codeboarding 0.10.1__tar.gz → 0.10.3__tar.gz

{codeboarding-0.10.1/codeboarding.egg-info → codeboarding-0.10.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codeboarding
-Version: 0.10.1
+Version: 0.10.3
 Summary: Interactive Diagrams for Code
 Author: CodeBoarding Team
 License-Expression: MIT
@@ -37,6 +37,7 @@ Requires-Dist: markdown>=3.8
 Requires-Dist: markdown-it-py>=3.0
 Requires-Dist: markitdown>=0.1
 Requires-Dist: networkx>=3.4
+Requires-Dist: nodeenv>=1.10.0
 Requires-Dist: pathspec>=0.12
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: regex>=2024.11

{codeboarding-0.10.1 → codeboarding-0.10.3}/README.md

@@ -16,6 +16,8 @@ Install the extension from Open VSX.
 [![Python](https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white)](https://www.python.org/)
 [![Go](https://img.shields.io/badge/Go-00ADD8?style=flat-square&logo=go&logoColor=white)](https://go.dev/)
 [![PHP](https://img.shields.io/badge/PHP-777BB4?style=flat-square&logo=php&logoColor=white)](https://www.php.net/)
+[![Rust](https://img.shields.io/badge/Rust-000000?style=flat-square&logo=rust&logoColor=white)](https://www.rust-lang.org/)
+[![C#](https://custom-icon-badges.demolab.com/badge/C%23-512BD4.svg?style=flat-square&logo=cshrp&logoColor=white)](https://learn.microsoft.com/en-us/dotnet/csharp/)
 
 ## Few use cases:
 
@@ -91,7 +93,7 @@ codeboarding --local /path/to/repo
 
 Output is written to `/path/to/repo/.codeboarding/`.
 
-`python install.py` and `codeboarding-setup` download language server binaries to `~/.codeboarding/servers/`, shared across projects. `npm` is required for Python, TypeScript, JavaScript, and PHP language servers; if it is missing, setup can install it via `nodeenv`.
+`python install.py` and `codeboarding-setup` download language server binaries to `~/.codeboarding/servers/`, shared across projects. Node.js (and its bundled `npm`) is required for the Python, TypeScript, JavaScript, and PHP language servers; if neither `node` nor `CODEBOARDING_NODE_PATH` is set, setup downloads a pinned Node.js runtime into `~/.codeboarding/servers/nodeenv/` automatically.
 
 ## Configuration
 
@@ -141,7 +143,7 @@ python main.py https://github.com/pytorch/pytorch
 
 ## Supported stack
 
-- Languages: Python, TypeScript, JavaScript, Java, Go, PHP.
+- Languages: Python, TypeScript, JavaScript, Java, Go, PHP, Rust.
 - LLM providers: OpenAI, Anthropic, Google, Vercel AI Gateway, AWS Bedrock, Ollama, OpenRouter, and more.
 
 ## Examples

{codeboarding-0.10.1 → codeboarding-0.10.3}/agents/agent.py

@@ -160,6 +160,11 @@ class CodeBoardingAgent(ReferenceResolverMixin, MonitoringMixin):
                     raise
 
             except Exception as e:
+                # HTTP 404 (e.g. retired model ID) is permanent — retrying won't help.
+                if getattr(e, "status_code", None) == 404:
+                    logger.error(f"Permanent HTTP 404 — not retrying: {type(e).__name__}: {e}")
+                    raise
+
                 # Other errors (network, parsing, etc.) get standard exponential backoff
                 if attempt < max_retries - 1:
                     delay = min(10 * (2**attempt), 120)

{codeboarding-0.10.1 → codeboarding-0.10.3}/agents/agent_responses.py

@@ -1,6 +1,7 @@
 import abc
 import logging
 from abc import abstractmethod
+from pathlib import PurePosixPath
 from typing import get_origin, Optional
 
 from pydantic import BaseModel, Field
@@ -261,6 +262,10 @@ class AnalysisInsights(LLMBaseModel):
         relations = "\n".join(cr.llm_str() for cr in self.components_relations)
         return title + body + relations
 
+    def file_to_component(self) -> dict[str, str]:
+        """Build file path -> component_id mapping from root components."""
+        return {str(PurePosixPath(fg.file_path)): c.component_id for c in self.components for fg in c.file_methods}
+
 
 def assign_component_ids(analysis: AnalysisInsights, parent_id: str = "") -> None:
     """Assign hierarchical component IDs based on sibling index.

{codeboarding-0.10.1 → codeboarding-0.10.3}/agents/cluster_methods_mixin.py

@@ -16,8 +16,11 @@ from agents.agent_responses import (
 from constants import MIN_CLUSTERS_THRESHOLD
 from static_analyzer.analysis_result import StaticAnalysisResults
 from static_analyzer.cluster_helpers import (
+    MAX_LLM_CLUSTERS,
+    enforce_cross_language_budget,
     get_all_cluster_ids,
     get_files_for_cluster_ids,
+    merge_clusters,
 )
 from static_analyzer.cluster_relations import (
     build_component_relations,
@@ -250,7 +253,6 @@ class ClusterMethodsMixin:
             abs_path = os.path.join(self.repo_dir, f) if not os.path.isabs(f) else f
             assigned_file_set.add(abs_path)
 
-        result_parts = []
         cluster_results: dict[str, ClusterResult] = {}
         subgraph_cfgs: dict[str, CallGraph] = {}
 
@@ -266,15 +268,33 @@ class ClusterMethodsMixin:
                 # Calculate clusters for the subgraph
                 sub_cluster_result = sub_cfg.cluster()
 
+                # Merge into super-clusters if too many (same limit as AbstractionAgent)
+                if len(sub_cluster_result.clusters) > MAX_LLM_CLUSTERS:
+                    n_before = len(sub_cluster_result.clusters)
+                    sub_cluster_result = merge_clusters(sub_cluster_result, sub_cfg.to_networkx(), MAX_LLM_CLUSTERS)
+                    logger.info(
+                        f"[DetailsAgent] Subgraph for '{component.name}': "
+                        f"merged {n_before} -> {len(sub_cluster_result.clusters)} super-clusters"
+                    )
+
                 # Expand to method-level if insufficient clusters
                 sub_cluster_result = self._expand_to_method_level_clusters(sub_cfg, sub_cluster_result)
                 cluster_results[lang] = sub_cluster_result
 
-                cluster_str = sub_cfg.to_cluster_string(cluster_result=sub_cluster_result)
-                if cluster_str.strip() and cluster_str not in ("empty", "none", "No clusters found."):
-                    result_parts.append(f"\n## {lang.capitalize()} - Component CFG\n")
-                    result_parts.append(cluster_str)
-                    result_parts.append("\n")
+        # Cross-language: enforce combined budget and unique IDs
+        if len(cluster_results) > 1:
+            cfg_nx = {lang: subgraph_cfgs[lang].to_networkx() for lang in cluster_results}
+            enforce_cross_language_budget(cluster_results, cfg_nx)
+
+        result_parts = []
+        for lang in self.static_analysis.get_languages():
+            if lang not in cluster_results:
+                continue
+            cluster_str = subgraph_cfgs[lang].to_cluster_string(cluster_result=cluster_results[lang])
+            if cluster_str.strip() and cluster_str not in ("empty", "none", "No clusters found."):
+                result_parts.append(f"\n## {lang.capitalize()} - Component CFG\n")
+                result_parts.append(cluster_str)
+                result_parts.append("\n")
 
         result = "".join(result_parts)
 

{codeboarding-0.10.1 → codeboarding-0.10.3}/agents/llm_config.py

@@ -136,7 +136,7 @@ LLM_PROVIDERS = {
     "anthropic": LLMConfig(
         chat_class=ChatAnthropic,
         api_key_env="ANTHROPIC_API_KEY",
-        agent_model="claude-3-7-sonnet-20250219",
+        agent_model="claude-sonnet-4-5-20250929",
         parsing_model="claude-3-haiku-20240307",
         llm_type=LLMType.CLAUDE,
         extra_args={
@@ -160,7 +160,7 @@ LLM_PROVIDERS = {
     "aws": LLMConfig(
         chat_class=ChatBedrockConverse,
         api_key_env="AWS_BEARER_TOKEN_BEDROCK",  # Used for existence check
-        agent_model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+        agent_model="us.anthropic.claude-sonnet-4-5-20250929-v1:0",
         parsing_model="us.anthropic.claude-3-haiku-20240307-v1:0",
         llm_type=LLMType.CLAUDE,
         extra_args={

{codeboarding-0.10.1 → codeboarding-0.10.3}/agents/meta_agent.py

@@ -46,7 +46,6 @@ class MetaAgent(CodeBoardingAgent):
         )
 
         self._meta_cache = MetaCache(repo_dir=repo_dir, ignore_manager=self.ignore_manager)
-        self._cache = self._meta_cache  # Backward-compatible alias for tests/callers.
 
     @trace
     def analyze_project_metadata(self, skip_cache: bool = False) -> MetaAnalysisInsights:

{codeboarding-0.10.1 → codeboarding-0.10.3/codeboarding.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codeboarding
-Version: 0.10.1
+Version: 0.10.3
 Summary: Interactive Diagrams for Code
 Author: CodeBoarding Team
 License-Expression: MIT
@@ -37,6 +37,7 @@ Requires-Dist: markdown>=3.8
 Requires-Dist: markdown-it-py>=3.0
 Requires-Dist: markitdown>=0.1
 Requires-Dist: networkx>=3.4
+Requires-Dist: nodeenv>=1.10.0
 Requires-Dist: pathspec>=0.12
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: regex>=2024.11

{codeboarding-0.10.1 → codeboarding-0.10.3}/codeboarding.egg-info/SOURCES.txt

@@ -9,7 +9,6 @@ install.py
 logging_config.py
 main.py
 pyproject.toml
-tool_registry.py
 user_config.py
 utils.py
 vscode_constants.py
@@ -69,7 +68,6 @@ diagram_analysis/file_coverage.py
 diagram_analysis/incremental_types.py
 diagram_analysis/incremental_updater.py
 diagram_analysis/io_utils.py
-diagram_analysis/manifest.py
 diagram_analysis/run_context.py
 diagram_analysis/version.py
 health/__init__.py
@@ -112,6 +110,7 @@ static_analyzer/cluster_change_analyzer.py
 static_analyzer/cluster_helpers.py
 static_analyzer/cluster_relations.py
 static_analyzer/constants.py
+static_analyzer/csharp_config_scanner.py
 static_analyzer/git_diff_analyzer.py
 static_analyzer/graph.py
 static_analyzer/incremental_orchestrator.py
@@ -138,10 +137,12 @@ static_analyzer/engine/source_inspector.py
 static_analyzer/engine/symbol_table.py
 static_analyzer/engine/utils.py
 static_analyzer/engine/adapters/__init__.py
+static_analyzer/engine/adapters/csharp_adapter.py
 static_analyzer/engine/adapters/go_adapter.py
 static_analyzer/engine/adapters/java_adapter.py
 static_analyzer/engine/adapters/php_adapter.py
 static_analyzer/engine/adapters/python_adapter.py
+static_analyzer/engine/adapters/rust_adapter.py
 static_analyzer/engine/adapters/typescript_adapter.py
 static_analyzer/lsp_client/__init__.py
 static_analyzer/lsp_client/diagnostics.py
@@ -150,8 +151,14 @@ tests/test_install.py
 tests/test_logging_config.py
 tests/test_main.py
 tests/test_pyproject_packages.py
+tests/test_registry_coverage.py
 tests/test_tool_registry.py
 tests/test_user_config.py
 tests/test_vscode_constants.py
 tests/test_windows_compatibility.py
-tests/test_windows_encoding.py
+tests/test_windows_encoding.py
+tool_registry/__init__.py
+tool_registry/installers.py
+tool_registry/manifest.py
+tool_registry/paths.py
+tool_registry/registry.py

{codeboarding-0.10.1 → codeboarding-0.10.3}/codeboarding.egg-info/requires.txt

@@ -19,6 +19,7 @@ markdown>=3.8
 markdown-it-py>=3.0
 markitdown>=0.1
 networkx>=3.4
+nodeenv>=1.10.0
 pathspec>=0.12
 pyyaml>=6.0
 regex>=2024.11

{codeboarding-0.10.1 → codeboarding-0.10.3}/diagram_analysis/__init__.py

@@ -1,4 +1,3 @@
 from .diagram_generator import DiagramGenerator
-from .manifest import AnalysisManifest, load_manifest, save_manifest
 from .run_context import RunContext
 from agents.llm_config import configure_models

{codeboarding-0.10.1 → codeboarding-0.10.3}/diagram_analysis/diagram_generator.py

@@ -21,10 +21,6 @@ from diagram_analysis.analysis_json import (
 )
 from diagram_analysis.file_coverage import FileCoverage
 from diagram_analysis.io_utils import save_analysis
-from diagram_analysis.manifest import (
-    build_manifest_from_analysis,
-    save_manifest,
-)
 from diagram_analysis.version import Version
 from health.config import initialize_health_dir, load_health_config
 from health.runner import run_health_checks
@@ -452,31 +448,8 @@ class DiagramGenerator:
             # Write file_coverage.json
             self._write_file_coverage()
 
-            # Save manifest for incremental updates
-            self._save_manifest(analysis, expanded_components)
-
             return analysis_path
 
-    def _save_manifest(self, analysis: AnalysisInsights, expanded_components: list) -> None:
-        """Save the analysis manifest for incremental updates."""
-        try:
-            repo_state_hash = get_repo_state_hash(self.repo_location)
-            base_commit = get_git_commit_hash(self.repo_location)
-
-            expanded_names = [c.component_id for c in expanded_components]
-
-            manifest = build_manifest_from_analysis(
-                analysis=analysis,
-                repo_state_hash=repo_state_hash,
-                base_commit=base_commit,
-                expanded_components=expanded_names,
-            )
-
-            save_manifest(manifest, self.output_dir)
-            logger.info(f"Saved manifest with {len(manifest.file_to_component)} file mappings")
-        except Exception as e:
-            logger.warning(f"Failed to save manifest: {e}")
-
     def generate_analysis_smart(self) -> Path:
         """Run full analysis."""
         return self.generate_analysis()

{codeboarding-0.10.1 → codeboarding-0.10.3}/diagram_analysis/incremental_updater.py

@@ -18,7 +18,6 @@ from typing import Callable
 from agents.agent_responses import AnalysisInsights, Component, FileEntry, FileMethodGroup, MethodEntry
 from agents.change_status import ChangeStatus
 from diagram_analysis.incremental_types import FileDelta, IncrementalDelta, MethodChange
-from diagram_analysis.manifest import AnalysisManifest
 from repo_utils.change_detector import ChangeSet
 from repo_utils.method_diff import get_method_statuses_for_file
 
@@ -35,17 +34,22 @@ class IncrementalUpdater:
     to ensure consistent behavior with the main analysis pipeline.
     """
 
+    # Callable that resolves a new file path to a component_id using
+    # the current file_to_component mapping.
+    ComponentResolver = Callable[[str, dict[str, str]], str]
+
     def __init__(
         self,
         analysis: AnalysisInsights,
-        manifest: AnalysisManifest,
         symbol_resolver: SymbolResolver,
         repo_dir: Path,
+        component_resolver: ComponentResolver | None = None,
     ):
         self.analysis = analysis
-        self.manifest = manifest
         self._symbol_resolver = symbol_resolver
         self._repo_dir = repo_dir
+        self._component_resolver = component_resolver
+        self._file_to_component = analysis.file_to_component()
 
     def _get_current_methods(self, file_path: str) -> list[MethodEntry]:
         return self._symbol_resolver(file_path)
@@ -59,14 +63,6 @@ class IncrementalUpdater:
     def _get_previous_active_methods(self, file_path: str) -> dict[str, MethodEntry]:
         return {qn: m for qn, m in self._get_previous_methods(file_path).items() if m.status != ChangeStatus.DELETED}
 
-    def _resolve_component(self, file_path: str, *, register_file: bool = False) -> tuple[str | None, bool]:
-        component_id = self.manifest.get_component_for_file(file_path)
-        if component_id is None:
-            return None, True
-        if register_file:
-            self.manifest.add_file(file_path, component_id)
-        return component_id, False
-
     def _apply_method_diff_statuses(
         self, file_path: str, current_methods: list[MethodEntry], changes: ChangeSet
     ) -> None:
@@ -95,7 +91,12 @@ class IncrementalUpdater:
         register_file: bool,
         changes: ChangeSet,
     ) -> tuple[FileDelta, bool]:
-        component_id, missing = self._resolve_component(file_path, register_file=register_file)
+        component_id = self._file_to_component.get(file_path)
+        if component_id is None and register_file and self._component_resolver is not None:
+            component_id = self._component_resolver(file_path, self._file_to_component)
+        if component_id is not None and register_file:
+            self._file_to_component[file_path] = component_id
+        missing = component_id is None
 
         if file_status == ChangeStatus.ADDED:
             current = self._get_current_methods(file_path)
@@ -105,7 +106,9 @@ class IncrementalUpdater:
                     file_path=file_path,
                     file_status=ChangeStatus.ADDED,
                     component_id=component_id,
-                    added_methods=[self._to_method_change(file_path, m) for m in current],
+                    added_methods=[
+                        self._to_method_change(file_path, m, change_type=ChangeStatus.ADDED) for m in current
+                    ],
                 ),
                 missing,
             )
@@ -186,7 +189,8 @@ class IncrementalUpdater:
         Replaces the stored file state with the current unchanged snapshot,
         removing stale added/deleted/modified statuses from prior incremental updates.
         """
-        component_id, missing = self._resolve_component(file_path)
+        component_id = self._file_to_component.get(file_path)
+        missing = component_id is None
         current = self._get_current_methods(file_path)
         for m in current:
             m.status = ChangeStatus.UNCHANGED
@@ -304,12 +308,66 @@ def _apply_file_delta_to_index(files: dict[str, FileEntry], file_delta: FileDelt
     existing.methods = _sorted_methods(methods_by_name)
 
 
-def _sync_component_methods(component: Component, files: dict[str, FileEntry]) -> None:
+def _sync_component_methods(
+    component: Component,
+    files: dict[str, FileEntry],
+    deltas_by_path: dict[str, FileDelta],
+    parent_ids: set[str],
+) -> None:
+    """Rebuild component's file_methods, preserving method boundaries.
+
+    Strategy:
+    1. Collect the qualified names this component originally owned.
+    2. Remove deleted methods from ownership.
+    3. Absorb newly added methods when the component is the primary owner
+       (``delta.component_id``) OR is an intermediate ancestor of the
+       primary (its ID is a descendant of the primary AND it has its own
+       children in ``parent_ids``).  Leaf components and siblings that
+       don't own the file are unaffected.
+    4. Filter the global files index to only include owned methods.
+    """
+    owned_qnames: set[str] = set()
+
+    for group in component.file_methods:
+        for method in group.methods:
+            owned_qnames.add(method.qualified_name)
+
+    for file_path, delta in deltas_by_path.items():
+        if not component.file_methods:
+            continue
+        if not any(group.file_path == file_path for group in component.file_methods):
+            continue
+
+        for method in delta.deleted_methods:
+            owned_qnames.discard(method.qualified_name)
+
+        primary_id = delta.component_id or ""
+        should_absorb = primary_id == component.component_id or (
+            component.component_id.startswith(primary_id + ".") and component.component_id in parent_ids
+        )
+
+        # A component that owned every pre-existing method in the file is a
+        # superset owner (e.g. a root component whose children partition its
+        # methods).  It must absorb new methods so it stays a superset.
+        if not should_absorb and delta.added_methods:
+            file_entry = files.get(file_path)
+            if file_entry is not None:
+                added_qnames = {m.qualified_name for m in delta.added_methods}
+                pre_existing = {m.qualified_name for m in file_entry.methods} - added_qnames
+                if pre_existing and pre_existing <= owned_qnames:
+                    should_absorb = True
+
+        if should_absorb:
+            for method in delta.added_methods:
+                owned_qnames.add(method.qualified_name)
+
     component.file_methods = [
         FileMethodGroup(
             file_path=fp,
-            file_status=entry.file_status,
-            methods=[m.model_copy(deep=True) for m in entry.methods],
+            file_status=entry.file_status if entry else ChangeStatus.UNCHANGED,
+            methods=[
+                m.model_copy(deep=True) for m in (entry.methods if entry else []) if m.qualified_name in owned_qnames
+            ],
         )
         for fp in sorted({g.file_path for g in component.file_methods})
         if (entry := files.get(fp)) is not None
@@ -327,8 +385,11 @@ def apply_delta(
 
     files = dict(root.files)
     component_lookup = _component_lookup(root, sub_analyses)
+    parent_ids = set(sub_analyses.keys())
 
+    deltas_by_path: dict[str, FileDelta] = {}
     for file_delta in delta.file_deltas:
+        deltas_by_path[file_delta.file_path] = file_delta
         _apply_file_delta_to_index(files, file_delta)
 
         component = component_lookup.get(file_delta.component_id or "")
@@ -342,9 +403,9 @@ def apply_delta(
 
     root.files = files
     for component in root.components:
-        _sync_component_methods(component, files)
+        _sync_component_methods(component, files, deltas_by_path, parent_ids)
 
     for sub in sub_analyses.values():
         sub.files = files
         for component in sub.components:
-            _sync_component_methods(component, files)
+            _sync_component_methods(component, files, deltas_by_path, parent_ids)

{codeboarding-0.10.1 → codeboarding-0.10.3}/health/checks/unused_code_diagnostics.py

@@ -95,6 +95,19 @@ DIAGNOSTIC_CODE_MAPPINGS: dict[str, DeadCodeCategory] = {
     "no-unused-vars": DeadCodeCategory.UNUSED_VARIABLE,
     "unused-imports/no-unused-imports": DeadCodeCategory.UNUSED_IMPORT,
     "@typescript-eslint/no-unused-vars": DeadCodeCategory.UNUSED_VARIABLE,
+    # csharp-ls / Roslyn (C#)
+    "CS8019": DeadCodeCategory.UNUSED_IMPORT,  # Unnecessary using directive
+    "CS0168": DeadCodeCategory.UNUSED_VARIABLE,  # Variable declared but never used
+    "CS0219": DeadCodeCategory.UNUSED_VARIABLE,  # Variable assigned but its value is never used
+    "CS0169": DeadCodeCategory.DEAD_CODE,  # Field is never used
+    "CS0414": DeadCodeCategory.DEAD_CODE,  # Field is assigned but its value is never used
+    "CS0649": DeadCodeCategory.DEAD_CODE,  # Field is never assigned and will always have its default value
+    "CS0162": DeadCodeCategory.UNREACHABLE_CODE,  # Unreachable code detected
+    "CS8321": DeadCodeCategory.UNUSED_FUNCTION,  # Local function is declared but never used
+    "IDE0051": DeadCodeCategory.UNUSED_FUNCTION,  # Private member is unused
+    "IDE0052": DeadCodeCategory.DEAD_CODE,  # Private member can be removed
+    "IDE0059": DeadCodeCategory.UNUSED_VARIABLE,  # Unnecessary value assignment
+    "IDE0060": DeadCodeCategory.UNUSED_PARAMETER,  # Remove unused parameter
 }
 
 # Keywords that indicate unused/dead code in diagnostic messages