spatial-memory-mcp 1.5.3__py3-none-any.whl → 1.6.0__py3-none-any.whl

spatial_memory/services/spatial.py

@@ -63,6 +63,28 @@ except ImportError:
     UMAP_AVAILABLE = False
     logger.debug("UMAP not available - visualize operation will be disabled")
 
+try:
+    from scipy.spatial.distance import cdist
+
+    SCIPY_AVAILABLE = True
+except ImportError:
+    SCIPY_AVAILABLE = False
+    logger.debug("scipy not available - using fallback for similarity calculations")
+
+# Common stop words for keyword extraction (module-level to avoid recreation)
+_STOP_WORDS: frozenset[str] = frozenset({
+    "the", "a", "an", "is", "are", "was", "were", "be", "been", "being",
+    "have", "has", "had", "do", "does", "did", "will", "would", "could",
+    "should", "may", "might", "must", "can", "to", "of", "in", "for",
+    "on", "with", "at", "by", "from", "as", "into", "through", "during",
+    "before", "after", "above", "below", "between", "under", "again",
+    "further", "then", "once", "here", "there", "when", "where", "why",
+    "how", "all", "each", "few", "more", "most", "other", "some", "such",
+    "no", "nor", "not", "only", "own", "same", "so", "than", "too",
+    "very", "just", "also", "now", "and", "but", "or", "if", "it", "its",
+    "this", "that", "these", "those", "i", "you", "he", "she", "we", "they",
+})
+
 if TYPE_CHECKING:
     from spatial_memory.ports.repositories import (
         EmbeddingServiceProtocol,
@@ -212,11 +234,12 @@ class SpatialService:
             )
 
             # Find nearest memories for each interpolation point
-            # Use batch search for efficiency
+            # Use batch search for efficiency, include vectors to avoid N+1 queries
             search_results = self._batch_vector_search(
                 interpolated_vectors,
                 limit_per_query=self._config.journey_neighbors_per_step,
                 namespace=namespace,
+                include_vector=True,  # Include vectors to avoid follow-up queries
             )
 
             # Build journey steps
@@ -230,9 +253,15 @@ class SpatialService:
                 distance_to_path = float("inf")
                 if neighbors:
                     for neighbor in neighbors:
-                        dist = self._cosine_distance(
-                            interp_vec, self._get_vector_for_memory(neighbor.id)
-                        )
+                        # Use vector from search result (included via include_vector=True)
+                        if neighbor.vector is not None:
+                            neighbor_vec = np.array(neighbor.vector, dtype=np.float32)
+                            dist = self._cosine_distance(interp_vec, neighbor_vec)
+                        else:
+                            # Fallback if vector not included (shouldn't happen)
+                            dist = self._cosine_distance(
+                                interp_vec, self._get_vector_for_memory(neighbor.id)
+                            )
                         if dist < distance_to_path:
                             distance_to_path = dist
                     steps_with_memories += 1
@@ -330,10 +359,12 @@ class SpatialService:
 
             for step_num in range(actual_steps):
                 # Find candidates from current position
+                # Include vectors to avoid follow-up get_with_vector queries
                 neighbors = self._repo.search(
                     current_vector,
                     limit=self._config.wander_candidates_per_step + len(visited_ids),
                     namespace=namespace,
+                    include_vector=True,
                 )
 
                 # Filter out recently visited
@@ -358,12 +389,16 @@ class SpatialService:
                     candidates, actual_temp
                 )
 
-                # Calculate distance traveled
-                next_result = self._repo.get_with_vector(next_memory.id)
-                if next_result is None:
-                    logger.warning(f"Memory {next_memory.id} disappeared during wander")
-                    break
-                _, next_vector = next_result
+                # Get vector from search result (included via include_vector=True)
+                if next_memory.vector is not None:
+                    next_vector = np.array(next_memory.vector, dtype=np.float32)
+                else:
+                    # Fallback if vector not included (shouldn't happen)
+                    next_result = self._repo.get_with_vector(next_memory.id)
+                    if next_result is None:
+                        logger.warning(f"Memory {next_memory.id} disappeared during wander")
+                        break
+                    _, next_vector = next_result
 
                 step_distance = self._cosine_distance(prev_vector, next_vector)
                 total_distance += step_distance
@@ -665,18 +700,26 @@ class SpatialService:
             # Build edges if requested
             edges: list[VisualizationEdge] = []
             if include_edges:
-                # Calculate pairwise similarities and create edges for high similarity
-                for i in range(len(vectors)):
-                    for j in range(i + 1, len(vectors)):
-                        similarity = 1.0 - self._cosine_distance(vectors[i], vectors[j])
-                        if similarity >= self._config.visualize_similarity_threshold:
-                            edges.append(
-                                VisualizationEdge(
-                                    from_id=nodes[i].id,
-                                    to_id=nodes[j].id,
-                                    weight=similarity,
-                                )
-                            )
+                # Calculate pairwise similarities using vectorized operations
+                similarity_matrix = self._compute_pairwise_similarities(vectors)
+                threshold = self._config.visualize_similarity_threshold
+
+                # Extract upper triangle indices where similarity >= threshold
+                # (upper triangle avoids duplicate edges)
+                upper_tri_indices = np.triu_indices(len(vectors), k=1)
+                similarities = similarity_matrix[upper_tri_indices]
+
+                # Filter by threshold and create edges
+                mask = similarities >= threshold
+                for idx in np.where(mask)[0]:
+                    i, j = upper_tri_indices[0][idx], upper_tri_indices[1][idx]
+                    edges.append(
+                        VisualizationEdge(
+                            from_id=nodes[i].id,
+                            to_id=nodes[j].id,
+                            weight=float(similarities[idx]),
+                        )
+                    )
 
             # Calculate bounds
             x_coords = [n.x for n in nodes]
@@ -783,25 +826,50 @@ class SpatialService:
         vectors: list[np.ndarray],
         limit_per_query: int,
         namespace: str | None,
+        include_vector: bool = False,
     ) -> list[list[MemoryResult]]:
-        """Perform batch vector search.
+        """Perform batch vector search using repository's native batch capability.
 
-        Delegates to repository if batch search is available, otherwise
-        performs individual searches.
+        Uses the repository's batch_vector_search for efficient multi-query
+        searches in a single database operation.
 
         Args:
             vectors: List of query vectors.
             limit_per_query: Results per query.
             namespace: Optional namespace filter.
+            include_vector: Whether to include embedding vectors in results.
+                Defaults to False to reduce response size.
 
         Returns:
-            List of result lists.
+            List of result lists. If include_vector=True, each MemoryResult
+            includes its embedding vector.
         """
-        # Fall back to individual searches (repository handles batch internally)
+        # Use native batch search for efficiency
+        raw_results = self._repo.batch_vector_search(
+            query_vectors=vectors,
+            limit_per_query=limit_per_query,
+            namespace=namespace,
+            include_vector=include_vector,
+        )
+
+        # Convert raw dict results to MemoryResult objects
         results: list[list[MemoryResult]] = []
-        for vec in vectors:
-            neighbors = self._repo.search(vec, limit=limit_per_query, namespace=namespace)
-            results.append(neighbors)
+        for query_results in raw_results:
+            memory_results: list[MemoryResult] = []
+            for record in query_results:
+                memory_result = MemoryResult(
+                    id=record["id"],
+                    content=record["content"],
+                    similarity=record.get("similarity", 0.0),
+                    namespace=record.get("namespace", "default"),
+                    tags=record.get("tags", []),
+                    importance=record.get("importance", 0.5),
+                    created_at=record.get("created_at"),
+                    metadata=record.get("metadata", {}),
+                    vector=record.get("vector") if include_vector else None,
+                )
+                memory_results.append(memory_result)
+            results.append(memory_results)
         return results
 
     def _get_vector_for_memory(self, memory_id: str) -> np.ndarray:
@@ -838,6 +906,35 @@ class SpatialService:
         similarity = np.dot(vec1, vec2) / (norm1 * norm2)
         return float(1.0 - similarity)
 
+    def _compute_pairwise_similarities(self, vectors: np.ndarray) -> np.ndarray:
+        """Compute pairwise cosine similarities using vectorized operations.
+
+        Uses scipy.cdist if available for optimal performance, otherwise
+        falls back to numpy matrix operations.
+
+        Args:
+            vectors: 2D array of shape (n_vectors, embedding_dim).
+
+        Returns:
+            Symmetric similarity matrix of shape (n_vectors, n_vectors).
+            Values range from -1 (opposite) to 1 (identical).
+        """
+        # Normalize vectors to unit length
+        norms = np.linalg.norm(vectors, axis=1, keepdims=True)
+        # Avoid division by zero for zero vectors
+        norms = np.where(norms < 1e-10, 1.0, norms)
+        normalized = vectors / norms
+
+        if SCIPY_AVAILABLE:
+            # scipy.cdist with cosine metric returns distances (1 - similarity)
+            distances = cdist(normalized, normalized, metric="cosine")
+            similarities = 1.0 - distances
+        else:
+            # Fallback: use numpy dot product (A @ A.T for normalized vectors)
+            similarities = normalized @ normalized.T
+
+        return similarities
+
     def _temperature_select(
         self,
         candidates: list[MemoryResult],
@@ -888,23 +985,9 @@ class SpatialService:
             List of top keywords.
         """
         # Simple keyword extraction using word frequency
-        # Remove common stop words and short words
-        stop_words = {
-            "the", "a", "an", "is", "are", "was", "were", "be", "been", "being",
-            "have", "has", "had", "do", "does", "did", "will", "would", "could",
-            "should", "may", "might", "must", "can", "to", "of", "in", "for",
-            "on", "with", "at", "by", "from", "as", "into", "through", "during",
-            "before", "after", "above", "below", "between", "under", "again",
-            "further", "then", "once", "here", "there", "when", "where", "why",
-            "how", "all", "each", "few", "more", "most", "other", "some", "such",
-            "no", "nor", "not", "only", "own", "same", "so", "than", "too",
-            "very", "just", "also", "now", "and", "but", "or", "if", "it", "its",
-            "this", "that", "these", "those", "i", "you", "he", "she", "we", "they",
-        }
-
-        # Tokenize and filter
+        # Tokenize and filter using module-level stop words
         words = re.findall(r"\b[a-zA-Z]+\b", text.lower())
-        filtered = [w for w in words if w not in stop_words and len(w) > 2]
+        filtered = [w for w in words if w not in _STOP_WORDS and len(w) > 2]
 
         # Count frequencies
         counter = Counter(filtered)

{spatial_memory_mcp-1.5.3.dist-info → spatial_memory_mcp-1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatial-memory-mcp
-Version: 1.5.3
+Version: 1.6.0
 Summary: Spatial bidirectional persistent memory MCP server for LLMs - vector-based semantic memory as a navigable landscape
 Project-URL: Homepage, https://github.com/arman-tech/spatial-memory-mcp
 Project-URL: Repository, https://github.com/arman-tech/spatial-memory-mcp
@@ -44,7 +44,7 @@ Description-Content-Type: text/markdown
 
 A vector-based spatial memory system that treats knowledge as a navigable landscape, not a filing cabinet.
 
-> **Project Status**: All phases complete. Production-ready with 1094 tests passing.
+> **Project Status**: All phases complete. Production-ready with 1360 tests passing.
 
 ## Supported Platforms
 
@@ -63,6 +63,42 @@ Spatial Memory MCP Server provides persistent, semantic memory for LLMs through
 - **Visual Understanding**: Generate Mermaid/SVG/JSON visualizations of your knowledge space
 - **Hybrid Search**: Combine vector similarity with full-text search
 
+## Why Spatial Memory?
+
+### Zero Cognitive Load
+**You never think about memory. Claude handles everything automatically.**
+
+- Auto-loads relevant context at session start
+- Recognizes memory-worthy moments and asks "Save this? y/n"
+- Synthesizes answers naturally—no raw JSON, no memory IDs
+- MCP instructions inject automatically—zero configuration
+
+### Cognitive Architecture, Not Storage
+Other memory systems store embeddings. Spatial Memory implements how memory actually works:
+
+- **Decay**: Memories fade over time (Ebbinghaus forgetting curve)
+- **Reinforcement**: Frequently accessed memories grow stronger
+- **Consolidation**: Similar memories merge intelligently
+- **Extraction**: Auto-capture facts, decisions, patterns from conversations
+
+### Spatial Navigation (Unique Innovation)
+Navigate knowledge like a landscape, not a filing cabinet:
+
+| Tool | What It Does |
+|------|-------------|
+| **Journey** | SLERP between two memories—discover what's conceptually in between |
+| **Wander** | Random walk exploration—find unexpected connections |
+| **Regions** | HDBSCAN clustering—see how your knowledge self-organizes |
+| **Visualize** | UMAP projection—view your memory space in 2D/3D |
+
+### 21 Tools vs. 3-6 in Competitors
+Full lifecycle management: core operations, spatial navigation, memory lifecycle, hybrid search, namespace management, data import/export, and health/stats monitoring.
+
+### Enterprise-Ready
+Connection pooling, circuit breakers, per-agent rate limiting, request tracing, response caching, and defense-in-depth security (path traversal prevention, SQL injection detection, input validation).
+
+> *See [MARKETING.md](MARKETING.md) for the complete comparison with competitors.*
+
 ## Features
 
 - **21 MCP tools** across 4 categories (core, spatial, lifecycle, utility)
@@ -72,7 +108,7 @@ Spatial Memory MCP Server provides persistent, semantic memory for LLMs through
 - **ONNX Runtime** by default for 2-3x faster embeddings
 - **Enterprise features**: Connection pooling, retry logic, batch operations
 - **Comprehensive security**: Path validation, SQL injection prevention, input sanitization
-- **1094 tests** including security edge cases
+- **1360 tests** including security edge cases
 
 ## Roadmap
 
@@ -130,6 +166,31 @@ If ONNX shows as unavailable, reinstall with:
 pip install --force-reinstall "sentence-transformers[onnx]"
 ```
 
+### Optional Performance Dependencies
+
+For best performance, install these optional dependencies:
+
+```bash
+# ONNX Runtime - 2-3x faster embeddings, 60% less memory
+pip install onnxruntime
+
+# Or install with sentence-transformers ONNX support
+pip install "sentence-transformers[onnx]"
+
+# scipy - Optimized pairwise similarity calculations
+# Used by visualize, regions, and consolidate operations
+pip install scipy
+```
+
+**Performance comparison:**
+
+| Component | Without | With | Benefit |
+|-----------|---------|------|---------|
+| ONNX Runtime | PyTorch inference | ONNX inference | 2-3x faster embeddings |
+| scipy | numpy matrix ops | scipy.cdist | Faster similarity calculations |
+
+Both are optional - the system includes fallbacks that use numpy when these aren't available.
+
 ## Configuration
 
 Copy `.env.example` to `.env` and customize:
@@ -292,6 +353,25 @@ Export all memories to parquet format
 - **Error Sanitization**: Internal errors return reference IDs, not stack traces
 - **Secure Credential Handling**: API keys stored as SecretStr
 
+## Deployment Considerations
+
+### Network Filesystems (NFS/SMB/CIFS)
+
+Spatial Memory uses file-based locking to prevent data corruption when multiple processes access the same storage. **File locking does not work reliably on network filesystems** such as NFS, SMB/CIFS, or SSHFS.
+
+If the storage path is on a network filesystem, you will see a warning at startup:
+
+```
+WARNING: Storage path appears to be on a network filesystem (nfs).
+File-based locking does not work reliably on network filesystems.
+Running multiple instances against this storage may cause data corruption.
+```
+
+**Recommendations:**
+1. **Use local storage** (default: `./.spatial-memory`) for reliable operation
+2. **Single instance only**: If you must use network storage, ensure only one MCP server instance accesses it
+3. **Acknowledge the risk**: Set `SPATIAL_MEMORY_ACKNOWLEDGE_NETWORK_FS_RISK=true` to suppress the warning
+
 ## Development
 
 ### Running Tests

spatial_memory_mcp-1.6.0.dist-info/RECORD

@@ -0,0 +1,54 @@
+spatial_memory/__init__.py,sha256=5llnvvlYGS28SmMQcE_DhSSTaFyvhh0BASb-ZHX4Z1o,2154
+spatial_memory/__main__.py,sha256=PaB4lkEBePNFCFDwjZo2mtQiWCNbK6U0fZ8jsQ9luNE,7761
+spatial_memory/config.py,sha256=SvG67Z8Hjw0XAFzVn59lLm-_Pz5dzL-c4Dli3_mtG0M,22537
+spatial_memory/factory.py,sha256=iuVKeE0q9SrDo816k2H744nELFeq7vVOdg4puHxCFOM,15806
+spatial_memory/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+spatial_memory/server.py,sha256=4a4WbS_Us0OiLfRyt5Mj3WU9rMCdMRbU6ziWajG-72I,45779
+spatial_memory/verify.py,sha256=4p4KQYRUBrKGax66n629hvb9Ul8sR2yXXnfyZLpNk-o,3939
+spatial_memory/adapters/__init__.py,sha256=xNPQCOYVsTP2ogMEcYGbxGJYH9pdksB66MZ7ctK6KbM,187
+spatial_memory/adapters/lancedb_repository.py,sha256=NwZQ-SGPTe82cFbOYtYERPRvY3eujz5iCd7EOaLiDfE,31247
+spatial_memory/core/__init__.py,sha256=wG6fws4AIF3X1vJdWA2_w2bMQo4ZXez_BYtcYvFGQvY,3033
+spatial_memory/core/cache.py,sha256=QqG0hhpaDH0mzBLIEinGP3WkKsb70QfCLMGpptguWIM,10038
+spatial_memory/core/circuit_breaker.py,sha256=zxqnOWiAnx_S7oX44UY57ihpk7V27fzW6rYgBn1BWp8,10734
+spatial_memory/core/connection_pool.py,sha256=ienTFQ-tFYwkaWD2_lcs9T8uYXL45OMpzCX5V-l_MMk,7617
+spatial_memory/core/consolidation_strategies.py,sha256=_PGdVuz4Kkf96cdIEPieGTOfubgOc6PoUYuXfJRwBd8,12805
+spatial_memory/core/database.py,sha256=3Llo2FLznQA2zUYf5r1JFnht61bPZQGTGeZ2IVhxDMI,118227
+spatial_memory/core/db_idempotency.py,sha256=B0EYdZFZYmQ7s101RviswySta7Qp7TZ2fiqWES_djyw,7978
+spatial_memory/core/db_indexes.py,sha256=p1glBuna81yY8bu8hhJkR6AhuzeZgaAaeKnsd3Oe4No,20115
+spatial_memory/core/db_migrations.py,sha256=x-_dXZrtfZZQwb4d3ZW32zw1-CzbDLC7Y33fdsvQM5Y,19138
+spatial_memory/core/db_search.py,sha256=XnNpqI2oto9EKbmp7bYBxeaxGfblJicR9KazvZKfhbg,19866
+spatial_memory/core/db_versioning.py,sha256=7LGWQO6EiwIgw-C5e81xG4jEO34b5y95Ag6uoVrU7Xw,5984
+spatial_memory/core/embeddings.py,sha256=g_C8rmrNH8qTroPcg-aYJo5Z6NR_YqGN050Iryytx5c,20892
+spatial_memory/core/errors.py,sha256=mGQlPNNiNOdErYPXdEQXM1_-IeueUB_jtgdt8P8lzUQ,8799
+spatial_memory/core/file_security.py,sha256=kHIYEnZIRFz94FxCJ7oOHiaihgQRB1rsOHHmJprHNhU,25766
+spatial_memory/core/filesystem.py,sha256=aE8BvM8tyIMbjtaiyG0Si0F1c85jxAwa3IM5I_kvkME,5602
+spatial_memory/core/health.py,sha256=Xq9TYfmBN3YLjYOrpFWtvbR1-fQbSrP1oorSVjRHOSg,9145
+spatial_memory/core/helpers.py,sha256=nxLXGfkpydWzEgMj8PkdX9gVvybN2aCH-CfbEkq6U_w,1931
+spatial_memory/core/import_security.py,sha256=DiG0BsX65JGGf6B1T855SVz1TZB1ViI3JXRi1uW03sQ,13296
+spatial_memory/core/lifecycle_ops.py,sha256=P8jc4JGBF39ayNikgLu0I3kGcJ3ph0VsvAHSxjp35FI,35836
+spatial_memory/core/logging.py,sha256=JfFRzHmhZ2BPNSJiKIHGjfUeskFVo8Bj7nOKznvv0kU,6542
+spatial_memory/core/metrics.py,sha256=8B26sAd2y6xrpaJr8mNgOAMzAZDd1uXOvAGxz_1nhfY,5383
+spatial_memory/core/models.py,sha256=VX61h5_pnsIQ5w5LjpElhVTW4UAa0RKadnrtLLOQb94,17353
+spatial_memory/core/rate_limiter.py,sha256=5A3YI6C0_YrWZeSBBxF7Eu5HUD8rodS45301730doF0,10582
+spatial_memory/core/response_types.py,sha256=VhfQLpTxgdJf3CYPtQALvh4KmaUbHzVAT_qtRVtoQgs,10603
+spatial_memory/core/security.py,sha256=fjIYqsyzK4qqm7sI8FNEE2xx9WjNJnrAslOBLVRVwgs,19759
+spatial_memory/core/spatial_ops.py,sha256=_xNrZzrbL7w2uAMJkQZEtTMjERQpo04cuSUoTNebiew,13360
+spatial_memory/core/tracing.py,sha256=9O3WdUJfCl2sohYWlaQETrCO7_P_N3qY_MqSAnpQPl0,8438
+spatial_memory/core/utils.py,sha256=YvvU3EbbAicR732LkHMM5-u4wvBaJ4G9DigBaB2CoI4,3438
+spatial_memory/core/validation.py,sha256=A8a5PF7X8Veg8S176UFEqkZDBlWILbQM-5wtAMOgG3U,13476
+spatial_memory/migrations/__init__.py,sha256=wljoV_u2PPx-dH6JOPmjEP5xEbwoM9HQ1WYDZr7PW58,1072
+spatial_memory/ports/__init__.py,sha256=Lq9ht9AS4VwPbMojtd_FYkA7lUuCXmYHwv6sweJi9AQ,243
+spatial_memory/ports/repositories.py,sha256=oJMU7UHoj4YudyeOQaSkI9A2z81L3Vn2q7hm3RILfXI,19920
+spatial_memory/services/__init__.py,sha256=epaF3aHxK2sgGVMp6rS_fxMMAvDVPxjaWm1n4hKOMWU,1564
+spatial_memory/services/export_import.py,sha256=2vZnFvX1deV-Zdj0HGkc2My8Oy1BrFJL8Peep25iUKI,38190
+spatial_memory/services/lifecycle.py,sha256=asxFBp06qfnaZJpAph6Dm6i7kN1cREXuoopkjuOMvwc,42937
+spatial_memory/services/memory.py,sha256=MZ9NMNXBRYEA39vzT5gAB7PXJrGFwC-D98SLZe7Z50Q,12944
+spatial_memory/services/spatial.py,sha256=3UMPm4mRQ42oXNwLUEYp4SAinnGX4dwOnWaK9CkVViA,42552
+spatial_memory/services/utility.py,sha256=89rn1gNJwNQIhrWjmVS3RKP5AQuCvjswFeefMp7yK-4,14950
+spatial_memory/tools/__init__.py,sha256=ZhFZp5j8HA4Qx5pVcRmgTcBbqY3X5TmgMNpSkyAMqJA,127
+spatial_memory/tools/definitions.py,sha256=Ueg_BrRGJcp_jnQD95DiYFPkxU419XPkbjzQFDG3jtY,25397
+spatial_memory_mcp-1.6.0.dist-info/METADATA,sha256=SKMn9h_8wYhMK45Vh5iqkH8-HSyjaf5r96Fkyv0tBek,15438
+spatial_memory_mcp-1.6.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+spatial_memory_mcp-1.6.0.dist-info/entry_points.txt,sha256=nJ4RJBB9SvhNktJdikcAS27fSwtKekpgPR4GTy2r1cE,64
+spatial_memory_mcp-1.6.0.dist-info/licenses/LICENSE,sha256=g65vrroU3yJxekbYV8xmDj7KFrXAg89eCM8vcWrpKmU,1095
+spatial_memory_mcp-1.6.0.dist-info/RECORD,,

spatial_memory_mcp-1.5.3.dist-info/RECORD

@@ -1,44 +0,0 @@
-spatial_memory/__init__.py,sha256=uunMrbEkIDKaLXB2nFaBQgIQZBGMaMuwQxBG_OKd3Mk,2154
-spatial_memory/__main__.py,sha256=bhoAnPQkuD-jAHavxQEbv3JxpsbWB9qvWlYEWk0_TWQ,288
-spatial_memory/config.py,sha256=rOUbKid57dCe2yAAOlw0K-5bQlK3UzyDSrMxqa5_Wrc,22122
-spatial_memory/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-spatial_memory/server.py,sha256=_C2NMd3ZasWftFbxrRy7Y2W9vgiJ78wIvKr4iQ_JZf8,50768
-spatial_memory/verify.py,sha256=4p4KQYRUBrKGax66n629hvb9Ul8sR2yXXnfyZLpNk-o,3939
-spatial_memory/adapters/__init__.py,sha256=xNPQCOYVsTP2ogMEcYGbxGJYH9pdksB66MZ7ctK6KbM,187
-spatial_memory/adapters/lancedb_repository.py,sha256=nFC3I_biNFMC546hoJLnqbTCgk5LSlyfnz3QDC77fX8,28430
-spatial_memory/core/__init__.py,sha256=VbQifJwVu-HY-HzfHVQvIDQbVgiMFRjvSw7xpTcxE8Q,2652
-spatial_memory/core/cache.py,sha256=QqG0hhpaDH0mzBLIEinGP3WkKsb70QfCLMGpptguWIM,10038
-spatial_memory/core/circuit_breaker.py,sha256=zxqnOWiAnx_S7oX44UY57ihpk7V27fzW6rYgBn1BWp8,10734
-spatial_memory/core/connection_pool.py,sha256=-mD8nvgiKpVlycMw24FNaEh3E1XA4hXNkaaQW023I40,6083
-spatial_memory/core/database.py,sha256=PTy6-SZsEGjvQm2VU93NJAIJ3yHOAgwcBrLqupTwnD0,121551
-spatial_memory/core/embeddings.py,sha256=M1fjBuY_e2LQ7kb5GjWQ55T3w832YoPXbO3pNciP0mA,18606
-spatial_memory/core/errors.py,sha256=yqLt9KqE5iEBvKha1wZWNtN_QaVYcX9YPpiRmeIN11A,6551
-spatial_memory/core/file_security.py,sha256=kHIYEnZIRFz94FxCJ7oOHiaihgQRB1rsOHHmJprHNhU,25766
-spatial_memory/core/health.py,sha256=Xq9TYfmBN3YLjYOrpFWtvbR1-fQbSrP1oorSVjRHOSg,9145
-spatial_memory/core/helpers.py,sha256=nxLXGfkpydWzEgMj8PkdX9gVvybN2aCH-CfbEkq6U_w,1931
-spatial_memory/core/import_security.py,sha256=DiG0BsX65JGGf6B1T855SVz1TZB1ViI3JXRi1uW03sQ,13296
-spatial_memory/core/lifecycle_ops.py,sha256=P8jc4JGBF39ayNikgLu0I3kGcJ3ph0VsvAHSxjp35FI,35836
-spatial_memory/core/logging.py,sha256=JfFRzHmhZ2BPNSJiKIHGjfUeskFVo8Bj7nOKznvv0kU,6542
-spatial_memory/core/metrics.py,sha256=8B26sAd2y6xrpaJr8mNgOAMzAZDd1uXOvAGxz_1nhfY,5383
-spatial_memory/core/models.py,sha256=QU3fryNMucHMV8Cbd-jiCU0ofrAK525QNerVk_Zb1oo,17190
-spatial_memory/core/rate_limiter.py,sha256=cn51dRe9G4UHq_f_BuVTMF_zfDsWZqdBTHsXzjjL8JU,10068
-spatial_memory/core/security.py,sha256=fjIYqsyzK4qqm7sI8FNEE2xx9WjNJnrAslOBLVRVwgs,19759
-spatial_memory/core/spatial_ops.py,sha256=_xNrZzrbL7w2uAMJkQZEtTMjERQpo04cuSUoTNebiew,13360
-spatial_memory/core/tracing.py,sha256=9O3WdUJfCl2sohYWlaQETrCO7_P_N3qY_MqSAnpQPl0,8438
-spatial_memory/core/utils.py,sha256=YvvU3EbbAicR732LkHMM5-u4wvBaJ4G9DigBaB2CoI4,3438
-spatial_memory/core/validation.py,sha256=azjJcr1vo39i5x3v2_xY5WnRR-onqpy1zad5iuEAFEU,10013
-spatial_memory/ports/__init__.py,sha256=Lq9ht9AS4VwPbMojtd_FYkA7lUuCXmYHwv6sweJi9AQ,243
-spatial_memory/ports/repositories.py,sha256=_54TvFw5OIQ6ED8mNSC-7m2jOKVlyrFsuGDefhEADok,18081
-spatial_memory/services/__init__.py,sha256=epaF3aHxK2sgGVMp6rS_fxMMAvDVPxjaWm1n4hKOMWU,1564
-spatial_memory/services/export_import.py,sha256=ihPmObVOS86dbo0q_vIUMqlXFZOX6dth8pulnbK2dVM,37639
-spatial_memory/services/lifecycle.py,sha256=bWGHdAjueU1dE16YmHO2BPsizxej8_RupdnjhiJuItg,32681
-spatial_memory/services/memory.py,sha256=TElVWAIENdIFErCEt5B4a1naG8iQsylfWl6htt_Op84,12975
-spatial_memory/services/spatial.py,sha256=7cnZbZbHHx3lhvSv_l6gEUCcx-drq6Q3XGtD5_oi0dc,38668
-spatial_memory/services/utility.py,sha256=89rn1gNJwNQIhrWjmVS3RKP5AQuCvjswFeefMp7yK-4,14950
-spatial_memory/tools/__init__.py,sha256=ZhFZp5j8HA4Qx5pVcRmgTcBbqY3X5TmgMNpSkyAMqJA,127
-spatial_memory/tools/definitions.py,sha256=Ueg_BrRGJcp_jnQD95DiYFPkxU419XPkbjzQFDG3jtY,25397
-spatial_memory_mcp-1.5.3.dist-info/METADATA,sha256=bNbwtM0JJ5fToF23vaCZREpcAOIMZRgE6_Fl8KjyjO8,12035
-spatial_memory_mcp-1.5.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-spatial_memory_mcp-1.5.3.dist-info/entry_points.txt,sha256=nJ4RJBB9SvhNktJdikcAS27fSwtKekpgPR4GTy2r1cE,64
-spatial_memory_mcp-1.5.3.dist-info/licenses/LICENSE,sha256=g65vrroU3yJxekbYV8xmDj7KFrXAg89eCM8vcWrpKmU,1095
-spatial_memory_mcp-1.5.3.dist-info/RECORD,,