codexa 0.4.1__tar.gz → 0.4.3__tar.gz

{codexa-0.4.1 → codexa-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codexa
-Version: 0.4.1
+Version: 0.4.3
 Summary: Developer intelligence CLI — semantic code search, AI-assisted understanding, and agent tooling for codebases
 License: MIT
 Project-URL: Homepage, https://codex-a.dev
@@ -28,7 +28,18 @@ License-File: LICENSE
 Requires-Dist: click>=8.1.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: rich>=13.0.0
+Requires-Dist: numpy>=1.24.0
 Requires-Dist: tree-sitter>=0.21.0
+Requires-Dist: tree-sitter-python>=0.21.0
+Requires-Dist: tree-sitter-javascript>=0.21.0
+Requires-Dist: tree-sitter-typescript>=0.21.0
+Requires-Dist: tree-sitter-java>=0.21.0
+Requires-Dist: tree-sitter-go>=0.21.0
+Requires-Dist: tree-sitter-rust>=0.21.0
+Requires-Dist: tree-sitter-cpp>=0.21.0
+Requires-Dist: tree-sitter-c-sharp>=0.21.0
+Requires-Dist: tree-sitter-ruby>=0.21.0
+Requires-Dist: tree-sitter-php>=0.22.0
 Requires-Dist: radon>=6.0.0
 Requires-Dist: bandit>=1.7.0
 Requires-Dist: mcp>=1.0.0
@@ -55,7 +66,7 @@ Dynamic: license-file
 <p align="center">
   <a href="https://github.com/M9nx/CodexA/actions"><img src="https://github.com/M9nx/CodexA/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
-  <img src="https://img.shields.io/badge/version-0.4.0-green" alt="Version">
+  <img src="https://img.shields.io/badge/version-0.4.3-green" alt="Version">
   <img src="https://img.shields.io/badge/tests-2595-brightgreen" alt="Tests">
   <img src="https://img.shields.io/badge/coverage-79%25-brightgreen" alt="Coverage">
   <img src="https://img.shields.io/badge/mypy-strict-blue" alt="mypy strict">
@@ -95,6 +106,12 @@ structured tool protocol that any AI agent can call over HTTP or CLI.
 pip install codexa
 ```
 
+For semantic indexing and vector search, install the ML extras:
+
+```bash
+pip install "codexa[ml]"
+```
+
 Or install from source:
 
 ```bash
@@ -133,6 +150,23 @@ codexa index .
 
 This parses all source files (Python, JS/TS, Java, Go, Rust, C#, Ruby, C++),
 extracts symbols, generates embeddings, and stores them in a local FAISS index.
+Semantic indexing requires `codexa[ml]`.
+
+If you need to keep secrets, generated files, or local config files out of the
+index, add patterns to `.codexaignore` at the project root or configure
+`index.exclude_files` in `.codexa/config.json`.
+
+Typical `.codexaignore` example:
+
+```text
+.env*
+secrets/*.json
+config/local-*.yml
+vendor/*
+```
+
+The default embedding model is small, but the PyTorch backend still needs about
+2 GB of available RAM. On lower-memory machines, prefer the ONNX backend.
 
 ### 4. Semantic Search
 
@@ -250,7 +284,7 @@ cd CodexA
 pip install -e ".[dev]"
 
 # Verify
-codexa --version    # → codexa, version 0.4.0
+codexa --version    # → codexa, version 0.4.3
 ```
 
 ### Step 2 — Initialize your target project

{codexa-0.4.1 → codexa-0.4.3}/README.md

@@ -6,7 +6,7 @@
 <p align="center">
   <a href="https://github.com/M9nx/CodexA/actions"><img src="https://github.com/M9nx/CodexA/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
-  <img src="https://img.shields.io/badge/version-0.4.0-green" alt="Version">
+  <img src="https://img.shields.io/badge/version-0.4.3-green" alt="Version">
   <img src="https://img.shields.io/badge/tests-2595-brightgreen" alt="Tests">
   <img src="https://img.shields.io/badge/coverage-79%25-brightgreen" alt="Coverage">
   <img src="https://img.shields.io/badge/mypy-strict-blue" alt="mypy strict">
@@ -46,6 +46,12 @@ structured tool protocol that any AI agent can call over HTTP or CLI.
 pip install codexa
 ```
 
+For semantic indexing and vector search, install the ML extras:
+
+```bash
+pip install "codexa[ml]"
+```
+
 Or install from source:
 
 ```bash
@@ -84,6 +90,23 @@ codexa index .
 
 This parses all source files (Python, JS/TS, Java, Go, Rust, C#, Ruby, C++),
 extracts symbols, generates embeddings, and stores them in a local FAISS index.
+Semantic indexing requires `codexa[ml]`.
+
+If you need to keep secrets, generated files, or local config files out of the
+index, add patterns to `.codexaignore` at the project root or configure
+`index.exclude_files` in `.codexa/config.json`.
+
+Typical `.codexaignore` example:
+
+```text
+.env*
+secrets/*.json
+config/local-*.yml
+vendor/*
+```
+
+The default embedding model is small, but the PyTorch backend still needs about
+2 GB of available RAM. On lower-memory machines, prefer the ONNX backend.
 
 ### 4. Semantic Search
 
@@ -201,7 +224,7 @@ cd CodexA
 pip install -e ".[dev]"
 
 # Verify
-codexa --version    # → codexa, version 0.4.0
+codexa --version    # → codexa, version 0.4.3
 ```
 
 ### Step 2 — Initialize your target project

{codexa-0.4.1 → codexa-0.4.3}/codexa.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codexa
-Version: 0.4.1
+Version: 0.4.3
 Summary: Developer intelligence CLI — semantic code search, AI-assisted understanding, and agent tooling for codebases
 License: MIT
 Project-URL: Homepage, https://codex-a.dev
@@ -28,7 +28,18 @@ License-File: LICENSE
 Requires-Dist: click>=8.1.0
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: rich>=13.0.0
+Requires-Dist: numpy>=1.24.0
 Requires-Dist: tree-sitter>=0.21.0
+Requires-Dist: tree-sitter-python>=0.21.0
+Requires-Dist: tree-sitter-javascript>=0.21.0
+Requires-Dist: tree-sitter-typescript>=0.21.0
+Requires-Dist: tree-sitter-java>=0.21.0
+Requires-Dist: tree-sitter-go>=0.21.0
+Requires-Dist: tree-sitter-rust>=0.21.0
+Requires-Dist: tree-sitter-cpp>=0.21.0
+Requires-Dist: tree-sitter-c-sharp>=0.21.0
+Requires-Dist: tree-sitter-ruby>=0.21.0
+Requires-Dist: tree-sitter-php>=0.22.0
 Requires-Dist: radon>=6.0.0
 Requires-Dist: bandit>=1.7.0
 Requires-Dist: mcp>=1.0.0
@@ -55,7 +66,7 @@ Dynamic: license-file
 <p align="center">
   <a href="https://github.com/M9nx/CodexA/actions"><img src="https://github.com/M9nx/CodexA/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%2B-blue" alt="Python 3.11+">
-  <img src="https://img.shields.io/badge/version-0.4.0-green" alt="Version">
+  <img src="https://img.shields.io/badge/version-0.4.3-green" alt="Version">
   <img src="https://img.shields.io/badge/tests-2595-brightgreen" alt="Tests">
   <img src="https://img.shields.io/badge/coverage-79%25-brightgreen" alt="Coverage">
   <img src="https://img.shields.io/badge/mypy-strict-blue" alt="mypy strict">
@@ -95,6 +106,12 @@ structured tool protocol that any AI agent can call over HTTP or CLI.
 pip install codexa
 ```
 
+For semantic indexing and vector search, install the ML extras:
+
+```bash
+pip install "codexa[ml]"
+```
+
 Or install from source:
 
 ```bash
@@ -133,6 +150,23 @@ codexa index .
 
 This parses all source files (Python, JS/TS, Java, Go, Rust, C#, Ruby, C++),
 extracts symbols, generates embeddings, and stores them in a local FAISS index.
+Semantic indexing requires `codexa[ml]`.
+
+If you need to keep secrets, generated files, or local config files out of the
+index, add patterns to `.codexaignore` at the project root or configure
+`index.exclude_files` in `.codexa/config.json`.
+
+Typical `.codexaignore` example:
+
+```text
+.env*
+secrets/*.json
+config/local-*.yml
+vendor/*
+```
+
+The default embedding model is small, but the PyTorch backend still needs about
+2 GB of available RAM. On lower-memory machines, prefer the ONNX backend.
 
 ### 4. Semantic Search
 
@@ -250,7 +284,7 @@ cd CodexA
 pip install -e ".[dev]"
 
 # Verify
-codexa --version    # → codexa, version 0.4.0
+codexa --version    # → codexa, version 0.4.3
 ```
 
 ### Step 2 — Initialize your target project

{codexa-0.4.1 → codexa-0.4.3}/codexa.egg-info/requires.txt

@@ -1,7 +1,18 @@
 click>=8.1.0
 pydantic>=2.0.0
 rich>=13.0.0
+numpy>=1.24.0
 tree-sitter>=0.21.0
+tree-sitter-python>=0.21.0
+tree-sitter-javascript>=0.21.0
+tree-sitter-typescript>=0.21.0
+tree-sitter-java>=0.21.0
+tree-sitter-go>=0.21.0
+tree-sitter-rust>=0.21.0
+tree-sitter-cpp>=0.21.0
+tree-sitter-c-sharp>=0.21.0
+tree-sitter-ruby>=0.21.0
+tree-sitter-php>=0.22.0
 radon>=6.0.0
 bandit>=1.7.0
 mcp>=1.0.0

{codexa-0.4.1 → codexa-0.4.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "codexa"
-version = "0.4.1"
+version = "0.4.3"
 description = "Developer intelligence CLI — semantic code search, AI-assisted understanding, and agent tooling for codebases"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -40,7 +40,18 @@ dependencies = [
     "click>=8.1.0",
     "pydantic>=2.0.0",
     "rich>=13.0.0",
+    "numpy>=1.24.0",
     "tree-sitter>=0.21.0",
+    "tree-sitter-python>=0.21.0",
+    "tree-sitter-javascript>=0.21.0",
+    "tree-sitter-typescript>=0.21.0",
+    "tree-sitter-java>=0.21.0",
+    "tree-sitter-go>=0.21.0",
+    "tree-sitter-rust>=0.21.0",
+    "tree-sitter-cpp>=0.21.0",
+    "tree-sitter-c-sharp>=0.21.0",
+    "tree-sitter-ruby>=0.21.0",
+    "tree-sitter-php>=0.22.0",
     "radon>=6.0.0",
     "bandit>=1.7.0",
     "mcp>=1.0.0",

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/cli/commands/index_cmd.py

@@ -122,6 +122,11 @@ def index_cmd(ctx: click.Context, path: str, force: bool, watch: bool) -> None:
 
     try:
         result = run_indexing(project_root=root, force=force)
+    except MemoryError as e:
+        print_error(f"Indexing failed: {e}")
+        print_info("Tip: semantic indexing needs the ML extras and enough RAM. Install with 'pip install codexa[ml]' and prefer ONNX or a machine with at least 2 GB available RAM.")
+        ctx.exit(1)
+        return
     except Exception as e:
         print_error(f"Indexing failed: {e}")
         logger.debug("Indexing error details:", exc_info=True)

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/cli/commands/init_cmd.py

@@ -131,9 +131,11 @@ def init_cmd(ctx: click.Context, path: str, auto_index: bool, setup_vscode: bool
     else:
         print_info("")
         print_info("Next steps:")
+        print_info("  pip install 'codexa[ml]'  — Enable semantic indexing and vector search")
         print_info("  codexa index    — Build the search index")
         print_info("  codexa search   — Search your code")
         print_info("  codexa grep     — Raw file search (no index needed)")
+        print_info("  .codexaignore   — Exclude secrets or generated files from indexing")
 
 
 def _run_index(root: Path) -> None:
@@ -147,6 +149,9 @@ def _run_index(root: Path) -> None:
             f"Indexed {result.chunks_stored} chunks from "
             f"{result.files_scanned} files"
         )
+    except MemoryError as e:
+        print_warning(f"Indexing failed: {e}")
+        print_info("Tip: install 'codexa[ml]' for semantic indexing and use a machine with at least 2 GB available RAM, or prefer the ONNX backend.")
     except Exception as e:
         print_warning(f"Indexing failed: {e}")
         print_info("Run 'codexa index' manually to build the index.")

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/config/settings.py

@@ -100,6 +100,10 @@ class IndexConfig(BaseModel):
 
     ignore_dirs: set[str] = Field(default_factory=lambda: DEFAULT_IGNORE_DIRS.copy())
     extensions: set[str] = Field(default_factory=lambda: DEFAULT_EXTENSIONS.copy())
+    exclude_files: set[str] = Field(
+        default_factory=set,
+        description="Glob patterns for files to exclude from indexing.",
+    )
     use_incremental: bool = Field(
         default=True,
         description="Enable incremental indexing using file hashes.",

codexa-0.4.3/semantic_code_intelligence/embeddings/generator.py

@@ -0,0 +1,269 @@
+"""Embedding generator — converts code chunks into vector embeddings.
+
+Supports two backends:
+- **sentence-transformers** (default): PyTorch-based, full-featured.
+- **onnx**: Lightweight ONNX Runtime backend via ``optimum`` — lower
+  memory (~50% less) and often faster inference on CPU.
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+from pathlib import Path
+import sys
+from typing import TYPE_CHECKING, Any
+
+import numpy as np
+
+from semantic_code_intelligence.embeddings.model_registry import resolve_model_name
+from semantic_code_intelligence.utils.logging import get_logger
+
+if TYPE_CHECKING:
+    from sentence_transformers import SentenceTransformer
+
+logger = get_logger("embeddings")
+
+# Module-level cache for loaded model instances
+_model_cache: dict[str, "SentenceTransformer"] = {}
+_MIN_TORCH_RAM_BYTES = 2 * 1024 * 1024 * 1024
+
+
+def _configure_hf_token() -> None:
+    """Set HF_TOKEN from common env vars if not already set.
+
+    Checks ``HF_TOKEN``, ``HUGGING_FACE_HUB_TOKEN``, and
+    ``HUGGINGFACE_TOKEN`` so the user only needs to export one.
+    """
+    if os.environ.get("HF_TOKEN"):
+        return
+    for var in ("HUGGING_FACE_HUB_TOKEN", "HUGGINGFACE_TOKEN"):
+        value = os.environ.get(var)
+        if value:
+            os.environ["HF_TOKEN"] = value
+            return
+
+
+def _onnx_available() -> bool:
+    """Check if the ONNX Runtime backend is available."""
+    try:
+        import optimum  # noqa: F401
+        import onnxruntime  # noqa: F401
+        return True
+    except ImportError:
+        return False
+
+
+def _model_cached_locally(model_name: str) -> bool:
+    """Check if a HuggingFace model is already downloaded to the local cache.
+
+    Looks in the standard ``HF_HOME`` / ``TRANSFORMERS_CACHE`` directory
+    for a snapshot of the model so we can skip network calls when loading.
+    """
+    try:
+        from huggingface_hub import try_to_load_from_cache
+        # Check for key model file in the cache
+        result = try_to_load_from_cache(model_name, "config.json")
+        return isinstance(result, str)  # str path means it's cached
+    except Exception:
+        # Also check via the default HF cache directory structure
+        hf_home = Path(os.environ.get("HF_HOME", Path.home() / ".cache" / "huggingface"))
+        hub_dir = hf_home / "hub"
+        if not hub_dir.exists():
+            return False
+        # HF stores models as models--org--name
+        model_dir_name = "models--" + model_name.replace("/", "--")
+        model_dir = hub_dir / model_dir_name
+        return model_dir.exists() and any(model_dir.rglob("config.json"))
+
+
+def _get_available_memory_bytes() -> int | None:
+    """Return approximate available system memory, if detectable."""
+    if sys.platform.startswith("linux"):
+        try:
+            with open("/proc/meminfo", encoding="utf-8") as handle:
+                for line in handle:
+                    if line.startswith("MemAvailable:"):
+                        parts = line.split()
+                        return int(parts[1]) * 1024
+        except OSError:
+            return None
+
+    if sys.platform == "win32":
+        try:
+            import ctypes
+
+            class MEMORYSTATUSEX(ctypes.Structure):
+                _fields_ = [
+                    ("dwLength", ctypes.c_ulong),
+                    ("dwMemoryLoad", ctypes.c_ulong),
+                    ("ullTotalPhys", ctypes.c_ulonglong),
+                    ("ullAvailPhys", ctypes.c_ulonglong),
+                    ("ullTotalPageFile", ctypes.c_ulonglong),
+                    ("ullAvailPageFile", ctypes.c_ulonglong),
+                    ("ullTotalVirtual", ctypes.c_ulonglong),
+                    ("ullAvailVirtual", ctypes.c_ulonglong),
+                    ("sullAvailExtendedVirtual", ctypes.c_ulonglong),
+                ]
+
+            status = MEMORYSTATUSEX()
+            status.dwLength = ctypes.sizeof(MEMORYSTATUSEX)
+            if ctypes.windll.kernel32.GlobalMemoryStatusEx(ctypes.byref(status)):
+                return int(status.ullAvailPhys)
+        except Exception:
+            return None
+
+    return None
+
+
+def _check_memory_requirements(use_onnx: bool) -> None:
+    """Warn on low-memory systems when using the torch backend."""
+    if use_onnx:
+        return
+
+    available_memory = _get_available_memory_bytes()
+    if available_memory is None or available_memory >= _MIN_TORCH_RAM_BYTES:
+        return
+
+    available_gb = available_memory / (1024 * 1024 * 1024)
+    required_gb = _MIN_TORCH_RAM_BYTES / (1024 * 1024 * 1024)
+    logger.warning(
+        "Low available RAM detected for the PyTorch embedding backend "
+        "(%.1f GB available, about %.0f GB recommended). If indexing fails, "
+        "prefer the ONNX backend or a machine with more memory.",
+        available_gb,
+        required_gb,
+    )
+
+
+def get_model(
+    model_name: str = "all-MiniLM-L6-v2",
+    backend: str = "auto",
+) -> "SentenceTransformer":
+    """Load and cache a sentence-transformers model.
+
+    Args:
+        model_name: Name of the model to load (full HF name or alias).
+        backend: ``"auto"`` (ONNX if available, else PyTorch),
+                 ``"onnx"``, or ``"torch"``.
+
+    Returns:
+        A SentenceTransformer model instance.
+    """
+    model_name = resolve_model_name(model_name)
+    cache_key = f"{model_name}:{backend}"
+
+    if cache_key not in _model_cache:
+        _configure_hf_token()
+        try:
+            from sentence_transformers import SentenceTransformer
+        except ImportError:
+            raise ImportError(
+                "sentence-transformers is required for embeddings. "
+                "Install it with: pip install codexa[ml]"
+            ) from None
+
+        # Suppress noisy HuggingFace Hub HTTP logs when model is cached
+        local_only = _model_cached_locally(model_name)
+        if local_only:
+            logger.debug("Model %s found in local cache — skipping network checks.", model_name)
+        # Quieten HF/transformers loggers that spam HTTP HEAD requests
+        for noisy_logger in ("huggingface_hub", "transformers", "sentence_transformers"):
+            logging.getLogger(noisy_logger).setLevel(logging.WARNING)
+
+        use_onnx = False
+        if backend == "onnx":
+            if _onnx_available():
+                use_onnx = True
+            else:
+                logger.warning("ONNX requested but optimum/onnxruntime not installed; falling back to PyTorch.")
+        elif backend == "auto" and _onnx_available():
+            use_onnx = True
+
+        _check_memory_requirements(use_onnx)
+
+        logger.info("Loading embedding model: %s (backend=%s)", model_name, "onnx" if use_onnx else "torch")
+
+        load_kwargs: dict[str, Any] = {}
+        if local_only:
+            load_kwargs["local_files_only"] = True
+
+        if use_onnx:
+            try:
+                _model_cache[cache_key] = SentenceTransformer(model_name, backend="onnx", **load_kwargs)
+                logger.info("Model loaded with ONNX backend.")
+                return _model_cache[cache_key]
+            except Exception:
+                logger.warning("ONNX load failed; falling back to PyTorch.")
+
+        try:
+            _model_cache[cache_key] = SentenceTransformer(model_name, **load_kwargs)
+        except OSError:
+            if local_only:
+                # Cache may be corrupted — retry with network access
+                logger.warning("Local cache load failed; re-downloading model.")
+                _model_cache[cache_key] = SentenceTransformer(model_name)
+            else:
+                raise
+        except RuntimeError as exc:
+            if "out of memory" in str(exc).lower():
+                raise MemoryError(
+                    "Embedding model loading ran out of memory. Try the ONNX backend or use a machine with at least 2 GB of available RAM."
+                ) from exc
+            raise
+        logger.info("Model loaded successfully (PyTorch).")
+
+    return _model_cache[cache_key]
+
+
+def generate_embeddings(
+    texts: list[str],
+    model_name: str = "all-MiniLM-L6-v2",
+    batch_size: int = 64,
+    show_progress: bool = False,
+    backend: str = "auto",
+) -> np.ndarray:
+    """Generate vector embeddings for a list of text strings.
+
+    Args:
+        texts: List of code/text strings to embed.
+        model_name: Name of the sentence-transformers model (or alias).
+        batch_size: Batch size for encoding.
+        show_progress: Whether to show a progress bar.
+        backend: ``"auto"``, ``"onnx"``, or ``"torch"``.
+
+    Returns:
+        NumPy array of shape (len(texts), embedding_dim).
+    """
+    if not texts:
+        return np.array([], dtype=np.float32).reshape(0, 0)
+
+    model = get_model(model_name, backend=backend)
+    embeddings = model.encode(
+        texts,
+        batch_size=batch_size,
+        show_progress_bar=show_progress,
+        convert_to_numpy=True,
+        normalize_embeddings=True,
+    )
+    return embeddings.astype(np.float32)
+
+
+def get_embedding_dimension(
+    model_name: str = "all-MiniLM-L6-v2",
+    backend: str = "auto",
+) -> int:
+    """Return the dimensionality of embeddings produced by the given model.
+
+    Args:
+        model_name: Name of the sentence-transformers model (or alias).
+        backend: ``"auto"``, ``"onnx"``, or ``"torch"``.
+
+    Returns:
+        Integer dimension of the embedding vectors.
+    """
+    model = get_model(model_name, backend=backend)
+    dim = model.get_sentence_embedding_dimension()
+    if dim is None:
+        raise RuntimeError(f"Model {model_name!r} returned None for embedding dimension")
+    return dim

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/indexing/scanner.py

@@ -108,6 +108,7 @@ def scan_repository(
 
     root = root.resolve()
     ignore_patterns = _load_ignore_patterns(root)
+    config_exclude_patterns = [pattern.replace("\\", "/") for pattern in index_config.exclude_files]
     results: list[ScannedFile] = []
 
     for file_path in sorted(root.rglob("*")):
@@ -127,6 +128,8 @@ def scan_repository(
             continue
         if ignore_patterns and _matches_ignore_patterns(rel, ignore_patterns):
             continue
+        if config_exclude_patterns and _matches_ignore_patterns(rel, config_exclude_patterns):
+            continue
 
         try:
             size = file_path.stat().st_size

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/tests/test_cli.py

@@ -38,7 +38,7 @@ class TestCLIMain:
     def test_cli_version(self, runner: CliRunner):
         result = runner.invoke(cli, ["--version"])
         assert result.exit_code == 0
-        assert "0.4.1" in result.output
+        assert "0.4.3" in result.output
 
     def test_cli_verbose_flag(self, runner: CliRunner):
         result = runner.invoke(cli, ["--verbose", "--help"])
@@ -186,3 +186,4 @@ class TestCommandRouting:
     def test_unknown_command_fails(self, runner: CliRunner):
         result = runner.invoke(cli, ["nonexistent"])
         assert result.exit_code != 0
+

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/tests/test_config.py

@@ -38,6 +38,7 @@ class TestDefaultConfigs:
         cfg = IndexConfig()
         assert cfg.ignore_dirs == DEFAULT_IGNORE_DIRS
         assert cfg.extensions == DEFAULT_EXTENSIONS
+        assert cfg.exclude_files == set()
         assert cfg.use_incremental is True
 
     def test_app_config_defaults(self):

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/tests/test_phase13.py

@@ -492,7 +492,7 @@ class TestPipelineMode:
     def test_version_option(self):
         runner = CliRunner()
         result = runner.invoke(cli, ["--version"])
-        assert "0.4.1" in result.output
+        assert "0.4.3" in result.output
 
 
 # =========================================================================
@@ -652,7 +652,7 @@ class TestProjectMetadata:
 
     def test_version_is_0_13(self):
         from semantic_code_intelligence import __version__
-        assert __version__ == "0.4.1"
+        assert __version__ == "0.4.3"
 
     def test_app_name(self):
         from semantic_code_intelligence import __app_name__
@@ -661,3 +661,4 @@ class TestProjectMetadata:
     def test_pyproject_exists(self):
         root = Path(__file__).resolve().parent.parent.parent
         assert (root / "pyproject.toml").is_file()
+

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/tests/test_phase14.py

@@ -515,7 +515,7 @@ class TestRouterPhase14:
 class TestVersionBump:
     def test_version_is_014(self):
         from semantic_code_intelligence import __version__
-        assert __version__ == "0.4.1"
+        assert __version__ == "0.4.3"
 
 
 # =========================================================================
@@ -566,3 +566,4 @@ class TestWebServerBackground:
         assert server._thread is None
         # stop() should be safe when not started
         server.stop()
+

{codexa-0.4.1 → codexa-0.4.3}/semantic_code_intelligence/tests/test_phase15.py

@@ -713,7 +713,7 @@ class TestVersionBump:
     def test_version_is_015(self):
         from semantic_code_intelligence import __version__
 
-        assert __version__ == "0.4.1"
+        assert __version__ == "0.4.3"
 
 
 class TestCIModuleStructure:
@@ -812,3 +812,4 @@ class TestBackwardCompatibility:
         validator = SafetyValidator()
         report = validator.validate("x = 1\n")
         assert report.safe is True
+