[pre-commit.ci] pre-commit autoupdate

.claude/skills/adapter-ops/SKILL.md

@@ -90,7 +90,9 @@ LiteLLM requires provider prefixes on model names:
 
        @staticmethod
        def validate(adapter_metadata: dict[str, "Any"]) -> dict[str, "Any"]:
-           adapter_metadata["model"] = NewProviderLLMParameters.validate_model(adapter_metadata)
+           adapter_metadata["model"] = NewProviderLLMParameters.validate_model(
+               adapter_metadata
+           )
            return NewProviderLLMParameters(**adapter_metadata).model_dump()
 
        @staticmethod
@@ -114,6 +116,7 @@ LiteLLM requires provider prefixes on model names:
 5. **Test the adapter**:
    ```python
    from unstract.sdk1.adapters.adapterkit import Adapterkit
+
    kit = Adapterkit()
    adapters = kit.get_adapters_list()
    # Verify new adapter appears
@@ -142,7 +145,9 @@ LiteLLM requires provider prefixes on model names:
 
        @staticmethod
        def validate(adapter_metadata: dict[str, "Any"]) -> dict[str, "Any"]:
-           adapter_metadata["model"] = NewProviderEmbeddingParameters.validate_model(adapter_metadata)
+           adapter_metadata["model"] = NewProviderEmbeddingParameters.validate_model(
+               adapter_metadata
+           )
            return NewProviderEmbeddingParameters(**adapter_metadata).model_dump()
 
        @staticmethod

.claude/skills/adapter-ops/references/adapter_patterns.md

@@ -253,7 +253,8 @@ def validate(adapter_metadata: dict[str, "Any"]) -> dict[str, "Any"]:
 
     # Exclude control fields before validation
     validation_metadata = {
-        k: v for k, v in adapter_metadata.items()
+        k: v
+        for k, v in adapter_metadata.items()
         if k not in ("enable_reasoning", "reasoning_effort")
     }
 
@@ -327,8 +328,7 @@ def validate(adapter_metadata: dict[str, "Any"]) -> dict[str, "Any"]:
 
     # Check if thinking was previously enabled
     has_thinking_config = (
-        "thinking" in adapter_metadata
-        and adapter_metadata.get("thinking") is not None
+        "thinking" in adapter_metadata and adapter_metadata.get("thinking") is not None
     )
     if not enable_thinking and has_thinking_config:
         enable_thinking = True
@@ -348,7 +348,8 @@ def validate(adapter_metadata: dict[str, "Any"]) -> dict[str, "Any"]:
 
     # Exclude control fields from validation
     validation_metadata = {
-        k: v for k, v in result_metadata.items()
+        k: v
+        for k, v in result_metadata.items()
         if k not in ("enable_thinking", "budget_tokens", "thinking")
     }
 
@@ -570,10 +571,12 @@ adapter_class = kit.get_adapter_class_by_adapter_id(
 )
 
 # Validate metadata
-validated = adapter_class.validate({
-    "model": "my-model",
-    "api_key": "sk-xxx",
-})
+validated = adapter_class.validate(
+    {
+        "model": "my-model",
+        "api_key": "sk-xxx",
+    }
+)
 print(validated)
 
 # Get JSON schema
@@ -645,9 +648,11 @@ unconditionally prepends `custom_openai/`, and **no** LiteLLM cost-map key uses
 class MiniMaxLLMParameters(OpenAICompatibleLLMParameters):
     api_base: str = "https://api.minimax.io/v1"
 
+
 # CORRECT - emits "minimax/MiniMax-M3", priced at $0.30 / $1.20 per 1M tokens
-class MiniMaxLLMParameters(BaseChatCompletionParameters):
-    ...  # follow OpenRouterLLMParameters
+class MiniMaxLLMParameters(
+    BaseChatCompletionParameters
+): ...  # follow OpenRouterLLMParameters
 ```
 
 Note that `get_provider()` returns `"minimax"` in *both* cases and matches `litellm_provider`

.claude/skills/connector-ops/references/connector_patterns.md

@@ -28,6 +28,7 @@ class GoogleDriveFS(UnstractFileSystem):
                 if self._client is None:  # Double-check
                     # Import heavy libraries here, not at module level
                     from google.oauth2.credentials import Credentials
+
                     self._client = self._create_client()
         return self._client
 ```
@@ -77,6 +78,7 @@ def __init__(self, settings: dict[str, Any]):
     self.ssl_key = settings.get("sslKey", "")
     self.ssl_ca = settings.get("sslCA", "")
 
+
 def get_engine(self):
     conn_params = {...}
 
@@ -128,14 +130,10 @@ def test_credentials(self) -> bool:
         conn.close()
         return True
     except AuthenticationError as e:
-        raise ConnectorError(
-            f"Authentication failed: {e}",
-            treat_as_user_message=True
-        )
+        raise ConnectorError(f"Authentication failed: {e}", treat_as_user_message=True)
     except ConnectionRefusedError as e:
         raise ConnectorError(
-            f"Connection refused - check host and port: {e}",
-            treat_as_user_message=True
+            f"Connection refused - check host and port: {e}", treat_as_user_message=True
         )
     except Exception as e:
         raise ConnectorError(f"Connection error: {e}")
@@ -186,9 +184,11 @@ def sql_to_db_mapping(self, value: Any, column_name: str | None = None) -> str:
 ```python
 from fsspec import AbstractFileSystem
 
+
 class MyStorageFS(UnstractFileSystem):
     def get_fsspec_fs(self) -> AbstractFileSystem:
         from myfs import MyFileSystem
+
         return MyFileSystem(
             key=self.access_key,
             secret=self.secret_key,
@@ -202,7 +202,10 @@ class MyStorageFS(UnstractFileSystem):
 
     def is_dir_by_metadata(self, metadata: dict[str, Any]) -> bool:
         """Check if path is directory from metadata."""
-        return metadata.get("type") == "directory" or metadata.get("StorageClass") == "DIRECTORY"
+        return (
+            metadata.get("type") == "directory"
+            or metadata.get("StorageClass") == "DIRECTORY"
+        )
 ```
 
 ---
@@ -220,8 +223,7 @@ SharePoint returned plain lists instead of dicts, breaking file processing silen
 **Bad** — reimplementing methods the base class already provides:
 ```python
 class MyFileSystem(AbstractFileSystem):
-    def ls(self, path, detail=True, **kwargs):
-        ...  # Core method - MUST implement
+    def ls(self, path, detail=True, **kwargs): ...  # Core method - MUST implement
 
     # BAD: These are all redundant reimplementations
     def listdir(self, path, detail=True, **kwargs):
@@ -240,25 +242,27 @@ class MyFileSystem(AbstractFileSystem):
     def isdir(self, path):
         return self.info(path)["type"] == "directory"  # Base already does this
 
-    def walk(self, path, maxdepth=None, **kwargs):
-        ...  # Base already delegates to ls() with full detail/on_error support
+    def walk(
+        self, path, maxdepth=None, **kwargs
+    ): ...  # Base already delegates to ls() with full detail/on_error support
 
     def delete(self, path, **kwargs):
         self.rm(path, **kwargs)  # Base already does this
 
     def read_bytes(self, path):
         return self.cat_file(path)  # Base already does this
 
-    def write_bytes(self, path, data, **kwargs):
-        ...  # Base already delegates to pipe_file()
+    def write_bytes(
+        self, path, data, **kwargs
+    ): ...  # Base already delegates to pipe_file()
 ```
 
 **Good** — implement only the core methods, let fsspec handle the rest:
 ```python
 class MyFileSystem(AbstractFileSystem):
     # REQUIRED: Core methods that talk to the service API
     def ls(self, path, detail=True, **kwargs): ...
-    def info(self, path, **kwargs): ...      # Optional optimization
+    def info(self, path, **kwargs): ...  # Optional optimization
     def _open(self, path, mode="rb", **kwargs): ...
     def cat_file(self, path, **kwargs): ...
     def pipe_file(self, path, value, **kwargs): ...  # NOT write_bytes
@@ -291,19 +295,21 @@ lists when False) and the `on_error` callback.
 from google.cloud import bigquery
 from google.oauth2 import service_account
 
-class BigQueryDB(UnstractDB):
-    ...
+
+class BigQueryDB(UnstractDB): ...
 ```
 
 **Good**:
 ```python
 # No heavy imports at module level
 
+
 class BigQueryDB(UnstractDB):
     def get_engine(self):
         # Import when needed
         from google.cloud import bigquery
         from google.oauth2 import service_account
+
         ...
 ```
 
@@ -341,6 +347,7 @@ def __init__(self, settings: dict[str, Any]):
 def get_id() -> str:
     return "postgres|abc123"
 
+
 # Version 2.0 - DON'T DO THIS
 @staticmethod
 def get_id() -> str:
@@ -362,9 +369,9 @@ def get_engine(self):
     conn_params = {
         # TCP keepalive settings
         "keepalives": 1,
-        "keepalives_idle": 30,      # Seconds before sending keepalive
+        "keepalives_idle": 30,  # Seconds before sending keepalive
         "keepalives_interval": 10,  # Seconds between keepalives
-        "keepalives_count": 5,      # Failed keepalives before disconnect
+        "keepalives_count": 5,  # Failed keepalives before disconnect
         "connect_timeout": 30,
         # ...
     }
@@ -441,7 +448,7 @@ def execute_batch(self, query: str, data: list[tuple], batch_size: int = 1000) -
     try:
         with engine.cursor() as cursor:
             for i in range(0, len(data), batch_size):
-                batch = data[i:i + batch_size]
+                batch = data[i : i + batch_size]
                 cursor.executemany(query, batch)
                 total_rows += len(batch)
             engine.commit()

.claude/skills/connector-ops/references/test_patterns.md

@@ -501,16 +501,19 @@ self.assertRegex(connector.get_id(), r"^[a-z_]+\|[a-f0-9-]+$")
 
 # JSON schema validity
 import json
+
 schema = json.loads(connector.get_json_schema())
 self.assertIn("title", schema)
 self.assertIn("type", schema)
 
 # Connection returns correct type
 from psycopg2.extensions import connection
+
 self.assertIsInstance(connector.get_engine(), connection)
 
 # Exception handling
 from unstract.connectors.exceptions import ConnectorError
+
 with self.assertRaises(ConnectorError) as ctx:
     connector.test_credentials()
 self.assertIn("expected message", str(ctx.exception))

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ ci:
     - hadolint-docker # Fails in pre-commit CI
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: trailing-whitespace
         exclude_types:
@@ -38,7 +38,7 @@ repos:
       - id: no-commit-to-branch
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.4
+    rev: v0.16.8
     hooks:
       - id: ruff
         args: [--fix]
@@ -57,7 +57,7 @@ repos:
   #       language: python
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.17.0
+    rev: v3.21.2
     hooks:
       - id: pyupgrade
         entry: pyupgrade --py39-plus --keep-runtime-typing
@@ -111,15 +111,15 @@ repos:
         stages: [pre-commit]
 
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.42.0
+    rev: v0.49.1
     hooks:
       - id: markdownlint
         args: [--disable, MD013]
       - id: markdownlint-fix
         args: [--disable, MD013]
 
   - repo: https://github.com/gitleaks/gitleaks
-    rev: v8.18.2
+    rev: v8.30.0
     hooks:
       - id: gitleaks
 
@@ -129,7 +129,7 @@ repos:
       - id: htmlhint
 
   - repo: https://github.com/hadolint/hadolint
-    rev: v2.12.1-beta
+    rev: v2.15.1
     hooks:
       - id: hadolint-docker
         args:

backend/account_v2/custom_auth_middleware.py

@@ -2,6 +2,8 @@
 import logging
 import uuid
 
+from backend.constants import RequestHeader
+from backend.internal_api_constants import INTERNAL_API_PREFIX
 from django.conf import settings
 from django.http import HttpRequest, HttpResponse, JsonResponse
 from utils.constants import Account
@@ -11,8 +13,6 @@
 from account_v2.authentication_plugin_registry import AuthenticationPluginRegistry
 from account_v2.authentication_service import AuthenticationService
 from account_v2.constants import Common
-from backend.constants import RequestHeader
-from backend.internal_api_constants import INTERNAL_API_PREFIX
 
 logger = logging.getLogger(__name__)
 

backend/account_v2/models.py

@@ -1,10 +1,9 @@
 import uuid
 
+from backend.constants import FieldLengthConstants as FieldLength
 from django.contrib.auth.models import AbstractUser, Group, Permission
 from django.db import models
 
-from backend.constants import FieldLengthConstants as FieldLength
-
 NAME_SIZE = 64
 KEY_SIZE = 64
 

backend/adapter_processor_v2/adapter_processor.py

@@ -8,6 +8,13 @@
 from django.core.exceptions import ObjectDoesNotExist
 from platform_settings_v2.platform_auth_service import PlatformAuthenticationService
 from tenant_account_v2.organization_member_service import OrganizationMemberService
+from unstract.sdk1.adapters.adapterkit import Adapterkit
+from unstract.sdk1.adapters.base import Adapter
+from unstract.sdk1.adapters.x2text.constants import X2TextConstants
+from unstract.sdk1.constants import AdapterTypes
+from unstract.sdk1.embedding import EmbeddingCompat
+from unstract.sdk1.exceptions import SdkError
+from unstract.sdk1.llm import LLM
 
 from adapter_processor_v2.constants import AdapterKeys, AllowedDomains
 from adapter_processor_v2.exceptions import (
@@ -16,13 +23,6 @@
     InValidAdapterId,
     TestAdapterError,
 )
-from unstract.sdk1.adapters.adapterkit import Adapterkit
-from unstract.sdk1.adapters.base import Adapter
-from unstract.sdk1.adapters.x2text.constants import X2TextConstants
-from unstract.sdk1.constants import AdapterTypes
-from unstract.sdk1.embedding import EmbeddingCompat
-from unstract.sdk1.exceptions import SdkError
-from unstract.sdk1.llm import LLM
 
 from .models import AdapterInstance, UserDefaultAdapter
 

backend/adapter_processor_v2/exceptions.py

@@ -1,9 +1,9 @@
 import logging
 
 from rest_framework.exceptions import APIException
+from unstract.sdk1.exceptions import SdkError
 
 from adapter_processor_v2.constants import AdapterKeys
-from unstract.sdk1.exceptions import SdkError
 
 logger = logging.getLogger(__name__)