Merge branch 'staging' into dvirdukhan/parallel-second-pass

Author: DvirDukhan

.github/workflows/mcp-tests.yml

@@ -0,0 +1,76 @@
+name: MCP tests
+
+on:
+  push:
+    branches: ["main", "staging", "mcp/**"]
+    paths:
+      - "api/mcp/**"
+      - "tests/mcp/**"
+      - "api/llm.py"
+      - "api/graph.py"
+      - "pyproject.toml"
+      - "uv.lock"
+      - ".github/workflows/mcp-tests.yml"
+  pull_request:
+    paths:
+      - "api/mcp/**"
+      - "tests/mcp/**"
+      - "api/llm.py"
+      - "api/graph.py"
+      - "pyproject.toml"
+      - "uv.lock"
+      - ".github/workflows/mcp-tests.yml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  mcp-tests:
+    runs-on: ubuntu-latest
+
+    services:
+      falkordb:
+        image: falkordb/falkordb:latest
+        ports:
+          - 6379:6379
+        options: >-
+          --health-cmd "redis-cli ping"
+          --health-interval 5s
+          --health-timeout 3s
+          --health-retries 12
+
+    env:
+      FALKORDB_HOST: localhost
+      FALKORDB_PORT: "6379"
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+
+      - name: Setup Python
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        with:
+          version: "latest"
+          enable-cache: true
+          cache-dependency-glob: "uv.lock"
+
+      - name: Install backend dependencies
+        run: uv sync --all-extras
+
+      - name: Verify FalkorDB reachable
+        run: |
+          sudo apt-get update -qq && sudo apt-get install -y redis-tools
+          redis-cli -h localhost -p 6379 ping
+
+      - name: Run MCP test suite
+        run: uv run pytest tests/mcp/ -v

.github/workflows/release-image.yml

@@ -23,7 +23,7 @@ jobs:
           fi
 
       - name: Login to DockerHub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}

Dockerfile

@@ -21,7 +21,9 @@ COPY --from=node-base /usr/local/bin/node /usr/local/bin/node
 COPY --from=node-base /usr/local/lib/node_modules /usr/local/lib/node_modules
 
 # Install netcat for wait loop in start.sh and system build tools
-RUN apt-get update && apt-get install -y --no-install-recommends \
+RUN apt-get update \
+    && apt-get install -y -f \
+    && apt-get install -y --no-install-recommends \
     netcat-openbsd \
     git \
     build-essential \

api/analyzers/analyzer.py

@@ -57,6 +57,12 @@ def resolve(self, files: dict[Path, File], lsp: SyncLanguageServer, file_path: P
             locations = lsp.request_definition(str(file_path), node.start_point.row, node.start_point.column)
             return [(files[Path(self.resolve_path(location['absolutePath'], path))], files[Path(self.resolve_path(location['absolutePath'], path))].tree.root_node.descendant_for_point_range(Point(location['range']['start']['line'], location['range']['start']['character']), Point(location['range']['end']['line'], location['range']['end']['character']))) for location in locations if location and Path(self.resolve_path(location['absolutePath'], path)) in files]
         except Exception:
+            import logging
+            logging.getLogger(__name__).warning(
+                "resolve() failed for %s @%d:%d",
+                file_path, node.start_point.row, node.start_point.column,
+                exc_info=True,
+            )
             return []
 
     @abstractmethod

api/analyzers/source_analyzer.py

@@ -19,6 +19,7 @@
 from multilspy.multilspy_logger import MultilspyLogger
 
 import logging
+import sys
 # Configure logging
 logging.basicConfig(level=logging.DEBUG, format='%(filename)s - %(asctime)s - %(levelname)s - %(message)s')
 
@@ -164,7 +165,29 @@ def second_pass(self, graph: Graph, files: list[Path], path: Path) -> None:
         else:
             lsps[".java"] = NullLanguageServer()
         if any(path.rglob('*.py')):
-            config = MultilspyConfig.from_dict({"code_language": "python", "environment_path": f"{path}/venv"})
+            py_venv = path / "venv"
+            py_dotvenv = path / ".venv"
+            if py_venv.is_dir() and (py_venv / "bin" / "python").exists():
+                env_path = str(py_venv)
+            elif py_dotvenv.is_dir() and (py_dotvenv / "bin" / "python").exists():
+                env_path = str(py_dotvenv)
+            else:
+                # Fall back to the host's Python environment so jedi has a
+                # valid interpreter to introspect; otherwise every
+                # request_definition() raises InvalidPythonEnvironment and
+                # we'd silently produce a graph with zero CALLS edges.
+                # sys.prefix is the active environment root and is more
+                # reliable than deriving it from sys.executable (which breaks
+                # when the interpreter is a wrapper/shim).
+                env_path = sys.prefix
+                logging.info(
+                    "No venv at %s; falling back to host env %s for jedi LSP",
+                    path, env_path,
+                )
+            config = MultilspyConfig.from_dict({
+                "code_language": "python",
+                "environment_path": env_path,
+            })
             lsps[".py"] = SyncLanguageServer.create(config, logger, str(path))
         else:
             lsps[".py"] = NullLanguageServer()
@@ -189,6 +212,14 @@ def second_pass(self, graph: Graph, files: list[Path], path: Path) -> None:
             resolvable: list[Path] = []
             for file_path in files:
                 if file_path not in self.files:
+                    # first_pass skipped this file (e.g. parse error, empty,
+                    # untracked, or ignored after entering the candidate list).
+                    # Skip in second_pass too instead of crashing the whole
+                    # index.
+                    logging.warning(
+                        "second_pass: %s not in files map (first_pass skipped it); skipping",
+                        file_path,
+                    )
                     continue
                 if isinstance(lsps.get(file_path.suffix), NullLanguageServer):
                     continue
@@ -287,21 +318,26 @@ def analyze_local_folder(self, path: str, g: Graph, ignore: Optional[list[str]]
 
         logging.info("Done analyzing path")
 
-    def analyze_local_repository(self, path: str, ignore: Optional[list[str]] = None) -> Graph:
+    def analyze_local_repository(self, path: str, ignore: Optional[list[str]] = None, branch: Optional[str] = None) -> Graph:
         """
         Analyze a local Git repository.
 
         Args:
             path (str): Path to a local git repository
             ignore (List(str)): List of paths to skip
+            branch (Optional[str]): Branch name. Auto-detected from the
+                checkout when ``None``.
         """
         if ignore is None:
             ignore = []
 
         from pygit2.repository import Repository
+        from ..project import detect_branch
 
         proj_name = Path(path).name
-        graph = Graph(proj_name)
+        if branch is None:
+            branch = detect_branch(Path(path))
+        graph = Graph(proj_name, branch=branch)
         self.analyze_local_folder(path, graph, ignore)
 
         # Save processed commit hash to the DB

api/auto_complete.py

@@ -1,15 +1,17 @@
+from typing import Optional
+
 from .graph import Graph, AsyncGraphQuery
 
 
-def prefix_search(repo: str, prefix: str) -> str:
+def prefix_search(repo: str, prefix: str, branch: Optional[str] = None) -> str:
     """ Returns a list of all entities in the repository that start with the given prefix. """
-    g = Graph(repo)
+    g = Graph(repo, branch=branch)
     return g.prefix_search(prefix)
 
 
-async def async_prefix_search(repo: str, prefix: str) -> list:
+async def async_prefix_search(repo: str, prefix: str, branch: Optional[str] = None) -> list:
     """Async version of prefix_search using AsyncGraphQuery."""
-    g = AsyncGraphQuery(repo)
+    g = AsyncGraphQuery(repo, branch=branch)
     try:
         return await g.prefix_search(prefix)
     finally: