superlocalmemory 3.4.43__tar.gz → 3.4.44__tar.gz

{superlocalmemory-3.4.43/src/superlocalmemory.egg-info → superlocalmemory-3.4.44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.4.43
+Version: 3.4.44
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: AGPL-3.0-or-later
@@ -27,37 +27,41 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: NOTICE
 License-File: AUTHORS.md
-Requires-Dist: httpx>=0.24.0
-Requires-Dist: numpy<3.0.0,>=1.26.0
-Requires-Dist: scipy<2.0.0,>=1.12.0
-Requires-Dist: networkx>=3.0
-Requires-Dist: mcp>=1.0.0
-Requires-Dist: python-dateutil>=2.9.0.post0
-Requires-Dist: rank-bm25>=0.2.2
-Requires-Dist: vadersentiment>=3.3.2
-Requires-Dist: einops>=0.8.2
-Requires-Dist: fastapi[all]>=0.135.1
-Requires-Dist: uvicorn>=0.42.0
-Requires-Dist: websockets>=16.0
-Requires-Dist: lightgbm>=4.0.0
-Requires-Dist: orjson>=3.9.0
-Requires-Dist: tree-sitter<1,>=0.23.0
-Requires-Dist: tree-sitter-language-pack<1,>=0.5
-Requires-Dist: rustworkx<1,>=0.15
-Requires-Dist: watchdog<6,>=4.0
-Requires-Dist: psutil>=5.9.0
-Requires-Dist: structlog<27.0.0,>=24.0.0
-Requires-Dist: portalocker<4.0.0,>=2.7.0
-Requires-Dist: sentence-transformers[onnx]>=5.2.0
-Requires-Dist: torch>=2.2.0
-Requires-Dist: scikit-learn<2.0.0,>=1.3.0
+Requires-Dist: httpx==0.28.1
+Requires-Dist: numpy==2.4.4
+Requires-Dist: scipy==1.17.1
+Requires-Dist: networkx==3.6.1
+Requires-Dist: mcp==1.27.1
+Requires-Dist: python-dateutil==2.9.0.post0
+Requires-Dist: rank-bm25==0.2.2
+Requires-Dist: vadersentiment==3.3.2
+Requires-Dist: einops==0.8.2
+Requires-Dist: fastapi[all]==0.136.1
+Requires-Dist: uvicorn==0.46.0
+Requires-Dist: websockets==16.0
+Requires-Dist: lightgbm==4.6.0
+Requires-Dist: orjson==3.11.9
+Requires-Dist: tree-sitter==0.25.2
+Requires-Dist: tree-sitter-language-pack==0.13.0
+Requires-Dist: rustworkx==0.17.1
+Requires-Dist: watchdog==5.0.3
+Requires-Dist: psutil==7.2.2
+Requires-Dist: structlog==25.5.0
+Requires-Dist: portalocker==3.2.0
+Requires-Dist: sentence-transformers[onnx]==5.3.0
+Requires-Dist: onnxruntime==1.24.4
+Requires-Dist: transformers==4.57.6
+Requires-Dist: huggingface_hub==0.36.2
+Requires-Dist: torch==2.11.0
+Requires-Dist: scikit-learn==1.8.0
+Requires-Dist: sqlite-vec==0.1.9
 Provides-Extra: search
-Requires-Dist: sentence-transformers[onnx]>=5.2.0; extra == "search"
-Requires-Dist: einops>=0.8.2; extra == "search"
-Requires-Dist: torch>=2.2.0; extra == "search"
-Requires-Dist: scikit-learn<2.0.0,>=1.3.0; extra == "search"
+Requires-Dist: sentence-transformers[onnx]==5.3.0; extra == "search"
+Requires-Dist: einops==0.8.2; extra == "search"
+Requires-Dist: torch==2.11.0; extra == "search"
+Requires-Dist: scikit-learn==1.8.0; extra == "search"
 Requires-Dist: geoopt>=0.5.0; extra == "search"
-Requires-Dist: onnxruntime>=1.17.0; extra == "search"
+Requires-Dist: onnxruntime==1.24.4; extra == "search"
 Provides-Extra: ui
 Requires-Dist: fastapi[all]>=0.135.1; extra == "ui"
 Requires-Dist: uvicorn>=0.42.0; extra == "ui"

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "superlocalmemory"
-version = "3.4.43"
+version = "3.4.44"
 description = "Information-geometric agent memory with mathematical guarantees"
 readme = "README.md"
 license = {text = "AGPL-3.0-or-later"}
@@ -29,48 +29,42 @@ classifiers = [
 ]
 
 dependencies = [
-    "httpx>=0.24.0",
-    "numpy>=1.26.0,<3.0.0",
-    "scipy>=1.12.0,<2.0.0",
-    "networkx>=3.0",
-    "mcp>=1.0.0",
-    "python-dateutil>=2.9.0.post0",
-    "rank-bm25>=0.2.2",
-    "vadersentiment>=3.3.2",
-    "einops>=0.8.2",
-    "fastapi[all]>=0.135.1",
-    "uvicorn>=0.42.0",
-    "websockets>=16.0",
-    "lightgbm>=4.0.0",
-    "orjson>=3.9.0",
-    # CodeGraph — code knowledge graph (v3.4)
-    "tree-sitter>=0.23.0,<1",
-    "tree-sitter-language-pack>=0.5,<1",
-    "rustworkx>=0.15,<1",
-    "watchdog>=4.0,<6",
-    # V3.4.3: Unified Brain
-    "psutil>=5.9.0",
-    "structlog>=24.0.0,<27.0.0",
-    # Cross-platform file locking for single-daemon enforcement.
-    "portalocker>=2.7.0,<4.0.0",
-    # V3.4.18: Semantic search + cross-encoder reranker (npm install parity).
-    # Previously under [search] extra — pip users silently lost 30pp of recall
-    # quality vs. npm users. Now ships by default for both install paths.
-    # v3.4.43: bumped from >=5.0.0 to >=5.2.0 so the resolver doesn't pick
-    # 5.0.0-5.1.2 which cap transformers<5.0.0 (security headroom for when
-    # optimum-onnx upstream eventually supports transformers 5.x).
-    "sentence-transformers[onnx]>=5.2.0",
-    # NOTE on CVE-2026-1839 (transformers Trainer.torch.load RCE):
-    # SLM does NOT use transformers.Trainer (inference-only path via
-    # sentence-transformers + ONNX backend). The vulnerable method
-    # Trainer._load_rng_state is never called by SLM code, so the CVE is
-    # unreachable through SLM's API surface. We CANNOT pin transformers>=5.0.0
-    # because optimum-onnx 0.1.0 (latest upstream) caps transformers<4.58.0
-    # and SLM's embedding_worker.py:68 hard-codes backend="onnx". Will
-    # tighten this pin in a future release once optimum-onnx ships a
-    # transformers-5.x-compatible build.
-    "torch>=2.2.0",
-    "scikit-learn>=1.3.0,<2.0.0",
+    # All versions hard-pinned to the verified-good combination.
+    # Mixing versions outside these pins triggers per-batch memory
+    # blow-up in the embedding worker on Apple Silicon and breaks
+    # recall/remember latency targets. Update only after benchmarking.
+    "httpx==0.28.1",
+    "numpy==2.4.4",
+    "scipy==1.17.1",
+    "networkx==3.6.1",
+    "mcp==1.27.1",
+    "python-dateutil==2.9.0.post0",
+    "rank-bm25==0.2.2",
+    "vadersentiment==3.3.2",
+    "einops==0.8.2",
+    "fastapi[all]==0.136.1",
+    "uvicorn==0.46.0",
+    "websockets==16.0",
+    "lightgbm==4.6.0",
+    "orjson==3.11.9",
+    "tree-sitter==0.25.2",
+    "tree-sitter-language-pack==0.13.0",
+    "rustworkx==0.17.1",
+    "watchdog==5.0.3",
+    "psutil==7.2.2",
+    "structlog==25.5.0",
+    "portalocker==3.2.0",
+    # Semantic search + cross-encoder reranker. Embedding stack is
+    # extremely sensitive to version drift on Apple Silicon — newer
+    # versions allocate dramatically more per-batch memory.
+    "sentence-transformers[onnx]==5.3.0",
+    "onnxruntime==1.24.4",
+    "transformers==4.57.6",
+    "huggingface_hub==0.36.2",
+    "torch==2.11.0",
+    "scikit-learn==1.8.0",
+    # Vector KNN extension for the semantic channel.
+    "sqlite-vec==0.1.9",
 ]
 
 [project.optional-dependencies]
@@ -78,12 +72,13 @@ dependencies = [
 # moved into core in v3.4.18. ``pip install superlocalmemory[search]`` still
 # works but installs nothing extra.
 search = [
-    "sentence-transformers[onnx]>=5.2.0",
-    "einops>=0.8.2",
-    "torch>=2.2.0",
-    "scikit-learn>=1.3.0,<2.0.0",
+    # Same hard pin as core deps — see comment above.
+    "sentence-transformers[onnx]==5.3.0",
+    "einops==0.8.2",
+    "torch==2.11.0",
+    "scikit-learn==1.8.0",
     "geoopt>=0.5.0",
-    "onnxruntime>=1.17.0",
+    "onnxruntime==1.24.4",
 ]
 ui = [
     "fastapi[all]>=0.135.1",

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44}/src/superlocalmemory/__init__.py

@@ -1,3 +1,3 @@
 """SuperLocalMemory — information-geometric agent memory."""
 
-__version__ = "3.4.39"
+__version__ = "3.4.44"

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44}/src/superlocalmemory/core/embedding_worker.py

@@ -53,24 +53,25 @@ def _start_parent_watchdog() -> None:
 
 
 def _load_embedding_model(name: str) -> tuple:
-    """Load embedding model. ONNX first (no memory leak), PyTorch fallback.
-
-    V3.3.17: PyTorch SentenceTransformer on ARM64 Mac leaks memory —
-    grows from 300MB to 17GB after ~200 encode calls. ONNX Runtime
-    has no such issue. Same approach as CrossEncoder ONNX migration.
+    """Load embedding model. ONNX CPU-only first, PyTorch fallback.
 
     Returns (model, backend_name) or (None, "").
     """
     from sentence_transformers import SentenceTransformer
 
-    # Tier 1: ONNX (stable memory; ~1.1 GB for nomic-embed-text-v1.5)
+    # ONNX with explicit CPU provider — avoids CoreML EP memory overhead.
     try:
-        m = SentenceTransformer(name, backend="onnx", trust_remote_code=True)
+        m = SentenceTransformer(
+            name,
+            backend="onnx",
+            trust_remote_code=True,
+            model_kwargs={"provider": "CPUExecutionProvider"},
+        )
         return m, "onnx"
     except Exception:
         pass
 
-    # Tier 2: PyTorch CPU (stable at ~1.4GB after 100+ calls, verified)
+    # PyTorch CPU fallback.
     try:
         import torch
         with torch.inference_mode():

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44}/src/superlocalmemory/core/engine_wiring.py

@@ -78,38 +78,19 @@ def init_embedder(config: SLMConfig) -> Any | None:
     emb_cfg = config.embedding
     provider = emb_cfg.provider
 
-    # --- Explicit ollama provider ---
-    # V3.3.27: HYBRID MODE B — use sentence-transformers subprocess for
-    # embeddings (fast, batched, ~2s) instead of Ollama HTTP per-call (~30s).
-    # Ollama is still used for LLM operations (fact extraction, context
-    # generation) via llm/backbone.py — that path is unchanged.
-    #
-    # Why: The store pipeline calls embed() 200+ times per remember
-    # (scene_builder, type_router, consolidator, entropy_gate, etc.).
-    # Ollama HTTP: 200 * 45ms = 9s minimum + cold starts.
-    # sentence-transformers subprocess: 200 embeds batched = ~1s.
-    #
-    # The embedding model is the SAME (nomic-embed-text-v1.5, 768d) —
-    # identical vectors, zero quality difference. Only the transport changes.
+    # All modes use sentence-transformers subprocess as primary so the
+    # embedding space matches stored vectors. Ollama is fallback only —
+    # Ollama's nomic-embed-text and sentence-transformers nomic-embed-text-v1.5
+    # produce different vectors, so mixing them against an ST-indexed
+    # corpus degrades semantic recall quality.
     if provider == "ollama":
-        if config.mode == Mode.B:
-            # Mode B hybrid: prefer subprocess embedder (fast, batched)
-            st_emb = _try_service_embedder(EmbeddingService, emb_cfg)
-            if st_emb is not None:
-                logger.info(
-                    "Mode B hybrid: using sentence-transformers subprocess "
-                    "for embeddings (fast batched). Ollama used for LLM only."
-                )
-                return st_emb
-            # Fallback: if subprocess unavailable, use Ollama embeddings
-            logger.info("Mode B: sentence-transformers unavailable, using Ollama embeddings")
-            result = _try_ollama_embedder(emb_cfg)
-            if result is not None:
-                return result
-            return None
-        # Mode A/C with explicit ollama: use Ollama embeddings
+        st_emb = _try_service_embedder(EmbeddingService, emb_cfg)
+        if st_emb is not None:
+            logger.info("Using sentence-transformers subprocess (matches stored embedding space)")
+            return st_emb
         result = _try_ollama_embedder(emb_cfg)
         if result is not None:
+            logger.warning("sentence-transformers unavailable; falling back to Ollama (semantic quality may degrade)")
             return result
         return None
 

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44}/src/superlocalmemory/server/unified_daemon.py

@@ -1342,7 +1342,7 @@ def _start_memory_watchdog() -> None:
     """
     import threading
 
-    MAX_WORKER_MB = 1800  # V3.4.37: 1.8GB — ONNX nomic-embed is ~1.7GB loaded
+    MAX_WORKER_MB = int(os.environ.get("SLM_MAX_WORKER_MB", "2500"))
 
     def watchdog_loop():
         while True:
@@ -1418,12 +1418,23 @@ def _start_pending_materializer() -> None:
                 for item in pending:
                     if _materializer_stop.is_set():
                         break
-                    # Yield to recalls: wait until none in flight
                     waits = 0
                     while _recalls_in_flight() > 0 and waits < 60:
                         time.sleep(0.5)
                         waits += 1
                     try:
+                        import hashlib
+                        content = item["content"]
+                        # Dedup: skip if identical content already stored.
+                        content_hash = hashlib.md5(content.encode()).hexdigest()
+                        dup = engine._db.execute(
+                            "SELECT 1 FROM atomic_facts WHERE "
+                            "content = ? LIMIT 1",
+                            (content,),
+                        )
+                        if dup:
+                            mark_done(item["id"])
+                            continue
                         import json as _json
                         md_str = item.get("metadata") or "{}"
                         try:
@@ -1432,7 +1443,29 @@ def _start_pending_materializer() -> None:
                             md = {}
                         if item.get("tags"):
                             md.setdefault("tags", item["tags"])
-                        engine.store(item["content"], metadata=md)
+                        # Create memory row (FK target for atomic_facts)
+                        from datetime import datetime, timezone
+                        from superlocalmemory.storage.models import (
+                            AtomicFact, FactType,
+                        )
+                        mem_id = content_hash[:16]
+                        engine._db.execute(
+                            "INSERT OR IGNORE INTO memories "
+                            "(memory_id, profile_id, content, "
+                            "session_id, speaker, role, created_at, "
+                            "metadata_json) VALUES (?,?,?,?,?,?,?,?)",
+                            (mem_id, engine._profile_id, content,
+                             "", "", "user",
+                             datetime.now(timezone.utc).isoformat(),
+                             _json.dumps(md)),
+                        )
+                        fact = AtomicFact(
+                            content=content,
+                            fact_type=FactType.EPISODIC,
+                            memory_id=mem_id,
+                            profile_id=engine._profile_id,
+                        )
+                        engine.store_fact_direct(fact)
                         mark_done(item["id"])
                     except Exception as exc:
                         logger.warning(

{superlocalmemory-3.4.43 → superlocalmemory-3.4.44/src/superlocalmemory.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.4.43
+Version: 3.4.44
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: AGPL-3.0-or-later
@@ -27,37 +27,41 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: NOTICE
 License-File: AUTHORS.md
-Requires-Dist: httpx>=0.24.0
-Requires-Dist: numpy<3.0.0,>=1.26.0
-Requires-Dist: scipy<2.0.0,>=1.12.0
-Requires-Dist: networkx>=3.0
-Requires-Dist: mcp>=1.0.0
-Requires-Dist: python-dateutil>=2.9.0.post0
-Requires-Dist: rank-bm25>=0.2.2
-Requires-Dist: vadersentiment>=3.3.2
-Requires-Dist: einops>=0.8.2
-Requires-Dist: fastapi[all]>=0.135.1
-Requires-Dist: uvicorn>=0.42.0
-Requires-Dist: websockets>=16.0
-Requires-Dist: lightgbm>=4.0.0
-Requires-Dist: orjson>=3.9.0
-Requires-Dist: tree-sitter<1,>=0.23.0
-Requires-Dist: tree-sitter-language-pack<1,>=0.5
-Requires-Dist: rustworkx<1,>=0.15
-Requires-Dist: watchdog<6,>=4.0
-Requires-Dist: psutil>=5.9.0
-Requires-Dist: structlog<27.0.0,>=24.0.0
-Requires-Dist: portalocker<4.0.0,>=2.7.0
-Requires-Dist: sentence-transformers[onnx]>=5.2.0
-Requires-Dist: torch>=2.2.0
-Requires-Dist: scikit-learn<2.0.0,>=1.3.0
+Requires-Dist: httpx==0.28.1
+Requires-Dist: numpy==2.4.4
+Requires-Dist: scipy==1.17.1
+Requires-Dist: networkx==3.6.1
+Requires-Dist: mcp==1.27.1
+Requires-Dist: python-dateutil==2.9.0.post0
+Requires-Dist: rank-bm25==0.2.2
+Requires-Dist: vadersentiment==3.3.2
+Requires-Dist: einops==0.8.2
+Requires-Dist: fastapi[all]==0.136.1
+Requires-Dist: uvicorn==0.46.0
+Requires-Dist: websockets==16.0
+Requires-Dist: lightgbm==4.6.0
+Requires-Dist: orjson==3.11.9
+Requires-Dist: tree-sitter==0.25.2
+Requires-Dist: tree-sitter-language-pack==0.13.0
+Requires-Dist: rustworkx==0.17.1
+Requires-Dist: watchdog==5.0.3
+Requires-Dist: psutil==7.2.2
+Requires-Dist: structlog==25.5.0
+Requires-Dist: portalocker==3.2.0
+Requires-Dist: sentence-transformers[onnx]==5.3.0
+Requires-Dist: onnxruntime==1.24.4
+Requires-Dist: transformers==4.57.6
+Requires-Dist: huggingface_hub==0.36.2
+Requires-Dist: torch==2.11.0
+Requires-Dist: scikit-learn==1.8.0
+Requires-Dist: sqlite-vec==0.1.9
 Provides-Extra: search
-Requires-Dist: sentence-transformers[onnx]>=5.2.0; extra == "search"
-Requires-Dist: einops>=0.8.2; extra == "search"
-Requires-Dist: torch>=2.2.0; extra == "search"
-Requires-Dist: scikit-learn<2.0.0,>=1.3.0; extra == "search"
+Requires-Dist: sentence-transformers[onnx]==5.3.0; extra == "search"
+Requires-Dist: einops==0.8.2; extra == "search"
+Requires-Dist: torch==2.11.0; extra == "search"
+Requires-Dist: scikit-learn==1.8.0; extra == "search"
 Requires-Dist: geoopt>=0.5.0; extra == "search"
-Requires-Dist: onnxruntime>=1.17.0; extra == "search"
+Requires-Dist: onnxruntime==1.24.4; extra == "search"
 Provides-Extra: ui
 Requires-Dist: fastapi[all]>=0.135.1; extra == "ui"
 Requires-Dist: uvicorn>=0.42.0; extra == "ui"

superlocalmemory-3.4.44/src/superlocalmemory.egg-info/requires.txt

@@ -0,0 +1,62 @@
+httpx==0.28.1
+numpy==2.4.4
+scipy==1.17.1
+networkx==3.6.1
+mcp==1.27.1
+python-dateutil==2.9.0.post0
+rank-bm25==0.2.2
+vadersentiment==3.3.2
+einops==0.8.2
+fastapi[all]==0.136.1
+uvicorn==0.46.0
+websockets==16.0
+lightgbm==4.6.0
+orjson==3.11.9
+tree-sitter==0.25.2
+tree-sitter-language-pack==0.13.0
+rustworkx==0.17.1
+watchdog==5.0.3
+psutil==7.2.2
+structlog==25.5.0
+portalocker==3.2.0
+sentence-transformers[onnx]==5.3.0
+onnxruntime==1.24.4
+transformers==4.57.6
+huggingface_hub==0.36.2
+torch==2.11.0
+scikit-learn==1.8.0
+sqlite-vec==0.1.9
+
+[dev]
+pytest>=8.0
+pytest-cov>=4.1
+pytest-asyncio>=0.21
+sqlite-vec>=0.1.6
+
+[full]
+superlocalmemory[ingestion,learning,performance,search,ui]
+
+[ingestion]
+keyring>=25.0.0
+google-auth-oauthlib>=1.2.0
+google-api-python-client>=2.100.0
+icalendar>=6.0.0
+
+[learning]
+lightgbm>=4.0.0
+
+[performance]
+orjson>=3.9.0
+
+[search]
+sentence-transformers[onnx]==5.3.0
+einops==0.8.2
+torch==2.11.0
+scikit-learn==1.8.0
+geoopt>=0.5.0
+onnxruntime==1.24.4
+
+[ui]
+fastapi[all]>=0.135.1
+uvicorn>=0.42.0
+python-multipart<1.0.0,>=0.0.6

superlocalmemory-3.4.43/src/superlocalmemory.egg-info/requires.txt

@@ -1,58 +0,0 @@
-httpx>=0.24.0
-numpy<3.0.0,>=1.26.0
-scipy<2.0.0,>=1.12.0
-networkx>=3.0
-mcp>=1.0.0
-python-dateutil>=2.9.0.post0
-rank-bm25>=0.2.2
-vadersentiment>=3.3.2
-einops>=0.8.2
-fastapi[all]>=0.135.1
-uvicorn>=0.42.0
-websockets>=16.0
-lightgbm>=4.0.0
-orjson>=3.9.0
-tree-sitter<1,>=0.23.0
-tree-sitter-language-pack<1,>=0.5
-rustworkx<1,>=0.15
-watchdog<6,>=4.0
-psutil>=5.9.0
-structlog<27.0.0,>=24.0.0
-portalocker<4.0.0,>=2.7.0
-sentence-transformers[onnx]>=5.2.0
-torch>=2.2.0
-scikit-learn<2.0.0,>=1.3.0
-
-[dev]
-pytest>=8.0
-pytest-cov>=4.1
-pytest-asyncio>=0.21
-sqlite-vec>=0.1.6
-
-[full]
-superlocalmemory[ingestion,learning,performance,search,ui]
-
-[ingestion]
-keyring>=25.0.0
-google-auth-oauthlib>=1.2.0
-google-api-python-client>=2.100.0
-icalendar>=6.0.0
-
-[learning]
-lightgbm>=4.0.0
-
-[performance]
-orjson>=3.9.0
-
-[search]
-sentence-transformers[onnx]>=5.2.0
-einops>=0.8.2
-torch>=2.2.0
-scikit-learn<2.0.0,>=1.3.0
-geoopt>=0.5.0
-onnxruntime>=1.17.0
-
-[ui]
-fastapi[all]>=0.135.1
-uvicorn>=0.42.0
-python-multipart<1.0.0,>=0.0.6