superlocalmemory 3.6.17 → 3.6.18

package/README.md

@@ -2,10 +2,10 @@
   <img src="https://superlocalmemory.com/assets/logo-mark.png" alt="SuperLocalMemory" width="200"/>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.6.17</h1>
+<h1 align="center">SuperLocalMemory V3.6.18</h1>
 <p align="center"><strong>Cache. Compress. Remember. Three surfaces — proxy, MCP tools, or skill. Every setup covered.</strong><br/>
 <em>To the best of our knowledge, the only zero-cloud agent memory that beats Mem0's zero-LLM score on LoCoMo. Mode A: 74.8% vs Mem0 64.2% — no GPU, no API key, on CPU.</em></p>
-<p align="center"><code>v3.6.17</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><br/>
+<p align="center"><code>v3.6.18</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><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 published research papers</strong> (arXiv preprints + Zenodo-archived) · <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": "3.6.17",
+  "version": "3.6.18",
   "description": "Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.",
   "keywords": [
     "ai-memory",

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

@@ -16,5 +16,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "3.6.17"
+  "version": "3.6.18"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.6.17 -->
+<!-- BEGIN SuperLocalMemory v3.6.18 -->
 
 ## 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) · slm-optimize-advisor (context compression + KV cache)
 
-<!-- END SuperLocalMemory v3.6.17 -->
+<!-- END SuperLocalMemory v3.6.18 -->
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -41,4 +41,4 @@ recall→`slm recall "<q>" --limit N` (add `--include-global`/`--include-shared`
 # 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.
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -35,4 +35,4 @@ stats→`slm optimize status`/`savings` · compress→`slm compress` · cache→
 # 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 %.
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.6.17
+superlocalmemory==3.6.18

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

@@ -137,4 +137,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -140,4 +140,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -297,4 +297,4 @@ Without this, the six graph tools are not registered and will appear as unknown
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -201,4 +201,4 @@ trusts that what you surface came from the store.
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -191,4 +191,4 @@ slm remember "<content>" --scope shared --shared-with alice,bob
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -204,4 +204,4 @@ slm doctor [--json]    # preflight check including daemon and embedding worker
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -146,4 +146,4 @@ Note: the `slm optimize` subcommands have known pre-existing parse-test failures
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -41,4 +41,4 @@ recall→`slm recall "<q>" --limit N` (add `--include-global`/`--include-shared`
 # 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.
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -35,4 +35,4 @@ stats→`slm optimize status`/`savings` · compress→`slm compress` · cache→
 # 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 %.
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

package/plugin-src/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.6.17",
+  "version": "3.6.18",
   "pluginName": "superlocalmemory",
   "displayName": "SuperLocalMemory",
   "repository": "https://github.com/qualixar/superlocalmemory",

package/plugin-src/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.6.17
+superlocalmemory==3.6.18

package/plugin-src/rules/AGENTS.md

@@ -88,4 +88,4 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 | `slm_cache_get`    | `key`                                                                          | KV cache get; returns hit, value   |
 | `slm_optimize_stats` | `()`                                                                         | Returns compress_runs, tokens_saved_compress, cache_kv_hits |
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/CLAUDE.md.fragment

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.6.17 -->
+<!-- BEGIN SuperLocalMemory v3.6.18 -->
 
 ## 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) · slm-optimize-advisor (context compression + KV cache)
 
-<!-- END SuperLocalMemory v3.6.17 -->
+<!-- END SuperLocalMemory v3.6.18 -->
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -137,4 +137,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -140,4 +140,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -297,4 +297,4 @@ Without this, the six graph tools are not registered and will appear as unknown
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

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

@@ -201,4 +201,4 @@ trusts that what you surface came from the store.
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -191,4 +191,4 @@ slm remember "<content>" --scope shared --shared-with alice,bob
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -204,4 +204,4 @@ slm doctor [--json]    # preflight check including daemon and embedding worker
 
 ---
 
-*SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later*

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

@@ -146,4 +146,4 @@ Note: the `slm optimize` subcommands have known pre-existing parse-test failures
 
 ---
 
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.6.18 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.6.17"
+version = "3.6.18"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "AGPL-3.0-or-later"}
@@ -146,8 +146,9 @@ superlocalmemory = ["ui/**/*"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 pythonpath = ["src"]
-addopts = "-m 'not slow and not ollama and not benchmark'"
+addopts = "-p no:cacheprovider -p no:subtests -m 'not slow and not ollama and not benchmark'"
 asyncio_mode = "auto"
+faulthandler_timeout = 0
 markers = [
     "slow: marks tests as slow — real engine/model loading (run with: pytest -m slow)",
     "ollama: marks tests that require a running Ollama instance",

package/scripts/build-plugin.js

@@ -30,7 +30,7 @@ import process from 'node:process';
 // ---------------------------------------------------------------------------
 // Constants
 // ---------------------------------------------------------------------------
-const VERSION = '3.6.17';
+const VERSION = '3.6.18';
 const MANIFEST_REL = 'plugin-src/manifest.json';
 const GENERATED_BANNER = `# _GENERATED — DO NOT HAND-EDIT
 

package/scripts/postinstall-interactive.js

@@ -489,19 +489,99 @@ async function runInteractiveFlow(rl, recommendedProfile) {
 // under 60 LOC per Stage-8 G2 scope.
 function printLivingBrainDelta() {
   console.log('');
-  console.log('What\'s new in v3.4.21 FINAL:');
-  console.log('  + Engagement reward model (action_outcomes populated)');
-  console.log('  + Online LightGBM retrain (shadow-tested, auto-rollback)');
-  console.log('  + Real consolidation (hnswlib, reversible merges)');
-  console.log('  + Inline entity detection (<2 ms trigram lookup)');
-  console.log('  + Opt-in skill evolution (Haiku 4.5 default)');
-  console.log('  + Evo-Memory public benchmark');
+  console.log('What\'s new in v3.6.18:');
+  console.log('  + session_init mandate hook — Claude calls ToolSearch→session_init first, every session');
+  console.log('  + Plugin auto-install on npm/pip install — skills, agents, hooks wired automatically');
+  console.log('  + M017 migration — ccq_consolidated_blocks gets scope column (no more silent CCQ scope drop)');
+  console.log('  + GC-safe test flags baked into pyproject.toml + Makefile (no more macOS ARM SIGSEGV)');
   console.log('What\'s unchanged:');
   console.log('  * Your memory.db — zero deletes, zero rewrites');
   console.log('  * Your profile settings');
   console.log('  * All CLI commands you already use');
 }
 
+// T1-B: Auto-install the Claude Code plugin after pip/npm install.
+// Best-effort: never fails the installer, never blocks the main flow.
+// Checks for `claude` CLI, then runs:
+//   1. claude plugin marketplace add qualixar/superlocalmemory
+//   2. claude plugin install superlocalmemory@qualixar
+//   3. slm hooks install
+async function tryInstallClaudePlugin() {
+  const { execFile } = require('child_process');
+  const { promisify } = require('util');
+  const execFileAsync = promisify(execFile);
+
+  // Find claude binary — try PATH first, then common install locations.
+  const claudeCandidates = ['claude'];
+  if (process.platform !== 'win32') {
+    claudeCandidates.push(
+      '/usr/local/bin/claude',
+      process.env.HOME + '/.npm-global/bin/claude',
+      process.env.HOME + '/.local/bin/claude',
+    );
+  }
+
+  let claudeBin = null;
+  for (const candidate of claudeCandidates) {
+    try {
+      await execFileAsync(candidate, ['--version'], { timeout: 5000 });
+      claudeBin = candidate;
+      break;
+    } catch (_e) { /* keep looking */ }
+  }
+
+  if (!claudeBin) {
+    // Claude Code not installed — print guidance and skip.
+    console.log('SLM: Claude Code CLI not found — skipping plugin auto-install.');
+    console.log('SLM: To install the plugin manually after installing Claude Code:');
+    console.log('SLM:   claude plugin marketplace add qualixar/superlocalmemory');
+    console.log('SLM:   claude plugin install superlocalmemory@qualixar');
+    console.log('SLM:   slm hooks install');
+    return;
+  }
+
+  console.log('SLM: Claude Code found — installing SLM plugin...');
+
+  // Step 1: Add marketplace
+  try {
+    await execFileAsync(claudeBin,
+      ['plugin', 'marketplace', 'add', 'qualixar/superlocalmemory'],
+      { timeout: 30000 });
+    console.log('SLM: marketplace added (qualixar/superlocalmemory)');
+  } catch (e) {
+    // "already exists" or network error — not fatal
+    console.log('SLM: marketplace add note: ' + (e.stderr || e.message || String(e)).trim().split('\n')[0]);
+  }
+
+  // Step 2: Install plugin
+  try {
+    await execFileAsync(claudeBin,
+      ['plugin', 'install', 'superlocalmemory@qualixar'],
+      { timeout: 30000 });
+    console.log('SLM: plugin installed (superlocalmemory@qualixar)');
+  } catch (e) {
+    console.log('SLM: plugin install note: ' + (e.stderr || e.message || String(e)).trim().split('\n')[0]);
+  }
+
+  // Step 3: Install hooks (only if not already current — avoids needless writes)
+  // `slm hooks install` uses atomic tmp-then-rename and only touches the SLM
+  // section of settings.json; all other Claude Code settings are preserved.
+  try {
+    const statusResult = await execFileAsync('slm', ['hooks', 'status', '--json'],
+      { timeout: 10000 }).catch(() => null);
+    const alreadyCurrent = statusResult &&
+      (() => { try { const s = JSON.parse(statusResult.stdout); return s.installed && !s.needs_upgrade; } catch { return false; } })();
+    if (!alreadyCurrent) {
+      await execFileAsync('slm', ['hooks', 'install'], { timeout: 15000 });
+      console.log('SLM: hooks installed into Claude Code settings');
+    } else {
+      console.log('SLM: hooks already current — skipped');
+    }
+  } catch (e) {
+    console.log('SLM: hooks install note: ' + (e.stderr || e.message || String(e)).trim().split('\n')[0]);
+  }
+}
+
 function printFirstRunChecklist(config) {
   console.log('');
   console.log('SuperLocalMemory is configured.');
@@ -692,6 +772,13 @@ async function main() {
 
   // UX-G2: show the one-screen delta banner so upgraders see what shipped.
   printLivingBrainDelta();
+
+  // T1-B: Auto-install Claude Code plugin + hooks. Best-effort, non-blocking.
+  // Only runs on npm install (not --dry-run), when claude CLI is present.
+  if (!args.dryRun) {
+    await tryInstallClaudePlugin();
+  }
+
   printFirstRunChecklist(config);
   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__ = "3.6.17"
+__version__ = "3.6.18"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",

package/src/superlocalmemory/cli/setup_wizard.py

@@ -789,6 +789,40 @@ def _maybe_install_hooks_on_first_use() -> None:
         # Best-effort: parity-fallback, never block CLI.
         pass
 
+    # T1-B: Auto-install Claude Code plugin (skills, agents, hooks).
+    # Runs after hooks install, best-effort — never blocks CLI startup.
+    _try_install_claude_plugin()
+
+
+def _try_install_claude_plugin() -> None:
+    """Auto-install the Claude Code plugin on first pip/uvx SLM install.
+
+    Runs ``claude plugin marketplace add qualixar/superlocalmemory`` then
+    ``claude plugin install superlocalmemory@qualixar`` if the ``claude``
+    CLI is found in PATH. Silent on any error — plugin install is a
+    convenience, not a hard requirement for SLM to function.
+    """
+    import shutil
+    import subprocess
+
+    claude = shutil.which("claude")
+    if not claude:
+        return  # Claude Code not in PATH — skip silently
+
+    _run = lambda cmd: subprocess.run(  # noqa: E731
+        cmd, capture_output=True, timeout=30, check=False
+    )
+
+    try:
+        _run([claude, "plugin", "marketplace", "add", "qualixar/superlocalmemory"])
+    except Exception:
+        pass
+
+    try:
+        _run([claude, "plugin", "install", "superlocalmemory@qualixar"])
+    except Exception:
+        pass
+
 
 # ---------------------------------------------------------------------------
 # Mode C provider config (preserved from original)

package/src/superlocalmemory/hooks/claude_code_hooks.py

@@ -21,6 +21,7 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 import sys
 import tempfile
 from pathlib import Path
@@ -31,7 +32,7 @@ CLAUDE_SETTINGS = Path.home() / ".claude" / "settings.json"
 VERSION_DIR = Path.home() / ".superlocalmemory" / "hooks"
 VERSION_FILE = VERSION_DIR / ".version"
 DISABLED_FILE = VERSION_DIR / ".hooks-disabled"
-HOOKS_VERSION = "3.4.43"
+HOOKS_VERSION = "3.6.18"
 
 # Cross-platform temp dir and marker paths
 _TMP = tempfile.gettempdir()
@@ -92,6 +93,19 @@ def _hook_definitions(include_gate: bool = False) -> dict[str, list]:
     """
     defs: dict[str, list] = {
         "SessionStart": [
+            # v3.6.18: mandate fires FIRST so session_init is never skipped.
+            # mcp__superlocalmemory__session_init is DEFERRED — Claude must call
+            # ToolSearch before it can invoke the tool. Without this hook,
+            # Claude responds before loading the schema → no 6-channel memory.
+            {
+                "hooks": [
+                    {
+                        "type": "command",
+                        "command": _wrap_python_cmd("mandate"),
+                        "timeout": 5000,
+                    }
+                ]
+            },
             {
                 "hooks": [
                     {
@@ -100,7 +114,7 @@ def _hook_definitions(include_gate: bool = False) -> dict[str, list]:
                         "timeout": 15000,
                     }
                 ]
-            }
+            },
         ],
         "PostToolUse": [
             {
@@ -278,9 +292,31 @@ def _read_settings() -> dict:
 
 
 def _write_settings(settings: dict) -> None:
-    """Write settings.json with pretty formatting."""
+    """Write settings.json atomically — tmp file + rename.
+
+    Direct .write_text() would truncate the file on a crash mid-write,
+    destroying the user's entire Claude Code configuration. The tmp-then-rename
+    pattern is atomic on POSIX (os.replace) and near-atomic on Windows: either
+    the full new content lands or the original file is untouched.
+
+    Never overwrites non-SLM settings — _merge_hooks() guarantees that only
+    the SLM hooks entries change; all other keys are preserved from the read.
+    """
     CLAUDE_SETTINGS.parent.mkdir(parents=True, exist_ok=True)
-    CLAUDE_SETTINGS.write_text(json.dumps(settings, indent=2) + "\n")
+    content = json.dumps(settings, indent=2) + "\n"
+    # Write to a sibling tmp file in the same directory so os.replace is atomic
+    # (cross-device rename would fail; same-dir rename is guaranteed atomic).
+    tmp_path = CLAUDE_SETTINGS.with_suffix(".json.slm_tmp")
+    try:
+        tmp_path.write_text(content, encoding="utf-8")
+        os.replace(tmp_path, CLAUDE_SETTINGS)
+    except Exception:
+        # Best-effort cleanup of the tmp file on failure
+        try:
+            tmp_path.unlink(missing_ok=True)
+        except Exception:
+            pass
+        raise
 
 
 # ---------------------------------------------------------------------------

package/src/superlocalmemory/hooks/hook_handlers.py

@@ -120,6 +120,7 @@ def handle_hook(action: str) -> None:
         sys.exit(_main())
 
     handlers = {
+        "mandate": _hook_mandate,
         "start": _hook_start,
         "gate": _hook_gate,
         "init-done": _hook_init_done,
@@ -167,6 +168,38 @@ def _launch_post_session_evolution(
     )
 
 
+# ---------------------------------------------------------------------------
+# 0. MANDATE — first SessionStart hook; fires before start
+# ---------------------------------------------------------------------------
+
+_MANDATE_TEXT = """<MANDATORY_SESSION_INIT>
+BEFORE writing any text or calling any other tool, you MUST execute these two steps in order:
+
+STEP 1 — Load schema:
+  Call ToolSearch with query: "select:mcp__superlocalmemory__session_init"
+
+STEP 2 — Initialize memory brain:
+  Call mcp__superlocalmemory__session_init with:
+    project_path = your current working directory
+    query = a short description of the session topic (derive from user's first message)
+
+This is non-negotiable. SLM is the brain. Without session_init, you have no 6-channel memory context (Ebbinghaus decay, entity graph, FSRS, spreading activation all go cold).
+DO NOT output any text until session_init has completed.
+</MANDATORY_SESSION_INIT>"""
+
+
+def _hook_mandate() -> None:
+    """Print the session_init mandate. MUST be the FIRST SessionStart hook.
+
+    mcp__superlocalmemory__session_init is DEFERRED at session start — Claude
+    cannot call it without ToolSearch first loading the schema. This hook
+    fires before `slm hook start` and injects the two-step protocol into the
+    system-reminder block so Claude's first action is always ToolSearch →
+    session_init, not a text response with no memory context.
+    """
+    print(_MANDATE_TEXT)
+
+
 # ---------------------------------------------------------------------------
 # 1. SESSION START — SessionStart hook
 # ---------------------------------------------------------------------------

package/src/superlocalmemory/storage/migrations/M017_ccq_scope_column.py

@@ -0,0 +1,79 @@
+# Copyright (c) 2026 Varun Pratap Bhardwaj / Qualixar
+# Licensed under AGPL-3.0-or-later - see LICENSE file
+# Part of SuperLocalMemory v3.6.18
+
+"""M017 — scope column on ccq_consolidated_blocks.
+
+The cognitive-consolidation queue table (``ccq_consolidated_blocks``) was
+created before the M016 multi-scope migration and therefore has no ``scope``
+column.  Without it, consolidation summaries are always stored as
+``personal`` regardless of the source facts' scope — a silent data-loss edge
+case when a user has opted into global or shared memory.
+
+Fix: add a ``scope TEXT NOT NULL DEFAULT 'personal'`` column plus a
+``(profile_id, scope)`` covering index for scope-filtered queries.
+
+Deferred (like M006, M011, M013, M016): the CCQ table is created by the
+engine, not by migration DDL, so we apply after engine init via
+``apply_deferred``.
+
+Author: Varun Pratap Bhardwaj / Qualixar
+"""
+
+from __future__ import annotations
+
+import sqlite3
+
+NAME = "M017_ccq_scope_column"
+DB_TARGET = "memory"
+
+TABLE = "ccq_consolidated_blocks"
+
+DDL = (
+    f"ALTER TABLE {TABLE} ADD COLUMN scope TEXT NOT NULL DEFAULT 'personal';"
+    f"CREATE INDEX IF NOT EXISTS idx_{TABLE}_scope ON {TABLE}(scope);"
+    f"CREATE INDEX IF NOT EXISTS idx_{TABLE}_profile_scope ON {TABLE}(profile_id, scope);"
+)
+
+
+def _table_exists(conn: sqlite3.Connection, table: str) -> bool:
+    return conn.execute(
+        "SELECT 1 FROM sqlite_master WHERE type='table' AND name=?", (table,)
+    ).fetchone() is not None
+
+
+def _column_names(conn: sqlite3.Connection, table: str) -> set[str]:
+    return {r[1] for r in conn.execute(f"PRAGMA table_info({table})").fetchall()}
+
+
+def apply(conn: sqlite3.Connection) -> None:
+    """Idempotently add scope column + indexes to ccq_consolidated_blocks.
+
+    Skips silently when the table doesn't exist yet (engine hasn't created it)
+    or when the column is already present (re-apply or fresh install).
+    """
+    if not _table_exists(conn, TABLE):
+        return
+    cols = _column_names(conn, TABLE)
+    if "scope" not in cols:
+        conn.execute(
+            f"ALTER TABLE {TABLE} ADD COLUMN scope TEXT NOT NULL DEFAULT 'personal'"
+        )
+    conn.execute(f"CREATE INDEX IF NOT EXISTS idx_{TABLE}_scope ON {TABLE}(scope)")
+    conn.execute(
+        f"CREATE INDEX IF NOT EXISTS idx_{TABLE}_profile_scope ON {TABLE}(profile_id, scope)"
+    )
+
+
+def verify(conn: sqlite3.Connection) -> bool:
+    """Applied when ccq_consolidated_blocks has the scope column and index."""
+    if not _table_exists(conn, TABLE):
+        return True  # table absent — apply() skips it; nothing to verify
+    cols = _column_names(conn, TABLE)
+    if "scope" not in cols:
+        return False
+    idx = conn.execute(
+        "SELECT 1 FROM sqlite_master WHERE type='index' AND name=?",
+        (f"idx_{TABLE}_scope",),
+    ).fetchone()
+    return idx is not None

package/src/superlocalmemory.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.6.17
+Version: 3.6.18
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: AGPL-3.0-or-later
@@ -96,10 +96,10 @@ Dynamic: license-file
   <img src="https://superlocalmemory.com/assets/logo-mark.png" alt="SuperLocalMemory" width="200"/>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.6.17</h1>
+<h1 align="center">SuperLocalMemory V3.6.18</h1>
 <p align="center"><strong>Cache. Compress. Remember. Three surfaces — proxy, MCP tools, or skill. Every setup covered.</strong><br/>
 <em>To the best of our knowledge, the only zero-cloud agent memory that beats Mem0's zero-LLM score on LoCoMo. Mode A: 74.8% vs Mem0 64.2% — no GPU, no API key, on CPU.</em></p>
-<p align="center"><code>v3.6.17</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><br/>
+<p align="center"><code>v3.6.18</code> — <strong>Plugin-native. Profile-aware. Distributed-ready.</strong><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 published research papers</strong> (arXiv preprints + Zenodo-archived) · <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/src/superlocalmemory.egg-info/SOURCES.txt

@@ -435,6 +435,7 @@ src/superlocalmemory/storage/migrations/M013_bi_temporal_columns.py
 src/superlocalmemory/storage/migrations/M014_v345_scale_ready.py
 src/superlocalmemory/storage/migrations/M015_add_pinned_column.py
 src/superlocalmemory/storage/migrations/M016_add_scope_support.py
+src/superlocalmemory/storage/migrations/M017_ccq_scope_column.py
 src/superlocalmemory/storage/migrations/__init__.py
 src/superlocalmemory/trust/__init__.py
 src/superlocalmemory/trust/gate.py

package/plugin-src/commands/slm-optimize.md

@@ -1,22 +0,0 @@
----
-description: Apply SLM context-optimization (compress large output / cache repeats) and report savings.
-argument-hint: [stats]
-allowed-tools: slm_compress, slm_cache_set, slm_cache_get, slm_optimize_stats, Bash
----
-
-Apply SuperLocalMemory context-optimization. Arguments: $ARGUMENTS
-
-If arguments are empty or "stats":
-- Call `slm_optimize_stats()` and report: cache_kv_hits, compress_runs, tokens_saved_compress.
-
-If there is large output to compress (>2000 chars):
-- Call `slm_compress(content=<output>, mode="auto", reversible=True)`.
-- Work from the compressed form; retain ccr_id if the result is lossy.
-
-Rules (apply strictly):
-- Rule 6 — NEVER compress/cache: code intended for Edit/Write; JSON being parsed; secrets/keys/tokens; ccr_ids; content <500 chars.
-- Rule 8 — FAIL-OPEN: if ok:false, continue with original; do not retry; do not surface the error unless the user asks.
-
-MCP unavailable → CLI fallback: `slm optimize status`.
-
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-recall.md

@@ -1,16 +0,0 @@
----
-description: Recall relevant facts and decisions from SuperLocalMemory by query.
-argument-hint: <what to recall>
-allowed-tools: recall, search, Bash
----
-
-Recall from SuperLocalMemory using the query: $ARGUMENTS
-
-1. Call `recall(query="$ARGUMENTS", limit=10)` via MCP.
-2. If no confident match or count==0, also call `search("$ARGUMENTS", 10)`.
-3. Present results concisely — fact, tags, importance, date. Never invent or fabricate a memory.
-4. If MCP is unavailable, fall back to CLI:
-   - `slm recall "$ARGUMENTS" --limit 10`
-   - then `slm search "$ARGUMENTS"`
-
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-remember.md

@@ -1,16 +0,0 @@
----
-description: Save an atomic fact or decision to SuperLocalMemory.
-argument-hint: <the fact> [#tag1,tag2]
-allowed-tools: recall, remember, Bash
----
-
-Save to SuperLocalMemory: $ARGUMENTS
-
-1. First call `recall("$ARGUMENTS", 5)` — dedupe check. If a near-identical memory exists, tell the user and stop; delegate to slm-memory-advisor to update_memory if a correction is needed.
-2. Extract tags from any trailing `#tag1,tag2` pattern in the arguments.
-3. Determine importance: use 8 for blockers/security/architecture decisions; use 7 for conventions and constraints; use 5 for general facts.
-4. Call `remember(content="$ARGUMENTS", tags=<extracted tags>, importance=<n>)`.
-5. Confirm only on success:true. If success is not true, report the error — never claim "saved."
-6. MCP unavailable → CLI fallback: `slm remember "$ARGUMENTS" --tags <tags>` (note: `--importance` is MCP-only, not a CLI flag).
-
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later

package/plugin-src/commands/slm-status.md

@@ -1,15 +0,0 @@
----
-description: Show SuperLocalMemory health and optimization counters.
-argument-hint: (no arguments)
-allowed-tools: slm_optimize_stats, Bash
----
-
-Show SuperLocalMemory status and optimization counters.
-
-1. Run `slm status` via Bash — this is the canonical health check (memory count, profile, daemon state, integrity).
-2. Also call `slm_optimize_stats()` via MCP for Surface-B counters (cache_kv_hits, compress_runs, tokens_saved_compress). If ok:false, omit silently — do not surface the error.
-3. Summarize both outputs in a concise report. Flag any integrity warnings from `slm status`.
-
-Note: MCP get_status is intentionally NOT used here — it is outside the core profile and would error. Use `slm status` (CLI) + `slm_optimize_stats` (MCP) only.
-
-SuperLocalMemory v3.6.17 · Qualixar · AGPL-3.0-or-later