feat: silent stop hook — direct save instead of blocking MCP calls

.claude-plugin/hooks/mempal-precompact-hook.sh

@@ -1,5 +1,20 @@
 #!/bin/bash
 # MemPalace PreCompact Hook — thin wrapper calling Python CLI
 # All logic lives in mempalace.hooks_cli for cross-harness extensibility
+#
+# Python resolution order:
+#   1. MEMPALACE_PYTHON env var (user override)
+#   2. Plugin root's venv (development installs)
+#   3. System python3 (pip install --user / pipx)
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PLUGIN_ROOT="$(dirname "$SCRIPT_DIR")"
+
+if [ -n "$MEMPALACE_PYTHON" ] && [ -x "$MEMPALACE_PYTHON" ]; then
+    PYTHON="$MEMPALACE_PYTHON"
+elif [ -x "$PLUGIN_ROOT/venv/bin/python3" ]; then
+    PYTHON="$PLUGIN_ROOT/venv/bin/python3"
+else
+    PYTHON="python3"
+fi
 INPUT=$(cat)
-echo "$INPUT" | python3 -m mempalace hook run --hook precompact --harness claude-code
+echo "$INPUT" | "$PYTHON" -m mempalace hook run --hook precompact --harness claude-code

.claude-plugin/hooks/mempal-stop-hook.sh

@@ -1,5 +1,20 @@
 #!/bin/bash
 # MemPalace Stop Hook — thin wrapper calling Python CLI
 # All logic lives in mempalace.hooks_cli for cross-harness extensibility
+#
+# Python resolution order:
+#   1. MEMPALACE_PYTHON env var (user override)
+#   2. Plugin root's venv (development installs)
+#   3. System python3 (pip install --user / pipx)
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PLUGIN_ROOT="$(dirname "$SCRIPT_DIR")"
+
+if [ -n "$MEMPALACE_PYTHON" ] && [ -x "$MEMPALACE_PYTHON" ]; then
+    PYTHON="$MEMPALACE_PYTHON"
+elif [ -x "$PLUGIN_ROOT/venv/bin/python3" ]; then
+    PYTHON="$PLUGIN_ROOT/venv/bin/python3"
+else
+    PYTHON="python3"
+fi
 INPUT=$(cat)
-echo "$INPUT" | python3 -m mempalace hook run --hook stop --harness claude-code
+echo "$INPUT" | "$PYTHON" -m mempalace hook run --hook stop --harness claude-code

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mempalace",
-  "version": "3.0.14",
+  "version": "3.1.0",
   "description": "Give your AI a memory — mine projects and conversations into a searchable palace. 19 MCP tools, auto-save hooks, and guided setup.",
   "author": {
     "name": "milla-jovovich"

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mempalace",
-  "version": "3.0.14",
+  "version": "3.1.0",
   "description": "Give your AI a memory — mine projects and conversations into a searchable palace. 19 MCP tools, auto-save hooks, and guided setup.",
   "author": {
     "name": "milla-jovovich"

CLAUDE.md

@@ -0,0 +1,55 @@
+# CLAUDE.md — memorypalace
+
+## What This Is
+
+JP's fork of [milla-jovovich/mempalace](https://github.com/milla-jovovich/mempalace) — a local AI memory system using ChromaDB for verbatim storage and semantic search.
+
+- **Fork**: `jphein/mempalace` (origin) / `milla-jovovich/mempalace` (upstream)
+- **Version**: 3.1.0 + local fixes
+- **Python**: venv at `./venv/`, editable install with dev deps
+- **Palace data**: `~/.mempalace/palace` (ChromaDB) + `~/.mempalace/config.json`
+
+## Key Files
+
+- `~/Projects/mempalace.yaml` — **do not delete**. Mining config with wing/room definitions. Regenerate with `mempalace init ~/Projects --yes` if lost.
+- `~/.mempalace/config.json` — topic wings and hall keywords, customized for JP's domains (infrastructure, development, tools, creative, projects, system).
+- `~/.mempalace/palace/` — ChromaDB vector store. The actual data.
+- `~/.mempalace/hook_state/` — stop hook session tracking.
+
+## Development
+
+```bash
+source venv/bin/activate
+python -m pytest tests/ -x -q           # run tests (576 expected)
+mempalace status                         # check palace state
+mempalace search "query"                 # test search
+python -m mempalace.mcp_server           # run MCP server standalone
+```
+
+Ruff for linting (`ruff check`), line length 100, target Python 3.9.
+
+## Fork Changes (ahead of upstream)
+
+1. **fix: epsilon mtime comparison** — `palace.py` uses `abs() < 0.01` instead of `==` for float mtime dedup
+2. **feat: bulk_check_mined()** — paginated pre-fetch of all source_file/mtime pairs
+3. **fix: MCP server** — search limit capped [1,100], status/taxonomy tools paginated past 10K, duplicate cache decls removed
+4. **perf: batch ChromaDB writes** — one upsert per file instead of per chunk in both miners
+5. **fix: entity detector STOPWORDS** — 73 technical terms added (Handler, Node, Service, etc.)
+6. **feat: similarity threshold** — `min_similarity` parameter in search, default 1.5 L2 distance in MCP
+7. **feat: hooks_cli** — stop hook saves directly via Python API with systemMessage notification, precompact blocks for AI-driven save, auto-ingest transcripts
+
+## Upstream PRs
+
+- milla-jovovich/mempalace#483 — mtime dedup fix
+- milla-jovovich/mempalace#484 — search limit + pagination + cache fix
+
+## Integration
+
+- **Claude Code plugin**: installed at user scope via marketplace
+- **MCP server**: global user scope — available in all projects
+- **Stop hook**: fires every 15 messages, saves directly via Python API + systemMessage notification + auto-ingests transcript
+- **PreCompact hook**: emergency save before context compaction
+
+## Testing
+
+Always run `python -m pytest tests/ -x -q` after changes. 576 tests expected to pass. Benchmark and stress tests are excluded by default (use `-m benchmark` or `-m stress` to include).

mempalace/cli.py

@@ -95,6 +95,7 @@ def cmd_mine(args):
             dry_run=args.dry_run,
             respect_gitignore=not args.no_gitignore,
             include_ignored=include_ignored,
+            workers=args.workers,
         )
 
 
@@ -150,6 +151,23 @@ def cmd_split(args):
         sys.argv = old_argv
 
 
+def cmd_export(args):
+    from .exporter import export_palace
+
+    palace_path = os.path.expanduser(args.palace) if args.palace else MempalaceConfig().palace_path
+    output_dir = os.path.expanduser(args.output)
+
+    print(f"\n{'=' * 55}")
+    print("  MemPalace Export")
+    print(f"{'=' * 55}\n")
+    print(f"  Palace: {palace_path}")
+    print(f"  Output: {output_dir}\n")
+
+    export_palace(palace_path=palace_path, output_dir=output_dir)
+
+    print(f"\n{'=' * 55}\n")
+
+
 def cmd_status(args):
     from .miner import status
 
@@ -442,6 +460,12 @@ def main():
         default="exchange",
         help="Extraction strategy for convos mode: 'exchange' (default) or 'general' (5 memory types)",
     )
+    p_mine.add_argument(
+        "--workers",
+        type=int,
+        default=0,
+        help="Parallel workers for file processing (default: min(8, cpu_count); 1 = sequential)",
+    )
 
     # search
     p_search = sub.add_parser("search", help="Find anything, exact words")
@@ -462,6 +486,15 @@ def main():
         "--config", default=None, help="Entity config JSON (e.g. entities.json)"
     )
 
+    # export
+    p_export = sub.add_parser("export", help="Export palace as browsable markdown files")
+    p_export.add_argument(
+        "--output",
+        "-o",
+        default="./palace-export",
+        help="Output directory (default: ./palace-export)",
+    )
+
     # wake-up
     p_wakeup = sub.add_parser("wake-up", help="Show L0 + L1 wake-up context (~600-900 tokens)")
     p_wakeup.add_argument("--wing", default=None, help="Wake-up for a specific project/wing")
@@ -561,6 +594,7 @@ def main():
         "mine": cmd_mine,
         "split": cmd_split,
         "search": cmd_search,
+        "export": cmd_export,
         "mcp": cmd_mcp,
         "compress": cmd_compress,
         "wake-up": cmd_wakeup,

mempalace/config.py

@@ -173,6 +173,42 @@ def hall_keywords(self):
         """Mapping of hall names to keyword lists."""
         return self._file_config.get("hall_keywords", DEFAULT_HALL_KEYWORDS)
 
+    @property
+    def hook_silent_save(self):
+        """Whether the stop hook saves directly (True) or blocks for MCP calls (False)."""
+        return self._file_config.get("hooks", {}).get("silent_save", True)
+
+    @property
+    def hook_desktop_toast(self):
+        """Whether the stop hook shows a desktop notification via notify-send."""
+        return self._file_config.get("hooks", {}).get("desktop_toast", False)
+
+    def set_hook_setting(self, key: str, value: bool):
+        """Update a hook setting and write config to disk."""
+        if "hooks" not in self._file_config:
+            self._file_config["hooks"] = {}
+        self._file_config["hooks"][key] = value
+        try:
+            with open(self._config_file, "w") as f:
+                json.dump(self._file_config, f, indent=2)
+        except OSError:
+            pass
+
+    @property
+    def chunk_size(self):
+        """Characters per drawer chunk."""
+        return self._file_config.get("chunk_size", 800)
+
+    @property
+    def chunk_overlap(self):
+        """Overlap between adjacent chunks."""
+        return self._file_config.get("chunk_overlap", 100)
+
+    @property
+    def min_chunk_size(self):
+        """Minimum chunk size — skip smaller chunks."""
+        return self._file_config.get("min_chunk_size", 50)
+
     def init(self):
         """Create config directory and write default config.json if it doesn't exist."""
         self._config_dir.mkdir(parents=True, exist_ok=True)
@@ -187,6 +223,9 @@ def init(self):
                 "collection_name": DEFAULT_COLLECTION_NAME,
                 "topic_wings": DEFAULT_TOPIC_WINGS,
                 "hall_keywords": DEFAULT_HALL_KEYWORDS,
+                "chunk_size": 800,
+                "chunk_overlap": 100,
+                "min_chunk_size": 50,
             }
             with open(self._config_file, "w") as f:
                 json.dump(default_config, f, indent=2)

mempalace/convo_miner.py

@@ -326,34 +326,44 @@ def mine_convos(
         if extract_mode != "general":
             room_counts[room] += 1
 
-        # File each chunk
-        drawers_added = 0
+        # Batch all chunks into a single add call per file
+        batch_docs = []
+        batch_ids = []
+        batch_metas = []
         for chunk in chunks:
             chunk_room = chunk.get("memory_type", room) if extract_mode == "general" else room
             if extract_mode == "general":
                 room_counts[chunk_room] += 1
             drawer_id = f"drawer_{wing}_{chunk_room}_{hashlib.sha256((source_file + str(chunk['chunk_index'])).encode()).hexdigest()[:24]}"
-            try:
-                collection.add(
-                    documents=[chunk["content"]],
-                    ids=[drawer_id],
-                    metadatas=[
-                        {
-                            "wing": wing,
-                            "room": chunk_room,
-                            "source_file": source_file,
-                            "chunk_index": chunk["chunk_index"],
-                            "added_by": agent,
-                            "filed_at": datetime.now().isoformat(),
-                            "ingest_mode": "convos",
-                            "extract_mode": extract_mode,
-                        }
-                    ],
-                )
-                drawers_added += 1
-            except Exception as e:
-                if "already exists" not in str(e).lower():
-                    raise
+            batch_docs.append(chunk["content"])
+            batch_ids.append(drawer_id)
+            batch_metas.append(
+                {
+                    "wing": wing,
+                    "room": chunk_room,
+                    "source_file": source_file,
+                    "chunk_index": chunk["chunk_index"],
+                    "added_by": agent,
+                    "filed_at": datetime.now().isoformat(),
+                    "ingest_mode": "convos",
+                    "extract_mode": extract_mode,
+                }
+            )
+        drawers_added = 0
+        _ADD_BATCH_SIZE = 100
+        if batch_docs:
+            for batch_start in range(0, len(batch_docs), _ADD_BATCH_SIZE):
+                batch_end = batch_start + _ADD_BATCH_SIZE
+                try:
+                    collection.add(
+                        documents=batch_docs[batch_start:batch_end],
+                        ids=batch_ids[batch_start:batch_end],
+                        metadatas=batch_metas[batch_start:batch_end],
+                    )
+                    drawers_added += len(batch_docs[batch_start:batch_end])
+                except Exception as e:
+                    if "already exists" not in str(e).lower():
+                        raise
 
         total_drawers += drawers_added
         print(f"  ✓ [{i:4}/{len(files)}] {filepath.name[:50]:50} +{drawers_added}")

mempalace/entity_detector.py

@@ -393,6 +393,78 @@
     "networks",
     "training",
     "inference",
+    # Common technical/documentation terms that appear capitalized but aren't entities
+    "handler",
+    "node",
+    "service",
+    "manager",
+    "client",
+    "server",
+    "worker",
+    "plugin",
+    "module",
+    "interface",
+    "event",
+    "request",
+    "response",
+    "update",
+    "config",
+    "builder",
+    "factory",
+    "component",
+    "controller",
+    "provider",
+    "wrapper",
+    "helper",
+    "util",
+    "parser",
+    "loader",
+    "renderer",
+    "adapter",
+    "proxy",
+    "listener",
+    "observer",
+    "validator",
+    "formatter",
+    "converter",
+    "resolver",
+    "selector",
+    "reducer",
+    "dispatcher",
+    "compiler",
+    "optimizer",
+    "analyzer",
+    "generator",
+    "template",
+    "registry",
+    "repository",
+    "gateway",
+    "middleware",
+    "pipeline",
+    "container",
+    "context",
+    "session",
+    "token",
+    "stream",
+    "buffer",
+    "cache",
+    "queue",
+    "schema",
+    "entity",
+    "instance",
+    "object",
+    "method",
+    "property",
+    "attribute",
+    "parameter",
+    "argument",
+    "variable",
+    "constant",
+    "function",
+    "package",
+    "framework",
+    "runtime",
+    "platform",
 }
 
 # For entity detection — prose only, no code files