code-graph-rag 0.0.945__tar.gz → 0.1.38__tar.gz

{code_graph_rag-0.0.945/code_graph_rag.egg-info → code_graph_rag-0.1.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.0.945
+Version: 0.1.38
 Summary: The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
 License-Expression: MIT
 Keywords: rag,retrieval-augmented-generation,knowledge-graph,code-analysis,tree-sitter,mcp,mcp-server,llm,graph-database,semantic-search,codebase,memgraph,developer-tools,monorepo
@@ -20,14 +20,14 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp>=1.28.1
-Requires-Dist: pydantic-ai>=2.0.0
+Requires-Dist: pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
 Requires-Dist: pymgclient>=1.5.1
 Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: tiktoken>=0.12.0
-Requires-Dist: toml>=0.10.2
+Requires-Dist: tomli-w>=1.2.0
 Requires-Dist: tree-sitter-python>=0.25.0
-Requires-Dist: tree-sitter==0.25.2
+Requires-Dist: tree-sitter==0.26.0
 Requires-Dist: watchdog>=6.0.0
 Requires-Dist: typer>=0.21.1
 Requires-Dist: rich>=14.2.0
@@ -67,13 +67,13 @@ Requires-Dist: tree-sitter-cpp>=0.23.0; extra == "treesitter-full"
 Requires-Dist: tree-sitter-lua>=0.0.19; extra == "treesitter-full"
 Requires-Dist: tree-sitter-php>=0.24.1; extra == "treesitter-full"
 Requires-Dist: tree-sitter-c-sharp>=0.23.5; extra == "treesitter-full"
-Requires-Dist: tree-sitter-dart>=0.1.0; extra == "treesitter-full"
+Requires-Dist: tree-sitter-dart==0.1.0; extra == "treesitter-full"
 Requires-Dist: tree-sitter-sql>=0.3.11; extra == "treesitter-full"
 Requires-Dist: tree-sitter-markdown>=0.5.1; extra == "treesitter-full"
 Provides-Extra: semantic
 Requires-Dist: qdrant-client>=1.9.0; extra == "semantic"
 Requires-Dist: torch>=2.6.0; extra == "semantic"
-Requires-Dist: transformers>=4.0.0; extra == "semantic"
+Requires-Dist: transformers>=5.0.0; extra == "semantic"
 Provides-Extra: milvus
 Requires-Dist: pymilvus[milvus-lite]>=3.0.0; extra == "milvus"
 Provides-Extra: ast-grep
@@ -85,7 +85,7 @@ Dynamic: license-file
 
 # Code-Graph-RAG
 
-Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
+Code-Graph-RAG parses a multi-language codebase with Tree-sitter, sharpened by compiler-grade frontends and runtime traces where available, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
 
 ## What It Does
 
@@ -142,12 +142,23 @@ uploads and GitHub Release binaries land on an every-50 cadence, so the tag on `
 usually runs ahead of the published version. A security fix is the exception: it
 ships immediately rather than waiting for the cadence.
 
-To run code newer than the latest release, install from git:
+To run code newer than the latest release, install from git with uv:
 
 ```bash
-pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
+uv tool install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
 ```
 
+Use uv for this: it applies the project's `[tool.uv.sources]`, which build the C
+and C++ grammars from forks that keep the declarations upstream drops after a
+`#define` whose value contains a block comment. `pip` ignores those sources and
+installs the upstream grammars.
+
+To upgrade, rerun the install with `--upgrade` and the extras you chose, for
+example `pip install --upgrade 'code-graph-rag[treesitter-full]'`. With uv or pipx,
+run `uv tool upgrade code-graph-rag` or `pipx upgrade code-graph-rag` instead; see the
+[installation guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#upgrade)
+for git installs and the other methods.
+
 ### Prerequisites
 
 - Python 3.12+
@@ -155,15 +166,12 @@ pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/c
 - `cmake` (for building pymgclient)
 - `ripgrep` (`rg`) (for shell command text searching)
 
-The wheel is pure Python (`py3-none-any`), so the package itself installs on
-any platform with Python 3.12 or newer (dependencies may still need platform
-wheels or build tools, such as `cmake` for `pymgclient`). The piwheels build for Debian Bookworm shows as failed
-because Bookworm's system Python is 3.11, which is below our floor. On
-Raspberry Pi OS Bookworm, install into a Python 3.12 environment so the pip
-commands above actually run under 3.12: with [uv](https://docs.astral.sh/uv/)
-run `uv venv --python 3.12 --seed && source .venv/bin/activate` (uv downloads
-3.12 automatically; `--seed` puts pip in the environment), or install CPython 3.12 yourself and use
-`python3.12 -m pip install ...`.
+The wheel is pure Python (`py3-none-any`), so it installs on any platform with
+Python 3.12 or newer. Some distributions ship an older interpreter (Debian
+Bookworm, and so Raspberry Pi OS Bookworm, ships 3.11), which also explains the
+failed piwheels Bookworm build. On those systems, see the [installation
+guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#older-system-interpreters)
+for the available interpreter-pinning alternatives.
 
 ## CLI Quick Start
 

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38}/PYPI_README.md

@@ -1,6 +1,6 @@
 # Code-Graph-RAG
 
-Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
+Code-Graph-RAG parses a multi-language codebase with Tree-sitter, sharpened by compiler-grade frontends and runtime traces where available, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
 
 ## What It Does
 
@@ -57,12 +57,23 @@ uploads and GitHub Release binaries land on an every-50 cadence, so the tag on `
 usually runs ahead of the published version. A security fix is the exception: it
 ships immediately rather than waiting for the cadence.
 
-To run code newer than the latest release, install from git:
+To run code newer than the latest release, install from git with uv:
 
 ```bash
-pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
+uv tool install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
 ```
 
+Use uv for this: it applies the project's `[tool.uv.sources]`, which build the C
+and C++ grammars from forks that keep the declarations upstream drops after a
+`#define` whose value contains a block comment. `pip` ignores those sources and
+installs the upstream grammars.
+
+To upgrade, rerun the install with `--upgrade` and the extras you chose, for
+example `pip install --upgrade 'code-graph-rag[treesitter-full]'`. With uv or pipx,
+run `uv tool upgrade code-graph-rag` or `pipx upgrade code-graph-rag` instead; see the
+[installation guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#upgrade)
+for git installs and the other methods.
+
 ### Prerequisites
 
 - Python 3.12+
@@ -70,15 +81,12 @@ pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/c
 - `cmake` (for building pymgclient)
 - `ripgrep` (`rg`) (for shell command text searching)
 
-The wheel is pure Python (`py3-none-any`), so the package itself installs on
-any platform with Python 3.12 or newer (dependencies may still need platform
-wheels or build tools, such as `cmake` for `pymgclient`). The piwheels build for Debian Bookworm shows as failed
-because Bookworm's system Python is 3.11, which is below our floor. On
-Raspberry Pi OS Bookworm, install into a Python 3.12 environment so the pip
-commands above actually run under 3.12: with [uv](https://docs.astral.sh/uv/)
-run `uv venv --python 3.12 --seed && source .venv/bin/activate` (uv downloads
-3.12 automatically; `--seed` puts pip in the environment), or install CPython 3.12 yourself and use
-`python3.12 -m pip install ...`.
+The wheel is pure Python (`py3-none-any`), so it installs on any platform with
+Python 3.12 or newer. Some distributions ship an older interpreter (Debian
+Bookworm, and so Raspberry Pi OS Bookworm, ships 3.11), which also explains the
+failed piwheels Bookworm build. On those systems, see the [installation
+guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#older-system-interpreters)
+for the available interpreter-pinning alternatives.
 
 ## CLI Quick Start
 

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38}/README.md

@@ -42,18 +42,26 @@
 
 # Code-Graph-RAG
 
-Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
+Code-Graph-RAG parses a multi-language codebase with Tree-sitter, sharpened by compiler-grade frontends and runtime traces where available, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
 
 <p align="center">
-  <img src="./assets/demo.gif" alt="demo">
+  <b>1. Index:</b> <code>cgr start --update-graph</code> parses a repository into a knowledge graph (sped up)
+</p>
+<p align="center">
+  <img src="./assets/demo-indexing.gif" alt="cgr parsing the code-graph-rag repository into a Memgraph knowledge graph, then printing node and relationship counts">
+</p>
+
+<p align="center">
+  <b>2. Ask:</b> <code>cgr start</code> answers questions and edits code, grounded in that graph
+</p>
+<p align="center">
+  <img src="./assets/demo.gif" alt="cgr agent answering questions about the indexed repository">
 </p>
 
 ## Latest News 🔥
 
 <!-- SECTION:latest_news -->
-- **UTF-8 Handling**: Improved handling of invalid UTF-8 bytes prevents file definitions from being dropped.
-- **Neo4j Backend Support**: Added support for Neo4j as a graph backend through a pluggable dialect seam.
-- **Gloss Node & Notes**: Introduced the Gloss node for agent-authored notes and enabled writing and reading Gloss notes via the MCP server.
+- **Incremental Indexing**: Improved handling of same-stem sibling matches and skipped EXPOSES cleanups during incremental updates.
 <!-- /SECTION:latest_news -->
 
 See [NEWS.md](NEWS.md) for the full history.
@@ -74,7 +82,7 @@ Point Code-Graph-RAG at a repository and it reads every source file, extracts fu
 
 The system has two components:
 
-1. **Multi-language parser.** A Tree-sitter based parser reads the codebase and ingests functions, classes, methods, modules, and their relationships into Memgraph under a single language-agnostic schema.
+1. **Multi-language parser.** A Tree-sitter based parser reads the codebase and ingests functions, classes, methods, modules, and their relationships into Memgraph under a single language-agnostic schema. Where a toolchain is available, compiler-grade frontends layer exact facts on top (libclang for C/C++, `go/types` for Go, and opt-in Roslyn, `javac` and Jedi for C#, Java and Python), and [dynamic tracing](docs/guide/dynamic-tracing.md) merges calls observed at runtime. Tree-sitter stays the backbone: a trace only sees code that ran, and a compiler frontend only covers what its toolchain can build.
 2. **RAG system** (`codebase_rag/`). An interactive CLI that turns natural language into Cypher queries, retrieves matching code, and drives AI-powered editing and optimisation.
 
 ```
@@ -126,10 +134,12 @@ To run code newer than the latest release, install from git:
 uv tool install "code-graph-rag[treesitter-full,semantic] @ git+https://github.com/vitali87/code-graph-rag@main"
 ```
 
+To upgrade an existing install, run `uv tool upgrade code-graph-rag` (with pipx, `pipx upgrade code-graph-rag`, or `pipx reinstall code-graph-rag` for a git install). [Upgrade](docs/getting-started/installation.md#upgrade) covers the other install methods.
+
 You also need Python 3.12+, Docker (for Memgraph), `cmake`, and `ripgrep`. Full prerequisites, source installs, and environment setup are in the [Installation](docs/getting-started/installation.md) guide.
 
 > [!NOTE]
-> The wheel is pure Python (`py3-none-any`), so the package itself installs on any platform with Python 3.12 or newer (dependencies may still need platform wheels or build tools, such as `cmake` for `pymgclient`). The [piwheels](https://www.piwheels.org/project/code-graph-rag/) build for Debian Bookworm shows as failed because Bookworm's system Python is 3.11, which is below our floor. On Raspberry Pi OS Bookworm, pin the interpreter explicitly, for example `uv tool install --python 3.12 "code-graph-rag[treesitter-full,semantic]"`; uv downloads Python 3.12 automatically and the PyPI wheel installs normally.
+> The wheel is pure Python (`py3-none-any`), so it installs on any platform with Python 3.12 or newer. Older system interpreters (Debian Bookworm ships 3.11) need the interpreter pinned explicitly; see [Installation](docs/getting-started/installation.md#older-system-interpreters) for the commands.
 
 ## Quick Start
 
@@ -212,3 +222,5 @@ For issues or questions, check the [Troubleshooting](docs/advanced/troubleshooti
 ## License
 
 MIT. See [LICENSE](LICENSE).
+
+Third-party components and their licences are credited on the [Credits page](https://docs.code-graph-rag.com/credits/).

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38/code_graph_rag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.0.945
+Version: 0.1.38
 Summary: The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
 License-Expression: MIT
 Keywords: rag,retrieval-augmented-generation,knowledge-graph,code-analysis,tree-sitter,mcp,mcp-server,llm,graph-database,semantic-search,codebase,memgraph,developer-tools,monorepo
@@ -20,14 +20,14 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp>=1.28.1
-Requires-Dist: pydantic-ai>=2.0.0
+Requires-Dist: pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
 Requires-Dist: pymgclient>=1.5.1
 Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: tiktoken>=0.12.0
-Requires-Dist: toml>=0.10.2
+Requires-Dist: tomli-w>=1.2.0
 Requires-Dist: tree-sitter-python>=0.25.0
-Requires-Dist: tree-sitter==0.25.2
+Requires-Dist: tree-sitter==0.26.0
 Requires-Dist: watchdog>=6.0.0
 Requires-Dist: typer>=0.21.1
 Requires-Dist: rich>=14.2.0
@@ -67,13 +67,13 @@ Requires-Dist: tree-sitter-cpp>=0.23.0; extra == "treesitter-full"
 Requires-Dist: tree-sitter-lua>=0.0.19; extra == "treesitter-full"
 Requires-Dist: tree-sitter-php>=0.24.1; extra == "treesitter-full"
 Requires-Dist: tree-sitter-c-sharp>=0.23.5; extra == "treesitter-full"
-Requires-Dist: tree-sitter-dart>=0.1.0; extra == "treesitter-full"
+Requires-Dist: tree-sitter-dart==0.1.0; extra == "treesitter-full"
 Requires-Dist: tree-sitter-sql>=0.3.11; extra == "treesitter-full"
 Requires-Dist: tree-sitter-markdown>=0.5.1; extra == "treesitter-full"
 Provides-Extra: semantic
 Requires-Dist: qdrant-client>=1.9.0; extra == "semantic"
 Requires-Dist: torch>=2.6.0; extra == "semantic"
-Requires-Dist: transformers>=4.0.0; extra == "semantic"
+Requires-Dist: transformers>=5.0.0; extra == "semantic"
 Provides-Extra: milvus
 Requires-Dist: pymilvus[milvus-lite]>=3.0.0; extra == "milvus"
 Provides-Extra: ast-grep
@@ -85,7 +85,7 @@ Dynamic: license-file
 
 # Code-Graph-RAG
 
-Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
+Code-Graph-RAG parses a multi-language codebase with Tree-sitter, sharpened by compiler-grade frontends and runtime traces where available, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
 
 ## What It Does
 
@@ -142,12 +142,23 @@ uploads and GitHub Release binaries land on an every-50 cadence, so the tag on `
 usually runs ahead of the published version. A security fix is the exception: it
 ships immediately rather than waiting for the cadence.
 
-To run code newer than the latest release, install from git:
+To run code newer than the latest release, install from git with uv:
 
 ```bash
-pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
+uv tool install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/code-graph-rag@main"
 ```
 
+Use uv for this: it applies the project's `[tool.uv.sources]`, which build the C
+and C++ grammars from forks that keep the declarations upstream drops after a
+`#define` whose value contains a block comment. `pip` ignores those sources and
+installs the upstream grammars.
+
+To upgrade, rerun the install with `--upgrade` and the extras you chose, for
+example `pip install --upgrade 'code-graph-rag[treesitter-full]'`. With uv or pipx,
+run `uv tool upgrade code-graph-rag` or `pipx upgrade code-graph-rag` instead; see the
+[installation guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#upgrade)
+for git installs and the other methods.
+
 ### Prerequisites
 
 - Python 3.12+
@@ -155,15 +166,12 @@ pip install "code-graph-rag[treesitter-full] @ git+https://github.com/vitali87/c
 - `cmake` (for building pymgclient)
 - `ripgrep` (`rg`) (for shell command text searching)
 
-The wheel is pure Python (`py3-none-any`), so the package itself installs on
-any platform with Python 3.12 or newer (dependencies may still need platform
-wheels or build tools, such as `cmake` for `pymgclient`). The piwheels build for Debian Bookworm shows as failed
-because Bookworm's system Python is 3.11, which is below our floor. On
-Raspberry Pi OS Bookworm, install into a Python 3.12 environment so the pip
-commands above actually run under 3.12: with [uv](https://docs.astral.sh/uv/)
-run `uv venv --python 3.12 --seed && source .venv/bin/activate` (uv downloads
-3.12 automatically; `--seed` puts pip in the environment), or install CPython 3.12 yourself and use
-`python3.12 -m pip install ...`.
+The wheel is pure Python (`py3-none-any`), so it installs on any platform with
+Python 3.12 or newer. Some distributions ship an older interpreter (Debian
+Bookworm, and so Raspberry Pi OS Bookworm, ships 3.11), which also explains the
+failed piwheels Bookworm build. On those systems, see the [installation
+guide](https://github.com/vitali87/code-graph-rag/blob/main/docs/getting-started/installation.md#older-system-interpreters)
+for the available interpreter-pinning alternatives.
 
 ## CLI Quick Start
 

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38}/code_graph_rag.egg-info/SOURCES.txt

@@ -10,12 +10,15 @@ code_graph_rag.egg-info/entry_points.txt
 code_graph_rag.egg-info/requires.txt
 code_graph_rag.egg-info/top_level.txt
 codebase_rag/__init__.py
+codebase_rag/_cli_env.py
 codebase_rag/ast_cache.py
 codebase_rag/capture.py
 codebase_rag/cgr_state.py
 codebase_rag/cli.py
 codebase_rag/cli_help.py
+codebase_rag/cli_runtime.py
 codebase_rag/config.py
+codebase_rag/console_marks.py
 codebase_rag/context_pruning.py
 codebase_rag/crash_correlation.py
 codebase_rag/cypher_queries.py
@@ -29,6 +32,7 @@ codebase_rag/exceptions.py
 codebase_rag/flow_verdict.py
 codebase_rag/function_registry.py
 codebase_rag/gloss.py
+codebase_rag/gloss_anchor.py
 codebase_rag/gloss_repair.py
 codebase_rag/graph_audit.py
 codebase_rag/graph_cli.py
@@ -162,6 +166,7 @@ codebase_rag/parsers/document_tier.py
 codebase_rag/parsers/endpoint_prefixes.py
 codebase_rag/parsers/endpoint_routes.py
 codebase_rag/parsers/endpoints.py
+codebase_rag/parsers/enum_variants.py
 codebase_rag/parsers/export_detection.py
 codebase_rag/parsers/factory.py
 codebase_rag/parsers/field_nodes.py
@@ -288,8 +293,17 @@ codebase_rag/parsers/rs/utils.py
 codebase_rag/providers/__init__.py
 codebase_rag/providers/base.py
 codebase_rag/providers/litellm.py
+codebase_rag/queries/highlights/c_sharp.scm
+codebase_rag/queries/highlights/dart.scm
+codebase_rag/queries/highlights/java.scm
+codebase_rag/queries/highlights/javascript.scm
+codebase_rag/queries/highlights/php.scm
+codebase_rag/queries/highlights/python.scm
+codebase_rag/queries/highlights/rust.scm
+codebase_rag/queries/highlights/typescript.scm
 codebase_rag/services/__init__.py
 codebase_rag/services/anthropic_token_counter.py
+codebase_rag/services/cypher_guard.py
 codebase_rag/services/filtering.py
 codebase_rag/services/gloss_cleanup.py
 codebase_rag/services/graph_diff.py
@@ -343,7 +357,9 @@ codebase_rag/trace/xdebug.py
 codebase_rag/utils/__init__.py
 codebase_rag/utils/dependencies.py
 codebase_rag/utils/fqn_resolver.py
+codebase_rag/utils/json_io.py
 codebase_rag/utils/path_utils.py
+codebase_rag/utils/qn_markers.py
 codebase_rag/utils/rich_markdown.py
 codebase_rag/utils/source_extraction.py
 codebase_rag/utils/token_utils.py

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38}/code_graph_rag.egg-info/requires.txt

@@ -1,13 +1,13 @@
 loguru>=0.7.3
 mcp>=1.28.1
-pydantic-ai>=2.0.0
+pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 pydantic-settings>=2.12.0
 pymgclient>=1.5.1
 python-dotenv>=1.2.1
 tiktoken>=0.12.0
-toml>=0.10.2
+tomli-w>=1.2.0
 tree-sitter-python>=0.25.0
-tree-sitter==0.25.2
+tree-sitter==0.26.0
 watchdog>=6.0.0
 typer>=0.21.1
 rich>=14.2.0
@@ -39,7 +39,7 @@ jedi>=0.19
 [semantic]
 qdrant-client>=1.9.0
 torch>=2.6.0
-transformers>=4.0.0
+transformers>=5.0.0
 
 [test]
 jedi>=0.19
@@ -66,6 +66,6 @@ tree-sitter-cpp>=0.23.0
 tree-sitter-lua>=0.0.19
 tree-sitter-php>=0.24.1
 tree-sitter-c-sharp>=0.23.5
-tree-sitter-dart>=0.1.0
+tree-sitter-dart==0.1.0
 tree-sitter-sql>=0.3.11
 tree-sitter-markdown>=0.5.1

code_graph_rag-0.1.38/codebase_rag/_cli_env.py

@@ -0,0 +1,14 @@
+"""Process defaults for the `cgr` command, applied before any settings load.
+
+`codebase_rag.cli` imports this first among its own modules. pydantic-ai
+depends on logfire, whose pydantic plugin pydantic loads the first time a
+model or settings class is built; that imports OpenTelemetry and friends
+(~0.13 s) on every start, and cgr never uses logfire (issue #2253). The
+default applies to the CLI process only, so an application embedding
+codebase_rag keeps its own plugins. A value the user set, including an empty
+one that keeps every plugin, is left alone.
+"""
+
+import os
+
+os.environ.setdefault("PYDANTIC_DISABLE_PLUGINS", "logfire-plugin")

{code_graph_rag-0.0.945 → code_graph_rag-0.1.38}/codebase_rag/ast_cache.py

@@ -2,7 +2,6 @@
 # re-parses from disk via the loader so an eviction cannot lose an AST that
 # type inference still needs (see load()).
 
-import sys
 from collections import OrderedDict
 from collections.abc import Callable, ItemsView
 from pathlib import Path
@@ -13,8 +12,24 @@ from . import constants as cs
 from .config import settings
 
 
+def _estimate_entry_bytes(value: tuple[Node, cs.SupportedLanguage]) -> int:
+    # The memory cap is measured in bytes of SOURCE the cached trees span, not
+    # the trees' true footprint: tree-sitter allocates nodes in C, invisible to
+    # sys.getsizeof (which reports ~56 bytes for any (Node, lang) tuple, so a
+    # cap summed from it never triggered). Tree size scales with source size,
+    # which makes this a stable proxy; the real heap cost is a multiple of it.
+    return value[0].end_byte
+
+
 class BoundedASTCache:
-    __slots__ = ("cache", "loader", "max_entries", "max_memory_bytes")
+    __slots__ = (
+        "cache",
+        "entry_sizes",
+        "loader",
+        "max_entries",
+        "max_memory_bytes",
+        "total_bytes",
+    )
 
     def __init__(
         self,
@@ -24,6 +39,10 @@ class BoundedASTCache:
         | None = None,
     ):
         self.cache: OrderedDict[Path, tuple[Node, cs.SupportedLanguage]] = OrderedDict()
+        # Sizes are recorded at insert so eviction and the running total never
+        # rescan every entry: each insert stays O(1) plus the evictions it causes.
+        self.entry_sizes: dict[Path, int] = {}
+        self.total_bytes = 0
         self.loader = loader
         self.max_entries = (
             max_entries if max_entries is not None else settings.CACHE_MAX_ENTRIES
@@ -47,11 +66,11 @@ class BoundedASTCache:
         return entry
 
     def __setitem__(self, key: Path, value: tuple[Node, cs.SupportedLanguage]) -> None:
-        if key in self.cache:
-            del self.cache[key]
-
+        self._remove(key)
+        size = _estimate_entry_bytes(value)
         self.cache[key] = value
-
+        self.entry_sizes[key] = size
+        self.total_bytes += size
         self._enforce_limits()
 
     def __getitem__(self, key: Path) -> tuple[Node, cs.SupportedLanguage]:
@@ -60,8 +79,7 @@ class BoundedASTCache:
         return value
 
     def __delitem__(self, key: Path) -> None:
-        if key in self.cache:
-            del self.cache[key]
+        self._remove(key)
 
     def __contains__(self, key: Path) -> bool:
         return key in self.cache
@@ -69,24 +87,25 @@ class BoundedASTCache:
     def items(self) -> ItemsView[Path, tuple[Node, cs.SupportedLanguage]]:
         return self.cache.items()
 
+    def clear(self) -> None:
+        self.cache.clear()
+        self.entry_sizes.clear()
+        self.total_bytes = 0
+
+    def _remove(self, key: Path) -> None:
+        if key in self.cache:
+            del self.cache[key]
+            self.total_bytes -= self.entry_sizes.pop(key)
+
+    def _evict_oldest(self) -> None:
+        key, _ = self.cache.popitem(last=False)
+        self.total_bytes -= self.entry_sizes.pop(key)
+
     def _enforce_limits(self) -> None:
-        while len(self.cache) > self.max_entries:
-            self.cache.popitem(last=False)
-
-        if self._should_evict_for_memory():
-            entries_to_remove = max(
-                1, len(self.cache) // settings.CACHE_EVICTION_DIVISOR
-            )
-            for _ in range(entries_to_remove):
-                if self.cache:
-                    self.cache.popitem(last=False)
-
-    def _should_evict_for_memory(self) -> bool:
-        try:
-            cache_size = sum(sys.getsizeof(v) for v in self.cache.values())
-            return cache_size > self.max_memory_bytes
-        except Exception:
-            return (
-                len(self.cache)
-                > self.max_entries * settings.CACHE_MEMORY_THRESHOLD_RATIO
-            )
+        # Evict LRU entries until both caps hold. The newest entry is kept even
+        # if it alone exceeds the memory cap: the caller just parsed it and is
+        # about to use it, and load() would only re-parse it on the next read.
+        while len(self.cache) > self.max_entries or (
+            self.total_bytes > self.max_memory_bytes and len(self.cache) > 1
+        ):
+            self._evict_oldest()