Merge pull request #502 from milla-jovovich/fix/chromadb-version-migration

feat: mempalace migrate — recover palaces from different ChromaDB versions

.github/CODEOWNERS

@@ -0,0 +1,13 @@
+# Default owners for everything
+* @milla-jovovich @bensig @igorls
+
+# Core library
+mempalace/ @milla-jovovich @bensig
+
+# CI and workflows
+.github/ @bensig
+
+# Plugins and integrations
+.claude-plugin/ @bensig
+.codex-plugin/ @bensig
+integrations/ @bensig

.github/dependabot.yml

@@ -0,0 +1,12 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 5
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 3

.github/workflows/ci.yml

@@ -18,7 +18,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
       - run: pip install -e ".[dev]"
-      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80
+      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80 --durations=10
 
   test-windows:
     runs-on: windows-latest
@@ -28,7 +28,7 @@ jobs:
         with:
           python-version: "3.9"
       - run: pip install -e ".[dev]"
-      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80
+      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80 --durations=10
 
   test-macos:
     runs-on: macos-latest
@@ -38,7 +38,7 @@ jobs:
         with:
           python-version: "3.9"
       - run: pip install -e ".[dev]"
-      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80
+      - run: python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing --cov-fail-under=80 --durations=10
   lint:
     runs-on: ubuntu-latest
     steps:

.gitignore

@@ -6,3 +6,30 @@ __pycache__/
 .pytest_cache/
 mempal.yaml
 .a5c/
+
+# Environment
+.env
+.env.*
+
+# OS
+.DS_Store
+Thumbs.db
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Coverage
+htmlcov/
+.coverage
+coverage.xml
+
+# Virtual environments
+.venv/
+venv/
+
+# ChromaDB local data
+*.sqlite3-journal

AGENTS.md

@@ -0,0 +1,78 @@
+# AGENTS.md
+
+> How to build, test, and contribute to MemPalace.
+
+## Setup
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Commands
+
+```bash
+# Run tests
+python -m pytest tests/ -v --ignore=tests/benchmarks
+
+# Run tests with coverage
+python -m pytest tests/ -v --ignore=tests/benchmarks --cov=mempalace --cov-report=term-missing
+
+# Lint
+ruff check .
+
+# Format
+ruff format .
+
+# Format check (CI mode)
+ruff format --check .
+```
+
+## Project structure
+
+```
+mempalace/
+├── mcp_server.py        # MCP server — all read/write tools
+├── miner.py             # Project file miner
+├── convo_miner.py       # Conversation transcript miner
+├── searcher.py          # Semantic search
+├── knowledge_graph.py   # Temporal entity-relationship graph (SQLite)
+├── palace.py            # Shared palace operations (ChromaDB access)
+├── config.py            # Configuration + input validation
+├── normalize.py         # Transcript format detection + normalization
+├── cli.py               # CLI dispatcher
+├── dialect.py           # AAAK compression dialect
+├── palace_graph.py      # Room traversal + cross-wing tunnels
+├── hooks_cli.py         # Hook system for auto-save
+└── version.py           # Single source of truth for version
+```
+
+## Conventions
+
+- **Python style**: snake_case for functions/variables, PascalCase for classes
+- **Linter**: ruff with E/F/W rules
+- **Formatter**: ruff format, double quotes
+- **Commits**: conventional commits (`fix:`, `feat:`, `test:`, `docs:`, `ci:`)
+- **Tests**: `tests/test_*.py`, fixtures in `tests/conftest.py`
+- **Coverage**: 85% threshold (80% on Windows due to ChromaDB file lock cleanup)
+
+## Architecture
+
+```
+User → CLI / MCP Server → ChromaDB (vector store) + SQLite (knowledge graph)
+
+Palace structure:
+  WING (person/project)
+    └── ROOM (topic)
+          └── DRAWER (verbatim text chunk)
+
+Knowledge Graph:
+  ENTITY → PREDICATE → ENTITY (with valid_from / valid_to dates)
+```
+
+## Key files for common tasks
+
+- **Adding an MCP tool**: `mempalace/mcp_server.py` — add handler function + TOOLS dict entry
+- **Changing search**: `mempalace/searcher.py`
+- **Modifying mining**: `mempalace/miner.py` (project files) or `mempalace/convo_miner.py` (transcripts)
+- **Input validation**: `mempalace/config.py` — `sanitize_name()` / `sanitize_content()`
+- **Tests**: mirror source structure in `tests/test_<module>.py`

docs/schema.sql

@@ -0,0 +1,36 @@
+-- MemPalace Knowledge Graph Schema
+-- SQLite database at ~/.mempalace/knowledge_graph.db
+
+CREATE TABLE IF NOT EXISTS entities (
+    id TEXT PRIMARY KEY,
+    name TEXT NOT NULL,
+    type TEXT DEFAULT 'unknown',
+    properties TEXT DEFAULT '{}'
+);
+
+CREATE TABLE IF NOT EXISTS triples (
+    id TEXT PRIMARY KEY,
+    subject TEXT NOT NULL,
+    predicate TEXT NOT NULL,
+    object TEXT NOT NULL,
+    valid_from TEXT,
+    valid_to TEXT,
+    confidence REAL DEFAULT 1.0,
+    source_closet TEXT,
+    source_file TEXT
+);
+
+CREATE TABLE IF NOT EXISTS attributes (
+    entity_id TEXT NOT NULL,
+    key TEXT NOT NULL,
+    value TEXT,
+    valid_from TEXT,
+    valid_to TEXT,
+    PRIMARY KEY (entity_id, key, valid_from)
+);
+
+-- Indexes
+CREATE INDEX IF NOT EXISTS idx_triples_subject ON triples(subject);
+CREATE INDEX IF NOT EXISTS idx_triples_object ON triples(object);
+CREATE INDEX IF NOT EXISTS idx_triples_predicate ON triples(predicate);
+CREATE INDEX IF NOT EXISTS idx_triples_valid ON triples(valid_from, valid_to);

mempalace/cli.py

@@ -150,6 +150,14 @@ def cmd_split(args):
         sys.argv = old_argv
 
 
+def cmd_migrate(args):
+    """Migrate palace from a different ChromaDB version."""
+    from .migrate import migrate
+
+    palace_path = os.path.expanduser(args.palace) if args.palace else MempalaceConfig().palace_path
+    migrate(palace_path=palace_path, dry_run=args.dry_run)
+
+
 def cmd_status(args):
     from .miner import status
 
@@ -531,6 +539,17 @@ def main():
     )
 
     # status
+    # migrate
+    p_migrate = sub.add_parser(
+        "migrate",
+        help="Migrate palace from a different ChromaDB version (fixes 3.0.0 → 3.1.0 upgrade)",
+    )
+    p_migrate.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Show what would be migrated without changing anything",
+    )
+
     sub.add_parser("status", help="Show what's been filed")
 
     args = parser.parse_args()
@@ -565,6 +584,7 @@ def main():
         "compress": cmd_compress,
         "wake-up": cmd_wakeup,
         "repair": cmd_repair,
+        "migrate": cmd_migrate,
         "status": cmd_status,
     }
     dispatch[args.command](args)

mempalace/migrate.py

@@ -0,0 +1,214 @@
+#!/usr/bin/env python3
+"""
+mempalace migrate — Recover a palace created with a different ChromaDB version.
+
+Reads documents and metadata directly from the palace's SQLite database
+(bypassing ChromaDB's API, which fails on version-mismatched palaces),
+then re-imports everything into a fresh palace using the currently installed
+ChromaDB version.
+
+This fixes the 3.0.0 → 3.1.0 upgrade path where chromadb was downgraded
+from 1.5.x to 0.6.x, breaking the on-disk storage format.
+
+Usage:
+    mempalace migrate                          # migrate default palace
+    mempalace migrate --palace /path/to/palace  # migrate specific palace
+    mempalace migrate --dry-run                # show what would be migrated
+"""
+
+import os
+import shutil
+import sqlite3
+from collections import defaultdict
+from datetime import datetime
+
+
+def extract_drawers_from_sqlite(db_path: str) -> list:
+    """Read all drawers directly from ChromaDB's SQLite, bypassing the API.
+
+    Works regardless of which ChromaDB version created the database.
+    Returns list of dicts with 'id', 'document', and 'metadata' keys.
+    """
+    conn = sqlite3.connect(db_path)
+    conn.row_factory = sqlite3.Row
+
+    # Get all embedding IDs and their documents
+    rows = conn.execute("""
+        SELECT e.embedding_id,
+               MAX(CASE WHEN em.key = 'chroma:document' THEN em.string_value END) as document
+        FROM embeddings e
+        JOIN embedding_metadata em ON em.id = e.id
+        GROUP BY e.embedding_id
+    """).fetchall()
+
+    drawers = []
+    for row in rows:
+        embedding_id = row["embedding_id"]
+        document = row["document"]
+        if not document:
+            continue
+
+        # Get metadata for this embedding
+        meta_rows = conn.execute(
+            """
+            SELECT em.key, em.string_value, em.int_value, em.float_value, em.bool_value
+            FROM embedding_metadata em
+            JOIN embeddings e ON e.id = em.id
+            WHERE e.embedding_id = ?
+              AND em.key NOT LIKE 'chroma:%'
+        """,
+            (embedding_id,),
+        ).fetchall()
+
+        metadata = {}
+        for mr in meta_rows:
+            key = mr["key"]
+            if mr["string_value"] is not None:
+                metadata[key] = mr["string_value"]
+            elif mr["int_value"] is not None:
+                metadata[key] = mr["int_value"]
+            elif mr["float_value"] is not None:
+                metadata[key] = mr["float_value"]
+            elif mr["bool_value"] is not None:
+                metadata[key] = bool(mr["bool_value"])
+
+        drawers.append(
+            {
+                "id": embedding_id,
+                "document": document,
+                "metadata": metadata,
+            }
+        )
+
+    conn.close()
+    return drawers
+
+
+def detect_chromadb_version(db_path: str) -> str:
+    """Detect which ChromaDB version created the database by checking schema."""
+    conn = sqlite3.connect(db_path)
+    try:
+        # 1.x has schema_str column in collections table
+        cols = [r[1] for r in conn.execute("PRAGMA table_info(collections)").fetchall()]
+        if "schema_str" in cols:
+            return "1.x"
+        # 0.6.x has embeddings_queue but no schema_str
+        tables = [
+            r[0]
+            for r in conn.execute("SELECT name FROM sqlite_master WHERE type='table'").fetchall()
+        ]
+        if "embeddings_queue" in tables:
+            return "0.6.x"
+        return "unknown"
+    finally:
+        conn.close()
+
+
+def migrate(palace_path: str, dry_run: bool = False):
+    """Migrate a palace to the currently installed ChromaDB version."""
+    import chromadb
+
+    palace_path = os.path.expanduser(palace_path)
+    db_path = os.path.join(palace_path, "chroma.sqlite3")
+
+    if not os.path.isfile(db_path):
+        print(f"\n  No palace database found at {db_path}")
+        return False
+
+    print(f"\n{'=' * 60}")
+    print("  MemPalace Migrate")
+    print(f"{'=' * 60}\n")
+    print(f"  Palace:    {palace_path}")
+    print(f"  Database:  {db_path}")
+    print(f"  DB size:   {os.path.getsize(db_path) / 1024 / 1024:.1f} MB")
+
+    # Detect version
+    source_version = detect_chromadb_version(db_path)
+    print(f"  Source:    ChromaDB {source_version}")
+    print(f"  Target:    ChromaDB {chromadb.__version__}")
+
+    # Try reading with current chromadb first
+    try:
+        client = chromadb.PersistentClient(path=palace_path)
+        col = client.get_collection("mempalace_drawers")
+        count = col.count()
+        print(f"\n  Palace is already readable by chromadb {chromadb.__version__}.")
+        print(f"  {count} drawers found. No migration needed.")
+        return True
+    except Exception:
+        print(f"\n  Palace is NOT readable by chromadb {chromadb.__version__}.")
+        print("  Extracting from SQLite directly...")
+
+    # Extract all drawers via raw SQL
+    drawers = extract_drawers_from_sqlite(db_path)
+    print(f"  Extracted {len(drawers)} drawers from SQLite")
+
+    if not drawers:
+        print("  Nothing to migrate.")
+        return True
+
+    # Show summary
+    wings = defaultdict(lambda: defaultdict(int))
+    for d in drawers:
+        w = d["metadata"].get("wing", "?")
+        r = d["metadata"].get("room", "?")
+        wings[w][r] += 1
+
+    print("\n  Summary:")
+    for wing, rooms in sorted(wings.items()):
+        total = sum(rooms.values())
+        print(f"    WING: {wing} ({total} drawers)")
+        for room, count in sorted(rooms.items(), key=lambda x: -x[1]):
+            print(f"      ROOM: {room:30} {count:5}")
+
+    if dry_run:
+        print("\n  DRY RUN — no changes made.")
+        print(f"  Would migrate {len(drawers)} drawers.")
+        return True
+
+    # Backup the old palace
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    backup_path = f"{palace_path}.pre-migrate.{timestamp}"
+    print(f"\n  Backing up to {backup_path}...")
+    shutil.copytree(palace_path, backup_path)
+
+    # Build fresh palace in a temp directory (avoids chromadb reading old state)
+    import tempfile
+
+    temp_palace = tempfile.mkdtemp(prefix="mempalace_migrate_")
+    print(f"  Creating fresh palace in {temp_palace}...")
+    client = chromadb.PersistentClient(path=temp_palace)
+    col = client.get_or_create_collection("mempalace_drawers")
+
+    # Re-import in batches
+    batch_size = 500
+    imported = 0
+    for i in range(0, len(drawers), batch_size):
+        batch = drawers[i : i + batch_size]
+        col.add(
+            ids=[d["id"] for d in batch],
+            documents=[d["document"] for d in batch],
+            metadatas=[d["metadata"] for d in batch],
+        )
+        imported += len(batch)
+        print(f"  Imported {imported}/{len(drawers)} drawers...")
+
+    # Verify before swapping
+    final_count = col.count()
+    del col
+    del client
+
+    # Swap: remove old palace, move new one into place
+    print("  Swapping old palace for migrated version...")
+    shutil.rmtree(palace_path)
+    shutil.move(temp_palace, palace_path)
+
+    print("\n  Migration complete.")
+    print(f"  Drawers migrated: {final_count}")
+    print(f"  Backup at: {backup_path}")
+
+    if final_count != len(drawers):
+        print(f"  WARNING: Expected {len(drawers)}, got {final_count}")
+
+    print(f"\n{'=' * 60}\n")
+    return True

pyproject.toml

@@ -54,11 +54,15 @@ packages = ["mempalace"]
 [tool.ruff]
 line-length = 100
 target-version = "py39"
+extend-exclude = ["benchmarks"]
 
 [tool.ruff.lint]
-select = ["E", "F", "W"]
+select = ["E", "F", "W", "C901"]
 ignore = ["E501"]
 
+[tool.ruff.lint.mccabe]
+max-complexity = 25
+
 [tool.ruff.format]
 quote-style = "double"