: str = f"engine:{os.getpid()}"
+        # Minted through the shared helper so this id is registered as
+        # invented rather than received; continuity and the reward pipeline
+        # both ask session_identity, and a hand-built prefix is invisible to it.
+        self._ambient_session_id: str = synthetic_session_id(
+            "engine", str(os.getpid()),
+        )
         self._initialized = False
 
         self._db = None

package/src/superlocalmemory/core/maintenance_scheduler.py

@@ -77,11 +77,43 @@ class MaintenanceScheduler:
         )
         self._initial_metrics_timer.daemon = True
         self._initial_metrics_timer.start()
+        # M048's re-read pass is idempotent and safe to replay (see its
+        # verify() docstring), but the migration runner never replays a
+        # completed migration and the cycle above only reaches it every
+        # ``scheduler_interval_minutes`` (360 by default). A store that
+        # drifted since the last cycle stays blocking — ready=false,
+        # migrations=false — for up to that whole interval after every
+        # restart, not because the fix is slow, but because nothing asks
+        # for it sooner. Staggered behind the other two so none of the
+        # three one-shots contend for the write lock.
+        self._initial_reclassify_timer = threading.Timer(
+            210.0, self._initial_reclassify_upcoming,
+        )
+        self._initial_reclassify_timer.daemon = True
+        self._initial_reclassify_timer.start()
         logger.info(
             "Maintenance scheduler started (interval=%dm)",
             self._config.forgetting.scheduler_interval_minutes,
         )
 
+    def _initial_reclassify_upcoming(self) -> None:
+        """Best-effort one-shot M048 re-read shortly after boot.
+
+        Runs the same pass the periodic cycle already runs (see below) so a
+        store that drifted before this restart converges within seconds
+        instead of waiting up to a full maintenance interval with the
+        daemon reporting itself not ready.
+        """
+        if not self._running:
+            return
+        try:
+            from superlocalmemory.storage.migrations import (
+                M048_upcoming_holds_only_what_is_upcoming as _reclassify,
+            )
+            _reclassify.apply(open_connection=self._db.raw_connection)
+        except Exception as exc:
+            logger.debug("Startup plan re-read skipped: %s", exc)
+
     def _initial_cache_gc(self) -> None:
         """Best-effort one-shot activation-cache GC shortly after boot."""
         if not self._running:
@@ -133,6 +165,10 @@ class MaintenanceScheduler:
         if _metrics_timer is not None:
             _metrics_timer.cancel()
             self._initial_metrics_timer = None
+        _reclassify_timer = getattr(self, "_initial_reclassify_timer", None)
+        if _reclassify_timer is not None:
+            _reclassify_timer.cancel()
+            self._initial_reclassify_timer = None
         logger.info("Maintenance scheduler stopped")
 
     def _schedule_next(self) -> None: