superlocalmemory 3.4.36 → 3.4.37

package/CHANGELOG.md

@@ -10,6 +10,48 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [3.4.37] - 2026-04-26
+
+**P0 RAM fix.** Total SLM footprint reduced from ~14 GB peak to ~2.3 GB peak
+(84% reduction). Idle dropped from ~2.5 GB to ~1.0 GB. Users with 16 GB
+laptops can now run SLM without uninstalling.
+
+### Fixed
+- **CoreML EP allocation** — Added `ORT_DISABLE_COREML=1` to
+  `recall_worker.py`, `cli/commands.py` (warmup diagnose path), and the
+  Popen environment dicts in `core/embeddings.py` and
+  `retrieval/reranker.py`. Previously only `embedding_worker.py` and
+  `reranker_worker.py` set this. On ARM64 Mac, ONNX Runtime's CoreML
+  Execution Provider allocated 3-5 GB per missing guard.
+- **Duplicate MemoryEngine** — The QueueConsumer (recall_queue.db drain)
+  was routing through `WorkerPool` → `recall_worker` subprocess, which
+  loaded a SECOND full MemoryEngine inside the daemon. Now routes through
+  the daemon's in-process engine via the new `EngineRecallAdapter`.
+  Eliminates ~800 MB of duplication.
+- **Eager warmup** — Removed `WorkerPool.shared().warmup()` from daemon
+  startup. The recall_worker subprocess no longer spawns at boot. It
+  remains available as a fallback for dashboard/chat routes.
+
+### Changed
+- **RSS limits tightened:**
+  - `embedding_worker` self-kill: 4000 MB → 1800 MB
+  - `recall_worker` self-kill: 2500 MB → 1500 MB
+  - Daemon watchdog `MAX_WORKER_MB`: 4096 MB → 1800 MB
+  - `HealthMonitor.global_rss_budget_mb`: 4096 MB → 2500 MB
+- **Watchdog interval:** 60s → 15s in both daemon watchdog and
+  HealthMonitor `check_interval_sec`. Catches memory spikes faster.
+- **Idle timeouts:**
+  - `SLM_EMBED_IDLE_TIMEOUT`: 1800s (30 min) → 300s (5 min)
+  - `SLM_RERANKER_IDLE_TIMEOUT`: 1800s → 300s
+  - Reduces idle RAM held by ML model subprocesses.
+
+### Added
+- **`EngineRecallAdapter`** in `unified_daemon.py` — wraps the in-process
+  MemoryEngine to satisfy `RecallPoolProtocol` for the QueueConsumer.
+  Eliminates the recall_worker subprocess on the hot path.
+
+---
+
 ## [3.4.36] - 2026-04-25
 
 Persistent hook daemon: recall latency drops from ~2.2s to sub-second by

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "3.4.36",
+  "version": "3.4.37",
   "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/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.4.36"
+version = "3.4.37"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "AGPL-3.0-or-later"}

package/src/superlocalmemory/__init__.py

@@ -1,3 +1,3 @@
 """SuperLocalMemory — information-geometric agent memory."""
 
-__version__ = "3.4.36"
+__version__ = "3.4.37"

package/src/superlocalmemory/cli/commands.py

@@ -1710,6 +1710,7 @@ def _warmup_diagnose() -> None:
     """Diagnostic helper when warmup fails."""
     print("\nDiagnosing...")
     print(f"  Python executable: {sys.executable}")
+    os.environ["ORT_DISABLE_COREML"] = "1"
     try:
         from sentence_transformers import SentenceTransformer
         print("  sentence-transformers: importable")

package/src/superlocalmemory/core/embedding_worker.py

@@ -151,7 +151,7 @@ def _worker_main() -> None:
                 _respond({"ok": False, "error": str(exc)})
 
             # V3.3.16: RSS watchdog — V3.4.24: cross-platform via platform_utils.
-            _rss_limit = int(os.environ.get("SLM_EMBED_WORKER_RSS_LIMIT_MB", 4000))
+            _rss_limit = int(os.environ.get("SLM_EMBED_WORKER_RSS_LIMIT_MB", 1800))
             rss_mb = get_rss_mb()
             if rss_mb > 0 and rss_mb > _rss_limit:
                 sys.exit(0)

package/src/superlocalmemory/core/embeddings.py

@@ -140,14 +140,10 @@ def release_embedding_lock() -> None:
         _embedding_lock_fd = None
 
 
-_IDLE_TIMEOUT_SECONDS = 1800  # 30 minutes — keep model warm across bursty use.
-# V3.3.12: Configurable via SLM_EMBED_IDLE_TIMEOUT env var (seconds).
-# V3.4.19: Bumped from 120 → 1800 to eliminate the 30-60s cold-start pain
-# when the embedding worker was killed too aggressively. Safety: the
-# per-embed RSS self-check (SLM_EMBED_WORKER_RSS_LIMIT_MB, 4GB default) and
-# the daemon memory watchdog (unified_daemon.py, 4GB/60s) still cap any
-# runaway. To restore the old aggressive policy without redeploying, set
-# ``SLM_EMBED_IDLE_TIMEOUT=120`` and ``slm restart``.
+_IDLE_TIMEOUT_SECONDS = 300  # 5 minutes — balance cold-start vs RAM.
+# V3.4.37: Reduced from 1800 → 300. Holding 1.1 GB for 30 min idle
+# wastes RAM on laptops. 5 min covers bursty session_init+recall
+# patterns while freeing memory between sessions.
 _IDLE_TIMEOUT_SECONDS = int(os.environ.get("SLM_EMBED_IDLE_TIMEOUT", _IDLE_TIMEOUT_SECONDS))
 # V3.3.21: Configurable response timeout — 180s default, but batch ingestion
 # (2-turn chunks across 10 conversations) needs 600s+ to survive cold-start
@@ -476,6 +472,7 @@ class EmbeddingService:
                 "PYTORCH_ENABLE_MPS_FALLBACK": "1",
                 "TOKENIZERS_PARALLELISM": "false",
                 "TORCH_DEVICE": "cpu",
+                "ORT_DISABLE_COREML": "1",
             }
             from superlocalmemory.core.platform_utils import popen_platform_kwargs
             self._worker_proc = subprocess.Popen(

package/src/superlocalmemory/core/health_monitor.py

@@ -133,9 +133,9 @@ class HealthMonitor:
 
     def __init__(
         self,
-        global_rss_budget_mb: int = 4096,
+        global_rss_budget_mb: int = 2500,
         heartbeat_timeout_sec: int = 60,
-        check_interval_sec: int = 30,
+        check_interval_sec: int = 15,
         enable_structured_logging: bool = True,
     ):
         self._budget_mb = global_rss_budget_mb

package/src/superlocalmemory/core/recall_worker.py

@@ -28,6 +28,8 @@ os.environ["PYTORCH_MPS_MEM_LIMIT"] = "0"
 os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 os.environ["TORCH_DEVICE"] = "cpu"
+# V3.4.37: Disable CoreML EP — uses 3-5GB on ARM64 Mac.
+os.environ["ORT_DISABLE_COREML"] = "1"
 
 # SIGTERM bridge: Docker/systemd send SIGTERM to stop processes.
 # Without this, the worker ignores SIGTERM and becomes a zombie.
@@ -324,7 +326,7 @@ def _worker_main() -> None:
 
         # V3.3.16: RSS watchdog — V3.4.24: cross-platform via platform_utils.
         rss_mb = get_rss_mb()
-        if rss_mb > 0 and rss_mb > 2500:
+        if rss_mb > 0 and rss_mb > 1500:
             sys.exit(0)
 
 

package/src/superlocalmemory/retrieval/reranker.py

@@ -51,7 +51,7 @@ _live_rerankers: set[weakref.ref] = set()
 
 logger = logging.getLogger(__name__)
 
-_IDLE_TIMEOUT_SECONDS = 1800  # 30 min — keep cross-encoder warm for active sessions.
+_IDLE_TIMEOUT_SECONDS = 300  # V3.4.37: 5 min (was 30) — balance cold-start vs RAM.
 # V3.3.12: Configurable via SLM_RERANKER_IDLE_TIMEOUT env var.
 # V3.4.19: Bumped from 120 → 1800 in lock-step with the embedding worker.
 # Set ``SLM_RERANKER_IDLE_TIMEOUT=120`` + ``slm restart`` to revert.
@@ -192,6 +192,7 @@ class CrossEncoderReranker:
                 "PYTORCH_ENABLE_MPS_FALLBACK": "1",
                 "TOKENIZERS_PARALLELISM": "false",
                 "TORCH_DEVICE": "cpu",
+                "ORT_DISABLE_COREML": "1",
             }
             from superlocalmemory.core.platform_utils import popen_platform_kwargs
             self._worker_proc = subprocess.Popen(

package/src/superlocalmemory/server/unified_daemon.py

@@ -66,6 +66,75 @@ class ObserveRequest(BaseModel):
     content: str
 
 
+# ---------------------------------------------------------------------------
+# V3.4.37: Engine recall adapter — routes QueueConsumer through the daemon's
+# in-process MemoryEngine instead of spawning a recall_worker subprocess.
+# Saves ~800 MB by eliminating the duplicate engine.
+# ---------------------------------------------------------------------------
+
+class EngineRecallAdapter:
+    """Adapts MemoryEngine.recall() to RecallPoolProtocol for QueueConsumer.
+
+    The daemon already has a full MemoryEngine in-process. The QueueConsumer
+    previously routed through WorkerPool → recall_worker subprocess, which
+    loaded a SECOND MemoryEngine. This adapter eliminates that duplication.
+    """
+
+    def __init__(self, engine) -> None:
+        self._engine = engine
+
+    def recall(self, query: str, limit: int = 10, session_id: str = "") -> dict:
+        response = self._engine.recall(
+            query, limit=limit, session_id=session_id or None,
+        )
+        memory_ids = list({
+            r.fact.memory_id for r in response.results[:limit]
+            if r.fact.memory_id
+        })
+        memory_map = (
+            self._engine._db.get_memory_content_batch(memory_ids)
+            if memory_ids else {}
+        )
+        results = []
+        for r in response.results[:limit]:
+            fact_type = getattr(r.fact, "fact_type", None)
+            lifecycle = getattr(r.fact, "lifecycle", None)
+            results.append({
+                "fact_id": r.fact.fact_id,
+                "memory_id": r.fact.memory_id,
+                "content": r.fact.content[:300],
+                "source_content": memory_map.get(r.fact.memory_id, ""),
+                "score": round(r.score, 4),
+                "confidence": round(r.confidence, 4),
+                "trust_score": round(r.trust_score, 4),
+                "channel_scores": {
+                    k: round(v, 4)
+                    for k, v in (r.channel_scores or {}).items()
+                },
+                "fact_type": fact_type.value
+                    if fact_type and hasattr(fact_type, "value") else "",
+                "lifecycle": lifecycle.value
+                    if lifecycle and hasattr(lifecycle, "value") else "",
+                "access_count": getattr(r.fact, "access_count", 0),
+                "evidence_chain": list(
+                    getattr(r, "evidence_chain", []) or []
+                ),
+            })
+        return {
+            "ok": True,
+            "query": query,
+            "query_type": response.query_type,
+            "result_count": len(results),
+            "retrieval_time_ms": round(response.retrieval_time_ms, 1),
+            "channel_weights": {
+                k: round(v, 3)
+                for k, v in (response.channel_weights or {}).items()
+            },
+            "total_candidates": getattr(response, "total_candidates", 0),
+            "results": results,
+        }
+
+
 # ---------------------------------------------------------------------------
 # v3.4.32: Recall-priority gate for the pending materializer.
 # All /remember writes go to pending.db and return fast; a background
@@ -397,9 +466,10 @@ async def lifespan(application: FastAPI):
         # Set up observe buffer
         _observe_buffer.set_engine(engine)
 
-        # Pre-warm workers (background)
-        from superlocalmemory.core.worker_pool import WorkerPool
-        WorkerPool.shared().warmup()
+        # V3.4.37: Removed WorkerPool.warmup() — the recall_worker subprocess
+        # duplicated the daemon's MemoryEngine (800+ MB). QueueConsumer now
+        # uses the daemon's engine directly via EngineRecallAdapter.
+        # WorkerPool is still available as fallback for dashboard/chat routes.
 
         # Force reranker warmup
         retrieval_eng = getattr(engine, '_retrieval_engine', None)
@@ -422,8 +492,9 @@ async def lifespan(application: FastAPI):
                 logger.warning("Embedding warmup failed: %s", exc)
         threading.Thread(target=_warmup_embedder, daemon=True, name="embed-warmup").start()
 
-        # v3.4.26: Start QueueConsumer — drains recall_queue.db via pool.recall().
-        # Must start AFTER WorkerPool.warmup() so the worker is ready.
+        # v3.4.37: QueueConsumer uses daemon's engine directly via adapter.
+        # Previously routed through WorkerPool → recall_worker subprocess,
+        # which loaded a duplicate MemoryEngine (~800 MB waste).
         try:
             from pathlib import Path as _QP
             from superlocalmemory.core.queue_consumer import QueueConsumer
@@ -432,7 +503,7 @@ async def lifespan(application: FastAPI):
             _recall_queue = RecallQueue(_queue_db)
             _queue_consumer = QueueConsumer(
                 queue=_recall_queue,
-                pool=WorkerPool.shared(),
+                pool=EngineRecallAdapter(engine),
             )
             _queue_consumer.start()
             application.state.queue_consumer = _queue_consumer
@@ -466,9 +537,9 @@ async def lifespan(application: FastAPI):
         from superlocalmemory.core.health_monitor import HealthMonitor
         health_config = getattr(config, 'health', None)
         monitor = HealthMonitor(
-            global_rss_budget_mb=getattr(health_config, 'global_rss_budget_mb', 4096) if health_config else 4096,
+            global_rss_budget_mb=getattr(health_config, 'global_rss_budget_mb', 2500) if health_config else 2500,
             heartbeat_timeout_sec=getattr(health_config, 'heartbeat_timeout_sec', 60) if health_config else 60,
-            check_interval_sec=getattr(health_config, 'health_check_interval_sec', 30) if health_config else 30,
+            check_interval_sec=getattr(health_config, 'health_check_interval_sec', 15) if health_config else 15,
             enable_structured_logging=getattr(health_config, 'enable_structured_logging', True) if health_config else True,
         )
         monitor.start()
@@ -1259,11 +1330,11 @@ def _start_memory_watchdog() -> None:
     """
     import threading
 
-    MAX_WORKER_MB = 4096  # 4GB per worker — ONNX full model is 1.6GB + overhead
+    MAX_WORKER_MB = 1800  # V3.4.37: 1.8GB — ONNX nomic-embed is ~1.7GB loaded
 
     def watchdog_loop():
         while True:
-            time.sleep(60)
+            time.sleep(15)  # V3.4.37: 15s (was 60s) — catch spikes faster
             try:
                 import psutil
                 parent = psutil.Process(os.getpid())