superlocalmemory 3.6.5 → 3.6.7

package/src/superlocalmemory/server/unified_daemon.py

@@ -34,11 +34,17 @@ import signal
 import sys
 import threading
 import time
-from contextlib import asynccontextmanager
+from contextlib import asynccontextmanager, AsyncExitStack
 from datetime import datetime, timezone
 from pathlib import Path
 from typing import Optional
 
+# v3.6.7: Tell mcp/server.py it is being imported inside the daemon process.
+# This suppresses the three side-effect threads (mcp-warmup, parent-watchdog,
+# stdin-eof-monitor) that are harmful when the MCP server runs embedded.
+# Must be set BEFORE any import of superlocalmemory.mcp.server.
+os.environ.setdefault("SLM_MCP_EMBEDDED", "1")
+
 from fastapi import FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.middleware.gzip import GZipMiddleware
@@ -95,32 +101,20 @@ class EngineRecallAdapter:
             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": _sanitize_json_text(r.fact.content[:300]),
-                "source_content": _sanitize_json_text(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),
-                "created_at": getattr(r.fact, "created_at", "") or "",
-                "evidence_chain": list(
-                    getattr(r, "evidence_chain", []) or []
-                ),
-            })
+        # v3.6.6: same shared chokepoint as the HTTP route — identical output.
+        from superlocalmemory.server.recall_serializer import (
+            serialize_recall_response,
+        )
+        _rc = getattr(self._engine._config, "retrieval", None)
+        results, no_confident_match = serialize_recall_response(
+            response,
+            limit=limit,
+            memory_map={k: _sanitize_json_text(v) for k, v in memory_map.items()},
+            per_fact_max=getattr(_rc, "recall_per_fact_max_chars", 2400),
+            total_max=getattr(_rc, "recall_total_max_chars", 12000),
+        )
+        for _r in results:
+            _r["content"] = _sanitize_json_text(_r.get("content", ""))
         return {
             "ok": True,
             "query": query,
@@ -133,6 +127,7 @@ class EngineRecallAdapter:
             },
             "total_candidates": getattr(response, "total_candidates", 0),
             "results": results,
+            "no_confident_match": no_confident_match,
         }
 
 
@@ -861,7 +856,20 @@ async def lifespan(application: FastAPI):
     except Exception as e:
         logger.warning("optimize module not available: %s", e)
 
-    yield
+    # v3.6.7: Start MCP Streamable-HTTP session manager (GOTCHA #1).
+    # streamable_http_app() carries its own Starlette lifespan that initialises
+    # an anyio task group inside the session manager. Without entering that
+    # lifespan every POST /mcp 500s with "Task group is not initialized."
+    # AsyncExitStack enters the context only when _mcp_app was mounted; if the
+    # mount failed (non-fatal) the daemon starts normally without HTTP MCP.
+    async with AsyncExitStack() as _mcp_stack:
+        if _mcp_app is not None:
+            await _mcp_stack.enter_async_context(
+                _mcp_app.router.lifespan_context(_mcp_app)
+            )
+            logger.info("MCP HTTP session manager started (Streamable-HTTP on /mcp)")
+
+        yield
 
     # Cancel optimize metrics flush loop + run final flush before shutdown
     try:
@@ -1160,6 +1168,28 @@ def create_app() -> FastAPI:
     # -- Daemon-specific routes --
     _register_daemon_routes(application)
 
+    # -- v3.6.7: MCP Streamable-HTTP transport at /mcp --
+    # Mount the FastMCP server as a Starlette ASGI sub-app so ALL clients
+    # (Claude Code sessions, subagents, desktop, hermes) share ONE daemon
+    # process instead of spawning an `slm mcp` subprocess per connection.
+    # The session manager lifespan is started in lifespan() via AsyncExitStack.
+    # Fail-open: if import or mount fails, stdio transport keeps working.
+    #
+    # streamable_http_path is set to "/" so that when mounted at "/mcp" the
+    # effective user-facing endpoint is exactly http://127.0.0.1:8765/mcp.
+    # (FastAPI strips the mount prefix before passing the request to the
+    # sub-app, so the sub-app's internal route must be "/".)
+    try:
+        from superlocalmemory.mcp.server import server as _mcp_fastmcp
+        _mcp_fastmcp.settings.streamable_http_path = "/"
+        _mcp_fastmcp._session_manager = None  # Defensive reset for idempotency
+        global _mcp_app
+        _mcp_app = _mcp_fastmcp.streamable_http_app()
+        application.mount("/mcp", _mcp_app)
+        logger.info("MCP HTTP transport mounted at /mcp (Streamable HTTP, port 8765)")
+    except Exception as _mcp_exc:  # pragma: no cover — defensive
+        logger.warning("MCP HTTP mount failed (non-fatal, stdio still works): %s", _mcp_exc)
+
     return application
 
 
@@ -1213,7 +1243,9 @@ def _register_dashboard_routes(application: FastAPI) -> None:
         # for Gemini), never X-SLM-API-Key. Verified: auth_middleware.py:50-82
         # returns False for POST when api_key file exists and X-SLM-API-Key
         # is absent.
-        _AUTH_EXEMPT_PREFIXES = ("/v1/", "/v1beta/")
+        # v3.6.7: /mcp is also exempt — MCP clients negotiate their own session
+        # via the MCP protocol; they have no knowledge of X-SLM-API-Key.
+        _AUTH_EXEMPT_PREFIXES = ("/v1/", "/v1beta/", "/mcp")
 
         @application.middleware("http")
         async def auth_middleware(request, call_next):
@@ -1563,6 +1595,8 @@ def _register_daemon_routes(application: FastAPI) -> None:
         q: str = "", query: str = "", limit: int = 20,
         session_id: str = "",
         fast: bool = False,
+        full: bool = False,
+        include_source: bool = False,
     ):
         _update_activity()
         search_query = q or query  # Accept both ?q= and ?query= for compatibility
@@ -1610,33 +1644,23 @@ def _register_daemon_routes(application: FastAPI) -> None:
                 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": _sanitize_json_text(r.fact.content),
-                    "source_content": _sanitize_json_text(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 getattr(r.fact, "fact_type", ""),
-                    "lifecycle": lifecycle.value
-                        if lifecycle and hasattr(lifecycle, "value") else "",
-                    "access_count": getattr(r.fact, "access_count", 0),
-                    "created_at": getattr(r.fact, "created_at", "") or "",
-                    "evidence_chain": list(
-                        getattr(r, "evidence_chain", []) or []
-                    ),
-                })
+            # v3.6.6: single shared serialization chokepoint — budget + source
+            # discipline + no_confident_match, identical across every surface.
+            from superlocalmemory.server.recall_serializer import (
+                serialize_recall_response,
+            )
+            _rc = getattr(engine._config, "retrieval", None)
+            results, no_confident_match = serialize_recall_response(
+                response,
+                limit=limit,
+                memory_map={k: _sanitize_json_text(v) for k, v in memory_map.items()},
+                per_fact_max=getattr(_rc, "recall_per_fact_max_chars", 2400),
+                total_max=getattr(_rc, "recall_total_max_chars", 12000),
+                full=full,
+                include_source=include_source,
+            )
+            for _r in results:
+                _r["content"] = _sanitize_json_text(_r.get("content", ""))
             return {
                 "ok": True,
                 "query": search_query,
@@ -1650,6 +1674,7 @@ def _register_daemon_routes(application: FastAPI) -> None:
                 "total_candidates": getattr(response, "total_candidates", 0),
                 "results": results,
                 "count": len(results),
+                "no_confident_match": no_confident_match,
             }
         except Exception as exc:
             raise HTTPException(500, detail=str(exc))
@@ -1838,6 +1863,10 @@ def _update_activity():
 
 _start_time: float | None = None
 
+# v3.6.7: Starlette app returned by mcp_server.streamable_http_app().
+# Set in create_app(); consumed by lifespan() to start the session manager.
+_mcp_app = None
+
 
 # ---------------------------------------------------------------------------
 # Server entry point

package/src/superlocalmemory/storage/models.py

@@ -411,3 +411,6 @@ class RecallResponse:
     channel_weights: dict[str, float] = field(default_factory=dict)
     total_candidates: int = 0
     retrieval_time_ms: float = 0.0
+    # v3.6.6: Evidence floor. True when floor gates out ALL results.
+    # Additive field — backward compatible (defaults to False).
+    no_confident_match: bool = False

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

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: superlocalmemory
-Version: 3.6.5
+Version: 3.6.7
 Summary: Information-geometric agent memory with mathematical guarantees
 Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
 License: AGPL-3.0-or-later
@@ -401,6 +401,32 @@ slm status
 
 ### MCP Integration (Claude, Cursor, Windsurf, VS Code, etc.)
 
+SLM supports **two MCP transports** — use whichever fits your tool. Both expose the same 33 tools and 7 resources.
+
+#### Option A — HTTP transport (v3.6.7+, recommended)
+
+One shared process handles every client. RAM is flat regardless of how many IDE windows, subagents, or concurrent sessions connect. Requires the SLM daemon to be running (`slm start`).
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
+      "type": "http",
+      "url": "http://127.0.0.1:8765/mcp/"
+    }
+  }
+}
+```
+
+> **Claude Code** also accepts:
+> ```bash
+> claude mcp add --transport http superlocalmemory http://127.0.0.1:8765/mcp/
+> ```
+
+#### Option B — stdio transport (universal, works everywhere)
+
+Spawns one `slm mcp` subprocess per client connection (~90–110 MB each). Works with every MCP-compatible tool including those that do not yet support HTTP transport. No daemon required.
+
 ```json
 {
   "mcpServers": {
@@ -412,7 +438,36 @@ slm status
 }
 ```
 
-33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`). **V3.3: Adaptive lifecycle, smart compression, and pattern learning.**
+#### Option C — `mcp-remote` bridge (for stdio-only tools that want HTTP)
+
+Some CLIs (e.g. Grok CLI) only speak stdio but you still want the RAM benefit of HTTP. The [`@modelcontextprotocol/client-cli`](https://www.npmjs.com/package/@modelcontextprotocol/client-cli) package bridges them:
+
+```bash
+npm install -g @modelcontextprotocol/client-cli
+```
+
+```json
+{
+  "mcpServers": {
+    "superlocalmemory": {
+      "command": "mcp-remote",
+      "args": ["http://127.0.0.1:8765/mcp/", "--allow-http", "--transport", "http-only"]
+    }
+  }
+}
+```
+
+#### When to use which
+
+| Situation | Use |
+|-----------|-----|
+| Claude Code / Claude Desktop (v3.6.7+) | **HTTP** — zero new processes per session |
+| Cursor, Windsurf, Gemini CLI, Antigravity | **HTTP** — native support |
+| Grok CLI, tools that only support stdio | **`mcp-remote` bridge** |
+| Offline / daemon-free usage | **stdio** |
+| Any tool, any version | **stdio** always works as fallback |
+
+See [`docs/ide-setup.md`](docs/ide-setup.md) for per-IDE configs. 33 MCP tools by default (+42 optional behind `SLM_MCP_ALL_TOOLS=1`) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in `ide/configs/`).
 
 ### Dual Interface: MCP + CLI
 

package/src/superlocalmemory.egg-info/SOURCES.txt

@@ -73,6 +73,7 @@ src/superlocalmemory/compliance/retention.py
 src/superlocalmemory/compliance/scheduler.py
 src/superlocalmemory/core/__init__.py
 src/superlocalmemory/core/backend_orchestrator.py
+src/superlocalmemory/core/block_hygiene.py
 src/superlocalmemory/core/clock_monitor.py
 src/superlocalmemory/core/config.py
 src/superlocalmemory/core/consolidation_engine.py
@@ -92,6 +93,7 @@ src/superlocalmemory/core/graph_analyzer.py
 src/superlocalmemory/core/graph_pruner.py
 src/superlocalmemory/core/health_monitor.py
 src/superlocalmemory/core/hooks.py
+src/superlocalmemory/core/ingest_gate.py
 src/superlocalmemory/core/injection.py
 src/superlocalmemory/core/loop_watchdog.py
 src/superlocalmemory/core/maintenance.py
@@ -358,6 +360,7 @@ src/superlocalmemory/retrieval/vector_store.py
 src/superlocalmemory/server/__init__.py
 src/superlocalmemory/server/api.py
 src/superlocalmemory/server/bandit_loops.py
+src/superlocalmemory/server/recall_serializer.py
 src/superlocalmemory/server/security_middleware.py
 src/superlocalmemory/server/ui.py
 src/superlocalmemory/server/unified_daemon.py