kodit 0.3.2__tar.gz → 0.3.4__tar.gz

kodit-0.3.4/.claude/commands/update-docs.md

@@ -0,0 +1,79 @@
+# Update Documentation Based on Recent Code Changes
+
+## Objective
+
+Analyze recent commits in the current Git branch and update relevant documentation to reflect code changes.
+
+## Steps to Complete
+
+### 1. Analyze Recent Commits
+
+- Run `git log --oneline -n 20` to view the last 20 commits on the current branch, or
+  all commits if it is not the main branch.
+- For each commit, run `git show --name-status <commit-hash>` to see which files were modified
+- Focus on commits that modified source code files (`.js`, `.py`, `.ts`, `.java`, `.go`, `.rs`, etc.)
+
+### 2. Identify Code Changes
+
+For each modified source file in recent commits:
+
+- Examine the diff using `git diff <commit-hash>^ <commit-hash> -- <file-path>`
+- Identify:
+  - New functions or methods added
+  - Functions or methods removed or renamed
+  - Changes to function signatures (parameters, return types)
+  - New classes or modules
+  - Changes to public APIs
+  - New configuration options or environment variables
+  - Breaking changes
+
+### 3. Update README.md
+
+Check if the README.md needs updates for:
+
+- **Installation instructions**: If dependencies or setup steps changed
+- **Usage examples**: If APIs or interfaces changed
+- **Configuration**: If new environment variables or config options were added
+- **Features list**: If new features were implemented
+- **Quick start guide**: If the basic usage pattern changed
+
+### 4. Update Documentation in /docs
+
+For each markdown file in the `docs/` folder:
+
+- Check if it references any of the changed code
+- Update:
+  - API documentation with new/changed function signatures
+  - Code examples that may no longer work
+  - Configuration guides if settings changed
+  - Architecture diagrams if structural changes occurred
+  - Migration guides if there are breaking changes
+
+### 5. Create or Update Specific Docs
+
+Based on the changes found:
+
+- If new features were added without documentation, create new doc files
+- If breaking changes exist, create or update a migration guide
+- If new APIs were added, ensure they have proper documentation
+
+### 6. Verify Documentation Accuracy
+
+- Ensure all code examples in documentation are up-to-date
+- Check that any referenced file paths still exist
+- Verify that installation and setup instructions still work
+
+## Output Required
+
+1. Summary of commits analyzed and significant changes found
+2. List of documentation files updated with brief description of changes
+3. Any new documentation files created
+4. Warnings about potentially outdated documentation that needs manual review
+
+## Important Notes
+
+- Focus on user-facing changes that affect how people use Kodit
+- Don't document internal implementation details unless they affect the public API
+- Keep documentation concise and example-driven
+- If unsure about a change's impact, flag it for manual review
+- Ensure all documentation follows the existing style and format in the repository

{kodit-0.3.2 → kodit-0.3.4}/.dockerignore

@@ -188,6 +188,6 @@ docs/
 .vscode/
 .gitignore
 LICENSE
-.python-version
+.python-version # Set in the Dockerfile
 .dockerignore
 tests/

{kodit-0.3.2 → kodit-0.3.4}/.github/workflows/docker.yaml

@@ -45,6 +45,9 @@ jobs:
     needs: test-build
     # Only run on main branch or when explicitly triggered
     if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name == github.repository
+    strategy:
+      matrix:
+        python-version: ["3.12.8", "3.13.5"]
     steps:
       - name: Free up disk space
         run: sudo rm -rf /usr/local/lib/android /usr/share/dotnet || true
@@ -65,11 +68,28 @@ jobs:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
 
+      - name: Set short Python version
+        id: pyver
+        run: |
+          echo "SHORT_PY=$(echo '${{ matrix.python-version }}' | cut -d. -f1,2)" >> $GITHUB_OUTPUT
+          echo "ENABLE_DEFAULT=$([ \"$(echo '${{ matrix.python-version }}' | cut -d. -f1,2)\" = \"3.13\" ] && echo true || echo false)" >> $GITHUB_OUTPUT
+
       - name: Extract metadata (tags, labels) for Docker
         id: meta
         uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
         with:
           images: ${{ vars.REGISTRY }}/${{ vars.REGISTRY_ORG }}/${{ github.event.repository.name }}
+          tags: |
+            type=semver,pattern={{version}},enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
+            type=semver,pattern={{version}},suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
+            type=semver,pattern={{major}}.{{minor}},enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
+            type=semver,pattern={{major}}.{{minor}},suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
+            type=ref,event=branch,enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
+            type=ref,event=branch,suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
+            type=ref,event=pr,enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
+            type=ref,event=pr,suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
+            type=sha,enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
+            type=sha,suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
 
       - name: Build and push Docker image
         id: push
@@ -81,6 +101,8 @@ jobs:
           push: true
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+          build-args: |
+            PYTHON_VERSION=${{ matrix.python-version }}
 
       - name: Generate artifact attestation
         uses: actions/attest-build-provenance@v2

{kodit-0.3.2 → kodit-0.3.4}/CLAUDE.md

@@ -50,18 +50,23 @@ The codebase follows Domain-Driven Design (DDD) with clean architecture:
 
 ### Key Components
 
-**Indexing Pipeline:**
+**Advanced Indexing Pipeline:**
 
-1. Clone/read source code
-2. Extract snippets using Tree-sitter
-3. Generate embeddings and BM25 indices
-4. Store in database
+1. Clone/read source code with Git metadata extraction
+2. Language detection for 20+ programming languages
+3. Advanced snippet extraction using Tree-sitter with dependency analysis
+4. Build call graphs and import maps for context-aware extraction
+5. Generate embeddings and BM25 indices
+6. Store in database with selective reindexing for performance
 
-**Search System:**
+**Advanced Search System:**
 
-- Hybrid search combining semantic (embeddings) and keyword (BM25)
+- Hybrid search combining semantic (embeddings) and keyword (BM25) with Reciprocal Rank Fusion
+- Multi-dimensional filtering: language, author, date range, source, file path
+- Context-aware results with dependency tracking and usage examples
 - Multiple providers: local models, OpenAI, custom APIs
 - Configurable via environment variables
+- Support for 20+ programming languages including HTML/CSS
 
 **MCP Server:**
 
@@ -96,4 +101,5 @@ Migrations managed with Alembic in `migrations/` directory. DO NOT EDIT THESE FI
 - Smoke tests for deployment validation
 - Performance tests for similarity search
 
-Test files mirror source structure under `tests/` directory.
+Test file names should mirror the source structure under `tests/` directory and end in
+the name `_test.py`.

{kodit-0.3.2 → kodit-0.3.4}/Dockerfile

@@ -30,9 +30,11 @@ COPY --from=ghcr.io/astral-sh/uv:0.7.2 /uv /usr/local/bin/uv
 ENV UV_LINK_MODE=copy \
     UV_COMPILE_BYTECODE=1 \
     UV_PYTHON_DOWNLOADS=never \
-    UV_PYTHON=python3.13 \
     UV_PROJECT_ENVIRONMENT=/app
 
+# Write the PYTHON_VERSION to a .python-version
+RUN echo ${PYTHON_VERSION} > .python-version
+
 # Synchronize DEPENDENCIES without the application itself.
 # This layer is cached until uv.lock or pyproject.toml change, which are
 # only temporarily mounted into the build container since we don't need
@@ -43,6 +45,7 @@ ENV UV_LINK_MODE=copy \
 RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=uv.lock,target=uv.lock \
     --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    UV_PYTHON="python$(echo ${PYTHON_VERSION} | cut -d. -f1-2)" \
     uv sync \
         --locked \
         --no-dev \
@@ -54,6 +57,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 COPY . /src
 WORKDIR /src
 RUN --mount=type=cache,target=/root/.cache/uv \
+    UV_PYTHON="python$(echo ${PYTHON_VERSION} | cut -d. -f1-2)" \
     uv sync \
         --locked \
         --no-dev \

{kodit-0.3.2 → kodit-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kodit
-Version: 0.3.2
+Version: 0.3.4
 Summary: Code indexing for better AI code generation
 Project-URL: Homepage, https://docs.helixml.tech/kodit/
 Project-URL: Documentation, https://docs.helixml.tech/kodit/
@@ -92,13 +92,16 @@ code. This index is used to build a snippet library, ready for ingestion into an
 
 - Index local directories and public Git repositories
 - Build comprehensive snippet libraries for LLM ingestion
-- Support for multiple codebase types and languages
-- Efficient indexing and search capabilities
+- Support for 20+ programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, C/C++, C#, HTML/CSS, and more
+- Advanced code analysis with dependency tracking and call graph generation
+- Intelligent snippet extraction with context-aware dependencies
+- Efficient indexing with selective reindexing (only processes modified files)
 - Privacy first: respects .gitignore and .noindex files
 - **NEW in 0.3**: Auto-indexing configuration for shared server deployments
 - **NEW in 0.3**: Enhanced Git provider support including Azure DevOps
 - **NEW in 0.3**: Index private repositories via a PAT
 - **NEW in 0.3**: Improved progress monitoring and reporting during indexing
+- **NEW in 0.3**: Advanced code slicing infrastructure with Tree-sitter parsing
 
 ### MCP Server
 
@@ -111,7 +114,9 @@ intent. Kodit has been tested to work well with:
   - [Cursor](https://docs.helix.ml/kodit/getting-started/integration/#integration-with-cursor)
   - [Cline](https://docs.helix.ml/kodit/getting-started/integration/#integration-with-cline)
 - Please contribute more instructions! ... any other assistant is likely to work ...
-- **New in 0.3**: Filter snippets by source, language, author or timestamp.
+- **New in 0.3**: Advanced search filters by source, language, author, date range, and file path
+- **New in 0.3**: Hybrid search combining BM25 keyword search with semantic search
+- **New in 0.4**: Enhanced MCP tools with rich context parameters and metadata
 
 ### Enterprise Ready
 

{kodit-0.3.2 → kodit-0.3.4}/README.md

@@ -39,13 +39,16 @@ code. This index is used to build a snippet library, ready for ingestion into an
 
 - Index local directories and public Git repositories
 - Build comprehensive snippet libraries for LLM ingestion
-- Support for multiple codebase types and languages
-- Efficient indexing and search capabilities
+- Support for 20+ programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, C/C++, C#, HTML/CSS, and more
+- Advanced code analysis with dependency tracking and call graph generation
+- Intelligent snippet extraction with context-aware dependencies
+- Efficient indexing with selective reindexing (only processes modified files)
 - Privacy first: respects .gitignore and .noindex files
 - **NEW in 0.3**: Auto-indexing configuration for shared server deployments
 - **NEW in 0.3**: Enhanced Git provider support including Azure DevOps
 - **NEW in 0.3**: Index private repositories via a PAT
 - **NEW in 0.3**: Improved progress monitoring and reporting during indexing
+- **NEW in 0.3**: Advanced code slicing infrastructure with Tree-sitter parsing
 
 ### MCP Server
 
@@ -58,7 +61,9 @@ intent. Kodit has been tested to work well with:
   - [Cursor](https://docs.helix.ml/kodit/getting-started/integration/#integration-with-cursor)
   - [Cline](https://docs.helix.ml/kodit/getting-started/integration/#integration-with-cline)
 - Please contribute more instructions! ... any other assistant is likely to work ...
-- **New in 0.3**: Filter snippets by source, language, author or timestamp.
+- **New in 0.3**: Advanced search filters by source, language, author, date range, and file path
+- **New in 0.3**: Hybrid search combining BM25 keyword search with semantic search
+- **New in 0.4**: Enhanced MCP tools with rich context parameters and metadata
 
 ### Enterprise Ready
 

kodit-0.3.4/docs/MIGRATION_TO_INDEX_AGGREGATE.md

@@ -0,0 +1,222 @@
+# Migration to Index Aggregate Architecture
+
+This document outlines the strategy for migrating from the current multiple-service architecture to the new Index aggregate root design.
+
+## Current Architecture Issues
+
+### Code Analysis of `CodeIndexingApplicationService`
+
+The current application service has several problems:
+
+1. **Service Proliferation**: 7+ domain services injected
+2. **Manual Orchestration**: Application layer contains complex business logic
+3. **Leaky Abstractions**: SQLAlchemy session management at application level
+4. **Scattered State**: Snippet state tracked across multiple services
+
+### Current Workflow Complexity
+
+```python
+# Current approach - complex orchestration
+async def run_index(self, index_id: int) -> None:
+    # 1. Get index from indexing service
+    index = await self.indexing_domain_service.get_index(index_id)
+    
+    # 2. Delete old snippets via snippet service
+    await self.snippet_domain_service.delete_snippets_for_index(index.id)
+    
+    # 3. Extract snippets via snippet service
+    snippets = await self.snippet_domain_service.extract_and_create_snippets(...)
+    
+    # 4. Manual transaction management
+    await self.session.commit()
+    
+    # 5. Create BM25 index via separate service
+    await self._create_bm25_index(snippets, progress_callback)
+    
+    # 6. Create embeddings via separate service
+    await self._create_code_embeddings(snippets, progress_callback)
+    
+    # 7. Enrich snippets via separate service
+    await self._enrich_snippets(snippets, progress_callback)
+    
+    # 8. More embeddings via separate service
+    await self._create_text_embeddings(snippets, progress_callback)
+    
+    # 9. Update timestamp via indexing service
+    await self.indexing_domain_service.update_index_timestamp(index.id)
+    
+    # 10. Final commit
+    await self.session.commit()
+```
+
+## New Architecture Benefits
+
+### Simplified Application Service
+
+```python
+# New approach - aggregate root handles complexity
+async def run_complete_indexing_workflow(
+    self, uri: AnyUrl, local_path: Path
+) -> domain_entities.Index:
+    # 1. Create index (aggregate root)
+    index = await self._index_domain_service.create_index(uri)
+    
+    # 2. Populate working copy (aggregate method)
+    index = await self._index_domain_service.clone_and_populate_working_copy(
+        index, local_path, SourceType.GIT
+    )
+    
+    # 3. Extract snippets (aggregate method)
+    index = await self._index_domain_service.extract_snippets(index)
+    
+    # 4. Simple transaction management
+    await self._session.commit()
+    
+    return index
+```
+
+## Migration Strategy
+
+### Phase 1: Parallel Implementation ✅
+
+- [x] Create new domain entities (`domain/models/entities.py`)
+- [x] Create repository protocol (`domain/models/protocols.py`)
+- [x] Create mapping layer (`infrastructure/mappers/index_mapper.py`)
+- [x] Create repository implementation (`infrastructure/sqlalchemy/index_repository.py`)
+- [x] Create domain service (`domain/services/index_service.py`)
+- [x] Create simplified application service (`application/services/simplified_indexing_service.py`)
+
+### Phase 2: Feature Parity (Next Steps)
+
+#### 2.1 Complete Index Domain Service
+- [ ] Implement actual cloning logic in `clone_and_populate_working_copy`
+- [ ] Complete snippet enrichment in `enrich_snippets_with_summaries`
+- [ ] Add snippet search capabilities to Index aggregate
+- [ ] Add BM25/embedding integration
+
+#### 2.2 Application Service Integration
+- [ ] Update application factories to create new services
+- [ ] Add legacy compatibility methods
+- [ ] Implement search functionality migration
+
+#### 2.3 CLI Integration
+- [ ] Update CLI commands to use new application service
+- [ ] Maintain backward compatibility for existing commands
+
+### Phase 3: Gradual Migration
+
+#### 3.1 New Endpoints First
+- [ ] Create new CLI commands using Index aggregate
+- [ ] Add new MCP tools using simplified service
+- [ ] Implement new features with aggregate root
+
+#### 3.2 Legacy Adaptation
+- [ ] Wrap old API calls to use new domain service
+- [ ] Provide compatibility layer for existing integrations
+- [ ] Migrate tests gradually
+
+#### 3.3 Search Migration
+- [ ] Move search logic into Index aggregate
+- [ ] Create search value objects in domain
+- [ ] Simplify search application service
+
+### Phase 4: Complete Migration
+
+#### 4.1 Remove Old Services
+- [ ] Remove `IndexingDomainService` 
+- [ ] Remove `SnippetDomainService`
+- [ ] Remove `SourceService`
+- [ ] Clean up old value objects
+
+#### 4.2 Final Cleanup
+- [ ] Remove legacy compatibility methods
+- [ ] Update all tests to use new architecture
+- [ ] Remove old application service
+
+## Code Examples
+
+### Before: Current Complexity
+
+```python
+class CodeIndexingApplicationService:
+    def __init__(self, 
+        indexing_domain_service: IndexingDomainService,
+        snippet_domain_service: SnippetDomainService,
+        source_service: SourceService,
+        bm25_service: BM25DomainService,
+        code_search_service: EmbeddingDomainService,
+        text_search_service: EmbeddingDomainService,
+        enrichment_service: EnrichmentDomainService,
+        session: AsyncSession,  # Leaky abstraction!
+    ):
+        # 7+ services to coordinate
+```
+
+### After: Aggregate Root Simplicity
+
+```python
+class SimplifiedIndexingApplicationService:
+    def __init__(self,
+        index_domain_service: IndexDomainService,
+        session: AsyncSession,
+    ):
+        # Single domain service + session
+        # All business logic in domain
+```
+
+## Benefits of Migration
+
+### 1. **Reduced Complexity**
+- Single domain service instead of 7+
+- Business logic moves to domain layer
+- Application layer focuses on coordination
+
+### 2. **Better Domain Modeling**
+- Index as true aggregate root
+- Rich domain objects with behavior
+- Proper encapsulation of business rules
+
+### 3. **Improved Testability**
+- Domain service can be tested in isolation
+- No SQLAlchemy dependencies in domain tests
+- Cleaner mocking for application tests
+
+### 4. **Enhanced Maintainability**
+- Clear boundaries between layers
+- Easier to add new features
+- Reduced coupling between services
+
+### 5. **Better Performance**
+- Fewer repository round trips
+- Optimized aggregate loading
+- Reduced object mapping overhead
+
+## Risks and Mitigation
+
+### Risk: Breaking Changes
+**Mitigation**: Implement compatibility layer during transition
+
+### Risk: Feature Regression
+**Mitigation**: Comprehensive test coverage for both old and new
+
+### Risk: Performance Impact
+**Mitigation**: Benchmark and optimize aggregate loading
+
+### Risk: Complex Migration
+**Mitigation**: Gradual, phase-by-phase approach
+
+## Success Metrics
+
+- [ ] Reduced lines of code in application service (target: 50% reduction)
+- [ ] Improved test coverage for domain logic
+- [ ] Faster indexing workflow execution
+- [ ] Fewer bugs related to state management
+- [ ] Easier onboarding for new developers
+
+## Next Immediate Steps
+
+1. **Complete Domain Service**: Finish implementing cloning and enrichment
+2. **Factory Integration**: Update application factories
+3. **Simple CLI Command**: Create one new command using aggregate
+4. **Performance Test**: Benchmark against current implementation
+5. **Migration Plan**: Detail specific steps for first legacy endpoint

{kodit-0.3.2 → kodit-0.3.4}/docs/_index.md

@@ -49,13 +49,16 @@ code. This index is used to build a snippet library, ready for ingestion into an
 
 - Index local directories and public Git repositories
 - Build comprehensive snippet libraries for LLM ingestion
-- Support for multiple codebase types and languages
-- Efficient indexing and search capabilities
+- Support for 20+ programming languages including Python, JavaScript/TypeScript, Java, Go, Rust, C/C++, C#, HTML/CSS, and more
+- Advanced code analysis with dependency tracking and call graph generation
+- Intelligent snippet extraction with context-aware dependencies
+- Efficient indexing with selective reindexing (only processes modified files)
 - Privacy first: respects .gitignore and .noindex files
 - **NEW in 0.3**: Auto-indexing configuration for shared server deployments
 - **NEW in 0.3**: Enhanced Git provider support including Azure DevOps
 - **NEW in 0.3**: Index private repositories via a PAT
 - **NEW in 0.3**: Improved progress monitoring and reporting during indexing
+- **NEW in 0.4**: Advanced code slicing infrastructure with Tree-sitter parsing
 
 ### MCP Server
 
@@ -68,7 +71,9 @@ intent. Kodit has been tested to work well with:
   - [Cursor](./getting-started/integration/index.md#integration-with-cursor)
   - [Cline](./getting-started/integration/index.md#integration-with-cline)
 - Please contribute more instructions! ... any other assistant is likely to work ...
-- **New in 0.3**: Filter snippets by source, language, author or timestamp.
+- **New in 0.3**: Advanced search filters by source, language, author, date range, and file path
+- **New in 0.3**: Hybrid search combining BM25 keyword search with semantic search
+- **New in 0.3**: Enhanced MCP tools with rich context parameters and metadata
 
 ### Enterprise Ready
 

{kodit-0.3.2 → kodit-0.3.4}/docs/reference/indexing/index.md

@@ -209,26 +209,51 @@ Kodit respects [standard ignore patterns](#ignore-patterns):
 - **`.gitignore`**: Standard Git ignore patterns
 - **`.noindex`**: Custom ignore patterns for Kodit (uses gitignore syntax)
 
-### Supported File Types
+### Supported Programming Languages
 
-Kodit automatically detects and processes files based on their extensions:
+Kodit automatically detects and processes files based on their extensions. The following languages are supported with advanced Tree-sitter parsing:
 
-| Language | Extensions |
-|----------|------------|
-| Python | `.py` |
-| JavaScript | `.js`, `.jsx` |
-| TypeScript | `.ts`, `.tsx` |
-| Go | `.go` |
-| C# | `.cs` |
+| Language | Extensions | Features |
+|----------|------------|----------|
+| Python | `.py`, `.pyw`, `.pyx`, `.pxd` | Function/method extraction, import analysis, call graph |
+| JavaScript | `.js`, `.jsx`, `.mjs` | Function extraction, ES6 modules, JSX support |
+| TypeScript | `.ts`, `.tsx` | Type definitions, interfaces, decorators |
+| Java | `.java` | Method declarations, constructors, class hierarchies |
+| Go | `.go` | Function/method extraction, package imports |
+| Rust | `.rs` | Function definitions, trait implementations |
+| C/C++ | `.c`, `.h`, `.cpp`, `.cc`, `.cxx`, `.hpp`, `.hxx` | Function definitions, header includes |
+| C# | `.cs` | Method declarations, using directives, constructors |
+| HTML | `.html`, `.htm` | Element extraction with ID/class identification |
+| CSS | `.css`, `.scss`, `.sass`, `.less` | Rule extraction, selector analysis, keyframes |
 
-### Snippet Extraction
+### Advanced Snippet Extraction
 
-Kodit uses tree-sitter to intelligently extract code snippets:
+Kodit uses a sophisticated Tree-sitter-based slicing system to intelligently extract code snippets with context:
+
+#### Core Features
 
 - **Functions and Methods**: Complete function definitions with their bodies
 - **Classes**: Class definitions and their methods
 - **Imports**: Import statements for context
 - **Dependencies**: Ancestor classes and functions that the snippet depends on
+- **Call Graph Analysis**: Builds relationships between functions to understand dependencies
+- **Context-Aware Extraction**: Includes related functions and usage examples
+- **Topological Sorting**: Orders dependencies for optimal LLM consumption
+
+#### Smart Dependency Tracking
+
+- **Import Maps**: Tracks import statements and their usage
+- **Function Calls**: Identifies which functions call which others
+- **Reverse Dependencies**: Finds all callers of a given function
+- **Usage Examples**: Includes examples of how functions are used in the codebase
+
+#### Language-Specific Extraction
+
+- **Python**: Decorators, async functions, class inheritance
+- **JavaScript/TypeScript**: Arrow functions, async/await, ES6 modules
+- **Java**: Annotations, generics, inheritance hierarchies
+- **Go**: Interfaces, struct methods, package organization
+- **HTML/CSS**: Elements with semantic context, CSS rules and selectors
 
 ## Configuration
 
@@ -269,9 +294,35 @@ DEFAULT_ENDPOINT_API_KEY=sk-your-api-key
 
 ## Advanced Features
 
-### Re-indexing Sources
+### Selective Re-indexing
+
+Kodit includes intelligent re-indexing that only processes files that have been modified:
+
+#### How It Works
+
+- **SHA256 Change Detection**: Compares file content hashes to detect changes
+- **File Status Tracking**: Tracks files as CLEAN, MODIFIED, or DELETED
+- **Incremental Updates**: Only re-processes changed files, improving performance for large codebases
+- **Metadata Preservation**: Maintains file metadata and Git information
 
-Future feature!
+#### Benefits
+
+- **Performance**: Dramatically faster re-indexing for large repositories
+- **Resource Efficiency**: Reduces CPU and memory usage during updates
+- **Consistency**: Ensures only actual changes trigger re-processing
+- **Scalability**: Enables efficient handling of large, frequently-updated codebases
+
+#### Usage
+
+Re-indexing automatically uses selective processing when you re-index an existing source:
+
+```sh
+# Re-index with selective processing
+kodit index /path/to/existing/source
+
+# Or for Git repositories
+kodit index https://github.com/username/repo.git
+```
 
 ### Progress Monitoring
 

{kodit-0.3.2 → kodit-0.3.4}/docs/reference/mcp/index.md

@@ -53,21 +53,30 @@ The search tool accepts the following parameters:
 | `related_file_paths` | list[Path] | Absolute paths to relevant files | `["/path/to/auth.py"]` |
 | `related_file_contents` | list[string] | Contents of relevant files | `["def authenticate(): ..."]` |
 | `keywords` | list[string] | Relevant keywords for the search | `["authentication", "jwt", "login"]` |
-| `language` | string \| None | Filter by programming language | `"python"`, `"go"`, `"javascript"` |
+| `language` | string \| None | Filter by programming language (20+ supported) | `"python"`, `"go"`, `"javascript"`, `"html"`, `"css"` |
 | `author` | string \| None | Filter by author name | `"john.doe"` |
 | `created_after` | string \| None | Filter by creation date (YYYY-MM-DD) | `"2023-01-01"` |
 | `created_before` | string \| None | Filter by creation date (YYYY-MM-DD) | `"2023-12-31"` |
 | `source_repo` | string \| None | Filter by source repository | `"github.com/example/repo"` |
+| `file_path` | string \| None | Filter by file path pattern | `"src/"`, `"*.test.py"` |
 
-### Search Functionality
+### Advanced Search Functionality
 
-The search tool combines multiple search strategies:
+The search tool combines multiple search strategies with sophisticated ranking:
 
-1. **Keyword Search** - Uses BM25 algorithm for exact keyword matching
-2. **Semantic Code Search** - Uses embeddings to find semantically similar code
+1. **BM25 Keyword Search** - Advanced keyword matching with relevance scoring
+2. **Semantic Code Search** - Uses embeddings to find semantically similar code patterns
 3. **Semantic Text Search** - Uses embeddings to find code matching natural language descriptions
+4. **Reciprocal Rank Fusion (RRF)** - Intelligently combines results from multiple search strategies
+5. **Context-Aware Filtering** - Advanced filtering by language, author, date, source, and file path
+6. **Dependency-Aware Results** - Returns code snippets with their dependencies and usage examples
 
-Results are fused together to provide the most relevant snippets for the user's intent.
+#### Enhanced Result Quality
+
+- **Smart Snippet Selection**: Returns functions with their dependencies and context
+- **Rich Metadata**: Each result includes file path, language, author, and creation date
+- **Usage Examples**: Includes examples of how functions are used in the codebase
+- **Topological Ordering**: Dependencies are ordered for optimal LLM consumption
 
 ## Filtering Capabilities
 
@@ -81,6 +90,8 @@ Filter results by programming language:
 > "I need to create a web server in Python. Please search for Flask or FastAPI examples and show me the best practices."
 > "I'm working on a Go microservice. Can you search for Go-specific patterns for handling HTTP requests and database connections?"
 > "I need JavaScript examples for form validation. Please search for modern JavaScript/TypeScript validation patterns."
+> "I'm building a responsive layout. Please search for CSS Grid and Flexbox examples in our stylesheets."
+> "I need HTML form examples. Please search for form elements with proper accessibility attributes."
 
 ### Author Filtering