superlocalmemory 3.8.7 → 3.8.9

package/CHANGELOG.md

@@ -5,6 +5,51 @@ All notable changes to SuperLocalMemory V3 will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.8.9] - 2026-07-27 — Reliable MCP recall and background processing
+
+### Fixed
+- MCP recall is reliable through both supported connection methods: local
+  stdio and Streamable HTTP. HTTP tool calls no longer hang the daemon.
+- Changing dashboard memory or model settings no longer leaves background
+  processing stuck. Your saved memories stay available while processing resumes
+  safely with the updated settings.
+- Newly saved memories remain immediately searchable while their richer
+  background indexing completes.
+
+### Notes
+- Existing memories and configuration are preserved during upgrade. No manual
+  migration is required.
+
+## [3.8.8] - 2026-07-27 — Live-database recall and vector integrity
+
+### Fixed
+- Foreground recall now retains priority while startup repair and canonical
+  remember enrichment are active. Background embedding work yields between
+  items and cannot cold-start the shared local model ahead of a user query.
+- Daemon readiness now verifies that the local embedding subprocess is
+  actually alive and has served a request instead of trusting a stale startup
+  flag.
+- Scene clustering reuses durable fact embeddings and ignores legacy scene
+  rows whose facts were already consolidated away. Mature databases no longer
+  issue thousands of redundant model requests or repeatedly recycle the
+  embedding worker after restart.
+- sqlite-vec row allocation is serialized across processes, and every metadata
+  pointer is validated against the vector payload's profile. Cross-profile
+  row-id collisions are repaired without exposing another profile's memory.
+- Vector writes roll back abandoned transactions, missing vectors are repaired
+  exactly, and semantic search expands past legacy orphan payloads.
+- Entity-cache startup reads are bounded and load only the columns used by the
+  entity channel.
+- Exact lexical evidence remains protected after learned ranking so a freshly
+  remembered exact marker cannot be displaced by a weaker semantic match.
+
+### Notes
+- Recall remains physically query-only; remember owns durable writes and
+  continues full canonical enrichment asynchronously after immediate queryable
+  admission.
+- This candidate must pass the installed wheel, installed npm tarball,
+  dashboard, MCP, CLI, and mature live-database gates before publication.
+
 ## [3.8.7] - 2026-07-27 — Existing graph-store compatibility
 
 ### Fixed
@@ -12,9 +57,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   Cozo graph stores. Version 3.8.6 selected PyCozo 0.7.6, whose incompatible
   on-disk format could stop the daemon at startup with
   `Unknown storage version 1`.
+- A native Cozo panic is now contained at the optional projection boundary.
+  The daemon remains available on canonical SQLite and preserves the graph
+  files unchanged instead of losing access to memory.
 
 ### Notes
-- No graph rebuild or database migration is required.
+- Existing PyCozo 0.3.0 graphs require no rebuild or database migration.
 - All serialized-write, read-only recall, admission-journal, and dead-letter
   fixes from 3.8.6 are unchanged.
 

package/README.md

@@ -5,15 +5,15 @@
   </picture>
 </p>
 
-<h1 align="center">SuperLocalMemory V3.8.7</h1>
+<h1 align="center">SuperLocalMemory V3.8.8</h1>
 <p align="center"><strong>Enterprise-grade, local-first memory for AI agents and teams.</strong><br/>
 <em>A persistent, auditable long-term brain for your agents that runs on your own infrastructure — with multi-workspace isolation, role-based access, and GDPR + EU AI Act governance controls built in.</em></p>
-<p align="center"><code>v3.8.7</code> — one control plane: auditable retrieval · multi-scope memory (personal / shared / global) · Cache · Compress · trusted-peer Mesh · bounded loops — across CLI, MCP, dashboard, the <strong>Claude plugin</strong>, the <strong>Codex add-on</strong>, and documented IDE integrations.<br/>
+<p align="center"><code>v3.8.8</code> — one control plane: auditable retrieval · multi-scope memory (personal / shared / global) · Cache · Compress · trusted-peer Mesh · bounded loops — across CLI, MCP, dashboard, the <strong>Claude plugin</strong>, the <strong>Codex add-on</strong>, and documented IDE integrations.<br/>
 Proxy: <code>slm wrap claude</code> &nbsp;·&nbsp; MCP: add <code>slm_compress</code> to your config &nbsp;·&nbsp; Skill: zero-config</p>
 <p align="center"><strong>3 public research preprints</strong> (arXiv + Zenodo archives) · <a href="https://arxiv.org/abs/2603.02240">arXiv:2603.02240</a> · <a href="https://arxiv.org/abs/2603.14588">arXiv:2603.14588</a> · <a href="https://arxiv.org/abs/2604.04514">arXiv:2604.04514</a></p>
 
 <p align="center">
-  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/v3.8.7-Current_Release-2ea44f?style=for-the-badge&logo=checkmarx&logoColor=white" alt="v3.8.7 — Current Release"/></a>
+  <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/v3.8.8-Current_Release-2ea44f?style=for-the-badge&logo=checkmarx&logoColor=white" alt="v3.8.8 — Current Release"/></a>
   <a href="https://arxiv.org/abs/2603.14588"><img src="https://img.shields.io/badge/arXiv-2603.14588-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"/></a>
   <a href="#three-surfaces-proxy--mcp-tools--skill"><img src="https://img.shields.io/badge/Proxy_|_MCP_|_Skill-22c55e?style=for-the-badge" alt="Three Surfaces: Proxy, MCP Tools, Skill"/></a>
   <a href="https://pypi.org/project/superlocalmemory/"><img src="https://img.shields.io/pypi/v/superlocalmemory?style=for-the-badge&logo=pypi&logoColor=white" alt="PyPI"/></a>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.8.7",
+  "version": "3.8.9",
   "description": "Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.",
   "keywords": [
     "ai-memory",

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

@@ -15,5 +15,5 @@
   "mcpServers": "./.mcp.json",
   "name": "superlocalmemory",
   "repository": "https://github.com/qualixar/superlocalmemory",
-  "version": "3.8.7"
+  "version": "3.8.9"
 }

package/plugin/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- BEGIN SuperLocalMemory v3.8.7 -->
+<!-- BEGIN SuperLocalMemory v3.8.9 -->
 
 ## SuperLocalMemory (SLM) — Agent Rules
 
@@ -39,6 +39,6 @@ slm-recall · slm-remember · slm-session · slm-status · slm-cache · slm-comp
 ### Subagents
 slm-memory-advisor (memory decisions, session hygiene, scope/profile guidance) · slm-optimize-advisor (context compression + KV cache) · slm-governance-advisor (scope/roles/compliance/GDPR)
 
-<!-- END SuperLocalMemory v3.8.7 -->
+<!-- END SuperLocalMemory v3.8.9 -->
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -77,4 +77,4 @@ slm-scope · slm-governance · slm-profile · slm-remember · slm-recall
 # What NOT to do
 Never session_init twice; never forget without dry-run preview; never store secrets; never bypass role checks; never claim an erasure succeeded without verifying via recall.
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -68,4 +68,4 @@ assessment. The gate is the authority.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -46,4 +46,4 @@ slm-recall · slm-remember · slm-session · slm-scope · slm-profile · slm-gov
 # What NOT to do
 Never session_init twice; never forget dry_run=False without reporting preview; never dump a whole file into remember; never invent a memory; never claim "saved" without success:true / clean CLI exit; never bypass scope or governance restrictions.
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -41,4 +41,4 @@ slm-compress · slm-cache · slm-status · slm-profile
 # What NOT to do
 Never compress code-for-edit/JSON-to-parse/<500 chars; never store secrets/ccr_ids; never let optimize failure block/alter the task; never claim a specific savings %; never carry ccr_ids across profile switches.
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

package/plugin/requirements.txt

@@ -1 +1 @@
-superlocalmemory==3.8.7
+superlocalmemory==3.8.9

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

@@ -145,4 +145,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -147,4 +147,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -245,4 +245,4 @@ Before running any destructive operation (`forget`, `compact_memories`):
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -311,4 +311,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -96,4 +96,4 @@ paused, name the approval needed; when errored, quote the short detail.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

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

@@ -279,4 +279,4 @@ mesh availability.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -145,4 +145,4 @@ Name them differently in your MCP config (e.g. `superlocalmemory-personal` and
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -236,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -238,4 +238,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -173,4 +173,4 @@ to review the impact. See `slm-remember` for the full deletion discipline.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -227,4 +227,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later*

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

@@ -163,4 +163,4 @@ multi-profile setup. To switch the active profile, see `slm-profile`.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.9 · Qualixar · AGPL-3.0-or-later

package/plugin-src/rules/AGENTS.md

@@ -128,4 +128,4 @@ When the SLM MCP server is unavailable, use these CLI equivalents:
 - **slm-optimize-advisor** — context compression and KV cache
 - **slm-governance-advisor** — scope/role compliance, retention policies, GDPR
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later

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

@@ -145,4 +145,4 @@ These subcommands control daemon-level cache settings. They do not read or write
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later

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

@@ -147,4 +147,4 @@ Content over 1 MB (1 000 000 bytes UTF-8) is processed but `reversible` is force
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later

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

@@ -311,4 +311,4 @@ profile. See `slm-profile` for the full profile switching workflow.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later

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

@@ -236,4 +236,4 @@ before recalling, then switch back. See `slm-profile` for workspace switching.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later*

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

@@ -238,4 +238,4 @@ different workspace, use `switch_profile` first. See `slm-profile`.
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later*

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

@@ -227,4 +227,4 @@ explicitly and call `recall` with `include_global`/`include_shared` after
 
 ---
 
-*SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later*
+*SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later*

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

@@ -163,4 +163,4 @@ multi-profile setup. To switch the active profile, see `slm-profile`.
 
 ---
 
-SuperLocalMemory v3.8.7 · Qualixar · AGPL-3.0-or-later
+SuperLocalMemory v3.8.8 · Qualixar · AGPL-3.0-or-later

package/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.8.7"
+version = "3.8.9"
 description = "Local-first agent memory with auditable hybrid retrieval"
 readme = "README.md"
 license = "AGPL-3.0-or-later"

package/src/superlocalmemory/__init__.py

@@ -32,7 +32,7 @@ if "OMP_NUM_THREADS" not in os.environ:
     os.environ["OMP_NUM_THREADS"] = "2"
 # ---------------------------------------------------------------------------
 
-__version__ = "3.8.7"
+__version__ = "3.8.9"
 
 _REQUIRED_VERSIONS = {
     "sentence_transformers": "5.3.0",

package/src/superlocalmemory/core/embeddings.py

@@ -220,6 +220,7 @@ class EmbeddingService:
         self._owns_worker_lock = False
         self._request_count: int = 0
         self._http_client: object | None = None
+        self._remote_ready = False
 
         # Register for atexit cleanup (prevent orphaned workers)
         ref = weakref.ref(self, _live_embedding_services.discard)
@@ -246,6 +247,31 @@ class EmbeddingService:
             return bool(self._config.api_endpoint and self._config.api_key)
         return self._available
 
+    @property
+    def is_warm(self) -> bool:
+        """Return whether the configured backend has served a request.
+
+        ``is_available`` only means that the backend may be started.  A local
+        sentence-transformers cold start can take minutes on Apple Silicon, so
+        background enrichment must not mistake availability for readiness and
+        occupy the only worker ahead of an interactive recall.
+        """
+        config = getattr(self, "_config", None)
+        if config is not None and (
+            config.is_openai_compatible or config.is_cloud
+        ):
+            return bool(
+                getattr(self, "_remote_ready", False)
+                and self.is_available
+            )
+        proc = getattr(self, "_worker_proc", None)
+        if proc is None or getattr(self, "_request_count", 0) <= 0:
+            return False
+        try:
+            return proc.poll() is None
+        except Exception:
+            return False
+
     @property
     def dimension(self) -> int:
         return self._config.dimension
@@ -291,13 +317,27 @@ class EmbeddingService:
         """Embed a single text string. Returns list of floats or None."""
         if not text or not text.strip():
             raise ValueError("Cannot embed empty text")
+        from superlocalmemory.core.recall_gate import wait_for_foreground_idle
+        wait_for_foreground_idle()
         if self._config.is_openai_compatible:
-            vecs = self._openai_compatible_embed_batch([text])
-            vec = vecs[0]
-            self._validate_dimension(np.asarray(vec))
-            return vec
+            try:
+                vecs = self._openai_compatible_embed_batch([text])
+                vec = vecs[0]
+                self._validate_dimension(np.asarray(vec))
+                self._remote_ready = True
+                return vec
+            except Exception:
+                self._remote_ready = False
+                raise
         if self._config.is_cloud:
-            return self._cloud_embed_single(text)
+            try:
+                vec = self._cloud_embed_single(text)
+                self._validate_dimension(np.asarray(vec))
+                self._remote_ready = True
+                return vec
+            except Exception:
+                self._remote_ready = False
+                raise
         result = self._subprocess_embed([text])
         if result is None:
             return None
@@ -309,14 +349,34 @@ class EmbeddingService:
         """Embed a batch of texts."""
         if not texts:
             raise ValueError("Cannot embed empty batch")
+        from superlocalmemory.core.recall_gate import is_background_work
+        if is_background_work():
+            # A single large background batch can own the only local inference
+            # worker for tens of seconds. Slice it so a recall arriving after
+            # this call started gets priority before the next text.
+            return [self.embed(text) for text in texts]
         if self._config.is_openai_compatible:
-            results = self._openai_compatible_embed_batch(texts)
-            for vec in results:
-                if vec is not None:
-                    self._validate_dimension(np.asarray(vec))
-            return results
+            try:
+                results = self._openai_compatible_embed_batch(texts)
+                for vec in results:
+                    if vec is not None:
+                        self._validate_dimension(np.asarray(vec))
+                self._remote_ready = any(vec is not None for vec in results)
+                return results
+            except Exception:
+                self._remote_ready = False
+                raise
         if self._config.is_cloud:
-            return self._cloud_embed_batch(texts)
+            try:
+                results = self._cloud_embed_batch(texts)
+                for vec in results:
+                    if vec is not None:
+                        self._validate_dimension(np.asarray(vec))
+                self._remote_ready = any(vec is not None for vec in results)
+                return results
+            except Exception:
+                self._remote_ready = False
+                raise
         result = self._subprocess_embed(texts)
         if result is None:
             return [None] * len(texts)
@@ -353,6 +413,8 @@ class EmbeddingService:
         Includes a timeout (_SUBPROCESS_RESPONSE_TIMEOUT seconds) so the CLI
         never hangs indefinitely on cold model loads or network issues.
         """
+        from superlocalmemory.core.recall_gate import wait_for_foreground_idle
+        wait_for_foreground_idle()
         with self._lock:
             # Only an explicit terminal disable (``False``) short-circuits. A
             # ``None`` availability is the recall-health self-heal's "re-probe"
@@ -738,9 +800,32 @@ class EmbeddingService:
         client = self._get_http_client()
         last_error: Exception | None = None
         for attempt in range(max_retries):
+            from superlocalmemory.core.materialization_control import (
+                MaterializationDeferred,
+            )
+            from superlocalmemory.core.recall_gate import (
+                background_preempt_requested,
+                is_background_work,
+            )
+            if background_preempt_requested():
+                raise MaterializationDeferred(
+                    "background embedding yielded to runtime transition"
+                )
             try:
-                resp = client.post(endpoint, headers=headers, json=body)
+                request_kwargs = {"headers": headers, "json": body}
+                if is_background_work():
+                    # Runtime reconfigure drains admitted operations in five
+                    # seconds.  A background remote read must leave enough
+                    # scheduling margin to observe that transition and release
+                    # its lease, while interactive recall keeps the provider's
+                    # normal timeout budget.
+                    request_kwargs["timeout"] = 3.5
+                resp = client.post(endpoint, **request_kwargs)
                 resp.raise_for_status()
+                if background_preempt_requested():
+                    raise MaterializationDeferred(
+                        "background embedding yielded to runtime transition"
+                    )
                 data = resp.json()
                 if "data" not in data or not isinstance(data["data"], list):
                     raise ValueError(
@@ -756,6 +841,12 @@ class EmbeddingService:
                     )
                 return results
             except Exception as exc:
+                if isinstance(exc, MaterializationDeferred):
+                    raise
+                if background_preempt_requested():
+                    raise MaterializationDeferred(
+                        "background embedding yielded to runtime transition"
+                    ) from exc
                 last_error = exc
                 if attempt < max_retries - 1:
                     time.sleep(2 ** attempt)
@@ -795,15 +886,39 @@ class EmbeddingService:
         client = self._get_http_client()
         last_error: Exception | None = None
         for attempt in range(max_retries):
+            from superlocalmemory.core.materialization_control import (
+                MaterializationDeferred,
+            )
+            from superlocalmemory.core.recall_gate import (
+                background_preempt_requested,
+                is_background_work,
+            )
+            if background_preempt_requested():
+                raise MaterializationDeferred(
+                    "background embedding yielded to runtime transition"
+                )
             try:
-                resp = client.post(url, headers=headers, json=body)
+                request_kwargs = {"headers": headers, "json": body}
+                if is_background_work():
+                    request_kwargs["timeout"] = 3.5
+                resp = client.post(url, **request_kwargs)
                 resp.raise_for_status()
+                if background_preempt_requested():
+                    raise MaterializationDeferred(
+                        "background embedding yielded to runtime transition"
+                    )
                 data = resp.json()
                 results = []
                 for item in sorted(data["data"], key=lambda d: d["index"]):
                     results.append(item["embedding"])
                 return results
             except Exception as exc:
+                if isinstance(exc, MaterializationDeferred):
+                    raise
+                if background_preempt_requested():
+                    raise MaterializationDeferred(
+                        "background embedding yielded to runtime transition"
+                    ) from exc
                 last_error = exc
                 if attempt < max_retries - 1:
                     time.sleep(2 ** attempt)

package/src/superlocalmemory/core/engine.py

@@ -637,7 +637,12 @@ class MemoryEngine:
             except (ValueError, TypeError):
                 _timeout_s = 0.5  # default 500 ms
             try:
-                _future = self._store_fast_embed_pool.submit(_embedder_ref.embed, fact_text)
+                def _best_effort_embed():
+                    from superlocalmemory.core.recall_gate import background_work
+                    with background_work():
+                        return _embedder_ref.embed(fact_text)
+
+                _future = self._store_fast_embed_pool.submit(_best_effort_embed)
                 try:
                     emb = _future.result(timeout=_timeout_s)
                     if emb:

package/src/superlocalmemory/core/engine_ingestion.py

@@ -736,6 +736,11 @@ def build_engine_ingestion_command(engine: MemoryEngine) -> IngestionCommand:
                 materialization_checkpoint=checkpoint_materialization,
             )
         except Exception as exc:
+            from superlocalmemory.core.materialization_control import (
+                MaterializationDeferred,
+            )
+            if isinstance(exc, MaterializationDeferred):
+                raise
             # ``run_store`` checkpoints the completed relational pipeline
             # immediately before post-hooks run.  Prefer that durable ledger
             # over rebuilding state from local variables: a one-time hook

package/src/superlocalmemory/core/ingestion_command.py

@@ -22,6 +22,7 @@ from dataclasses import dataclass, field
 from enum import Enum
 from typing import Any, Callable
 
+from superlocalmemory.core.materialization_control import MaterializationDeferred
 from superlocalmemory.storage.database import DatabaseManager
 
 logger = logging.getLogger("superlocalmemory.ingestion_command")
@@ -606,6 +607,31 @@ class IngestionOperationRepository:
                 ) from exc
         return self._from_row(rows[0])
 
+    def defer_enriching(
+        self,
+        operation_id: str,
+        *,
+        owner: str,
+    ) -> IngestionOperation:
+        """Release a transition-preempted lease without consuming a retry.
+
+        Queryable evidence remains durable.  The compare-and-swap owner check
+        prevents a stale worker from requeueing work that another process has
+        already reclaimed.
+        """
+        rows = self.db.execute(
+            "UPDATE ingestion_operations SET state='queryable', "
+            "lease_owner='', lease_expires_at=0, next_retry_at=0, "
+            "attempt_count=CASE WHEN attempt_count > 0 THEN attempt_count - 1 ELSE 0 END, "
+            "last_error='', updated_at=strftime('%Y-%m-%dT%H:%M:%fZ', 'now') "
+            "WHERE operation_id=? AND state='enriching' AND lease_owner=? "
+            "RETURNING *",
+            (operation_id, owner),
+        )
+        if not rows:
+            raise InvalidStateTransition("enriching lease ownership was lost")
+        return self._from_row(rows[0])
+
     def reap_stuck_enriching(
         self,
         *,
@@ -936,6 +962,11 @@ class IngestionCommand:
                 )
         except LeaseLost:
             raise
+        except MaterializationDeferred:
+            return self.repository.defer_enriching(
+                operation_id,
+                owner=self._owner,
+            )
         except Exception as exc:
             return self.repository.finish_enriching(
                 operation_id,
@@ -983,6 +1014,11 @@ class IngestionCommand:
             )
         except LeaseLost:
             raise
+        except MaterializationDeferred:
+            return self.repository.defer_enriching(
+                operation.operation_id,
+                owner=self._owner,
+            )
         except Exception as exc:
             return self.repository.finish_enriching(
                 operation.operation_id,

package/src/superlocalmemory/core/materialization_control.py

@@ -0,0 +1,20 @@
+# Copyright (c) 2026 Varun Pratap Bhardwaj / Qualixar
+# Licensed under AGPL-3.0-or-later - see LICENSE file
+# Part of SuperLocalMemory V3
+
+"""Control-flow signals for best-effort materialization work.
+
+These exceptions deliberately live outside the ingestion state machine and
+embedding implementation so either layer can request a durable deferral
+without introducing an import cycle.
+"""
+
+from __future__ import annotations
+
+
+class MaterializationDeferred(RuntimeError):
+    """Best-effort enrichment yielded to a runtime transition.
+
+    The queryable projection is already durable.  This signal must be handled
+    by :class:`IngestionCommand` as a requeue, never as a failed attempt.
+    """