superlocalmemory 4.2.2 → 4.2.4

package/.claude-plugin/marketplace.json

@@ -21,7 +21,7 @@
       "license": "AGPL-3.0-or-later",
       "name": "superlocalmemory",
       "source": "./plugin",
-      "version": "4.2.2"
+      "version": "4.2.4"
     },
     {
       "author": {
@@ -39,7 +39,7 @@
       "license": "AGPL-3.0-or-later",
       "name": "superlocalmemory-codex",
       "source": "./codex-plugin",
-      "version": "4.2.2"
+      "version": "4.2.4"
     }
   ]
 }

package/CHANGELOG.md

@@ -5,6 +5,84 @@ 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).
 
+## [4.2.4] — Recall in under a second on large memories, with the answer check on every question
+
+A performance release. Nothing is moved or deleted. One data-only migration
+(M063) stores blank temporal dates as NULL.
+
+Measured on a real store of 27,000 memories and 16,800 entities, the same 24
+questions, through the daemon's recall endpoint:
+
+| | 4.2.3 | 4.2.4 |
+|---|---|---|
+| Median recall, idle machine | 5.29 s | 0.41 s |
+| 90th percentile, idle | 7.02 s | 0.55 s |
+| Three agents recalling at once (median / p90) | — | 0.72 s / 0.90 s |
+| While the Mode B language model works (median / p90) | — | 2.15 s / 2.92 s |
+| Questions whose answer check ran | 0 of 24 | 24 of 24 |
+
+### Fixes
+
+- **The answer check now runs on every question.** It was held to the
+  three-second budget while the question itself may run longer, so on a large
+  store it was skipped ("budget_exhausted") on nearly every recall, though it
+  takes 30-140 ms. It now shares the question's own time.
+- **Entity name lookups were rebuilt on almost every recall.** They were kept
+  only while nothing at all had been saved, so any save, hook note or access
+  count threw them away; on a store with 16,800 entities that cost up to several
+  seconds of a recall. They are now kept while the entities themselves are
+  unchanged, grow in place when new entities arrive, and are built when the
+  service starts instead of inside the first recall.
+- **The time-based search never reused its work** on a store holding a blank
+  date: one empty date switched its cache off for good. Blank dates are now
+  stored as no date (migration M063 cleans the existing ones).
+- **Concurrent recalls queued behind each other** in one search layer (the
+  associative "Hopfield" layer) on large stores. They now run side by side.
+- **The vector store kept a week of history**, one version per saved memory:
+  a busy store reached 7,194 versions and 4.1 GB, and every semantic search
+  walked them. It now keeps an hour (`SLM_VECTOR_HISTORY_DAYS` still sets it).
+  A store that already grew can be shrunk at once with SuperLocalMemory
+  stopped: `slm db compact --offline`.
+
+## [4.2.3] — Recall answers on large memories from every agent, hook and harness
+
+A fix release. Nothing is moved or deleted, and no setting changes.
+
+### Fixes
+
+- **A quick look at memory came back empty on large stores.** An agent's
+  `recall` at `depth=0` (the cheap one-line glance the tool suggests starting
+  with) was treated like the prompt hook and given its three-second limit. On a
+  store where full recall takes about 2.5 seconds (27,000 memories), it timed
+  out and returned nothing, with every search channel marked "timeout". A
+  glance is now a question like any other and waits for the full answer.
+- **`session_init` lost its search on large stores.** The first call every
+  agent makes loaded only pinned rules: its search ran under the same short
+  limit and timed out. It now gets the full time. It is still never judged by
+  the answer check.
+- **When the prompt hook ran out of time it injected nothing.** The keyword
+  backup only started after the full search was given up, with about 0.2
+  seconds left, so it never finished. Now, when a hook's search is still running
+  a second before its limit, the keyword backup starts beside it, and whichever
+  is ready first answers. The hook still never holds up a prompt longer than
+  before. This is the same for every harness (Claude Code, Codex, Cursor,
+  Copilot, Antigravity, Hermes).
+- **Hermes prefetch gave up before recall answered.** Hermes waits 3 seconds
+  for the memory it adds to each turn, but asked for a full recall. It now sends
+  its time budget (`budget_s`, a new optional `recall` parameter), and recall
+  answers inside it.
+- **`prestage_context` always said `recall_error`.** It recalled inside the
+  MCP process, which may not; it now recalls through the memory service, as
+  `session_init` does.
+- **Smaller tool fixes found by an end-to-end run of every MCP tool:**
+  `skill_lineage` reports an empty history instead of an error on a store where
+  no skill has evolved; `correct_pattern` refuses a pattern that does not exist
+  instead of reporting success; `review_correction` no longer tells an agent to
+  retry a review the memory service refused (an unknown or settled case).
+- **Docs:** the `slm-loop` skill and the MCP tool reference now say what
+  `slm_loop_run` needs to finish: an operator-registered check
+  (`gate_contract`). A matching memory alone never ends a loop.
+
 ## [4.2.2] — Recall never refuses answers it has after a model change, and "What am I working on?" answers from your work
 
 A fix release. Upgrading never moves or deletes memory. Text stays on the model it uses today.

package/README.md

@@ -32,9 +32,7 @@ In Mode A, core remember and recall make no model-provider call: no API key, no
 
 ## Install
 
-Three ways in. All three end in the same setup: your text memory on this machine, and, if you say yes, your pictures and documents too.
-
-**1. Ask your agent.** Copy this into Claude Code, Codex, Cursor or any agent that can run commands:
+> **The easiest way: let your AI agent install it.** Copy the block below into Claude Code, Codex, Cursor or any agent that can run commands. It reads the setup guide, asks you one question, sets everything up and tells you what works. No terminal commands for you to learn.
 
 ```
 Install SuperLocalMemory on this computer for me. Follow
@@ -45,7 +43,17 @@ screenshots and PDFs by describing them. Connect SuperLocalMemory to the agent
 I am using. When you finish, run slm doctor and tell me in plain words what works.
 ```
 
-**2. npm**, the primary route (Node 18+). It installs SLM into a package-owned virtual environment:
+**No AI agent? One line in Terminal** (macOS and Linux). It brings its own Python, sets everything up, connects the AI tools it finds and opens the dashboard; no Python or npm needed beforehand:
+
+```bash
+curl -fsSLo get-slm.sh https://raw.githubusercontent.com/qualixar/superlocalmemory/main/scripts/get-slm.sh && sh get-slm.sh
+```
+
+Add pictures and documents from the start with `sh get-slm.sh --media` at the end. It downloads the script first, so you can read it before it runs. Windows: use the agent prompt above, or npm or pip below.
+
+**Prefer the terminal?** Both routes end in the same setup: your text memory on this machine, and, if you say yes, your pictures and documents too.
+
+**npm**, the primary route (Node 18+). It installs SLM into a package-owned virtual environment:
 
 ```bash
 npm install -g superlocalmemory   # add --media to also turn on pictures and documents
@@ -53,7 +61,7 @@ slm setup                         # pick Mode A to keep everything on this machi
 slm connect claude-code           # or codex, cursor, windsurf, zed, claude-desktop, jetbrains, opencode ...
 ```
 
-**3. pip**, the other primary route (Python 3.12 to 3.14), in a Python virtual environment you activate:
+**pip**, the other primary route (Python 3.12 to 3.14), in a Python virtual environment you activate:
 
 ```bash
 python3 -m venv .venv

package/antigravity-plugin/_GENERATED.md

@@ -2,7 +2,7 @@
 
 Built by `scripts/build-antigravity-plugin.mjs` from `plugin-src/`. Version stamped from `plugin-src/manifest.json`.
 
-Version: **4.2.2**
+Version: **4.2.4**
 
 Do not edit by hand — regenerate instead.
 

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

@@ -81,4 +81,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall · slm-
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never run `slm gdpr erase --yes` unasked; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -79,4 +79,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -51,4 +51,4 @@ 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 switch the active profile unasked; 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 v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/antigravity-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 hand a ccr_id to another agent.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/antigravity-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "4.2.2",
+  "version": "4.2.4",
   "description": "Local-first agent memory with auditable hybrid retrieval. Remember decisions and recall them by asking, entirely on your machine.",
   "author": {
     "name": "Qualixar",

package/antigravity-plugin/skills/slm-bot-memory/SKILL.md

@@ -178,4 +178,4 @@ store every local bot on that computer can reach.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -144,4 +144,4 @@ These subcommands control daemon-level cache settings and bulk removal. They do
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/antigravity-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 v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/antigravity-plugin/skills/slm-getting-started-bot/SKILL.md

@@ -194,4 +194,4 @@ quality on a shared box.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -274,4 +274,4 @@ Before running any destructive or state-changing operation (`forget`,
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -324,4 +324,4 @@ All are host-only: a remote caller cannot use them.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -1,6 +1,6 @@
 ---
 name: slm-loop
-description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for a recall gate to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
+description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for an independently executed check registered by the operator to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
 when_to_use: "run a bounded loop, gate-verified task, iterate until tests pass, verify against an independent gate, don't trust the agent's own done claim, slm loop, convergence loop, loop until green, loop ledger, wait for another agent's result"
 allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash
 ---
@@ -26,7 +26,7 @@ subprocess or sandbox machinery. What each surface gives you:
 
 | Surface | What it does |
 |---|---|
-| `slm_loop_run` (MCP) | A *watcher*: each lap is a recall of `gate_query`; the loop ends when a confident match appears, or a bound trips. Use it to wait for a verification or coordination memory another agent will write (for example "build passed"). |
+| `slm_loop_run` (MCP) | A *watcher* for a registered check. DONE needs `gate_contract={"job_id": ...}`: a job the operator registered with `superlocalmemory.loops.receipt_jobs.register_job` and executed with `run_registered_check`. Each lap's recall of `gate_query` only locates context; a matching memory alone never passes. Without a registered job the run ends HALT ("operator-registered job_id required"), which is the correct, honest outcome. |
 | `slm loop demo` (CLI) | A keyless convergence demo: a stub proposer, a deterministic gate that passes on lap 3, every lap recorded. Proves the engine and ledger work end to end. |
 | `slm loop history`, `slm loop show` / `slm_loop_history`, `slm_loop_show` | Read the ledger of past runs. |
 | `superlocalmemory.loops.run_bounded_loop` (Python) | The engine itself, for code that supplies its own runner and gate callables. |
@@ -62,6 +62,7 @@ slm_loop_run(
   max_tokens: int = 0,          # optional token budget; 0 disables
   no_progress_window: int = 0,  # halt after N no-change laps; leave 0 for a watcher
   require_support: bool = False,# pass only if the answer check ran and judged it sufficient
+  gate_contract: dict | None = None,  # {"job_id": <operator registration>}; required for DONE
 )
 ```
 
@@ -170,4 +171,4 @@ Guides: `docs/skill-evolution.md`, `docs/bounded-loops-bridge.md`.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/antigravity-plugin/skills/slm-media/SKILL.md

@@ -337,4 +337,4 @@ minutes (previous vectors are kept) and let them decide.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -386,4 +386,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -161,4 +161,4 @@ anything but `core` or `mesh`.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -515,4 +515,4 @@ See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -372,4 +372,4 @@ sessions on this machine, so use it only when the user asks to move. See
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -180,4 +180,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -288,4 +288,4 @@ answered. To also surface shared or global facts, call `recall` with
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -228,4 +228,4 @@ the memory-engine upgrade is pending.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -15,5 +15,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory-codex",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "4.2.2"
+  "version": "4.2.4"
 }

package/codex-plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory-codex",
-  "version": "4.2.2",
+  "version": "4.2.4",
   "description": "Local-first agent memory with auditable hybrid retrieval. Remember decisions and recall them by asking, entirely on your machine.",
   "author": {
     "name": "Qualixar",

package/codex-plugin/AGENTS.md

@@ -187,4 +187,4 @@ Using this memory from a web assistant or another computer: see the slm-web-acce
 - **slm-governance-advisor** — scope/role compliance, retention and lifecycle, GDPR
 - **slm-loop-runner** — bounded, gate-verified loops (the `/slm-loop` command delegates to it)
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-plugin/README.md

@@ -2,7 +2,7 @@
 
 Local-first agent memory + reversible context compression for OpenAI Codex CLI.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later
 
 ---
 
@@ -204,4 +204,4 @@ root (not inside a subdirectory), then restart Codex.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · https://github.com/qualixar/superlocalmemory
+SuperLocalMemory v4.2.4 · Qualixar · https://github.com/qualixar/superlocalmemory

package/codex-plugin/_GENERATED.md

@@ -2,7 +2,7 @@
 
 Built by `scripts/build-codex-plugin.mjs` from the single source in `plugin-src/`. Version stamped from `plugin-src/manifest.json`.
 
-Version: **4.2.2**
+Version: **4.2.4**
 
 ## Derived — do not edit by hand
 

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

@@ -81,4 +81,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall · slm-
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never run `slm gdpr erase --yes` unasked; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -79,4 +79,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -51,4 +51,4 @@ 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 switch the active profile unasked; 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 v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-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 hand a ccr_id to another agent.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-plugin/skills/slm-bot-memory/SKILL.md

@@ -178,4 +178,4 @@ store every local bot on that computer can reach.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -144,4 +144,4 @@ These subcommands control daemon-level cache settings and bulk removal. They do
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-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 v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-plugin/skills/slm-getting-started-bot/SKILL.md

@@ -194,4 +194,4 @@ quality on a shared box.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -274,4 +274,4 @@ Before running any destructive or state-changing operation (`forget`,
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -324,4 +324,4 @@ All are host-only: a remote caller cannot use them.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

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

@@ -1,6 +1,6 @@
 ---
 name: slm-loop
-description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for a recall gate to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
+description: Gate-verified bounded loops with SuperLocalMemory as the durable ledger. Use when a task has a checkable acceptance condition and you must iterate until an INDEPENDENT gate passes — never stopping because the agent believes it is done. `slm_loop_run` (MCP) waits, under hard bounds, for an independently executed check registered by the operator to pass; `slm loop demo` shows the control flow keyless; `slm loop history` and `slm loop show <run_id>` (or `slm_loop_history` / `slm_loop_show`) inspect past runs, whose every lap is stored as queryable SLM memory (tag `loop:<name>`). Terminal statuses are DONE / HALT / PAUSE / KILLED / ERROR — report them exactly, never converting HALT/PAUSE/ERROR into success.
 when_to_use: "run a bounded loop, gate-verified task, iterate until tests pass, verify against an independent gate, don't trust the agent's own done claim, slm loop, convergence loop, loop until green, loop ledger, wait for another agent's result"
 allowed-tools: slm_loop_run, slm_loop_history, slm_loop_show, recall, report_outcome, get_soft_prompts, skill_health, skill_lineage, evolve_skill, observe_bounded_loop_evidence, Bash
 ---
@@ -26,7 +26,7 @@ subprocess or sandbox machinery. What each surface gives you:
 
 | Surface | What it does |
 |---|---|
-| `slm_loop_run` (MCP) | A *watcher*: each lap is a recall of `gate_query`; the loop ends when a confident match appears, or a bound trips. Use it to wait for a verification or coordination memory another agent will write (for example "build passed"). |
+| `slm_loop_run` (MCP) | A *watcher* for a registered check. DONE needs `gate_contract={"job_id": ...}`: a job the operator registered with `superlocalmemory.loops.receipt_jobs.register_job` and executed with `run_registered_check`. Each lap's recall of `gate_query` only locates context; a matching memory alone never passes. Without a registered job the run ends HALT ("operator-registered job_id required"), which is the correct, honest outcome. |
 | `slm loop demo` (CLI) | A keyless convergence demo: a stub proposer, a deterministic gate that passes on lap 3, every lap recorded. Proves the engine and ledger work end to end. |
 | `slm loop history`, `slm loop show` / `slm_loop_history`, `slm_loop_show` | Read the ledger of past runs. |
 | `superlocalmemory.loops.run_bounded_loop` (Python) | The engine itself, for code that supplies its own runner and gate callables. |
@@ -62,6 +62,7 @@ slm_loop_run(
   max_tokens: int = 0,          # optional token budget; 0 disables
   no_progress_window: int = 0,  # halt after N no-change laps; leave 0 for a watcher
   require_support: bool = False,# pass only if the answer check ran and judged it sufficient
+  gate_contract: dict | None = None,  # {"job_id": <operator registration>}; required for DONE
 )
 ```
 
@@ -170,4 +171,4 @@ Guides: `docs/skill-evolution.md`, `docs/bounded-loops-bridge.md`.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/codex-plugin/skills/slm-media/SKILL.md

@@ -337,4 +337,4 @@ minutes (previous vectors are kept) and let them decide.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -386,4 +386,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -161,4 +161,4 @@ anything but `core` or `mesh`.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -515,4 +515,4 @@ See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -372,4 +372,4 @@ sessions on this machine, so use it only when the user asks to move. See
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -180,4 +180,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -288,4 +288,4 @@ answered. To also surface shared or global facts, call `recall` with
 
 ---
 
-*SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later*

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

@@ -228,4 +228,4 @@ the memory-engine upgrade is pending.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/copilot-plugin/.github/agents/slm-governance-advisor.agent.md

@@ -9,7 +9,7 @@ description: >
 tools: recall, search, remember, update_memory, list_recent, Read, Bash
 model: inherit
 target: vscode
-version: "4.2.2"
+version: "4.2.4"
 ---
 
 # Role
@@ -83,4 +83,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall · slm-
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never run `slm gdpr erase --yes` unasked; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/copilot-plugin/.github/agents/slm-loop-runner.agent.md

@@ -11,7 +11,7 @@ description: >
 tools: Bash, recall, remember, Read, slm_loop_run, slm_loop_history, slm_loop_show
 model: inherit
 target: vscode
-version: "4.2.2"
+version: "4.2.4"
 ---
 
 # Role
@@ -81,4 +81,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/copilot-plugin/.github/agents/slm-memory-advisor.agent.md

@@ -8,7 +8,7 @@ description: >
 tools: session_init, recall, search, remember, update_memory, forget, list_recent, Read
 model: inherit
 target: vscode
-version: "4.2.2"
+version: "4.2.4"
 ---
 
 # Role
@@ -53,4 +53,4 @@ 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 switch the active profile unasked; 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 v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later

package/copilot-plugin/.github/agents/slm-optimize-advisor.agent.md

@@ -9,7 +9,7 @@ description: >
 tools: slm_compress, slm_retrieve, slm_cache_set, slm_cache_get, slm_optimize_stats, Read, Bash
 model: inherit
 target: vscode
-version: "4.2.2"
+version: "4.2.4"
 ---
 
 # Role
@@ -43,4 +43,4 @@ 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 hand a ccr_id to another agent.
 
-SuperLocalMemory v4.2.2 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v4.2.4 · Qualixar · AGPL-3.0-or-later