code-graph-rag 0.0.484__tar.gz → 0.0.584__tar.gz

{code_graph_rag-0.0.484/code_graph_rag.egg-info → code_graph_rag-0.0.584}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.0.484
+Version: 0.0.584
 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
@@ -20,7 +20,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp>=1.28.1
-Requires-Dist: pydantic-ai>=1.102.0
+Requires-Dist: pydantic-ai>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
 Requires-Dist: pymgclient>=1.5.1
 Requires-Dist: python-dotenv>=1.2.1
@@ -37,7 +37,6 @@ Requires-Dist: click>=8.3.1
 Requires-Dist: protobuf>=6.33.5
 Requires-Dist: defusedxml>=0.7.1
 Requires-Dist: huggingface-hub[hf-xet]>=1.7.2
-Requires-Dist: griffe<2,>=1.0
 Requires-Dist: pathspec>=1.0.4
 Provides-Extra: test
 Requires-Dist: pytest>=8.4.1; extra == "test"
@@ -76,7 +75,25 @@ Dynamic: license-file
 
 # Code-Graph-RAG
 
-A graph-based RAG system that parses multi-language codebases with Tree-sitter, builds knowledge graphs in Memgraph, and enables natural language querying, editing, and optimisation.
+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.
+
+## What It Does
+
+Point it at a repository and it reads every source file, extracts functions, classes, methods, and modules along with the relationships between them, and stores the result as an interconnected graph. Once the graph exists you can:
+
+- Ask questions about the codebase in natural language and get answers grounded in the real structure.
+- Retrieve the actual source of any function, class, or method by name or by intent.
+- Edit code through the agent with AST-based surgical patching and a diff preview before anything changes.
+- Search and rewrite code structurally by AST pattern with ast-grep, instead of text or regex.
+- Trace data flow through assignments, calls, and I/O sinks via `FLOWS_TO` taint edges.
+- Optimise code against language best practices or your own coding standards.
+- Find dead code by walking call and reference edges from entry points.
+- Group several repositories into a named workspace and query them as one graph.
+- Trace calls between microservices: route decorators become endpoint templates, and HTTP client URLs resolve to the handlers that serve them, linking services across project boundaries.
+
+## Supported Languages
+
+Python, TypeScript, TSX, JavaScript, Rust, Go, Java, C, C++, C#, PHP, Lua, and Dart are fully supported. Scala is in development, and Ruby has structural support (modules, functions, classes, and imports) through the pluggable ast-grep tier, which requires the `ast-grep` extra (`pip install 'code-graph-rag[ast-grep]'`).
 
 ## Install
 
@@ -154,18 +171,31 @@ cgr dead-code --format json --fail-on-found     # CI-friendly report
 Results are candidates for review, not a guaranteed delete list. See the
 [Dead Code Detection guide](https://docs.code-graph-rag.com/guide/dead-code/).
 
-**Run as an MCP server (for Claude Code):**
+**Group repositories into a workspace and query them together:**
 
 ```bash
-cgr mcp-server
+cgr workspace create my-platform
+cgr workspace add-repo my-platform ./service-a
+cgr workspace add-repo my-platform ./service-b
+cgr start --workspace my-platform
 ```
 
-**Check your setup:**
+**Inspect the graph and the stack:**
 
 ```bash
-cgr doctor
+cgr stats                                  # node and relationship counts
+cgr status                                 # stack state and last sync per project
+cgr doctor                                 # check dependencies and configuration
 ```
 
+## MCP Server
+
+Run `cgr mcp-server` to serve the tools over stdio or HTTP for Claude Code and other MCP clients. The MCP surface registers:
+
+- **Ask and retrieve:** `ask_agent`, `query_code_graph`, `get_code_snippet`, and `semantic_search` (needs the `semantic` extra)
+- **Structural editing:** `surgical_replace_code`, plus `structural_search` and `structural_replace` (need the `ast-grep` extra)
+- **Files and projects:** `read_file`, `write_file`, `list_directory`, `list_projects`, `index_repository`, `update_repository`, `delete_project`, `wipe_database`
+
 ## Python SDK
 
 The `cgr` package provides short imports for programmatic use.
@@ -225,8 +255,8 @@ print(f"Embedding dimension: {len(embedding)}")
 ```python
 from cgr import settings
 
-settings.set_orchestrator("openai", "gpt-4o", api_key="sk-...")
-settings.set_cypher("google", "gemini-2.5-flash", api_key="your-key")
+settings.set_orchestrator("openai", "gpt-5.6-terra", api_key="sk-...")
+settings.set_cypher("google", "gemini-3.5-flash-lite", api_key="your-key")
 ```
 
 ## Environment Variables
@@ -238,10 +268,10 @@ Configure via `.env` or environment variables:
 | `MEMGRAPH_HOST` | `localhost` | Memgraph hostname |
 | `MEMGRAPH_PORT` | `7687` | Memgraph port |
 | `ORCHESTRATOR_PROVIDER` | | Provider: `google`, `openai`, `anthropic`, `azure`, `ollama`, `minimax`, `litellm_proxy` |
-| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-4o`, `gemini-2.5-pro`) |
+| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-5.6-terra`, `gemini-3.6-flash`, `claude-sonnet-5`, `qwen2.5-coder`) |
 | `ORCHESTRATOR_API_KEY` | | API key for the provider (not needed for `ollama`) |
 | `CYPHER_PROVIDER` | | Provider for Cypher generation |
-| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `codellama`, `gpt-4o-mini`) |
+| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `qwen2.5-coder`, `gpt-5.6-luna`, `gemini-3.5-flash-lite`) |
 | `CYPHER_API_KEY` | | API key for Cypher provider (not needed for `ollama`) |
 | `TARGET_REPO_PATH` | `.` | Default repository path |
 

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/PYPI_README.md

@@ -1,6 +1,24 @@
 # Code-Graph-RAG
 
-A graph-based RAG system that parses multi-language codebases with Tree-sitter, builds knowledge graphs in Memgraph, and enables natural language querying, editing, and optimisation.
+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.
+
+## What It Does
+
+Point it at a repository and it reads every source file, extracts functions, classes, methods, and modules along with the relationships between them, and stores the result as an interconnected graph. Once the graph exists you can:
+
+- Ask questions about the codebase in natural language and get answers grounded in the real structure.
+- Retrieve the actual source of any function, class, or method by name or by intent.
+- Edit code through the agent with AST-based surgical patching and a diff preview before anything changes.
+- Search and rewrite code structurally by AST pattern with ast-grep, instead of text or regex.
+- Trace data flow through assignments, calls, and I/O sinks via `FLOWS_TO` taint edges.
+- Optimise code against language best practices or your own coding standards.
+- Find dead code by walking call and reference edges from entry points.
+- Group several repositories into a named workspace and query them as one graph.
+- Trace calls between microservices: route decorators become endpoint templates, and HTTP client URLs resolve to the handlers that serve them, linking services across project boundaries.
+
+## Supported Languages
+
+Python, TypeScript, TSX, JavaScript, Rust, Go, Java, C, C++, C#, PHP, Lua, and Dart are fully supported. Scala is in development, and Ruby has structural support (modules, functions, classes, and imports) through the pluggable ast-grep tier, which requires the `ast-grep` extra (`pip install 'code-graph-rag[ast-grep]'`).
 
 ## Install
 
@@ -78,18 +96,31 @@ cgr dead-code --format json --fail-on-found     # CI-friendly report
 Results are candidates for review, not a guaranteed delete list. See the
 [Dead Code Detection guide](https://docs.code-graph-rag.com/guide/dead-code/).
 
-**Run as an MCP server (for Claude Code):**
+**Group repositories into a workspace and query them together:**
 
 ```bash
-cgr mcp-server
+cgr workspace create my-platform
+cgr workspace add-repo my-platform ./service-a
+cgr workspace add-repo my-platform ./service-b
+cgr start --workspace my-platform
 ```
 
-**Check your setup:**
+**Inspect the graph and the stack:**
 
 ```bash
-cgr doctor
+cgr stats                                  # node and relationship counts
+cgr status                                 # stack state and last sync per project
+cgr doctor                                 # check dependencies and configuration
 ```
 
+## MCP Server
+
+Run `cgr mcp-server` to serve the tools over stdio or HTTP for Claude Code and other MCP clients. The MCP surface registers:
+
+- **Ask and retrieve:** `ask_agent`, `query_code_graph`, `get_code_snippet`, and `semantic_search` (needs the `semantic` extra)
+- **Structural editing:** `surgical_replace_code`, plus `structural_search` and `structural_replace` (need the `ast-grep` extra)
+- **Files and projects:** `read_file`, `write_file`, `list_directory`, `list_projects`, `index_repository`, `update_repository`, `delete_project`, `wipe_database`
+
 ## Python SDK
 
 The `cgr` package provides short imports for programmatic use.
@@ -149,8 +180,8 @@ print(f"Embedding dimension: {len(embedding)}")
 ```python
 from cgr import settings
 
-settings.set_orchestrator("openai", "gpt-4o", api_key="sk-...")
-settings.set_cypher("google", "gemini-2.5-flash", api_key="your-key")
+settings.set_orchestrator("openai", "gpt-5.6-terra", api_key="sk-...")
+settings.set_cypher("google", "gemini-3.5-flash-lite", api_key="your-key")
 ```
 
 ## Environment Variables
@@ -162,10 +193,10 @@ Configure via `.env` or environment variables:
 | `MEMGRAPH_HOST` | `localhost` | Memgraph hostname |
 | `MEMGRAPH_PORT` | `7687` | Memgraph port |
 | `ORCHESTRATOR_PROVIDER` | | Provider: `google`, `openai`, `anthropic`, `azure`, `ollama`, `minimax`, `litellm_proxy` |
-| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-4o`, `gemini-2.5-pro`) |
+| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-5.6-terra`, `gemini-3.6-flash`, `claude-sonnet-5`, `qwen2.5-coder`) |
 | `ORCHESTRATOR_API_KEY` | | API key for the provider (not needed for `ollama`) |
 | `CYPHER_PROVIDER` | | Provider for Cypher generation |
-| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `codellama`, `gpt-4o-mini`) |
+| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `qwen2.5-coder`, `gpt-5.6-luna`, `gemini-3.5-flash-lite`) |
 | `CYPHER_API_KEY` | | API key for Cypher provider (not needed for `ollama`) |
 | `TARGET_REPO_PATH` | `.` | Default repository path |
 

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/README.md

@@ -129,10 +129,16 @@ You also need Docker (for Memgraph), `cmake`, and `ripgrep`. Full prerequisites,
 cgr daemon up
 
 # Parse a repository into the graph, then query it
-cgr start --repo-path /path/to/repo --update-graph --clean
+cgr start --repo-path /path/to/repo --update-graph
 cgr start --repo-path /path/to/repo
 ```
 
+Repeat the first command for each repository you want indexed; the graph is
+shared, and syncing one project leaves the others alone. To start over from an
+empty graph, add `--clean` — it deletes **every** project in the shared graph,
+not just this one, and asks for confirmation first when other
+projects would be destroyed.
+
 The [Quick Start](docs/getting-started/quickstart.md) guide walks through parsing, querying, and exporting in five minutes.
 
 ## MCP Server

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584/code_graph_rag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.0.484
+Version: 0.0.584
 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
@@ -20,7 +20,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp>=1.28.1
-Requires-Dist: pydantic-ai>=1.102.0
+Requires-Dist: pydantic-ai>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
 Requires-Dist: pymgclient>=1.5.1
 Requires-Dist: python-dotenv>=1.2.1
@@ -37,7 +37,6 @@ Requires-Dist: click>=8.3.1
 Requires-Dist: protobuf>=6.33.5
 Requires-Dist: defusedxml>=0.7.1
 Requires-Dist: huggingface-hub[hf-xet]>=1.7.2
-Requires-Dist: griffe<2,>=1.0
 Requires-Dist: pathspec>=1.0.4
 Provides-Extra: test
 Requires-Dist: pytest>=8.4.1; extra == "test"
@@ -76,7 +75,25 @@ Dynamic: license-file
 
 # Code-Graph-RAG
 
-A graph-based RAG system that parses multi-language codebases with Tree-sitter, builds knowledge graphs in Memgraph, and enables natural language querying, editing, and optimisation.
+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.
+
+## What It Does
+
+Point it at a repository and it reads every source file, extracts functions, classes, methods, and modules along with the relationships between them, and stores the result as an interconnected graph. Once the graph exists you can:
+
+- Ask questions about the codebase in natural language and get answers grounded in the real structure.
+- Retrieve the actual source of any function, class, or method by name or by intent.
+- Edit code through the agent with AST-based surgical patching and a diff preview before anything changes.
+- Search and rewrite code structurally by AST pattern with ast-grep, instead of text or regex.
+- Trace data flow through assignments, calls, and I/O sinks via `FLOWS_TO` taint edges.
+- Optimise code against language best practices or your own coding standards.
+- Find dead code by walking call and reference edges from entry points.
+- Group several repositories into a named workspace and query them as one graph.
+- Trace calls between microservices: route decorators become endpoint templates, and HTTP client URLs resolve to the handlers that serve them, linking services across project boundaries.
+
+## Supported Languages
+
+Python, TypeScript, TSX, JavaScript, Rust, Go, Java, C, C++, C#, PHP, Lua, and Dart are fully supported. Scala is in development, and Ruby has structural support (modules, functions, classes, and imports) through the pluggable ast-grep tier, which requires the `ast-grep` extra (`pip install 'code-graph-rag[ast-grep]'`).
 
 ## Install
 
@@ -154,18 +171,31 @@ cgr dead-code --format json --fail-on-found     # CI-friendly report
 Results are candidates for review, not a guaranteed delete list. See the
 [Dead Code Detection guide](https://docs.code-graph-rag.com/guide/dead-code/).
 
-**Run as an MCP server (for Claude Code):**
+**Group repositories into a workspace and query them together:**
 
 ```bash
-cgr mcp-server
+cgr workspace create my-platform
+cgr workspace add-repo my-platform ./service-a
+cgr workspace add-repo my-platform ./service-b
+cgr start --workspace my-platform
 ```
 
-**Check your setup:**
+**Inspect the graph and the stack:**
 
 ```bash
-cgr doctor
+cgr stats                                  # node and relationship counts
+cgr status                                 # stack state and last sync per project
+cgr doctor                                 # check dependencies and configuration
 ```
 
+## MCP Server
+
+Run `cgr mcp-server` to serve the tools over stdio or HTTP for Claude Code and other MCP clients. The MCP surface registers:
+
+- **Ask and retrieve:** `ask_agent`, `query_code_graph`, `get_code_snippet`, and `semantic_search` (needs the `semantic` extra)
+- **Structural editing:** `surgical_replace_code`, plus `structural_search` and `structural_replace` (need the `ast-grep` extra)
+- **Files and projects:** `read_file`, `write_file`, `list_directory`, `list_projects`, `index_repository`, `update_repository`, `delete_project`, `wipe_database`
+
 ## Python SDK
 
 The `cgr` package provides short imports for programmatic use.
@@ -225,8 +255,8 @@ print(f"Embedding dimension: {len(embedding)}")
 ```python
 from cgr import settings
 
-settings.set_orchestrator("openai", "gpt-4o", api_key="sk-...")
-settings.set_cypher("google", "gemini-2.5-flash", api_key="your-key")
+settings.set_orchestrator("openai", "gpt-5.6-terra", api_key="sk-...")
+settings.set_cypher("google", "gemini-3.5-flash-lite", api_key="your-key")
 ```
 
 ## Environment Variables
@@ -238,10 +268,10 @@ Configure via `.env` or environment variables:
 | `MEMGRAPH_HOST` | `localhost` | Memgraph hostname |
 | `MEMGRAPH_PORT` | `7687` | Memgraph port |
 | `ORCHESTRATOR_PROVIDER` | | Provider: `google`, `openai`, `anthropic`, `azure`, `ollama`, `minimax`, `litellm_proxy` |
-| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-4o`, `gemini-2.5-pro`) |
+| `ORCHESTRATOR_MODEL` | | Model ID (e.g. `gpt-5.6-terra`, `gemini-3.6-flash`, `claude-sonnet-5`, `qwen2.5-coder`) |
 | `ORCHESTRATOR_API_KEY` | | API key for the provider (not needed for `ollama`) |
 | `CYPHER_PROVIDER` | | Provider for Cypher generation |
-| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `codellama`, `gpt-4o-mini`) |
+| `CYPHER_MODEL` | | Model ID for Cypher generation (e.g. `qwen2.5-coder`, `gpt-5.6-luna`, `gemini-3.5-flash-lite`) |
 | `CYPHER_API_KEY` | | API key for Cypher provider (not needed for `ollama`) |
 | `TARGET_REPO_PATH` | `.` | Default repository path |
 

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/code_graph_rag.egg-info/SOURCES.txt

@@ -22,6 +22,7 @@ codebase_rag/decorators.py
 codebase_rag/docker-compose.yaml
 codebase_rag/embedder.py
 codebase_rag/exceptions.py
+codebase_rag/flow_verdict.py
 codebase_rag/function_registry.py
 codebase_rag/graph_audit.py
 codebase_rag/graph_loader.py
@@ -124,8 +125,11 @@ codebase_rag/parsers/__init__.py
 codebase_rag/parsers/ast_grep_tier.py
 codebase_rag/parsers/call_processor.py
 codebase_rag/parsers/call_resolver.py
+codebase_rag/parsers/contract_linking.py
+codebase_rag/parsers/contracts.py
 codebase_rag/parsers/definition_processor.py
 codebase_rag/parsers/dependency_parser.py
+codebase_rag/parsers/dispatch_registry.py
 codebase_rag/parsers/endpoint_prefixes.py
 codebase_rag/parsers/endpoint_routes.py
 codebase_rag/parsers/endpoints.py
@@ -134,6 +138,7 @@ codebase_rag/parsers/factory.py
 codebase_rag/parsers/function_ingest.py
 codebase_rag/parsers/import_processor.py
 codebase_rag/parsers/python_source_roots.py
+codebase_rag/parsers/rpc_exposure.py
 codebase_rag/parsers/stdlib_extractor.py
 codebase_rag/parsers/structure_processor.py
 codebase_rag/parsers/type_inference.py
@@ -200,6 +205,7 @@ codebase_rag/parsers/java/utils.py
 codebase_rag/parsers/java/variable_analyzer.py
 codebase_rag/parsers/js_ts/__init__.py
 codebase_rag/parsers/js_ts/ingest.py
+codebase_rag/parsers/js_ts/module_paths.py
 codebase_rag/parsers/js_ts/module_system.py
 codebase_rag/parsers/js_ts/type_inference.py
 codebase_rag/parsers/js_ts/utils.py

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/code_graph_rag.egg-info/requires.txt

@@ -1,6 +1,6 @@
 loguru>=0.7.3
 mcp>=1.28.1
-pydantic-ai>=1.102.0
+pydantic-ai>=2.0.0
 pydantic-settings>=2.12.0
 pymgclient>=1.5.1
 python-dotenv>=1.2.1
@@ -17,7 +17,6 @@ click>=8.3.1
 protobuf>=6.33.5
 defusedxml>=0.7.1
 huggingface-hub[hf-xet]>=1.7.2
-griffe<2,>=1.0
 pathspec>=1.0.4
 
 [ast-grep]

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/codebase_rag/cli.py

@@ -2,6 +2,7 @@
 
 import asyncio
 import json
+import sys
 import time
 from collections.abc import Callable
 from fnmatch import fnmatch
@@ -199,6 +200,78 @@ def _capture_selection(capture: list[str] | None) -> CaptureSelection:
     return resolve_capture([*split_spec(settings.CGR_CAPTURE), *(capture or [])])
 
 
+def _stdin_is_interactive() -> bool:
+    try:
+        return sys.stdin.isatty()
+    except (AttributeError, ValueError):
+        return False
+
+
+def _projects_in_graph(ingestor: MemgraphIngestor) -> list[str] | None:
+    """Every project in the graph, or None when the graph cannot be read.
+
+    None is NOT an empty graph: treating a failed enumeration as "no other
+    projects" would skip the confirmation and wipe every project precisely
+    when we cannot say what would be lost.
+    """
+    try:
+        return sorted(ingestor.list_projects())
+    except Exception as exc:
+        logger.warning(ls.MG_LIST_PROJECTS_FAILED.format(error=exc))
+        return None
+
+
+def _confirm_destructive_clean(
+    ingestor: MemgraphIngestor, project_name: str, assume_yes: bool
+) -> None:
+    """Abort unless the user accepts losing every other project in the graph."""
+    if assume_yes:
+        return
+
+    # `--clean` deletes the whole graph, so the prompt counts every project in
+    # it. Deriving that count from `others` would understate it by one whenever
+    # this project has not been synced yet and so is not in the graph.
+    projects = _projects_in_graph(ingestor)
+    if projects is None:
+        # Fail closed: an unreadable project list cannot show what the wipe
+        # would destroy, so it must not be read as an empty graph.
+        app_context.console.print(
+            style(cs.CLI_ERR_CLEAN_UNKNOWN_PROJECTS, cs.Color.RED)
+        )
+        raise typer.Exit(1)
+
+    others = [name for name in projects if name != project_name]
+    if not others:
+        return
+
+    app_context.console.print(
+        style(
+            cs.CLI_WARN_CLEAN_OTHER_PROJECTS.format(
+                project_name=project_name,
+                count=len(others),
+                projects=", ".join(others),
+            ),
+            cs.Color.YELLOW,
+        )
+    )
+
+    if not _stdin_is_interactive():
+        app_context.console.print(
+            style(
+                cs.CLI_ERR_CLEAN_NEEDS_CONFIRMATION.format(project_name=project_name),
+                cs.Color.RED,
+            )
+        )
+        raise typer.Exit(1)
+
+    confirmed = typer.confirm(
+        cs.CLI_PROMPT_CLEAN_CONFIRM.format(count=len(projects)), default=False
+    )
+    if not confirmed:
+        app_context.console.print(style(cs.CLI_MSG_CLEAN_ABORTED, cs.Color.CYAN))
+        raise typer.Exit(1)
+
+
 def _run_graph_sync(
     repo: Path,
     project_name: str,
@@ -209,6 +282,7 @@ def _run_graph_sync(
     output: str | None = None,
     capture: list[str] | None = None,
     skip_embeddings: bool | None = None,
+    assume_yes: bool = False,
 ) -> None:
     cgrignore = load_ignore_patterns(repo)
     cli_excludes = frozenset(exclude) if exclude else frozenset()
@@ -222,6 +296,7 @@ def _run_graph_sync(
     elapsed = time.monotonic()
     with connect_memgraph(batch_size) as ingestor:
         if clean:
+            _confirm_destructive_clean(ingestor, project_name, assume_yes)
             _info(style(cs.CLI_MSG_CLEANING_DB, cs.Color.YELLOW))
             ingestor.clean_database()
             _delete_hash_cache(repo)
@@ -336,6 +411,12 @@ def start(
         "--clean",
         help=ch.HELP_CLEAN_DB,
     ),
+    yes: bool = typer.Option(
+        False,
+        "--yes",
+        "-y",
+        help=ch.HELP_ASSUME_YES,
+    ),
     output: str | None = typer.Option(
         None,
         "-o",
@@ -452,6 +533,7 @@ def start(
     if clean and not update_graph:
         repo_to_clean = Path(target_repo_path)
         with connect_memgraph(effective_batch_size) as ingestor:
+            _confirm_destructive_clean(ingestor, resolved_project_name, yes)
             _info(style(cs.CLI_MSG_CLEANING_DB, cs.Color.YELLOW))
             ingestor.clean_database()
 
@@ -481,6 +563,7 @@ def start(
             output=output,
             capture=capture,
             skip_embeddings=no_embeddings or None,
+            assume_yes=yes,
         )
         _info(style(cs.CLI_MSG_GRAPH_UPDATED, cs.Color.GREEN))
         return

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/codebase_rag/cli_help.py

@@ -124,7 +124,7 @@ HELP_MEMGRAPH_HOST = "Memgraph host."
 HELP_MEMGRAPH_PORT = "Memgraph port."
 HELP_ORCHESTRATOR = (
     "Model for the planning assistant, in provider:model form "
-    "(for example openai:gpt-4 or ollama:llama3.2)."
+    "(for example openai:gpt-5.6-terra or ollama:qwen2.5-coder)."
 )
 HELP_CYPHER_MODEL = "Model used to generate Cypher, in provider:model form."
 HELP_NO_CONFIRM = "Skip edit confirmation prompts."
@@ -146,8 +146,13 @@ HELP_MAX_WAIT = (
 
 HELP_UPDATE_GRAPH = "Parse the repository and sync its graph before continuing."
 HELP_CLEAN_DB = (
-    "Delete every project from the shared graph and clear the selected repository's "
-    "sync cache. With --update-graph, rebuild after deletion."
+    "DESTRUCTIVE: Delete every project from the shared graph and clear the selected "
+    "repository's sync cache. With --update-graph, rebuild after deletion. Asks for "
+    "confirmation when other projects would be destroyed; use --yes to skip the prompt."
+)
+HELP_ASSUME_YES = (
+    "Answer yes to destructive confirmations, such as the one --clean asks before "
+    "deleting other projects from the shared graph."
 )
 HELP_OUTPUT_GRAPH = "Write the updated graph to PATH as JSON. Requires --update-graph."
 HELP_OUTPUT_PATH = "Write the exported graph to PATH."

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/codebase_rag/constants/ast_go.py

@@ -1,9 +1,13 @@
 # Go tree-sitter node types.
 
+TS_GO_PACKAGE_CLAUSE = "package_clause"
+TS_GO_PACKAGE_IDENTIFIER = "package_identifier"
 TS_GO_TYPE_DECLARATION = "type_declaration"
 TS_GO_TYPE_SPEC = "type_spec"
 TS_GO_TYPE_ALIAS = "type_alias"
 TS_GO_STRUCT_TYPE = "struct_type"
+TS_GO_METHOD_ELEM = "method_elem"
+TS_GO_BLOCK = "block"
 TS_GO_SELECTOR_EXPRESSION = "selector_expression"
 TS_GO_TYPE_ASSERTION_EXPRESSION = "type_assertion_expression"
 # A Go source file ending in `_test.go` is compiled only under `go test`; its

{code_graph_rag-0.0.484 → code_graph_rag-0.0.584}/codebase_rag/constants/ast_java.py

@@ -238,3 +238,8 @@ JAVA_SRC_FOLDERS = frozenset(
         JAVA_PATH_TEST,
     }
 )
+
+JAVA_MAVEN_SOURCE_ROOTS = (
+    (JAVA_PATH_SRC, JAVA_PATH_MAIN, JAVA_PATH_JAVA),
+    (JAVA_PATH_SRC, JAVA_PATH_TEST, JAVA_PATH_JAVA),
+)