Merge remote-tracking branch 'upstream/main' into improving-ci-coverage-and-configuring-.coveragerc

Author: leseb

client-sdks/stainless/openapi.yml

@@ -3329,6 +3329,7 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
       - Admin
+      - Connectors
       summary: List all connectors.
       description: List all configured connectors.
       operationId: list_connectors_v1alpha_admin_connectors_get
@@ -3355,6 +3356,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a tool by name from a connector.
       description: Get a tool definition by its name from a connector.
       operationId: get_connector_tool_v1alpha_admin_connectors__connector_id__tools__tool_name__get
@@ -3408,6 +3410,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: List tools from a connector.
       description: List all tools available from a connector.
       operationId: list_connector_tools_v1alpha_admin_connectors__connector_id__tools_get
@@ -3453,6 +3456,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a connector by its ID.
       description: Get a connector by its ID.
       operationId: get_connector_v1alpha_admin_connectors__connector_id__get

docs/docs/providers/responses/inline_builtin.mdx

@@ -76,7 +76,7 @@ Metadata: {metadata}
 | `vector_stores_config.contextual_retrieval_params.default_timeout_seconds` | `int` | No | 120 | Default timeout in seconds for each LLM contextualization call. |
 | `vector_stores_config.contextual_retrieval_params.default_max_concurrency` | `int` | No | 3 | Default maximum concurrent LLM calls for contextualization. |
 | `vector_stores_config.contextual_retrieval_params.max_document_tokens` | `int` | No | 100000 | Maximum document size in tokens. Documents exceeding this are rejected for contextual retrieval. |
-| `compaction_config` | `CompactionConfig` | No | summarization_prompt='You are performing a CONTEXT CHECKPOINT COMPACTION. Create a handoff summary for another LLM that will resume the task.\n\nInclude:\n- Current progress and key decisions made\n- Important context, constraints, or user preferences\n- What remains to be done (clear next steps)\n- Any critical data, examples, or references needed to continue\n\nBe concise, structured, and focused on helping the next LLM seamlessly continue the work.' summary_prefix='Another language model started to solve this problem and produced a summary of its thinking process. You also have access to the state of the tools that were used by that language model. Use this to build on the work that has already been done and avoid duplicating work. Here is the summary produced by the other language model, use the information in this summary to assist with your own analysis:' summarization_model=None default_compact_threshold=None tokenizer_encoding=None | Configuration for conversation compaction behavior and prompt templates |
+| `compaction_config` | `CompactionConfig` | No | summarization_prompt='You are performing a CONTEXT CHECKPOINT COMPACTION. Create a handoff summary for another LLM that will resume the task.\n\nInclude:\n- Current progress and key decisions made\n- Important context, constraints, or user preferences\n- What remains to be done (clear next steps)\n- Any critical data, examples, or references needed to continue\n\nBe concise, structured, and focused on helping the next LLM seamlessly continue the work.' summary_prefix='Another language model started to solve this problem and produced a summary of its thinking process. You also have access to the state of the tools that were used by that language model. Use this to build on the work that has already been done and avoid duplicating work. Here is the summary produced by the other language model, use the information in this summary to assist with your own analysis:' summarization_model=None default_compact_threshold=None tokenizer_encoding=None model_tokenizer_mappings={'llama': 'cl100k_base', 'mistral': 'cl100k_base', 'claude': 'cl100k_base', 'gemma': 'cl100k_base', 'qwen': 'cl100k_base', 'phi': 'cl100k_base', 'deepseek': 'cl100k_base'} | Configuration for conversation compaction behavior and prompt templates |
 | `compaction_config.summarization_prompt` | `str` | No | You are performing a CONTEXT CHECKPOINT COMPACTION. Create a handoff summary for another LLM that will resume the task.
 
 Include:
@@ -89,7 +89,8 @@ Be concise, structured, and focused on helping the next LLM seamlessly continue
 | `compaction_config.summary_prefix` | `str` | No | Another language model started to solve this problem and produced a summary of its thinking process. You also have access to the state of the tools that were used by that language model. Use this to build on the work that has already been done and avoid duplicating work. Here is the summary produced by the other language model, use the information in this summary to assist with your own analysis: | Text prepended to the compaction summary to frame it as a handoff for the next LLM. |
 | `compaction_config.summarization_model` | `str \| None` | No |  | Model to use for generating compaction summaries. If not set, uses the same model as the conversation. |
 | `compaction_config.default_compact_threshold` | `int \| None` | No |  | Default token threshold for auto-compaction via context_management. If set, conversations exceeding this token count will be automatically compacted. |
-| `compaction_config.tokenizer_encoding` | `str \| None` | No |  | Tiktoken encoding name for token counting (e.g. 'o200k_base', 'cl100k_base'). If not set, the encoding is resolved from the model name via tiktoken.encoding_for_model(). |
+| `compaction_config.tokenizer_encoding` | `str \| None` | No |  | Default tiktoken encoding name for token counting (e.g. 'o200k_base', 'cl100k_base'). Applied as a server-level default after any per-request override via extra_body. If not set, encoding is resolved from the model name via tiktoken, then model-family prefix mappings, then character-based estimation. |
+| `compaction_config.model_tokenizer_mappings` | `dict[str, str]` | No | {'llama': 'cl100k_base', 'mistral': 'cl100k_base', 'claude': 'cl100k_base', 'gemma': 'cl100k_base', 'qwen': 'cl100k_base', 'phi': 'cl100k_base', 'deepseek': 'cl100k_base'} | Map model name prefixes to tiktoken encoding names. Used as a heuristic fallback when tiktoken cannot resolve the model name directly. Matching is case-insensitive on the model name after stripping any provider prefix (e.g., 'ollama/llama3.2:3b' matches the 'llama' prefix). Admins can extend this to support custom or fine-tuned models. |
 | `moderation_endpoint` | `str \| None` | No |  | URL of an OpenAI-compatible /v1/moderations endpoint for guardrails. The endpoint must accept POST {"input": "text"} and return {"results": [{"flagged": bool, "categories": {...}}]}. |
 
 ## Sample Configuration

docs/static/experimental-ogx-spec.yaml

@@ -225,6 +225,7 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
       - Admin
+      - Connectors
       summary: List all connectors.
       description: List all configured connectors.
       operationId: list_connectors_v1alpha_admin_connectors_get
@@ -251,6 +252,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a tool by name from a connector.
       description: Get a tool definition by its name from a connector.
       operationId: get_connector_tool_v1alpha_admin_connectors__connector_id__tools__tool_name__get
@@ -304,6 +306,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: List tools from a connector.
       description: List all tools available from a connector.
       operationId: list_connector_tools_v1alpha_admin_connectors__connector_id__tools_get
@@ -349,6 +352,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a connector by its ID.
       description: Get a connector by its ID.
       operationId: get_connector_v1alpha_admin_connectors__connector_id__get

docs/static/stainless-ogx-spec.yaml

@@ -3329,6 +3329,7 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
       - Admin
+      - Connectors
       summary: List all connectors.
       description: List all configured connectors.
       operationId: list_connectors_v1alpha_admin_connectors_get
@@ -3355,6 +3356,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a tool by name from a connector.
       description: Get a tool definition by its name from a connector.
       operationId: get_connector_tool_v1alpha_admin_connectors__connector_id__tools__tool_name__get
@@ -3408,6 +3410,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: List tools from a connector.
       description: List all tools available from a connector.
       operationId: list_connector_tools_v1alpha_admin_connectors__connector_id__tools_get
@@ -3453,6 +3456,7 @@ paths:
           description: Default Response
       tags:
       - Admin
+      - Connectors
       summary: Get a connector by its ID.
       description: Get a connector by its ID.
       operationId: get_connector_v1alpha_admin_connectors__connector_id__get

src/ogx/core/datatypes.py

@@ -10,7 +10,7 @@
 from typing import Annotated, Any, Literal, Self
 from urllib.parse import urlparse
 
-from pydantic import BaseModel, Field, field_validator, model_validator
+from pydantic import BaseModel, Field, SecretStr, field_validator, model_validator
 
 from ogx.core.access_control.datatypes import AccessRule, RouteAccessRule
 from ogx.core.storage.datatypes import (
@@ -193,7 +193,7 @@ class OAuth2IntrospectionConfig(BaseModel):
 
     url: str
     client_id: str
-    client_secret: str
+    client_secret: SecretStr
     send_secret_in_body: bool = False
 
 

src/ogx/core/resolver.py

@@ -132,7 +132,6 @@ def additional_protocols_map() -> dict[Api, Any]:
     }
 
 
-# TODO: make all this naming far less atrocious. Provider. ProviderSpec. ProviderWithSpec. WTF!
 class ProviderWithSpec(Provider):
     """A Provider paired with its resolved ProviderSpec for instantiation."""
 

src/ogx/core/routers/inference.py

@@ -65,6 +65,11 @@
 logger = get_logger(name=__name__, category="core::routers")
 
 
+def _log_background_task_error(task: asyncio.Task) -> None:
+    if not task.cancelled() and (exc := task.exception()):
+        logger.error("Failed to store chat completion in background", error=str(exc))
+
+
 class InferenceRouter(Inference):
     """Routes to an provider based on the model"""
 
@@ -268,7 +273,8 @@ async def openai_chat_completion(
 
         # Store the response with the ID that will be returned to the client
         if self.store:
-            asyncio.create_task(self.store.store_chat_completion(response, params.messages))
+            task = asyncio.create_task(self.store.store_chat_completion(response, params.messages))
+            task.add_done_callback(_log_background_task_error)
 
         return response
 
@@ -555,4 +561,5 @@ async def stream_tokens_and_compute_metrics_openai_chat(
                     object="chat.completion",
                 )
                 logger.debug("InferenceRouter.completion_response", final_response=final_response)
-                asyncio.create_task(self.store.store_chat_completion(final_response, messages))
+                task = asyncio.create_task(self.store.store_chat_completion(final_response, messages))
+                task.add_done_callback(_log_background_task_error)

src/ogx/core/routers/vector_io.py

@@ -103,9 +103,7 @@ def _get_provider_id(self, vector_store_id: str) -> str:
                 return "unknown"
             return obj.provider_id
         except Exception:
-            logger.warning(
-                "Could not resolve provider for vector store", vector_store_id=vector_store_id, exc_info=True
-            )
+            logger.exception("Could not resolve provider for vector store", vector_store_id=vector_store_id)
             return "unknown"
 
     async def _rewrite_query_for_search(self, query: str) -> str:

src/ogx/core/server/auth_providers.py

@@ -246,12 +246,12 @@ async def introspect_token(self, token: str, scope: Scope | None = None) -> User
 
         if self.config.introspection.send_secret_in_body:
             form["client_id"] = self.config.introspection.client_id
-            form["client_secret"] = self.config.introspection.client_secret
+            form["client_secret"] = self.config.introspection.client_secret.get_secret_value()
         else:
             # httpx auth parameter expects tuple[str | bytes, str | bytes]
             post_kwargs["auth"] = (
                 self.config.introspection.client_id,
-                self.config.introspection.client_secret,
+                self.config.introspection.client_secret.get_secret_value(),
             )
 
         try:

src/ogx/core/storage/kvstore/redis/redis.py

@@ -46,7 +46,6 @@ async def get(self, key: str) -> str | None:
         value = await client.get(key)
         if value is None:
             return None
-        await client.ttl(key)
         if isinstance(value, bytes):
             return value.decode("utf-8")
         if isinstance(value, str):