kodit 0.3.12__tar.gz → 0.3.13__tar.gz

{kodit-0.3.12 → kodit-0.3.13}/.github/workflows/docker.yaml

@@ -91,6 +91,8 @@ jobs:
             type=sha,enable=${{ steps.pyver.outputs.ENABLE_DEFAULT }}
             type=sha,suffix=-py${{ steps.pyver.outputs.SHORT_PY }}
             type=raw,value=latest,enable=${{ steps.pyver.outputs.ENABLE_DEFAULT && startsWith(github.ref, 'refs/tags/') }}
+          flavor: |
+            latest=false
 
       - name: Build and push Docker image
         id: push

{kodit-0.3.12 → kodit-0.3.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kodit
-Version: 0.3.12
+Version: 0.3.13
 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-0.3.12 → kodit-0.3.13}/docs/reference/api/index.md

@@ -12,7 +12,7 @@ look at the [hosted version](https://kodit.helix.ml/docs).
 This is the REST API for the Kodit server. Please refer to the
 [Kodit documentation](https://docs.helix.ml/kodit/) for more information.
     
-Current version: 0.3.12
+Current version: 0.3.13
 
 ## Authentication
 

{kodit-0.3.12 → kodit-0.3.13}/docs/reference/api/openapi.json

@@ -3,7 +3,7 @@
   "info": {
     "title": "kodit API",
     "description": "\nThis is the REST API for the Kodit server. Please refer to the\n[Kodit documentation](https://docs.helix.ml/kodit/) for more information.\n    ",
-    "version": "0.3.12"
+    "version": "0.3.13"
   },
   "paths": {
     "/healthz": {

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.3.12'
-__version_tuple__ = version_tuple = (0, 3, 12)
+__version__ = version = '0.3.13'
+__version_tuple__ = version_tuple = (0, 3, 13)

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/app.py

@@ -13,6 +13,7 @@ from kodit.application.services.sync_scheduler import SyncSchedulerService
 from kodit.config import AppContext
 from kodit.infrastructure.api.v1.routers import indexes_router, search_router
 from kodit.infrastructure.api.v1.schemas.context import AppLifespanState
+from kodit.log import configure_logging, configure_telemetry
 from kodit.mcp import mcp
 from kodit.middleware import ASGICancelledErrorMiddleware, logging_middleware
 
@@ -26,10 +27,13 @@ async def app_lifespan(_: FastAPI) -> AsyncIterator[AppLifespanState]:
     """Manage application lifespan for auto-indexing and sync."""
     global _auto_indexing_service, _sync_scheduler_service  # noqa: PLW0603
 
+    # Setup app_context and implement logging and telemetry
     app_context = AppContext()
-    db = await app_context.get_db()
+    configure_logging(app_context)
+    configure_telemetry(app_context)
 
     # Start auto-indexing service
+    db = await app_context.get_db()
     _auto_indexing_service = AutoIndexingService(
         app_context=app_context,
         session_factory=db.session_factory,

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/config.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import asyncio
+from enum import Enum
 from functools import wraps
 from pathlib import Path
 from typing import TYPE_CHECKING, Annotated, Any, Literal, TypeVar
@@ -18,15 +19,22 @@ from pydantic_settings import (
     SettingsConfigDict,
 )
 
+from kodit.database import Database
+
 if TYPE_CHECKING:
     from collections.abc import Callable, Coroutine
 
 
-from kodit.database import Database
+class LogFormat(Enum):
+    """The format of the log output."""
+
+    PRETTY = "pretty"
+    JSON = "json"
+
 
 DEFAULT_BASE_DIR = Path.home() / ".kodit"
 DEFAULT_LOG_LEVEL = "INFO"
-DEFAULT_LOG_FORMAT = "pretty"
+DEFAULT_LOG_FORMAT = LogFormat.PRETTY
 DEFAULT_DISABLE_TELEMETRY = False
 T = TypeVar("T")
 
@@ -40,6 +48,7 @@ class Endpoint(BaseModel):
     base_url: str | None = None
     model: str | None = None
     api_key: str | None = None
+    num_parallel_tasks: int | None = None
 
 
 class Search(BaseModel):
@@ -165,7 +174,7 @@ class AppContext(BaseSettings):
         default_factory=lambda data: f"sqlite+aiosqlite:///{data['data_dir']}/kodit.db"
     )
     log_level: str = Field(default=DEFAULT_LOG_LEVEL)
-    log_format: str = Field(default=DEFAULT_LOG_FORMAT)
+    log_format: LogFormat = Field(default=DEFAULT_LOG_FORMAT)
     disable_telemetry: bool = Field(default=DEFAULT_DISABLE_TELEMETRY)
     default_endpoint: Endpoint | None = Field(
         default=None,

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/infrastructure/embedding/embedding_factory.py

@@ -14,6 +14,7 @@ from kodit.infrastructure.embedding.embedding_providers.local_embedding_provider
     LocalEmbeddingProvider,
 )
 from kodit.infrastructure.embedding.embedding_providers.openai_embedding_provider import (  # noqa: E501
+    OPENAI_NUM_PARALLEL_TASKS,
     OpenAIEmbeddingProvider,
 )
 from kodit.infrastructure.embedding.local_vector_search_repository import (
@@ -55,6 +56,7 @@ def embedding_domain_service_factory(
                 max_retries=2,
             ),
             model_name=endpoint.model or "text-embedding-3-small",
+            num_parallel_tasks=endpoint.num_parallel_tasks or OPENAI_NUM_PARALLEL_TASKS,
         )
     else:
         log_event("kodit.embedding", {"provider": "local"})

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/infrastructure/embedding/embedding_providers/openai_embedding_provider.py

@@ -18,14 +18,17 @@ MAX_TOKENS = 8192  # Conservative token limit for the embedding model
 BATCH_SIZE = (
     10  # Maximum number of items per API call (keeps existing test expectations)
 )
-OPENAI_NUM_PARALLEL_TASKS = 25  # Semaphore limit for concurrent OpenAI requests
+OPENAI_NUM_PARALLEL_TASKS = 10  # Semaphore limit for concurrent OpenAI requests
 
 
 class OpenAIEmbeddingProvider(EmbeddingProvider):
     """OpenAI embedding provider that uses OpenAI's embedding API."""
 
     def __init__(
-        self, openai_client: AsyncOpenAI, model_name: str = "text-embedding-3-small"
+        self,
+        openai_client: AsyncOpenAI,
+        model_name: str = "text-embedding-3-small",
+        num_parallel_tasks: int = OPENAI_NUM_PARALLEL_TASKS,
     ) -> None:
         """Initialize the OpenAI embedding provider.
 
@@ -36,6 +39,7 @@ class OpenAIEmbeddingProvider(EmbeddingProvider):
         """
         self.openai_client = openai_client
         self.model_name = model_name
+        self.num_parallel_tasks = num_parallel_tasks
         self.log = structlog.get_logger(__name__)
 
         # Lazily initialised token encoding
@@ -78,7 +82,7 @@ class OpenAIEmbeddingProvider(EmbeddingProvider):
         # Process batches concurrently (but bounded by a semaphore)
         # -----------------------------------------------------------------
 
-        sem = asyncio.Semaphore(OPENAI_NUM_PARALLEL_TASKS)
+        sem = asyncio.Semaphore(self.num_parallel_tasks)
 
         async def _process_batch(
             batch: list[EmbeddingRequest],

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/infrastructure/enrichment/enrichment_factory.py

@@ -9,6 +9,7 @@ from kodit.infrastructure.enrichment.local_enrichment_provider import (
     LocalEnrichmentProvider,
 )
 from kodit.infrastructure.enrichment.openai_enrichment_provider import (
+    OPENAI_NUM_PARALLEL_TASKS,
     OpenAIEnrichmentProvider,
 )
 from kodit.log import log_event
@@ -54,6 +55,7 @@ def enrichment_domain_service_factory(
                 max_retries=2,
             ),
             model_name=endpoint.model or "gpt-4o-mini",
+            num_parallel_tasks=endpoint.num_parallel_tasks or OPENAI_NUM_PARALLEL_TASKS,
         )
     else:
         log_event("kodit.enrichment", {"provider": "local"})

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/infrastructure/enrichment/openai_enrichment_provider.py

@@ -21,7 +21,12 @@ OPENAI_NUM_PARALLEL_TASKS = 40
 class OpenAIEnrichmentProvider(EnrichmentProvider):
     """OpenAI enrichment provider implementation."""
 
-    def __init__(self, openai_client: Any, model_name: str = "gpt-4o-mini") -> None:
+    def __init__(
+        self,
+        openai_client: Any,
+        model_name: str = "gpt-4o-mini",
+        num_parallel_tasks: int = OPENAI_NUM_PARALLEL_TASKS,
+    ) -> None:
         """Initialize the OpenAI enrichment provider.
 
         Args:
@@ -32,6 +37,7 @@ class OpenAIEnrichmentProvider(EnrichmentProvider):
         self.log = structlog.get_logger(__name__)
         self.openai_client = openai_client
         self.model_name = model_name
+        self.num_parallel_tasks = num_parallel_tasks
 
     async def enrich(
         self, requests: list[EnrichmentRequest]
@@ -50,7 +56,7 @@ class OpenAIEnrichmentProvider(EnrichmentProvider):
             return
 
         # Process batches in parallel with a semaphore to limit concurrent requests
-        sem = asyncio.Semaphore(OPENAI_NUM_PARALLEL_TASKS)
+        sem = asyncio.Semaphore(self.num_parallel_tasks)
 
         async def process_request(request: EnrichmentRequest) -> EnrichmentResponse:
             async with sem:

{kodit-0.3.12 → kodit-0.3.13}/src/kodit/log.py

@@ -7,7 +7,6 @@ import shutil
 import subprocess
 import sys
 import uuid
-from enum import Enum
 from functools import lru_cache
 from pathlib import Path
 from typing import Any
@@ -17,7 +16,7 @@ import structlog
 from structlog.types import EventDict
 
 from kodit import _version
-from kodit.config import AppContext
+from kodit.config import AppContext, LogFormat
 
 _MAC_RE = re.compile(r"(?:[0-9A-Fa-f]{2}[:-]){5}[0-9A-Fa-f]{2}")
 
@@ -35,13 +34,6 @@ def drop_color_message_key(_, __, event_dict: EventDict) -> EventDict:  # noqa:
     return event_dict
 
 
-class LogFormat(Enum):
-    """The format of the log output."""
-
-    PRETTY = "pretty"
-    JSON = "json"
-
-
 def configure_logging(app_context: AppContext) -> None:
     """Configure logging for the application."""
     timestamper = structlog.processors.TimeStamper(fmt="iso")

{kodit-0.3.12 → kodit-0.3.13}/tests/conftest.py

@@ -14,7 +14,7 @@ from sqlalchemy.ext.asyncio import (
     create_async_engine,
 )
 
-from kodit.config import AppContext
+from kodit.config import AppContext, LogFormat
 
 # Need to import these models to create the tables
 from kodit.infrastructure.sqlalchemy.entities import (
@@ -86,7 +86,7 @@ def app_context() -> Generator[AppContext, None, None]:
                 data_dir=Path(data_dir),
                 db_url="sqlite+aiosqlite:///:memory:",
                 log_level="DEBUG",
-                log_format="json",
+                log_format=LogFormat.JSON,
                 disable_telemetry=True,
                 _env_file=None,  # type: ignore[call-arg]
             )