kodit 0.5.5__py3-none-any.whl → 0.5.6__py3-none-any.whl

kodit/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.5.5'
-__version_tuple__ = version_tuple = (0, 5, 5)
+__version__ = version = '0.5.6'
+__version_tuple__ = version_tuple = (0, 5, 6)
 
 __commit_id__ = commit_id = None

kodit/app.py

@@ -63,6 +63,8 @@ async def app_lifespan(_: FastAPI) -> AsyncIterator[AppLifespanState]:
                 )
             )
         )
+    except StopAsyncIteration:
+        pass
     except Exception as e:
         raise ValueError("Embedding service is not accessible") from e
     try:

kodit/application/factories/server_factory.py

@@ -50,6 +50,9 @@ from kodit.infrastructure.bm25.vectorchord_bm25_repository import (
     VectorChordBM25Repository,
 )
 from kodit.infrastructure.cloning.git.git_python_adaptor import GitPythonAdapter
+from kodit.infrastructure.database_schema.database_schema_detector import (
+    DatabaseSchemaDetector,
+)
 from kodit.infrastructure.embedding.embedding_factory import (
     embedding_domain_service_factory,
 )
@@ -255,6 +258,7 @@ class ServerFactory:
                 text_search_service=self.text_search_service(),
                 embedding_repository=self.embedding_repository(),
                 architecture_service=self.architecture_service(),
+                database_schema_detector=DatabaseSchemaDetector(),
                 enrichment_v2_repository=self.enrichment_v2_repository(),
                 enricher_service=self.enricher(),
                 enrichment_association_repository=self.enrichment_association_repository(),

kodit/application/services/commit_indexing_application_service.py

@@ -14,6 +14,9 @@ if TYPE_CHECKING:
     from kodit.application.services.enrichment_query_service import (
         EnrichmentQueryService,
     )
+from kodit.domain.enrichments.architecture.database_schema.database_schema import (
+    DatabaseSchemaEnrichment,
+)
 from kodit.domain.enrichments.architecture.physical.physical import (
     PhysicalArchitectureEnrichment,
 )
@@ -27,6 +30,9 @@ from kodit.domain.enrichments.enrichment import (
     EnrichmentAssociation,
     EnrichmentV2,
 )
+from kodit.domain.enrichments.history.commit_description.commit_description import (
+    CommitDescriptionEnrichment,
+)
 from kodit.domain.enrichments.request import (
     EnrichmentRequest as GenericEnrichmentRequest,
 )
@@ -63,6 +69,9 @@ from kodit.domain.value_objects import (
     TaskOperation,
     TrackableType,
 )
+from kodit.infrastructure.database_schema.database_schema_detector import (
+    DatabaseSchemaDetector,
+)
 from kodit.infrastructure.slicing.api_doc_extractor import APIDocExtractor
 from kodit.infrastructure.slicing.slicer import Slicer
 from kodit.infrastructure.sqlalchemy import entities as db_entities
@@ -82,6 +91,73 @@ You are a professional software developer. You will be given a snippet of code.
 Please provide a concise explanation of the code.
 """
 
+COMMIT_DESCRIPTION_SYSTEM_PROMPT = """
+You are a professional software developer. You will be given a git commit diff.
+Please provide a concise description of what changes were made and why.
+"""
+
+DATABASE_SCHEMA_SYSTEM_PROMPT = """
+You are an expert database architect and documentation specialist.
+Your task is to create clear, visual documentation of database schemas.
+"""
+
+DATABASE_SCHEMA_TASK_PROMPT = """
+You will be provided with a database schema discovery report.
+Please create comprehensive database schema documentation.
+
+<schema_report>
+{schema_report}
+</schema_report>
+
+**Return the following:**
+
+## Entity List
+
+For each table/entity, write one line:
+- **[Table Name]**: [brief description of what it stores]
+
+## Mermaid ERD
+
+Create a Mermaid Entity Relationship Diagram showing:
+- All entities (tables)
+- Key relationships between entities (if apparent from names or common patterns)
+- Use standard ERD notation
+
+Example format:
+```mermaid
+erDiagram
+    User ||--o{{ Order : places
+    User {{
+        int id PK
+        string email
+        string name
+    }}
+    Order {{
+        int id PK
+        int user_id FK
+        datetime created_at
+    }}
+```
+
+If specific field details aren't available, show just the entity boxes and
+relationships.
+
+## Key Observations
+
+Answer these questions in 1-2 sentences each:
+1. What is the primary data model pattern (e.g., user-centric,
+   event-sourced, multi-tenant)?
+2. What migration strategy is being used?
+3. Are there any notable database design patterns or concerns?
+
+## Rules:
+- Be concise and focus on the high-level structure
+- Infer reasonable relationships from table names when explicit information
+  isn't available
+- If no database schema is found, state that clearly
+- Keep entity descriptions to 10 words or less
+"""
+
 
 class CommitIndexingApplicationService:
     """Application service for commit indexing operations."""
@@ -103,6 +179,7 @@ class CommitIndexingApplicationService:
         text_search_service: EmbeddingDomainService,
         embedding_repository: SqlAlchemyEmbeddingRepository,
         architecture_service: PhysicalArchitectureService,
+        database_schema_detector: DatabaseSchemaDetector,
         enricher_service: Enricher,
         enrichment_v2_repository: EnrichmentV2Repository,
         enrichment_association_repository: EnrichmentAssociationRepository,
@@ -124,6 +201,7 @@ class CommitIndexingApplicationService:
         self.text_search_service = text_search_service
         self.embedding_repository = embedding_repository
         self.architecture_service = architecture_service
+        self.database_schema_detector = database_schema_detector
         self.enrichment_v2_repository = enrichment_v2_repository
         self.enrichment_association_repository = enrichment_association_repository
         self.enricher_service = enricher_service
@@ -191,6 +269,10 @@ class CommitIndexingApplicationService:
                 await self.process_architecture_discovery(repository_id, commit_sha)
             elif task.type == TaskOperation.CREATE_PUBLIC_API_DOCS_FOR_COMMIT:
                 await self.process_api_docs(repository_id, commit_sha)
+            elif task.type == TaskOperation.CREATE_COMMIT_DESCRIPTION_FOR_COMMIT:
+                await self.process_commit_description(repository_id, commit_sha)
+            elif task.type == TaskOperation.CREATE_DATABASE_SCHEMA_FOR_COMMIT:
+                await self.process_database_schema(repository_id, commit_sha)
             else:
                 raise ValueError(f"Unknown task type: {task.type}")
         else:
@@ -798,6 +880,137 @@ class CommitIndexingApplicationService:
                     ]
                 )
 
+    async def process_commit_description(
+        self, repository_id: int, commit_sha: str
+    ) -> None:
+        """Handle COMMIT_DESCRIPTION task - generate commit descriptions."""
+        async with self.operation.create_child(
+            TaskOperation.CREATE_COMMIT_DESCRIPTION_FOR_COMMIT,
+            trackable_type=TrackableType.KODIT_REPOSITORY,
+            trackable_id=repository_id,
+        ) as step:
+            # Check if commit description already exists for this commit
+            if await self.enrichment_query_service.has_commit_description_for_commit(
+                commit_sha
+            ):
+                await step.skip("Commit description already exists for commit")
+                return
+
+            # Get repository path
+            repo = await self.repo_repository.get(repository_id)
+            if not repo.cloned_path:
+                raise ValueError(f"Repository {repository_id} has never been cloned")
+
+            await step.set_total(3)
+            await step.set_current(1, "Getting commit diff")
+
+            # Get the diff for this commit
+            diff = await self.scanner.git_adapter.get_commit_diff(
+                repo.cloned_path, commit_sha
+            )
+
+            if not diff or len(diff.strip()) == 0:
+                await step.skip("No diff found for commit")
+                return
+
+            await step.set_current(2, "Enriching commit description with LLM")
+
+            # Enrich the diff through the enricher
+            enrichment_request = GenericEnrichmentRequest(
+                id=commit_sha,
+                text=diff,
+                system_prompt=COMMIT_DESCRIPTION_SYSTEM_PROMPT,
+            )
+
+            enriched_content = ""
+            async for response in self.enricher_service.enrich([enrichment_request]):
+                enriched_content = response.text
+
+            # Create and save commit description enrichment
+            enrichment = await self.enrichment_v2_repository.save(
+                CommitDescriptionEnrichment(
+                    content=enriched_content,
+                )
+            )
+            if not enrichment or not enrichment.id:
+                raise ValueError(
+                    f"Failed to save commit description enrichment for commit "
+                    f"{commit_sha}"
+                )
+            await self.enrichment_association_repository.save(
+                CommitEnrichmentAssociation(
+                    enrichment_id=enrichment.id,
+                    entity_id=commit_sha,
+                )
+            )
+
+            await step.set_current(3, "Commit description enrichment completed")
+
+    async def process_database_schema(
+        self, repository_id: int, commit_sha: str
+    ) -> None:
+        """Handle DATABASE_SCHEMA task - discover and document database schemas."""
+        async with self.operation.create_child(
+            TaskOperation.CREATE_DATABASE_SCHEMA_FOR_COMMIT,
+            trackable_type=TrackableType.KODIT_REPOSITORY,
+            trackable_id=repository_id,
+        ) as step:
+            # Check if database schema already exists for this commit
+            if await self.enrichment_query_service.has_database_schema_for_commit(
+                commit_sha
+            ):
+                await step.skip("Database schema already exists for commit")
+                return
+
+            # Get repository path
+            repo = await self.repo_repository.get(repository_id)
+            if not repo.cloned_path:
+                raise ValueError(f"Repository {repository_id} has never been cloned")
+
+            await step.set_total(3)
+            await step.set_current(1, "Discovering database schemas")
+
+            # Discover database schemas
+            schema_report = await self.database_schema_detector.discover_schemas(
+                repo.cloned_path
+            )
+
+            if "No database schemas detected" in schema_report:
+                await step.skip("No database schemas found in repository")
+                return
+
+            await step.set_current(2, "Enriching schema documentation with LLM")
+
+            # Enrich the schema report through the enricher
+            enrichment_request = GenericEnrichmentRequest(
+                id=commit_sha,
+                text=DATABASE_SCHEMA_TASK_PROMPT.format(schema_report=schema_report),
+                system_prompt=DATABASE_SCHEMA_SYSTEM_PROMPT,
+            )
+
+            enriched_content = ""
+            async for response in self.enricher_service.enrich([enrichment_request]):
+                enriched_content = response.text
+
+            # Create and save database schema enrichment
+            enrichment = await self.enrichment_v2_repository.save(
+                DatabaseSchemaEnrichment(
+                    content=enriched_content,
+                )
+            )
+            if not enrichment or not enrichment.id:
+                raise ValueError(
+                    f"Failed to save database schema enrichment for commit {commit_sha}"
+                )
+            await self.enrichment_association_repository.save(
+                CommitEnrichmentAssociation(
+                    enrichment_id=enrichment.id,
+                    entity_id=commit_sha,
+                )
+            )
+
+            await step.set_current(3, "Database schema enrichment completed")
+
     async def _new_snippets_for_type(
         self, all_snippets: list[EnrichmentV2], embedding_type: EmbeddingType
     ) -> list[EnrichmentV2]:

kodit/application/services/enrichment_query_service.py

@@ -5,6 +5,9 @@ import structlog
 from kodit.domain.enrichments.architecture.architecture import (
     ENRICHMENT_TYPE_ARCHITECTURE,
 )
+from kodit.domain.enrichments.architecture.database_schema.database_schema import (
+    ENRICHMENT_SUBTYPE_DATABASE_SCHEMA,
+)
 from kodit.domain.enrichments.architecture.physical.physical import (
     ENRICHMENT_SUBTYPE_PHYSICAL,
 )
@@ -14,6 +17,10 @@ from kodit.domain.enrichments.development.snippet.snippet import (
     ENRICHMENT_SUBTYPE_SNIPPET_SUMMARY,
 )
 from kodit.domain.enrichments.enrichment import EnrichmentAssociation, EnrichmentV2
+from kodit.domain.enrichments.history.commit_description.commit_description import (
+    ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION,
+)
+from kodit.domain.enrichments.history.history import ENRICHMENT_TYPE_HISTORY
 from kodit.domain.enrichments.usage.api_docs import ENRICHMENT_SUBTYPE_API_DOCS
 from kodit.domain.enrichments.usage.usage import ENRICHMENT_TYPE_USAGE
 from kodit.domain.protocols import (
@@ -215,6 +222,36 @@ class EnrichmentQueryService:
         api_docs = await self.get_api_docs_for_commit(commit_sha)
         return len(api_docs) > 0
 
+    async def get_commit_description_for_commit(
+        self, commit_sha: str
+    ) -> list[EnrichmentV2]:
+        """Get commit description enrichments for a commit."""
+        return await self.get_enrichments_for_commit(
+            commit_sha,
+            enrichment_type=ENRICHMENT_TYPE_HISTORY,
+            enrichment_subtype=ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION,
+        )
+
+    async def has_commit_description_for_commit(self, commit_sha: str) -> bool:
+        """Check if a commit has commit description enrichments."""
+        commit_descriptions = await self.get_commit_description_for_commit(commit_sha)
+        return len(commit_descriptions) > 0
+
+    async def get_database_schema_for_commit(
+        self, commit_sha: str
+    ) -> list[EnrichmentV2]:
+        """Get database schema enrichments for a commit."""
+        return await self.get_enrichments_for_commit(
+            commit_sha,
+            enrichment_type=ENRICHMENT_TYPE_ARCHITECTURE,
+            enrichment_subtype=ENRICHMENT_SUBTYPE_DATABASE_SCHEMA,
+        )
+
+    async def has_database_schema_for_commit(self, commit_sha: str) -> bool:
+        """Check if a commit has database schema enrichments."""
+        database_schemas = await self.get_database_schema_for_commit(commit_sha)
+        return len(database_schemas) > 0
+
     async def associations_for_enrichments(
         self, enrichments: list[EnrichmentV2]
     ) -> list[EnrichmentAssociation]:

kodit/domain/enrichments/architecture/database_schema/__init__.py

@@ -0,0 +1 @@
+"""Database schema enrichments."""

kodit/domain/enrichments/architecture/database_schema/database_schema.py

@@ -0,0 +1,17 @@
+"""Database schema enrichment domain entity."""
+
+from dataclasses import dataclass
+
+from kodit.domain.enrichments.architecture.architecture import ArchitectureEnrichment
+
+ENRICHMENT_SUBTYPE_DATABASE_SCHEMA = "database_schema"
+
+
+@dataclass(frozen=True)
+class DatabaseSchemaEnrichment(ArchitectureEnrichment):
+    """Enrichment containing database schema information for a commit."""
+
+    @property
+    def subtype(self) -> str | None:
+        """Return the enrichment subtype."""
+        return ENRICHMENT_SUBTYPE_DATABASE_SCHEMA

kodit/domain/enrichments/history/__init__.py

@@ -0,0 +1 @@
+"""History enrichments."""

kodit/domain/enrichments/history/commit_description/__init__.py

@@ -0,0 +1 @@
+"""Commit description enrichments."""

kodit/domain/enrichments/history/commit_description/commit_description.py

@@ -0,0 +1,17 @@
+"""Commit description enrichment domain entity."""
+
+from dataclasses import dataclass
+
+from kodit.domain.enrichments.history.history import HistoryEnrichment
+
+ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION = "commit_description"
+
+
+@dataclass(frozen=True)
+class CommitDescriptionEnrichment(HistoryEnrichment):
+    """Enrichment containing a description of what a commit did."""
+
+    @property
+    def subtype(self) -> str | None:
+        """Return the enrichment subtype."""
+        return ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION

kodit/domain/enrichments/history/history.py

@@ -0,0 +1,18 @@
+"""History enrichment domain entity."""
+
+from abc import ABC
+from dataclasses import dataclass
+
+from kodit.domain.enrichments.enrichment import CommitEnrichment
+
+ENRICHMENT_TYPE_HISTORY = "history"
+
+
+@dataclass(frozen=True)
+class HistoryEnrichment(CommitEnrichment, ABC):
+    """Enrichment containing historical information for a commit."""
+
+    @property
+    def type(self) -> str:
+        """Return the enrichment type."""
+        return ENRICHMENT_TYPE_HISTORY

kodit/domain/protocols.py

@@ -213,6 +213,10 @@ class GitAdapter(ABC):
     ) -> list[str]:
         """Get only commit SHAs for a branch (much faster than full commit data)."""
 
+    @abstractmethod
+    async def get_commit_diff(self, local_path: Path, commit_sha: str) -> str:
+        """Get the diff for a specific commit."""
+
 
 class SnippetRepositoryV2(ABC):
     """Repository for snippet operations."""

kodit/domain/value_objects.py

@@ -614,6 +614,8 @@ class TaskOperation(StrEnum):
         "kodit.commit.create_architecture_enrichment"
     )
     CREATE_PUBLIC_API_DOCS_FOR_COMMIT = "kodit.commit.create_public_api_docs"
+    CREATE_COMMIT_DESCRIPTION_FOR_COMMIT = "kodit.commit.create_commit_description"
+    CREATE_DATABASE_SCHEMA_FOR_COMMIT = "kodit.commit.create_database_schema"
 
     def is_repository_operation(self) -> bool:
         """Check if the task operation is a repository operation."""
@@ -639,6 +641,8 @@ class PrescribedOperations:
         TaskOperation.CREATE_SUMMARY_EMBEDDINGS_FOR_COMMIT,
         TaskOperation.CREATE_ARCHITECTURE_ENRICHMENT_FOR_COMMIT,
         TaskOperation.CREATE_PUBLIC_API_DOCS_FOR_COMMIT,
+        TaskOperation.CREATE_COMMIT_DESCRIPTION_FOR_COMMIT,
+        TaskOperation.CREATE_DATABASE_SCHEMA_FOR_COMMIT,
     ]
     SYNC_REPOSITORY: ClassVar[list[TaskOperation]] = [
         TaskOperation.SCAN_REPOSITORY,

kodit/infrastructure/cloning/git/git_python_adaptor.py

@@ -532,3 +532,44 @@ class GitPythonAdapter(GitAdapter):
                 raise
 
         return await asyncio.get_event_loop().run_in_executor(self.executor, _get_tags)
+
+    async def get_commit_diff(self, local_path: Path, commit_sha: str) -> str:
+        """Get the diff for a specific commit."""
+
+        def _get_diff() -> str:
+            try:
+                repo = Repo(local_path)
+                commit = repo.commit(commit_sha)
+
+                # If this is the first commit (no parents), show diff against empty tree
+                if not commit.parents:
+                    diffs = commit.diff(None, create_patch=True)
+                    if not diffs:
+                        return ""
+                    first_diff = diffs[0]
+                    diff_bytes = first_diff.diff
+                    if isinstance(diff_bytes, bytes):
+                        return diff_bytes.decode("utf-8")
+                    return str(diff_bytes) if diff_bytes is not None else ""
+
+                # For commits with parents, show diff against first parent
+                parent = commit.parents[0]
+                diffs = parent.diff(commit, create_patch=True)
+
+                # Combine all diffs into a single string
+                diff_text = ""
+                for diff in diffs:
+                    diff_bytes = diff.diff
+                    if diff_bytes and isinstance(diff_bytes, bytes):
+                        diff_text += diff_bytes.decode("utf-8")
+            except Exception as e:
+                self._log.error(
+                    f"Failed to get diff for commit {commit_sha} in {local_path}: {e}"
+                )
+                raise
+            else:
+                return diff_text
+
+        return await asyncio.get_event_loop().run_in_executor(
+            self.executor, _get_diff
+        )

kodit/infrastructure/database_schema/__init__.py

@@ -0,0 +1 @@
+"""Database schema detection infrastructure."""

kodit/infrastructure/database_schema/database_schema_detector.py

@@ -0,0 +1,268 @@
+"""Database schema detector for discovering database schemas in a repository."""
+
+import re
+from pathlib import Path
+from typing import ClassVar
+
+
+class DatabaseSchemaDetector:
+    """Detects database schemas from various sources in a repository."""
+
+    # File patterns to look for
+    MIGRATION_PATTERNS: ClassVar[list[str]] = [
+        "**/migrations/**/*.sql",
+        "**/migrations/**/*.py",
+        "**/migrate/**/*.sql",
+        "**/migrate/**/*.go",
+        "**/db/migrate/**/*.rb",
+        "**/alembic/versions/**/*.py",
+        "**/liquibase/**/*.xml",
+        "**/flyway/**/*.sql",
+    ]
+
+    SQL_FILE_PATTERNS: ClassVar[list[str]] = [
+        "**/*.sql",
+        "**/schema/**/*.sql",
+        "**/schemas/**/*.sql",
+        "**/database/**/*.sql",
+        "**/db/**/*.sql",
+    ]
+
+    ORM_MODEL_PATTERNS: ClassVar[list[str]] = [
+        "**/models/**/*.py",  # SQLAlchemy, Django
+        "**/models/**/*.go",  # GORM
+        "**/entities/**/*.py",  # SQLAlchemy
+        "**/entities/**/*.ts",  # TypeORM
+        "**/entities/**/*.js",  # TypeORM/Sequelize
+    ]
+
+    # Regex patterns for schema detection
+    CREATE_TABLE_PATTERN = re.compile(
+        r"CREATE\s+TABLE\s+(?:IF\s+NOT\s+EXISTS\s+)?[`\"]?(\w+)[`\"]?",
+        re.IGNORECASE,
+    )
+
+    SQLALCHEMY_MODEL_PATTERN = re.compile(
+        r"class\s+(\w+)\s*\([^)]*(?:Base|Model|db\.Model)[^)]*\):",
+        re.MULTILINE,
+    )
+
+    GORM_MODEL_PATTERN = re.compile(
+        r"type\s+(\w+)\s+struct\s*{[^}]*gorm\.Model",
+        re.MULTILINE | re.DOTALL,
+    )
+
+    TYPEORM_ENTITY_PATTERN = re.compile(
+        r"@Entity\([^)]*\)\s*(?:export\s+)?class\s+(\w+)",
+        re.MULTILINE,
+    )
+
+    async def discover_schemas(self, repo_path: Path) -> str:
+        """Discover database schemas and generate a structured report."""
+        findings: dict[str, set[str] | list[str] | list[dict] | None] = {
+            "tables": set(),
+            "migration_files": [],
+            "sql_files": [],
+            "orm_models": [],
+            "orm_type": None,
+        }
+
+        # Detect migration files
+        await self._detect_migrations(repo_path, findings)
+
+        # Detect SQL schema files
+        await self._detect_sql_files(repo_path, findings)
+
+        # Detect ORM models
+        await self._detect_orm_models(repo_path, findings)
+
+        # Generate report
+        return self._generate_report(findings)
+
+    async def _detect_migrations(self, repo_path: Path, findings: dict) -> None:
+        """Detect migration files."""
+        for pattern in self.MIGRATION_PATTERNS:
+            for file_path in repo_path.glob(pattern):
+                if file_path.is_file():
+                    findings["migration_files"].append(str(file_path.relative_to(repo_path)))
+                    # Try to extract table names from migrations
+                    await self._extract_tables_from_file(file_path, findings)
+
+    async def _detect_sql_files(self, repo_path: Path, findings: dict) -> None:
+        """Detect SQL schema files."""
+        migration_paths = set(findings["migration_files"])
+
+        for pattern in self.SQL_FILE_PATTERNS:
+            for file_path in repo_path.glob(pattern):
+                if file_path.is_file():
+                    rel_path = str(file_path.relative_to(repo_path))
+                    # Skip if already counted as migration
+                    if rel_path not in migration_paths:
+                        findings["sql_files"].append(rel_path)
+                        await self._extract_tables_from_file(file_path, findings)
+
+    async def _detect_orm_models(self, repo_path: Path, findings: dict) -> None:
+        """Detect ORM model files."""
+        for pattern in self.ORM_MODEL_PATTERNS:
+            for file_path in repo_path.glob(pattern):
+                if file_path.is_file():
+                    rel_path = str(file_path.relative_to(repo_path))
+                    models = await self._extract_orm_models(file_path)
+                    if models:
+                        findings["orm_models"].append({
+                            "file": rel_path,
+                            "models": models,
+                        })
+                        findings["tables"].update(models)
+
+    async def _extract_tables_from_file(self, file_path: Path, findings: dict) -> None:
+        """Extract table names from SQL or migration files."""
+        try:
+            content = file_path.read_text(encoding="utf-8", errors="ignore")
+
+            # Look for CREATE TABLE statements
+            for match in self.CREATE_TABLE_PATTERN.finditer(content):
+                table_name = match.group(1)
+                findings["tables"].add(table_name)
+
+        except (OSError, UnicodeDecodeError):
+            pass
+
+    async def _extract_orm_models(self, file_path: Path) -> list[str]:
+        """Extract ORM model names from model files."""
+        models: list[str] = []
+
+        try:
+            content = file_path.read_text(encoding="utf-8", errors="ignore")
+            suffix = file_path.suffix
+
+            if suffix == ".py":
+                # SQLAlchemy or Django models
+                models.extend(
+                    match.group(1)
+                    for match in self.SQLALCHEMY_MODEL_PATTERN.finditer(content)
+                )
+
+            elif suffix == ".go":
+                # GORM models
+                models.extend(
+                    match.group(1)
+                    for match in self.GORM_MODEL_PATTERN.finditer(content)
+                )
+
+            elif suffix in [".ts", ".js"]:
+                # TypeORM entities
+                models.extend(
+                    match.group(1)
+                    for match in self.TYPEORM_ENTITY_PATTERN.finditer(content)
+                )
+
+        except (OSError, UnicodeDecodeError):
+            pass
+
+        return models
+
+    def _generate_report(self, findings: dict) -> str:  # noqa: PLR0915, C901, PLR0912
+        """Generate a structured report of database schema findings."""
+        lines = []
+
+        # Summary
+        lines.append("# Database Schema Discovery Report")
+        lines.append("")
+
+        has_findings = (
+            findings["tables"]
+            or findings["migration_files"]
+            or findings["sql_files"]
+            or findings["orm_models"]
+        )
+        if not has_findings:
+            lines.append("No database schemas detected in this repository.")
+            return "\n".join(lines)
+
+        # Tables/Entities found
+        if findings["tables"]:
+            lines.append(f"## Detected Tables/Entities ({len(findings['tables'])})")
+            lines.append("")
+            lines.extend(f"- {table}" for table in sorted(findings["tables"]))
+            lines.append("")
+
+        # Migration files
+        if findings["migration_files"]:
+            lines.append(f"## Migration Files ({len(findings['migration_files'])})")
+            lines.append("")
+            lines.append(
+                "Database migrations detected, suggesting schema evolution over time:"
+            )
+            lines.extend(
+                f"- {mig_file}" for mig_file in findings["migration_files"][:10]
+            )
+            if len(findings["migration_files"]) > 10:
+                lines.append(f"- ... and {len(findings['migration_files']) - 10} more")
+            lines.append("")
+
+        # SQL files
+        if findings["sql_files"]:
+            lines.append(f"## SQL Schema Files ({len(findings['sql_files'])})")
+            lines.append("")
+            lines.extend(f"- {sql_file}" for sql_file in findings["sql_files"][:10])
+            if len(findings["sql_files"]) > 10:
+                lines.append(f"- ... and {len(findings['sql_files']) - 10} more")
+            lines.append("")
+
+        # ORM models
+        if findings["orm_models"]:
+            lines.append(f"## ORM Models ({len(findings['orm_models'])} files)")
+            lines.append("")
+            lines.append(
+                "ORM models detected, suggesting object-relational mapping:"
+            )
+            for orm_info in findings["orm_models"][:10]:  # Limit to first 10
+                model_names = ", ".join(orm_info["models"][:5])
+                lines.append(f"- {orm_info['file']}: {model_names}")
+                if len(orm_info["models"]) > 5:
+                    lines.append(f"  (and {len(orm_info['models']) - 5} more models)")
+            if len(findings["orm_models"]) > 10:
+                lines.append(f"- ... and {len(findings['orm_models']) - 10} more files")
+            lines.append("")
+
+        # Inferred database type
+        lines.append("## Inferred Information")
+        lines.append("")
+
+        mig_files_str = str(findings.get("migration_files", []))
+        mig_files = findings.get("migration_files", [])
+
+        if "alembic" in mig_files_str:
+            lines.append("- Migration framework: Alembic (Python/SQLAlchemy)")
+        elif "django" in mig_files_str or any(
+            "migrations" in f and f.endswith(".py") for f in mig_files
+        ):
+            lines.append("- Migration framework: Django Migrations")
+        elif any(".go" in f for f in mig_files):
+            lines.append(
+                "- Migration framework: Go-based migrations (golang-migrate)"
+            )
+        elif "flyway" in mig_files_str:
+            lines.append("- Migration framework: Flyway")
+        elif "liquibase" in mig_files_str:
+            lines.append("- Migration framework: Liquibase")
+
+        if findings["orm_models"]:
+            orm_models = findings["orm_models"]
+            py_models = sum(1 for m in orm_models if m["file"].endswith(".py"))
+            go_models = sum(1 for m in orm_models if m["file"].endswith(".go"))
+            ts_models = sum(
+                1 for m in orm_models if m["file"].endswith((".ts", ".js"))
+            )
+
+            if py_models > 0:
+                lines.append("- ORM: Python (likely SQLAlchemy or Django ORM)")
+            if go_models > 0:
+                lines.append("- ORM: Go (likely GORM)")
+            if ts_models > 0:
+                lines.append(
+                    "- ORM: TypeScript/JavaScript (likely TypeORM or Sequelize)"
+                )
+
+        return "\n".join(lines)

kodit/infrastructure/sqlalchemy/enrichment_v2_repository.py

@@ -7,6 +7,10 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from kodit.domain.enrichments.architecture.architecture import (
     ENRICHMENT_TYPE_ARCHITECTURE,
 )
+from kodit.domain.enrichments.architecture.database_schema.database_schema import (
+    ENRICHMENT_SUBTYPE_DATABASE_SCHEMA,
+    DatabaseSchemaEnrichment,
+)
 from kodit.domain.enrichments.architecture.physical.physical import (
     ENRICHMENT_SUBTYPE_PHYSICAL,
     PhysicalArchitectureEnrichment,
@@ -19,6 +23,11 @@ from kodit.domain.enrichments.development.snippet.snippet import (
     SnippetEnrichmentSummary,
 )
 from kodit.domain.enrichments.enrichment import EnrichmentV2
+from kodit.domain.enrichments.history.commit_description.commit_description import (
+    ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION,
+    CommitDescriptionEnrichment,
+)
+from kodit.domain.enrichments.history.history import ENRICHMENT_TYPE_HISTORY
 from kodit.domain.enrichments.usage.api_docs import (
     ENRICHMENT_SUBTYPE_API_DOCS,
     APIDocEnrichment,
@@ -131,6 +140,26 @@ class SQLAlchemyEnrichmentV2Repository(
                 created_at=db_entity.created_at,
                 updated_at=db_entity.updated_at,
             )
+        if (
+            db_entity.type == ENRICHMENT_TYPE_HISTORY
+            and db_entity.subtype == ENRICHMENT_SUBTYPE_COMMIT_DESCRIPTION
+        ):
+            return CommitDescriptionEnrichment(
+                id=db_entity.id,
+                content=db_entity.content,
+                created_at=db_entity.created_at,
+                updated_at=db_entity.updated_at,
+            )
+        if (
+            db_entity.type == ENRICHMENT_TYPE_ARCHITECTURE
+            and db_entity.subtype == ENRICHMENT_SUBTYPE_DATABASE_SCHEMA
+        ):
+            return DatabaseSchemaEnrichment(
+                id=db_entity.id,
+                content=db_entity.content,
+                created_at=db_entity.created_at,
+                updated_at=db_entity.updated_at,
+            )
 
         raise ValueError(
             f"Unknown enrichment type: {db_entity.type}/{db_entity.subtype}"

{kodit-0.5.5.dist-info → kodit-0.5.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kodit
-Version: 0.5.5
+Version: 0.5.6
 Summary: Code indexing for better AI code generation
 Project-URL: Homepage, https://docs.helixml.tech/kodit/
 Project-URL: Documentation, https://docs.helixml.tech/kodit/

{kodit-0.5.5.dist-info → kodit-0.5.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
 kodit/.gitignore,sha256=ztkjgRwL9Uud1OEi36hGQeDGk3OLK1NfDEO8YqGYy8o,11
 kodit/__init__.py,sha256=aEKHYninUq1yh6jaNfvJBYg-6fenpN132nJt1UU6Jxs,59
-kodit/_version.py,sha256=0gHg6pqkExJvz1iV3rjNnM6ZmxmZPlhVrGzZVWp6WuA,704
-kodit/app.py,sha256=niIfZiuuDp7mLzrBwQhx_FU7RvKfUALNV5y0o43miss,5802
+kodit/_version.py,sha256=cK44j3gESPDerYNsAlInZd36FaFcP1dYcSF1jeRDXF8,704
+kodit/app.py,sha256=7WxSQcktnpYBmjO1skIjMeBu55rVVRf4lotBEq55pAM,5846
 kodit/cli.py,sha256=QSTXIUDxZo3anIONY-grZi9_VSehWoS8QoVJZyOmWPQ,3086
 kodit/cli_utils.py,sha256=umkvt4kWNapk6db6RGz6bmn7oxgDpsW2Vo09MZ37OGg,2430
 kodit/config.py,sha256=x_67lawaejOenJvl8yMxzXgdIkeWx8Yyc2ISO37GCvc,8031
@@ -13,19 +13,19 @@ kodit/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 kodit/application/__init__.py,sha256=mH50wTpgP9dhbKztFsL8Dda9Hi18TSnMVxXtpp4aGOA,35
 kodit/application/factories/__init__.py,sha256=bU5CvEnaBePZ7JbkCOp1MGTNP752bnU2uEqmfy5FdRk,37
 kodit/application/factories/reporting_factory.py,sha256=3IpRiAw_olM69db-jbDAtjyGtd6Nh5o8jUJX3-rXCA8,1421
-kodit/application/factories/server_factory.py,sha256=Y99haqn_cv9Gci4cC4YRzkfoLUTWtERS9Ghgo5NjGFI,17236
+kodit/application/factories/server_factory.py,sha256=dr0X_zQRUlEybtGZ3NS-kkwTU-K96u2D1Qw5xhWkd88,17409
 kodit/application/services/__init__.py,sha256=p5UQNw-H5sxQvs5Etfte93B3cJ1kKW6DNxK34uFvU1E,38
 kodit/application/services/code_search_application_service.py,sha256=ceyv5TTN-jvlOFOupGa9XwfTTraLNN2GU55kFeulVXY,7763
-kodit/application/services/commit_indexing_application_service.py,sha256=SZEWjgFR1dd1yFsWnVxtOUQ_Dh_AA37cXhIsbrmAvd0,34746
-kodit/application/services/enrichment_query_service.py,sha256=ICAuMY8iw1LlioXXGDPLCcxeL9kPQYMbNg9YNvOpbXk,13362
+kodit/application/services/commit_indexing_application_service.py,sha256=CIJdBdAIdere6fEJ1KytQgDu0jNXoDiE748aFcEiOmQ,42631
+kodit/application/services/enrichment_query_service.py,sha256=RMVze-DzS5zAki1iC96Kid7tbg-nHSv0z8eqPsiURqc,15002
 kodit/application/services/indexing_worker_service.py,sha256=59cZthlzViOVrAWEoZqUTCfLzxx2OO_FOGdM3pYf9Mc,4065
 kodit/application/services/queue_service.py,sha256=pIHTS8M65FzAhZH5kn54BTiZ43sCbsALYdCFTz9wdqE,2692
 kodit/application/services/reporting.py,sha256=cwe-S-UpSOE6xSAEhoD1hi4hSWk1bW3YRLJ7463fIvM,3518
 kodit/application/services/sync_scheduler.py,sha256=hVT3dlmvfbqXKOV_KU5ZQ5gEKBGPJTlvJcF9gP2ZHQM,2853
 kodit/domain/__init__.py,sha256=TCpg4Xx-oF4mKV91lo4iXqMEfBT1OoRSYnbG-zVWolA,66
 kodit/domain/errors.py,sha256=yIsgCjM_yOFIg8l7l-t7jM8pgeAX4cfPq0owf7iz3DA,106
-kodit/domain/protocols.py,sha256=YQqL1XO2OWqYhPC8W7nyPrqGW3NKafMEJn2HEGXwHIk,7664
-kodit/domain/value_objects.py,sha256=svHQixeLa8fzaJ5NuKl3rBLBVrPfV7VvFd2-U-Vh_Sk,17818
+kodit/domain/protocols.py,sha256=KxTHnYbECvMoXdbvXNHVF-l-OEr2kzQsoxlVXbatgwg,7814
+kodit/domain/value_objects.py,sha256=FW0sTMtcl0Q1qej7vzEg7-Gsv86Z01IbPrDdudsgU3g,18097
 kodit/domain/enrichments/__init__.py,sha256=UpQMnMEHqaK3u3K-eJZOC28kfBPHALLAjFMdyYBXSPE,33
 kodit/domain/enrichments/enricher.py,sha256=jnZ5X9RmZA8Acy-RBS2TbEoBg9QSm8AgleqwS9h5WlY,512
 kodit/domain/enrichments/enrichment.py,sha256=_4lAOFibvSRN-01HB7it61k38IGQsub0gVERqRrhWPs,1776
@@ -33,6 +33,8 @@ kodit/domain/enrichments/request.py,sha256=6zBQhliDcdw8vS4sYPG2mqZSDSbQ5VzY1YQ-4
 kodit/domain/enrichments/response.py,sha256=NzoMAKgs7c2yo9vvgWjQDo1yO0koKHbbY_SrsqsalAk,205
 kodit/domain/enrichments/architecture/__init__.py,sha256=hBSliXMuixUZKtF-_zvcgQjnqrdyc4_SjYG2PTRFYpg,39
 kodit/domain/enrichments/architecture/architecture.py,sha256=_3nF9qdBdcA8rTXPkb1KO2F7OXTcH9SajqNYB-ICaZA,507
+kodit/domain/enrichments/architecture/database_schema/__init__.py,sha256=xS5UGMfHqOXjpr4ZZQup3IUtevJxBDXMH4fO7wuH5vM,35
+kodit/domain/enrichments/architecture/database_schema/database_schema.py,sha256=OOiG5SrN4Jyw_L6_-UVg4DaGWNo5JLiii7e21ZLtDvY,529
 kodit/domain/enrichments/architecture/physical/__init__.py,sha256=4jc89cGxALWo8d3Xzfb5t-YjcCyDb1dDVGwTqVYBFmc,48
 kodit/domain/enrichments/architecture/physical/discovery_notes.py,sha256=Wdv41rkUcMgRqXWB5Q9roaGMGFznH4V_I7mELUvDShw,636
 kodit/domain/enrichments/architecture/physical/formatter.py,sha256=V_JvHsGDPPJ-TqGS-G61P3OS3xe0QpS2NLBEk5jX6Yc,351
@@ -41,6 +43,10 @@ kodit/domain/enrichments/development/__init__.py,sha256=ls7zlKUpSpyLZRl-WTuaow9C
 kodit/domain/enrichments/development/development.py,sha256=amzcheLEtXbOyhhmjlay_yt1Z2FRyW2CrR8wZWkpC0g,483
 kodit/domain/enrichments/development/snippet/__init__.py,sha256=M5XVnlDgfqSE5UiAqkQwE1Mbr5Rg8zQpcspHKC3k_xU,34
 kodit/domain/enrichments/development/snippet/snippet.py,sha256=A1f385Bu3_ZBaDKQrGHZMb6GIiQoo-hORFSw2ca56yQ,791
+kodit/domain/enrichments/history/__init__.py,sha256=OXS0MOFEjD76rBOmLl8yA2L3Q8NYebBkoGhAmgbO2O0,27
+kodit/domain/enrichments/history/history.py,sha256=pdmkU2ZZGFBsZDQ7kKo1hj-GaVKUd0v4Q2Fu15WE2A8,464
+kodit/domain/enrichments/history/commit_description/__init__.py,sha256=j0fVMIkao9RzkLa6JakBPP40KrELl1eb-dfOLvfADMQ,38
+kodit/domain/enrichments/history/commit_description/commit_description.py,sha256=96yKz-YsyWPfUu7zFtnT9AhRe7DjLmky9z0jy7oreFo,518
 kodit/domain/enrichments/usage/__init__.py,sha256=7W36rvCF6DH-VqW2RiqU6GMlkYYHZy9Wm0DL_3_fbRc,40
 kodit/domain/enrichments/usage/api_docs.py,sha256=5cvkNXUfAWDb0HJGIViAzIEZDGEnBnWYhkacs4lHCYA,470
 kodit/domain/enrichments/usage/usage.py,sha256=U_JrxwXWlFtOzCP7fbfMd-NH75W44MwVFliONMzYB4U,453
@@ -89,8 +95,10 @@ kodit/infrastructure/bm25/__init__.py,sha256=DmGbrEO34FOJy4e685BbyxLA7gPW1eqs2gA
 kodit/infrastructure/bm25/local_bm25_repository.py,sha256=YE3pUkPS5n1JNu6oSM_HRBOXM8U04HiY8dMMZCf9CMQ,5197
 kodit/infrastructure/bm25/vectorchord_bm25_repository.py,sha256=LjbUPj4nPMb9pdEudThUbZTmQjhxvpN314EzKGpXfi0,8621
 kodit/infrastructure/cloning/git/__init__.py,sha256=20ePcp0qE6BuLsjsv4KYB1DzKhMIMsPXwEqIEZtjTJs,34
-kodit/infrastructure/cloning/git/git_python_adaptor.py,sha256=X0cyoBz3AWeY4lEmAyAqD4i3bXhSBh0ggKng1ERoswI,19944
+kodit/infrastructure/cloning/git/git_python_adaptor.py,sha256=GCBdswC5txbt8_TWbMEbhvRvlmOvPCLwb6qBlx7b3XU,21594
 kodit/infrastructure/cloning/git/working_copy.py,sha256=sPKQN-A1gDVV_QJISNNP4PqxRWxyj5owv5tvWfXMl44,3909
+kodit/infrastructure/database_schema/__init__.py,sha256=jgejYX70fjV69zCuOBiNw3oCQlCKYzxTkjnUUUU7DY0,48
+kodit/infrastructure/database_schema/database_schema_detector.py,sha256=zXU7HqrZU4_EYckloKDbH0gZvZ3_TJG5-Bd5PAkEkXc,10167
 kodit/infrastructure/embedding/__init__.py,sha256=F-8nLlWAerYJ0MOIA4tbXHLan8bW5rRR84vzxx6tRKI,39
 kodit/infrastructure/embedding/embedding_factory.py,sha256=6nP8HKKlNWmDE8ATT5tNQHgPqeTDUMpRuWwn2rsfrOQ,3446
 kodit/infrastructure/embedding/local_vector_search_repository.py,sha256=urccvadIF-uizmYuzK7ii7hl2HaV7swHCiS8P6n7U18,3507
@@ -134,7 +142,7 @@ kodit/infrastructure/slicing/slicer.py,sha256=EDYkoLf6RsTVloudZUq6LS5X10JJAHWcKW
 kodit/infrastructure/sqlalchemy/__init__.py,sha256=UXPMSF_hgWaqr86cawRVqM8XdVNumQyyK5B8B97GnlA,33
 kodit/infrastructure/sqlalchemy/embedding_repository.py,sha256=OhSIuNEQ725WoxaIpK3jcZvUVPW-b95HKRXr1HjurmI,8824
 kodit/infrastructure/sqlalchemy/enrichment_association_repository.py,sha256=mjlGH4vkIv1cPfhkZ4SUyGWpMbgeS7QljsK54yQvV4g,2615
-kodit/infrastructure/sqlalchemy/enrichment_v2_repository.py,sha256=9Yiv8I86qOD3YiNcucs6686JtY_8DOQFpEFJmx1_8HM,5177
+kodit/infrastructure/sqlalchemy/enrichment_v2_repository.py,sha256=9C7y6aRzHHkKJYTTAFxU5p0kwJVBjhqHvs-wUZDWsmk,6350
 kodit/infrastructure/sqlalchemy/entities.py,sha256=kvZqUPCN2TNgovdNAT_0h4Y8zrgFWwkk-OecvcHIz-A,14852
 kodit/infrastructure/sqlalchemy/git_branch_repository.py,sha256=dW9kBr8aDBXXVmw1zEux2mueiKhTcpG0JxnLuz5yZ3w,3106
 kodit/infrastructure/sqlalchemy/git_commit_repository.py,sha256=jzYpFV1gjI-Wfgai-hxesglYn6XD384mqIorV1AtNCA,1991
@@ -169,8 +177,8 @@ kodit/utils/dump_config.py,sha256=dd5uPgqh6ATk02Zt59t2JFKR9X17YWjHudV0nE8VktE,11
 kodit/utils/dump_openapi.py,sha256=EasYOnnpeabwb_sTKQUBrrOLHjPcOFQ7Zx0YKpx9fmM,1239
 kodit/utils/generate_api_paths.py,sha256=TMtx9v55podDfUmiWaHgJHLtEWLV2sLL-5ejGFMPzAo,3569
 kodit/utils/path_utils.py,sha256=UB_81rx7Y1G1jalVv2PX8miwaprBbcqEdtoQ3hPT3kU,2451
-kodit-0.5.5.dist-info/METADATA,sha256=KprUWaNcvHEDmwR0zjo59ln_jUNOC_d6-AokObNZbk4,7703
-kodit-0.5.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kodit-0.5.5.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
-kodit-0.5.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-kodit-0.5.5.dist-info/RECORD,,
+kodit-0.5.6.dist-info/METADATA,sha256=7G7BfnWWbmDkwSSiKribmesiUY5NlzjcxwqsZiTJjUw,7703
+kodit-0.5.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kodit-0.5.6.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
+kodit-0.5.6.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kodit-0.5.6.dist-info/RECORD,,