feat(providers): add Mistral embedding provider, route registry through dynaconf

Adds a hosted Mistral embedding option (mistral-embed, 1024-dim) alongside
the existing Bedrock / OpenAI / Ollama / Simple providers. Implementation
mirrors OpenAIProvider: lazy dimension detection with a known-models lookup,
chunked batch requests, defensive index sort, and a 429-aware retry decorator.

In the same change, ProviderRegistry switches from os.getenv to the
dynaconf-backed Settings dataclass so all five providers share a single
configuration path. config.py gains the previously-uncovered Bedrock keys,
the new Mistral keys, the missing OPENAI_GENERATION_MODEL /
OLLAMA_GENERATION_MODEL, and SIMPLE_EMBEDDING_DIMENSION.

Auto-detection priority: Bedrock → OpenAI → Mistral → Ollama → Simple.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/ADR-015-unified-provider-architecture.md

@@ -118,10 +118,16 @@ class ProviderRegistry:
     @staticmethod
     def create_provider() -> Provider:
         # 1. Bedrock (AWS_REGION or BEDROCK_*_MODEL)
-        # 2. Ollama (OLLAMA_BASE_URL)
-        # 3. Simple (fallback)
+        # 2. OpenAI (OPENAI_API_KEY)
+        # 3. Mistral (MISTRAL_API_KEY)
+        # 4. Ollama (OLLAMA_BASE_URL)
+        # 5. Simple (fallback)
 ```
 
+Configuration is sourced via the dynaconf-backed `Settings` dataclass in
+`config.py`; the registry reads `get_settings()` rather than `os.getenv`
+directly, so settings files and env vars share one resolution path.
+
 **Environment Variables:**
 
 **Bedrock:**
@@ -131,6 +137,17 @@ class ProviderRegistry:
 - `BEDROCK_EMBEDDING_MODEL`: Model ID for embeddings (e.g., "amazon.titan-embed-text-v2:0")
 - `BEDROCK_GENERATION_MODEL`: Model ID for text generation (e.g., "anthropic.claude-3-sonnet-20240229-v1:0")
 
+**OpenAI:**
+- `OPENAI_API_KEY`: OpenAI API key (or `GITHUB_TOKEN` for GitHub Models)
+- `OPENAI_BASE_URL`: Optional base URL override for OpenAI-compatible APIs
+- `OPENAI_EMBEDDING_MODEL`: Embedding model (default: "text-embedding-3-small")
+- `OPENAI_GENERATION_MODEL`: Generation model (e.g., "gpt-4o-mini")
+
+**Mistral (embeddings only):**
+- `MISTRAL_API_KEY`: Mistral API key from console.mistral.ai
+- `MISTRAL_EMBEDDING_MODEL`: Embedding model (default: "mistral-embed", 1024-dim)
+- `MISTRAL_BASE_URL`: Optional server URL override (proxies, on-prem)
+
 **Ollama:**
 - `OLLAMA_BASE_URL`: Ollama API base URL (e.g., "http://localhost:11434")
 - `OLLAMA_EMBEDDING_MODEL`: Model for embeddings (default: "nomic-embed-text")

docs/configuration.md

@@ -410,9 +410,16 @@ DOCUMENT_CHUNK_OVERLAP=50             # Overlapping words between chunks (defaul
 
 ### Embedding Service Configuration
 
-The server uses an embedding service to generate vector representations. Two options are available:
+The server picks an embedding provider via auto-detection. Priority order
+(see `nextcloud_mcp_server/providers/registry.py`):
 
-#### Ollama (Recommended)
+1. **Bedrock** — if `AWS_REGION` or `BEDROCK_EMBEDDING_MODEL` is set
+2. **OpenAI** — if `OPENAI_API_KEY` is set
+3. **Mistral** — if `MISTRAL_API_KEY` is set
+4. **Ollama** — if `OLLAMA_BASE_URL` is set
+5. **Simple** — fallback when nothing else is configured
+
+#### Ollama (Recommended for self-hosted)
 
 Use a local Ollama instance for embeddings:
 
@@ -422,9 +429,52 @@ OLLAMA_EMBEDDING_MODEL=nomic-embed-text  # Default model
 OLLAMA_VERIFY_SSL=true                   # Verify SSL certificates
 ```
 
+#### OpenAI
+
+Hosted OpenAI embeddings (or any OpenAI-compatible API via `OPENAI_BASE_URL`):
+
+```dotenv
+OPENAI_API_KEY=sk-...
+OPENAI_EMBEDDING_MODEL=text-embedding-3-small  # default
+# OPENAI_BASE_URL=https://models.github.ai/inference  # optional
+```
+
+#### Mistral
+
+Hosted Mistral embeddings. Requires a Mistral API key from
+[console.mistral.ai](https://console.mistral.ai). Currently embeddings only
+(no text generation).
+
+```dotenv
+MISTRAL_API_KEY=...
+MISTRAL_EMBEDDING_MODEL=mistral-embed   # default; produces 1024-dim vectors
+# MISTRAL_BASE_URL=https://api.mistral.ai  # optional override (proxies, on-prem)
+```
+
+Switching to or from Mistral forces a new Qdrant collection because the
+collection name encodes the model (see "Qdrant Collection Naming" above).
+
+#### Amazon Bedrock
+
+Bedrock provides hosted embedding models (Titan, Cohere) and uses the AWS
+credential chain (env vars, profiles, or IAM role):
+
+```dotenv
+AWS_REGION=us-east-1
+BEDROCK_EMBEDDING_MODEL=amazon.titan-embed-text-v2:0
+# AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY are optional — boto3 will use
+# the standard credential chain if not set.
+```
+
 #### Simple Embedding Provider (Fallback)
 
-If `OLLAMA_BASE_URL` is not set, the server uses a simple random embedding provider for testing. This is **not suitable for production** as it generates random embeddings with no semantic meaning.
+If no provider env var is set, the server falls back to a simple deterministic
+embedding provider for testing. This is **not suitable for production** as
+its embeddings have no semantic meaning.
+
+```dotenv
+SIMPLE_EMBEDDING_DIMENSION=384  # optional; default 384
+```
 
 ### Document Chunking Configuration
 
@@ -534,6 +584,16 @@ equivalent.** Operators who need a runtime toggle should open an issue.
 | `OLLAMA_BASE_URL` | ⚠️ Optional | - | Ollama API endpoint for embeddings |
 | `OLLAMA_EMBEDDING_MODEL` | ⚠️ Optional | `nomic-embed-text` | Embedding model to use |
 | `OLLAMA_VERIFY_SSL` | ⚠️ Optional | `true` | Verify SSL certificates |
+| `OPENAI_API_KEY` | ⚠️ Optional | - | OpenAI API key (selects OpenAI provider) |
+| `OPENAI_BASE_URL` | ⚠️ Optional | - | OpenAI base URL override (for compatible APIs) |
+| `OPENAI_EMBEDDING_MODEL` | ⚠️ Optional | `text-embedding-3-small` | OpenAI embedding model |
+| `MISTRAL_API_KEY` | ⚠️ Optional | - | Mistral API key (selects Mistral provider) |
+| `MISTRAL_EMBEDDING_MODEL` | ⚠️ Optional | `mistral-embed` | Mistral embedding model (1024-dim) |
+| `MISTRAL_BASE_URL` | ⚠️ Optional | - | Mistral base URL override (proxies, on-prem) |
+| `AWS_REGION` | ⚠️ Optional | - | AWS region (selects Bedrock provider) |
+| `BEDROCK_EMBEDDING_MODEL` | ⚠️ Optional | - | Bedrock embedding model ID |
+| `BEDROCK_GENERATION_MODEL` | ⚠️ Optional | - | Bedrock generation model ID |
+| `SIMPLE_EMBEDDING_DIMENSION` | ⚠️ Optional | `384` | Dimension for the fallback Simple provider |
 | `DOCUMENT_CHUNK_SIZE` | ⚠️ Optional | `512` | Words per chunk for document embedding |
 | `DOCUMENT_CHUNK_OVERLAP` | ⚠️ Optional | `50` | Overlapping words between chunks (must be < chunk size) |
 

nextcloud_mcp_server/config.py

@@ -77,11 +77,25 @@ _DEFAULTS: dict[str, Any] = {
     # Ollama
     "ollama_base_url": None,
     "ollama_embedding_model": "nomic-embed-text",
+    "ollama_generation_model": None,
     "ollama_verify_ssl": True,
     # OpenAI
     "openai_api_key": None,
     "openai_base_url": None,
     "openai_embedding_model": "text-embedding-3-small",
+    "openai_generation_model": None,
+    # Bedrock (AWS)
+    "aws_region": None,
+    "aws_access_key_id": None,
+    "aws_secret_access_key": None,
+    "bedrock_embedding_model": None,
+    "bedrock_generation_model": None,
+    # Mistral
+    "mistral_api_key": None,
+    "mistral_embedding_model": "mistral-embed",
+    "mistral_base_url": None,
+    # Simple (fallback) embedding dimension
+    "simple_embedding_dimension": 384,
     # Document chunking
     "document_chunk_size": 2048,
     "document_chunk_overlap": 200,
@@ -486,15 +500,32 @@ class Settings:
     qdrant_api_key: str | None = None
     qdrant_collection: str = "nextcloud_content"
 
-    # Ollama settings (for embeddings)
+    # Ollama settings (embeddings + optional generation)
     ollama_base_url: str | None = None
     ollama_embedding_model: str = "nomic-embed-text"
+    ollama_generation_model: str | None = None
     ollama_verify_ssl: bool = True
 
-    # OpenAI settings (for embeddings)
+    # OpenAI settings (embeddings + optional generation)
     openai_api_key: str | None = None
     openai_base_url: str | None = None
     openai_embedding_model: str = "text-embedding-3-small"
+    openai_generation_model: str | None = None
+
+    # Bedrock (AWS) settings — boto3 also reads these from its credential chain
+    aws_region: str | None = None
+    aws_access_key_id: str | None = None
+    aws_secret_access_key: str | None = None
+    bedrock_embedding_model: str | None = None
+    bedrock_generation_model: str | None = None
+
+    # Mistral settings (embeddings only)
+    mistral_api_key: str | None = None
+    mistral_embedding_model: str = "mistral-embed"
+    mistral_base_url: str | None = None
+
+    # Simple (fallback) provider — dimension when no real provider configured
+    simple_embedding_dimension: int = 384
 
     # Document chunking settings (for vector embeddings)
     document_chunk_size: int = 2048  # Characters per chunk
@@ -573,23 +604,28 @@ class Settings:
         Get the active embedding model name based on provider priority.
 
         Priority order (same as ProviderRegistry):
-        1. OpenAI - if OPENAI_API_KEY is set
-        2. Ollama - if OLLAMA_BASE_URL is set
-        3. Simple - fallback (returns "simple-384")
+        1. Bedrock - if AWS_REGION or BEDROCK_EMBEDDING_MODEL is set
+        2. OpenAI - if OPENAI_API_KEY is set
+        3. Mistral - if MISTRAL_API_KEY is set
+        4. Ollama - if OLLAMA_BASE_URL is set
+        5. Simple - fallback (returns "simple-{dimension}")
 
         Returns:
             Active embedding model name
         """
-        # Check OpenAI first (higher priority than Ollama in registry)
+        if self.aws_region or self.bedrock_embedding_model:
+            return self.bedrock_embedding_model or "bedrock-default"
+
         if self.openai_api_key:
             return self.openai_embedding_model
 
-        # Check Ollama
+        if self.mistral_api_key:
+            return self.mistral_embedding_model
+
         if self.ollama_base_url:
             return self.ollama_embedding_model
 
-        # Fallback to simple provider indicator
-        return "simple-384"
+        return f"simple-{self.simple_embedding_dimension}"
 
     def get_collection_name(self) -> str:
         """
@@ -835,11 +871,25 @@ def get_settings() -> Settings:
         # Ollama settings
         "ollama_base_url": "OLLAMA_BASE_URL",
         "ollama_embedding_model": "OLLAMA_EMBEDDING_MODEL",
+        "ollama_generation_model": "OLLAMA_GENERATION_MODEL",
         "ollama_verify_ssl": "OLLAMA_VERIFY_SSL",
         # OpenAI settings
         "openai_api_key": "OPENAI_API_KEY",
         "openai_base_url": "OPENAI_BASE_URL",
         "openai_embedding_model": "OPENAI_EMBEDDING_MODEL",
+        "openai_generation_model": "OPENAI_GENERATION_MODEL",
+        # Bedrock (AWS) settings
+        "aws_region": "AWS_REGION",
+        "aws_access_key_id": "AWS_ACCESS_KEY_ID",
+        "aws_secret_access_key": "AWS_SECRET_ACCESS_KEY",
+        "bedrock_embedding_model": "BEDROCK_EMBEDDING_MODEL",
+        "bedrock_generation_model": "BEDROCK_GENERATION_MODEL",
+        # Mistral settings
+        "mistral_api_key": "MISTRAL_API_KEY",
+        "mistral_embedding_model": "MISTRAL_EMBEDDING_MODEL",
+        "mistral_base_url": "MISTRAL_BASE_URL",
+        # Simple provider
+        "simple_embedding_dimension": "SIMPLE_EMBEDDING_DIMENSION",
         # Document chunking settings
         "document_chunk_size": "DOCUMENT_CHUNK_SIZE",
         "document_chunk_overlap": "DOCUMENT_CHUNK_OVERLAP",

nextcloud_mcp_server/providers/__init__.py

@@ -3,6 +3,7 @@
 from .anthropic import AnthropicProvider
 from .base import Provider
 from .bedrock import BedrockProvider
+from .mistral import MistralProvider
 from .ollama import OllamaProvider
 from .openai import OpenAIProvider
 from .registry import get_provider, reset_provider
@@ -13,6 +14,7 @@ __all__ = [
     "OllamaProvider",
     "OpenAIProvider",
     "AnthropicProvider",
+    "MistralProvider",
     "SimpleProvider",
     "BedrockProvider",
     "get_provider",

nextcloud_mcp_server/providers/mistral.py

@@ -0,0 +1,231 @@
+"""Mistral provider for embeddings.
+
+Currently supports embeddings only (``mistral-embed``, 1024-dim). Generation
+can be added later if needed; see ADR-015.
+"""
+
+import logging
+from functools import wraps
+
+import anyio
+from mistralai.client import Mistral
+from mistralai.client.errors.sdkerror import SDKError
+
+from .base import Provider
+
+logger = logging.getLogger(__name__)
+
+MAX_RETRIES = 5
+INITIAL_RETRY_DELAY = 2.0
+MAX_RETRY_DELAY = 60.0
+
+
+def retry_on_rate_limit(func):
+    """Retry on Mistral 429 (rate limit) responses with exponential backoff."""
+
+    @wraps(func)
+    async def wrapper(*args, **kwargs):
+        retry_delay = INITIAL_RETRY_DELAY
+        last_error: Exception | None = None
+
+        for attempt in range(1, MAX_RETRIES + 1):
+            try:
+                return await func(*args, **kwargs)
+            except SDKError as e:
+                # SDKError carries a status_code attribute populated from the
+                # raw response. Only 429 is retryable here.
+                status = getattr(e, "status_code", None)
+                if status != 429:
+                    raise
+                last_error = e
+                if attempt < MAX_RETRIES:
+                    logger.warning(
+                        "Mistral rate limit hit (attempt %d/%d), retrying in %.1fs...",
+                        attempt,
+                        MAX_RETRIES,
+                        retry_delay,
+                    )
+                    await anyio.sleep(retry_delay)
+                    retry_delay = min(retry_delay * 2, MAX_RETRY_DELAY)
+
+        logger.error("Mistral rate limit exceeded after %d attempts", MAX_RETRIES)
+        raise last_error  # type: ignore[misc]
+
+    return wrapper
+
+
+# Well-known Mistral embedding model dimensions
+MISTRAL_EMBEDDING_DIMENSIONS: dict[str, int] = {
+    "mistral-embed": 1024,
+}
+
+# Conservative chunk size for batch embeddings. Mistral allows large batches,
+# but we keep this in line with sibling providers (OpenAI=100, Ollama=32).
+BATCH_SIZE = 64
+
+
+class MistralProvider(Provider):
+    """
+    Mistral provider — embeddings only.
+
+    Uses the official ``mistralai`` SDK. Lazy dimension detection mirrors the
+    OpenAI provider: known models populate the cached dimension at construction
+    time; unknown models get their dimension detected on the first ``embed()``
+    call.
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        embedding_model: str | None = "mistral-embed",
+        base_url: str | None = None,
+    ):
+        """
+        Initialize the Mistral provider.
+
+        Args:
+            api_key: Mistral API key.
+            embedding_model: Embedding model ID (default: ``mistral-embed``).
+                Pass ``None`` to disable embeddings (the provider will then
+                support no capabilities, which is mostly useful for tests).
+            base_url: Optional base URL override (e.g. proxies, on-prem).
+        """
+        self.embedding_model = embedding_model
+        self._dimension: int | None = None
+
+        self.client = Mistral(api_key=api_key, server_url=base_url)
+
+        if embedding_model and embedding_model in MISTRAL_EMBEDDING_DIMENSIONS:
+            self._dimension = MISTRAL_EMBEDDING_DIMENSIONS[embedding_model]
+
+        logger.info(
+            "Initialized Mistral provider: base_url=%s, embedding_model=%s, "
+            "dimension=%s",
+            base_url or "default",
+            embedding_model,
+            self._dimension,
+        )
+
+    @property
+    def supports_embeddings(self) -> bool:
+        return self.embedding_model is not None
+
+    @property
+    def supports_generation(self) -> bool:
+        return False
+
+    @retry_on_rate_limit
+    async def embed(self, text: str) -> list[float]:
+        """Generate an embedding for a single text."""
+        if not self.supports_embeddings:
+            raise NotImplementedError(
+                "Embedding not supported - no embedding_model configured"
+            )
+
+        assert self.embedding_model is not None
+        response = await self.client.embeddings.create_async(
+            model=self.embedding_model,
+            inputs=[text],
+        )
+
+        if not response.data or response.data[0].embedding is None:
+            raise RuntimeError(
+                f"Mistral embeddings API returned no embedding for model "
+                f"{self.embedding_model}"
+            )
+
+        embedding = response.data[0].embedding
+
+        if self._dimension is None:
+            self._dimension = len(embedding)
+            logger.info(
+                "Detected embedding dimension: %d for model %s",
+                self._dimension,
+                self.embedding_model,
+            )
+
+        return embedding
+
+    async def embed_batch(self, texts: list[str]) -> list[list[float]]:
+        """Generate embeddings for multiple texts, chunking by ``BATCH_SIZE``."""
+        if not self.supports_embeddings:
+            raise NotImplementedError(
+                "Embedding not supported - no embedding_model configured"
+            )
+
+        if not texts:
+            return []
+
+        all_embeddings: list[list[float]] = []
+        for i in range(0, len(texts), BATCH_SIZE):
+            batch = texts[i : i + BATCH_SIZE]
+            batch_embeddings = await self._embed_batch_request(batch)
+            all_embeddings.extend(batch_embeddings)
+
+            if self._dimension is None and batch_embeddings:
+                self._dimension = len(batch_embeddings[0])
+                logger.info(
+                    "Detected embedding dimension: %d for model %s",
+                    self._dimension,
+                    self.embedding_model,
+                )
+
+        return all_embeddings
+
+    @retry_on_rate_limit
+    async def _embed_batch_request(self, batch: list[str]) -> list[list[float]]:
+        """Single batch request with rate-limit retry."""
+        assert self.embedding_model is not None
+        response = await self.client.embeddings.create_async(
+            model=self.embedding_model,
+            inputs=batch,
+        )
+
+        # Defensive: response.data items have Optional fields. Sort by index
+        # (default 0 if missing) and reject None embeddings explicitly.
+        sorted_data = sorted(response.data or [], key=lambda x: x.index or 0)
+        result: list[list[float]] = []
+        for item in sorted_data:
+            if item.embedding is None:
+                raise RuntimeError(
+                    f"Mistral embeddings API returned a null embedding for "
+                    f"model {self.embedding_model}"
+                )
+            result.append(item.embedding)
+
+        if len(result) != len(batch):
+            raise RuntimeError(
+                f"Mistral embeddings API returned {len(result)} embeddings "
+                f"for {len(batch)} inputs"
+            )
+        return result
+
+    def get_dimension(self) -> int:
+        if not self.supports_embeddings:
+            raise NotImplementedError(
+                "Embedding not supported - no embedding_model configured"
+            )
+
+        if self._dimension is None:
+            raise RuntimeError(
+                f"Embedding dimension not detected yet for model "
+                f"{self.embedding_model}. Call embed() first or use a known "
+                "model."
+            )
+        return self._dimension
+
+    async def generate(self, prompt: str, max_tokens: int = 500) -> str:
+        raise NotImplementedError(
+            "MistralProvider does not support generation. "
+            "Use OpenAI, Anthropic, or Bedrock for text generation."
+        )
+
+    async def close(self) -> None:
+        # The Mistral SDK manages its own httpx client lifecycle; close it
+        # via the SDK's context-manager hook if present, otherwise no-op.
+        close = getattr(self.client, "__aexit__", None)
+        if close is not None:
+            try:
+                await close(None, None, None)
+            except Exception:  # pragma: no cover - best-effort cleanup
+                logger.debug("Mistral client close raised; ignoring", exc_info=True)

nextcloud_mcp_server/providers/registry.py

@@ -1,10 +1,11 @@
 """Provider registry and factory for auto-detection and instantiation."""
 
 import logging
-import os
 
+from ..config import get_settings
 from .base import Provider
 from .bedrock import BedrockProvider
+from .mistral import MistralProvider
 from .ollama import OllamaProvider
 from .openai import OpenAIProvider
 from .simple import SimpleProvider
@@ -16,117 +17,112 @@ class ProviderRegistry:
     """
     Registry for provider auto-detection and instantiation.
 
-    Checks environment variables in priority order and creates appropriate provider:
-    1. Bedrock (AWS_REGION + BEDROCK_*_MODEL)
-    2. OpenAI (OPENAI_API_KEY)
-    3. Ollama (OLLAMA_BASE_URL)
-    4. Simple (fallback for testing/development)
+    Reads configuration via dynaconf-backed Settings (see ``config.py``).
+    Checks provider settings in priority order and creates the appropriate
+    provider:
+
+    1. Bedrock (``AWS_REGION`` or ``BEDROCK_*_MODEL``)
+    2. OpenAI (``OPENAI_API_KEY``)
+    3. Mistral (``MISTRAL_API_KEY``)
+    4. Ollama (``OLLAMA_BASE_URL``)
+    5. Simple (fallback for testing/development)
     """
 
     @staticmethod
     def create_provider() -> Provider:
         """
-        Auto-detect and create provider based on environment variables.
+        Auto-detect and create provider based on configured settings.
+
+        Settings are sourced via :func:`nextcloud_mcp_server.config.get_settings`,
+        which reads from settings files and environment variables (env vars
+        always win, see ADR-024/025).
 
         Priority order:
-        1. Bedrock - if AWS_REGION or BEDROCK_EMBEDDING_MODEL is set
-        2. OpenAI - if OPENAI_API_KEY is set
-        3. Ollama - if OLLAMA_BASE_URL is set
-        4. Simple - fallback for testing/development
+
+        1. Bedrock - if ``aws_region`` or ``bedrock_embedding_model`` is set
+        2. OpenAI - if ``openai_api_key`` is set
+        3. Mistral - if ``mistral_api_key`` is set
+        4. Ollama - if ``ollama_base_url`` is set
+        5. Simple - fallback for testing/development
 
         Returns:
             Provider instance
-
-        Environment Variables:
-            Bedrock:
-                - AWS_REGION: AWS region (e.g., "us-east-1")
-                - AWS_ACCESS_KEY_ID: AWS access key (optional, uses credential chain)
-                - AWS_SECRET_ACCESS_KEY: AWS secret key (optional)
-                - BEDROCK_EMBEDDING_MODEL: Model ID for embeddings (e.g., "amazon.titan-embed-text-v2:0")
-                - BEDROCK_GENERATION_MODEL: Model ID for text generation (e.g., "anthropic.claude-3-sonnet-20240229-v1:0")
-
-            OpenAI:
-                - OPENAI_API_KEY: OpenAI API key (or GITHUB_TOKEN for GitHub Models)
-                - OPENAI_BASE_URL: Base URL override (e.g., "https://models.github.ai/inference")
-                - OPENAI_EMBEDDING_MODEL: Model for embeddings (default: "text-embedding-3-small")
-                - OPENAI_GENERATION_MODEL: Model for text generation (e.g., "gpt-4o-mini")
-
-            Ollama:
-                - OLLAMA_BASE_URL: Ollama API base URL (e.g., "http://localhost:11434")
-                - OLLAMA_EMBEDDING_MODEL: Model for embeddings (default: "nomic-embed-text")
-                - OLLAMA_GENERATION_MODEL: Model for text generation (e.g., "llama3.2:1b")
-                - OLLAMA_VERIFY_SSL: Verify SSL certificates (default: "true")
-
-            Simple (no configuration needed, fallback):
-                - SIMPLE_EMBEDDING_DIMENSION: Embedding dimension (default: 384)
         """
-        # 1. Check for Bedrock
-        aws_region = os.getenv("AWS_REGION")
-        bedrock_embedding_model = os.getenv("BEDROCK_EMBEDDING_MODEL")
-        bedrock_generation_model = os.getenv("BEDROCK_GENERATION_MODEL")
+        settings = get_settings()
 
-        if aws_region or bedrock_embedding_model or bedrock_generation_model:
+        # 1. Bedrock
+        if (
+            settings.aws_region
+            or settings.bedrock_embedding_model
+            or settings.bedrock_generation_model
+        ):
             logger.info(
-                f"Using Bedrock provider: region={aws_region}, "
-                f"embedding_model={bedrock_embedding_model}, "
-                f"generation_model={bedrock_generation_model}"
+                "Using Bedrock provider: region=%s, embedding_model=%s, "
+                "generation_model=%s",
+                settings.aws_region,
+                settings.bedrock_embedding_model,
+                settings.bedrock_generation_model,
             )
             return BedrockProvider(
-                region_name=aws_region,
-                embedding_model=bedrock_embedding_model,
-                generation_model=bedrock_generation_model,
-                aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
-                aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
+                region_name=settings.aws_region,
+                embedding_model=settings.bedrock_embedding_model,
+                generation_model=settings.bedrock_generation_model,
+                aws_access_key_id=settings.aws_access_key_id,
+                aws_secret_access_key=settings.aws_secret_access_key,
             )
 
-        # 2. Check for OpenAI
-        openai_api_key = os.getenv("OPENAI_API_KEY")
-        if openai_api_key:
-            base_url = os.getenv("OPENAI_BASE_URL")
-            embedding_model = os.getenv(
-                "OPENAI_EMBEDDING_MODEL", "text-embedding-3-small"
-            )
-            generation_model = os.getenv("OPENAI_GENERATION_MODEL")
-
+        # 2. OpenAI
+        if settings.openai_api_key:
             logger.info(
-                f"Using OpenAI provider: base_url={base_url or 'default'}, "
-                f"embedding_model={embedding_model}, "
-                f"generation_model={generation_model}"
+                "Using OpenAI provider: base_url=%s, embedding_model=%s, "
+                "generation_model=%s",
+                settings.openai_base_url or "default",
+                settings.openai_embedding_model,
+                settings.openai_generation_model,
             )
             return OpenAIProvider(
-                api_key=openai_api_key,
-                base_url=base_url,
-                embedding_model=embedding_model,
-                generation_model=generation_model,
+                api_key=settings.openai_api_key,
+                base_url=settings.openai_base_url,
+                embedding_model=settings.openai_embedding_model,
+                generation_model=settings.openai_generation_model,
             )
 
-        # 3. Check for Ollama (local LLM)
-        ollama_url = os.getenv("OLLAMA_BASE_URL")
-        if ollama_url:
-            embedding_model = os.getenv("OLLAMA_EMBEDDING_MODEL", "nomic-embed-text")
-            generation_model = os.getenv("OLLAMA_GENERATION_MODEL")
-            verify_ssl = os.getenv("OLLAMA_VERIFY_SSL", "true").lower() == "true"
-
+        # 3. Mistral
+        if settings.mistral_api_key:
             logger.info(
-                f"Using Ollama provider: {ollama_url}, "
-                f"embedding_model={embedding_model}, "
-                f"generation_model={generation_model}"
+                "Using Mistral provider: base_url=%s, embedding_model=%s",
+                settings.mistral_base_url or "default",
+                settings.mistral_embedding_model,
+            )
+            return MistralProvider(
+                api_key=settings.mistral_api_key,
+                base_url=settings.mistral_base_url,
+                embedding_model=settings.mistral_embedding_model,
+            )
+
+        # 4. Ollama
+        if settings.ollama_base_url:
+            logger.info(
+                "Using Ollama provider: %s, embedding_model=%s, generation_model=%s",
+                settings.ollama_base_url,
+                settings.ollama_embedding_model,
+                settings.ollama_generation_model,
             )
             return OllamaProvider(
-                base_url=ollama_url,
-                embedding_model=embedding_model,
-                generation_model=generation_model,
-                verify_ssl=verify_ssl,
+                base_url=settings.ollama_base_url,
+                embedding_model=settings.ollama_embedding_model,
+                generation_model=settings.ollama_generation_model,
+                verify_ssl=settings.ollama_verify_ssl,
             )
 
-        # 4. Fallback to Simple provider for development/testing
-        dimension = int(os.getenv("SIMPLE_EMBEDDING_DIMENSION", "384"))
+        # 5. Simple (fallback)
         logger.warning(
-            "No provider configured (AWS_REGION, OPENAI_API_KEY, OLLAMA_BASE_URL not set). "
+            "No provider configured (AWS_REGION, OPENAI_API_KEY, "
+            "MISTRAL_API_KEY, OLLAMA_BASE_URL not set). "
             "Using SimpleProvider for testing/development. "
-            "For production, configure Bedrock, OpenAI, or Ollama."
+            "For production, configure Bedrock, OpenAI, Mistral, or Ollama."
         )
-        return SimpleProvider(dimension=dimension)
+        return SimpleProvider(dimension=settings.simple_embedding_dimension)
 
 
 # Singleton instance

pyproject.toml

@@ -43,6 +43,7 @@ dependencies = [
     "pymupdf4llm>=0.2.2",
     "openai>=2.8.1",
     "dynaconf>=3.2.13,<4.0",
+    "mistralai>=2.4.5",
 ]
 classifiers = [
     "Development Status :: 4 - Beta",

tests/unit/providers/test_mistral.py

@@ -0,0 +1,198 @@
+"""Unit tests for Mistral provider."""
+
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nextcloud_mcp_server.providers.mistral import (
+    BATCH_SIZE,
+    MISTRAL_EMBEDDING_DIMENSIONS,
+    MistralProvider,
+)
+
+
+def _make_data(embedding: list[float], index: int) -> MagicMock:
+    """Build a mock EmbeddingResponseData entry."""
+    item = MagicMock()
+    item.embedding = embedding
+    item.index = index
+    return item
+
+
+def _make_response(embeddings: list[list[float]]) -> MagicMock:
+    """Build a mock EmbeddingResponse with `embeddings` indexed in order."""
+    response = MagicMock()
+    response.data = [_make_data(emb, i) for i, emb in enumerate(embeddings)]
+    return response
+
+
+@pytest.fixture
+def mock_mistral_client(mocker):
+    """Mock the Mistral SDK constructor."""
+    mock_client = MagicMock()
+    mock_client.embeddings = MagicMock()
+    mocker.patch(
+        "nextcloud_mcp_server.providers.mistral.Mistral", return_value=mock_client
+    )
+    return mock_client
+
+
+@pytest.mark.unit
+async def test_mistral_embedding_single(mock_mistral_client):
+    """Single text embed: round-trip through SDK with correct kwargs."""
+    mock_mistral_client.embeddings.create_async = AsyncMock(
+        return_value=_make_response([[0.1, 0.2, 0.3]])
+    )
+
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    embedding = await provider.embed("hello world")
+
+    assert embedding == [0.1, 0.2, 0.3]
+    mock_mistral_client.embeddings.create_async.assert_awaited_once_with(
+        model="mistral-embed",
+        inputs=["hello world"],
+    )
+
+
+@pytest.mark.unit
+async def test_mistral_embedding_batch_single_call(mock_mistral_client):
+    """Batch smaller than BATCH_SIZE issues a single API call."""
+    mock_mistral_client.embeddings.create_async = AsyncMock(
+        return_value=_make_response([[0.1, 0.2], [0.3, 0.4], [0.5, 0.6]])
+    )
+
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    embeddings = await provider.embed_batch(["a", "b", "c"])
+
+    assert embeddings == [[0.1, 0.2], [0.3, 0.4], [0.5, 0.6]]
+    assert mock_mistral_client.embeddings.create_async.await_count == 1
+
+
+@pytest.mark.unit
+async def test_mistral_embedding_batch_chunking(mock_mistral_client):
+    """Batches exceeding BATCH_SIZE are split into multiple API calls."""
+
+    # Each call returns one embedding per input it received; capture by side
+    # effect so we can inspect lengths per chunk.
+    def _side_effect(*, model, inputs, **_kwargs):
+        return _make_response([[float(i)] for i in range(len(inputs))])
+
+    mock_mistral_client.embeddings.create_async = AsyncMock(side_effect=_side_effect)
+
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    total = BATCH_SIZE * 2 + 5  # forces three chunks: 64, 64, 5 (with default)
+    embeddings = await provider.embed_batch([f"text-{i}" for i in range(total)])
+
+    assert len(embeddings) == total
+    assert mock_mistral_client.embeddings.create_async.await_count == 3
+    # Verify the chunk sizes the SDK was actually called with.
+    chunk_sizes = [
+        len(call.kwargs["inputs"])
+        for call in mock_mistral_client.embeddings.create_async.await_args_list
+    ]
+    assert chunk_sizes == [BATCH_SIZE, BATCH_SIZE, 5]
+
+
+@pytest.mark.unit
+async def test_mistral_embedding_batch_order_preserved(mock_mistral_client):
+    """Out-of-order index in response data is sorted before returning."""
+    response = MagicMock()
+    response.data = [
+        _make_data([0.3, 0.3], 2),
+        _make_data([0.1, 0.1], 0),
+        _make_data([0.2, 0.2], 1),
+    ]
+    mock_mistral_client.embeddings.create_async = AsyncMock(return_value=response)
+
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    embeddings = await provider.embed_batch(["x", "y", "z"])
+
+    assert embeddings == [[0.1, 0.1], [0.2, 0.2], [0.3, 0.3]]
+
+
+@pytest.mark.unit
+async def test_mistral_supports_capabilities(mock_mistral_client):
+    """Mistral provider advertises embeddings only."""
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    assert provider.supports_embeddings is True
+    assert provider.supports_generation is False
+
+
+@pytest.mark.unit
+async def test_mistral_generate_not_implemented(mock_mistral_client):
+    """generate() always raises NotImplementedError."""
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    with pytest.raises(NotImplementedError, match="does not support generation"):
+        await provider.generate("test prompt")
+
+
+@pytest.mark.unit
+async def test_mistral_get_dimension_known_model(mock_mistral_client):
+    """Known model: dimension available without an API call."""
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    assert provider.get_dimension() == MISTRAL_EMBEDDING_DIMENSIONS["mistral-embed"]
+    mock_mistral_client.embeddings.create_async.assert_not_called()
+
+
+@pytest.mark.unit
+async def test_mistral_get_dimension_unknown_model_detected(mock_mistral_client):
+    """Unknown model: dimension detected on first embed() call."""
+    mock_mistral_client.embeddings.create_async = AsyncMock(
+        return_value=_make_response([[0.1] * 768])
+    )
+
+    provider = MistralProvider(api_key="test-key", embedding_model="custom-mistral")
+
+    with pytest.raises(RuntimeError, match="not detected yet"):
+        provider.get_dimension()
+
+    await provider.embed("test")
+    assert provider.get_dimension() == 768
+
+
+@pytest.mark.unit
+async def test_mistral_no_embeddings_disabled():
+    """Setting embedding_model=None disables the embedding capability."""
+    provider = MistralProvider(api_key="test-key", embedding_model=None)
+    assert provider.supports_embeddings is False
+
+    with pytest.raises(NotImplementedError, match="no embedding_model configured"):
+        await provider.embed("test")
+    with pytest.raises(NotImplementedError, match="no embedding_model configured"):
+        await provider.embed_batch(["test"])
+    with pytest.raises(NotImplementedError, match="no embedding_model configured"):
+        provider.get_dimension()
+
+
+@pytest.mark.unit
+async def test_mistral_empty_batch(mock_mistral_client):
+    """An empty batch returns [] without calling the API."""
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    assert await provider.embed_batch([]) == []
+    mock_mistral_client.embeddings.create_async.assert_not_called()
+
+
+@pytest.mark.unit
+async def test_mistral_close_no_error(mock_mistral_client):
+    """close() is best-effort and does not raise."""
+    provider = MistralProvider(api_key="test-key", embedding_model="mistral-embed")
+    # No __aexit__ on the mock by default → close() should silently no-op.
+    await provider.close()
+
+
+@pytest.mark.unit
+async def test_mistral_base_url_passed_to_sdk(mocker):
+    """base_url is forwarded as server_url to the Mistral SDK constructor."""
+    mock_ctor = mocker.patch(
+        "nextcloud_mcp_server.providers.mistral.Mistral", return_value=MagicMock()
+    )
+
+    MistralProvider(
+        api_key="test-key",
+        embedding_model="mistral-embed",
+        base_url="https://example.com/mistral",
+    )
+    mock_ctor.assert_called_once_with(
+        api_key="test-key",
+        server_url="https://example.com/mistral",
+    )

tests/unit/providers/test_registry.py

@@ -0,0 +1,130 @@
+"""Unit tests for ProviderRegistry — dynaconf-driven auto-detection."""
+
+import pytest
+
+from nextcloud_mcp_server.config import _reload_config
+from nextcloud_mcp_server.providers import (
+    BedrockProvider,
+    MistralProvider,
+    OllamaProvider,
+    OpenAIProvider,
+    SimpleProvider,
+    get_provider,
+    reset_provider,
+)
+from nextcloud_mcp_server.providers.bedrock import BOTO3_AVAILABLE
+
+
+def _clear_provider_envs(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Strip every provider-selection env var so each test starts clean."""
+    for name in (
+        "AWS_REGION",
+        "AWS_ACCESS_KEY_ID",
+        "AWS_SECRET_ACCESS_KEY",
+        "BEDROCK_EMBEDDING_MODEL",
+        "BEDROCK_GENERATION_MODEL",
+        "OPENAI_API_KEY",
+        "OPENAI_BASE_URL",
+        "OPENAI_EMBEDDING_MODEL",
+        "OPENAI_GENERATION_MODEL",
+        "MISTRAL_API_KEY",
+        "MISTRAL_BASE_URL",
+        "MISTRAL_EMBEDDING_MODEL",
+        "OLLAMA_BASE_URL",
+        "OLLAMA_EMBEDDING_MODEL",
+        "OLLAMA_GENERATION_MODEL",
+        "OLLAMA_VERIFY_SSL",
+        "SIMPLE_EMBEDDING_DIMENSION",
+    ):
+        monkeypatch.delenv(name, raising=False)
+
+
+@pytest.fixture
+def clean_provider_env(monkeypatch):
+    """Reset provider singleton + dynaconf cache around each test."""
+    _clear_provider_envs(monkeypatch)
+    reset_provider()
+    _reload_config()
+    yield monkeypatch
+    reset_provider()
+
+
+@pytest.mark.unit
+def test_registry_falls_back_to_simple(clean_provider_env):
+    """No provider env set → SimpleProvider (with default dimension)."""
+    provider = get_provider()
+    assert isinstance(provider, SimpleProvider)
+    assert provider.get_dimension() == 384
+
+
+@pytest.mark.unit
+def test_registry_picks_simple_with_custom_dimension(clean_provider_env):
+    """SIMPLE_EMBEDDING_DIMENSION flows through dynaconf to SimpleProvider."""
+    clean_provider_env.setenv("SIMPLE_EMBEDDING_DIMENSION", "512")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, SimpleProvider)
+    assert provider.get_dimension() == 512
+
+
+@pytest.mark.unit
+def test_registry_picks_mistral_when_api_key_set(clean_provider_env):
+    """MISTRAL_API_KEY alone is enough to select MistralProvider."""
+    clean_provider_env.setenv("MISTRAL_API_KEY", "test-key")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, MistralProvider)
+
+
+@pytest.mark.unit
+def test_registry_picks_ollama_when_base_url_set(clean_provider_env, mocker):
+    """OLLAMA_BASE_URL selects OllamaProvider."""
+    # OllamaProvider eagerly probes /api/tags in __init__; stub it out.
+    mocker.patch(
+        "nextcloud_mcp_server.providers.ollama.OllamaProvider._check_model_is_loaded"
+    )
+    clean_provider_env.setenv("OLLAMA_BASE_URL", "http://localhost:11434")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, OllamaProvider)
+
+
+@pytest.mark.unit
+def test_registry_openai_wins_over_mistral_and_ollama(clean_provider_env):
+    """OpenAI takes priority when multiple provider env vars are set."""
+    clean_provider_env.setenv("OPENAI_API_KEY", "openai-key")
+    clean_provider_env.setenv("MISTRAL_API_KEY", "mistral-key")
+    clean_provider_env.setenv("OLLAMA_BASE_URL", "http://localhost:11434")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, OpenAIProvider)
+
+
+@pytest.mark.unit
+def test_registry_mistral_wins_over_ollama(clean_provider_env):
+    """Mistral takes priority over Ollama when both are configured."""
+    clean_provider_env.setenv("MISTRAL_API_KEY", "mistral-key")
+    clean_provider_env.setenv("OLLAMA_BASE_URL", "http://localhost:11434")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, MistralProvider)
+
+
+@pytest.mark.unit
+def test_registry_bedrock_wins_when_aws_region_set(clean_provider_env):
+    """AWS_REGION alone routes to Bedrock, even with other providers configured."""
+    if not BOTO3_AVAILABLE:
+        pytest.skip("boto3 not installed")
+
+    clean_provider_env.setenv("AWS_REGION", "us-east-1")
+    clean_provider_env.setenv("OPENAI_API_KEY", "openai-key")
+    clean_provider_env.setenv("MISTRAL_API_KEY", "mistral-key")
+    _reload_config()
+
+    provider = get_provider()
+    assert isinstance(provider, BedrockProvider)

uv.lock

@@ -769,6 +769,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/97/43/11d6e5d2c00bf000b5329717c74563bf76a9193f4a41cb0c4ef277dde4fa/dynaconf-3.2.13-py2.py3-none-any.whl", hash = "sha256:4305527aef4834bdba3e39479b23c005186e83fb85f65bcaa4bcea58fa26759b", size = 238041, upload-time = "2026-03-17T19:38:45.337Z" },
 ]
 
+[[package]]
+name = "eval-type-backport"
+version = "0.3.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fb/a3/cafafb4558fd638aadfe4121dc6cefb8d743368c085acb2f521df0f3d9d7/eval_type_backport-0.3.1.tar.gz", hash = "sha256:57e993f7b5b69d271e37482e62f74e76a0276c82490cf8e4f0dffeb6b332d5ed", size = 9445, upload-time = "2025-12-02T11:51:42.987Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cf/22/fdc2e30d43ff853720042fa15baa3e6122722be1a7950a98233ebb55cd71/eval_type_backport-0.3.1-py3-none-any.whl", hash = "sha256:279ab641905e9f11129f56a8a78f493518515b83402b860f6f06dd7c011fdfa8", size = 6063, upload-time = "2025-12-02T11:51:41.665Z" },
+]
+
 [[package]]
 name = "executing"
 version = "2.2.1"
@@ -1478,6 +1487,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/73/07/02e16ed01e04a374e644b575638ec7987ae846d25ad97bcc9945a3ee4b0e/jsonpatch-1.33-py2.py3-none-any.whl", hash = "sha256:0ae28c0cd062bbd8b8ecc26d7d164fbbea9652a1a3693f3b956c1eae5145dade", size = 12898, upload-time = "2023-06-16T21:01:28.466Z" },
 ]
 
+[[package]]
+name = "jsonpath-python"
+version = "1.1.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/18/4ca8742534a5993ff383f7602e325ce2d5d7cc93d72ac5e1cdedbea8a458/jsonpath_python-1.1.6.tar.gz", hash = "sha256:dded9932b4ec41fb8726e09c83afa4e6be618f938c2db287cc2a81723c639671", size = 88178, upload-time = "2026-05-07T01:26:34.482Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/55/8a/1270a6803bd821cbfcdda387eaa13cb41a7b1f7b9bd145979b3bfb9d6cb7/jsonpath_python-1.1.6-py3-none-any.whl", hash = "sha256:a1c50afd8d3fbbaf47a4873bc890dcb3c15da96f5c020327977d844d8731a2d4", size = 14453, upload-time = "2026-05-07T01:26:33.306Z" },
+]
+
 [[package]]
 name = "jsonpointer"
 version = "3.0.0"
@@ -1842,6 +1860,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b3/38/89ba8ad64ae25be8de66a6d463314cf1eb366222074cfda9ee839c56a4b4/mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8", size = 9979, upload-time = "2022-08-14T12:40:09.779Z" },
 ]
 
+[[package]]
+name = "mistralai"
+version = "2.4.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "eval-type-backport" },
+    { name = "httpx" },
+    { name = "jsonpath-python" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "pydantic" },
+    { name = "python-dateutil" },
+    { name = "typing-inspection" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/8e/3f/5624d57c5897c83c55d3e4c7dd4127de42ad14fd3183e26566cdc7dca1bf/mistralai-2.4.5.tar.gz", hash = "sha256:ef165bb004ec4423cbf19a440bf0983ca0c3fc92ab12a35ebca097bdf418e33a", size = 424611, upload-time = "2026-05-07T11:46:43.888Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1b/48/2c5c4f853dec32a625c1a3d23809b80cf2e135c3441fe1764f72910dfea9/mistralai-2.4.5-py3-none-any.whl", hash = "sha256:bf3b6550258ab16dec8547b90e9c18bebf9099f55b7fc25a884bf0bbeffced0f", size = 995999, upload-time = "2026-05-07T11:46:41.915Z" },
+]
+
 [[package]]
 name = "mmh3"
 version = "5.2.0"
@@ -2104,6 +2141,7 @@ dependencies = [
     { name = "langchain-text-splitters" },
     { name = "markdownify" },
     { name = "mcp", extra = ["cli"] },
+    { name = "mistralai" },
     { name = "openai" },
     { name = "opentelemetry-api" },
     { name = "opentelemetry-exporter-otlp-proto-grpc" },
@@ -2157,6 +2195,7 @@ requires-dist = [
     { name = "langchain-text-splitters", specifier = ">=1.0.0" },
     { name = "markdownify", specifier = ">=0.14.1" },
     { name = "mcp", extras = ["cli"], specifier = ">=1.27,<1.28" },
+    { name = "mistralai", specifier = ">=2.4.5" },
     { name = "openai", specifier = ">=2.8.1" },
     { name = "opentelemetry-api", specifier = ">=1.28.2" },
     { name = "opentelemetry-exporter-otlp-proto-grpc", specifier = ">=1.28.2" },
@@ -2341,45 +2380,45 @@ wheels = [
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "importlib-metadata" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c0/0b/e5428c009d4d9af0515b0a8371a8aaae695371af291f45e702f7969dce6b/opentelemetry_api-1.39.0.tar.gz", hash = "sha256:6130644268c5ac6bdffaf660ce878f10906b3e789f7e2daa5e169b047a2933b9", size = 65763, upload-time = "2025-12-03T13:19:56.378Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/97/b9/3161be15bb8e3ad01be8be5a968a9237c3027c5be504362ff800fca3e442/opentelemetry_api-1.39.1.tar.gz", hash = "sha256:fbde8c80e1b937a2c61f20347e91c0c18a1940cecf012d62e65a7caf08967c9c", size = 65767, upload-time = "2025-12-11T13:32:39.182Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/05/85/d831a9bc0a9e0e1a304ff3d12c1489a5fbc9bf6690a15dcbdae372bbca45/opentelemetry_api-1.39.0-py3-none-any.whl", hash = "sha256:3c3b3ca5c5687b1b5b37e5c5027ff68eacea8675241b29f13110a8ffbb8f0459", size = 66357, upload-time = "2025-12-03T13:19:33.043Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/df/d3f1ddf4bb4cb50ed9b1139cc7b1c54c34a1e7ce8fd1b9a37c0d1551a6bd/opentelemetry_api-1.39.1-py3-none-any.whl", hash = "sha256:2edd8463432a7f8443edce90972169b195e7d6a05500cd29e6d13898187c9950", size = 66356, upload-time = "2025-12-11T13:32:17.304Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-exporter-otlp-proto-grpc" },
     { name = "opentelemetry-exporter-otlp-proto-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/13/be/0e9d889f47e55cadc4041e5b53d4e0cc688f9a74811134fb0ba7cbee6905/opentelemetry_exporter_otlp-1.39.0.tar.gz", hash = "sha256:b405da0287b895fe4e2450dedb2a5b072debba1dfcfed5bdb3d1d183d8daa296", size = 6146, upload-time = "2025-12-03T13:19:58.381Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/30/9c/3ab1db90f32da200dba332658f2bbe602369e3d19f6aba394031a42635be/opentelemetry_exporter_otlp-1.39.1.tar.gz", hash = "sha256:7cf7470e9fd0060c8a38a23e4f695ac686c06a48ad97f8d4867bc9b420180b9c", size = 6147, upload-time = "2025-12-11T13:32:40.309Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fc/35/212d2cae4fa9a2c02e74438612268b640ab577b8ccb04590371eb4e0f542/opentelemetry_exporter_otlp-1.39.0-py3-none-any.whl", hash = "sha256:fe155d6968d581b325574ad6dc267c8de299397b18d11feeda2206d0a47928a9", size = 7017, upload-time = "2025-12-03T13:19:35.686Z" },
+    { url = "https://files.pythonhosted.org/packages/00/6c/bdc82a066e6fb1dcf9e8cc8d4e026358fe0f8690700cc6369a6bf9bd17a7/opentelemetry_exporter_otlp-1.39.1-py3-none-any.whl", hash = "sha256:68ae69775291f04f000eb4b698ff16ff685fdebe5cb52871bc4e87938a7b00fe", size = 7019, upload-time = "2025-12-11T13:32:19.387Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-proto" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/11/cb/3a29ce606b10c76d413d6edd42d25a654af03e73e50696611e757d2602f3/opentelemetry_exporter_otlp_proto_common-1.39.0.tar.gz", hash = "sha256:a135fceed1a6d767f75be65bd2845da344dd8b9258eeed6bc48509d02b184409", size = 20407, upload-time = "2025-12-03T13:19:59.003Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e9/9d/22d241b66f7bbde88a3bfa6847a351d2c46b84de23e71222c6aae25c7050/opentelemetry_exporter_otlp_proto_common-1.39.1.tar.gz", hash = "sha256:763370d4737a59741c89a67b50f9e39271639ee4afc999dadfe768541c027464", size = 20409, upload-time = "2025-12-11T13:32:40.885Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ef/c6/215edba62d13a3948c718b289539f70e40965bc37fc82ecd55bb0b749c1a/opentelemetry_exporter_otlp_proto_common-1.39.0-py3-none-any.whl", hash = "sha256:3d77be7c4bdf90f1a76666c934368b8abed730b5c6f0547a2ec57feb115849ac", size = 18367, upload-time = "2025-12-03T13:19:36.906Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/02/ffc3e143d89a27ac21fd557365b98bd0653b98de8a101151d5805b5d4c33/opentelemetry_exporter_otlp_proto_common-1.39.1-py3-none-any.whl", hash = "sha256:08f8a5862d64cc3435105686d0216c1365dc5701f86844a8cd56597d0c764fde", size = 18366, upload-time = "2025-12-11T13:32:20.2Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "googleapis-common-protos" },
@@ -2390,14 +2429,14 @@ dependencies = [
     { name = "opentelemetry-sdk" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/7e/62/4db083ee9620da3065eeb559e9fc128f41a1d15e7c48d7c83aafbccd354c/opentelemetry_exporter_otlp_proto_grpc-1.39.0.tar.gz", hash = "sha256:7e7bb3f436006836c0e0a42ac619097746ad5553ad7128a5bd4d3e727f37fc06", size = 24650, upload-time = "2025-12-03T13:20:00.06Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/53/48/b329fed2c610c2c32c9366d9dc597202c9d1e58e631c137ba15248d8850f/opentelemetry_exporter_otlp_proto_grpc-1.39.1.tar.gz", hash = "sha256:772eb1c9287485d625e4dbe9c879898e5253fea111d9181140f51291b5fec3ad", size = 24650, upload-time = "2025-12-11T13:32:41.429Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/56/e8/d420b94ffddfd8cff85bb4aa5d98da26ce7935dc3cf3eca6b83cd39ab436/opentelemetry_exporter_otlp_proto_grpc-1.39.0-py3-none-any.whl", hash = "sha256:758641278050de9bb895738f35ff8840e4a47685b7e6ef4a201fe83196ba7a05", size = 19765, upload-time = "2025-12-03T13:19:38.143Z" },
+    { url = "https://files.pythonhosted.org/packages/81/a3/cc9b66575bd6597b98b886a2067eea2693408d2d5f39dad9ab7fc264f5f3/opentelemetry_exporter_otlp_proto_grpc-1.39.1-py3-none-any.whl", hash = "sha256:fa1c136a05c7e9b4c09f739469cbdb927ea20b34088ab1d959a849b5cc589c18", size = 19766, upload-time = "2025-12-11T13:32:21.027Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "googleapis-common-protos" },
@@ -2408,14 +2447,14 @@ dependencies = [
     { name = "requests" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/81/dc/1e9bf3f6a28e29eba516bc0266e052996d02bc7e92675f3cd38169607609/opentelemetry_exporter_otlp_proto_http-1.39.0.tar.gz", hash = "sha256:28d78fc0eb82d5a71ae552263d5012fa3ebad18dfd189bf8d8095ba0e65ee1ed", size = 17287, upload-time = "2025-12-03T13:20:01.134Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/80/04/2a08fa9c0214ae38880df01e8bfae12b067ec0793446578575e5080d6545/opentelemetry_exporter_otlp_proto_http-1.39.1.tar.gz", hash = "sha256:31bdab9745c709ce90a49a0624c2bd445d31a28ba34275951a6a362d16a0b9cb", size = 17288, upload-time = "2025-12-11T13:32:42.029Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/bc/46/e4a102e17205bb05a50dbf24ef0e92b66b648cd67db9a68865af06a242fd/opentelemetry_exporter_otlp_proto_http-1.39.0-py3-none-any.whl", hash = "sha256:5789cb1375a8b82653328c0ce13a054d285f774099faf9d068032a49de4c7862", size = 19639, upload-time = "2025-12-03T13:19:39.536Z" },
+    { url = "https://files.pythonhosted.org/packages/95/f1/b27d3e2e003cd9a3592c43d099d2ed8d0a947c15281bf8463a256db0b46c/opentelemetry_exporter_otlp_proto_http-1.39.1-py3-none-any.whl", hash = "sha256:d9f5207183dd752a412c4cd564ca8875ececba13be6e9c6c370ffb752fd59985", size = 19641, upload-time = "2025-12-11T13:32:22.248Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -2423,14 +2462,14 @@ dependencies = [
     { name = "packaging" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/55/3c/bd53dbb42eff93d18e3047c7be11224aa9966ce98ac4cc5bfb860a32c95a/opentelemetry_instrumentation-0.60b0.tar.gz", hash = "sha256:4e9fec930f283a2677a2217754b40aaf9ef76edae40499c165bc7f1d15366a74", size = 31707, upload-time = "2025-12-03T13:22:00.352Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/41/0f/7e6b713ac117c1f5e4e3300748af699b9902a2e5e34c9cf443dde25a01fa/opentelemetry_instrumentation-0.60b1.tar.gz", hash = "sha256:57ddc7974c6eb35865af0426d1a17132b88b2ed8586897fee187fd5b8944bd6a", size = 31706, upload-time = "2025-12-11T13:36:42.515Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5c/7b/5b5b9f8cfe727a28553acf9cd287b1d7f706f5c0a00d6e482df55b169483/opentelemetry_instrumentation-0.60b0-py3-none-any.whl", hash = "sha256:aaafa1483543a402819f1bdfb06af721c87d60dd109501f9997332862a35c76a", size = 33096, upload-time = "2025-12-03T13:20:51.785Z" },
+    { url = "https://files.pythonhosted.org/packages/77/d2/6788e83c5c86a2690101681aeef27eeb2a6bf22df52d3f263a22cee20915/opentelemetry_instrumentation-0.60b1-py3-none-any.whl", hash = "sha256:04480db952b48fb1ed0073f822f0ee26012b7be7c3eac1a3793122737c78632d", size = 33096, upload-time = "2025-12-11T13:35:33.067Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-asgi"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref" },
@@ -2439,14 +2478,14 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b0/0a/715ea7044708d3c215385fb2a1c6ffe429aacb3cd23a348060aaeda52834/opentelemetry_instrumentation_asgi-0.60b0.tar.gz", hash = "sha256:928731218050089dca69f0fe980b8bfe109f384be8b89802d7337372ddb67b91", size = 26083, upload-time = "2025-12-03T13:22:05.672Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/77/db/851fa88db7441da82d50bd80f2de5ee55213782e25dc858e04d0c9961d60/opentelemetry_instrumentation_asgi-0.60b1.tar.gz", hash = "sha256:16bfbe595cd24cda309a957456d0fc2523f41bc7b076d1f2d7e98a1ad9876d6f", size = 26107, upload-time = "2025-12-11T13:36:47.015Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9b/8c/c6c59127fd996107243ca45669355665a7daff578ddafb86d6d2d3b01428/opentelemetry_instrumentation_asgi-0.60b0-py3-none-any.whl", hash = "sha256:9d76a541269452c718a0384478f3291feb650c5a3f29e578fdc6613ea3729cf3", size = 16907, upload-time = "2025-12-03T13:20:58.962Z" },
+    { url = "https://files.pythonhosted.org/packages/76/76/1fb94367cef64420d2171157a6b9509582873bd09a6afe08a78a8d1f59d9/opentelemetry_instrumentation_asgi-0.60b1-py3-none-any.whl", hash = "sha256:d48def2dbed10294c99cfcf41ebbd0c414d390a11773a41f472d20000fcddc25", size = 16933, upload-time = "2025-12-11T13:35:40.462Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-httpx"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -2455,70 +2494,70 @@ dependencies = [
     { name = "opentelemetry-util-http" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/09/71/9dc0bc5ab14122251f520ffe9fc8dd892ca688d7d591482b5b1843d685d2/opentelemetry_instrumentation_httpx-0.60b0.tar.gz", hash = "sha256:fcf349a92fb0b941a2a18bec65141f4ba62cbf7a457a1aa580794bad44dc477c", size = 20612, upload-time = "2025-12-03T13:22:20.5Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/86/08/11208bcfcab4fc2023252c3f322aa397fd9ad948355fea60f5fc98648603/opentelemetry_instrumentation_httpx-0.60b1.tar.gz", hash = "sha256:a506ebaf28c60112cbe70ad4f0338f8603f148938cb7b6794ce1051cd2b270ae", size = 20611, upload-time = "2025-12-11T13:37:01.661Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/3a/22/a340c8bfad6f31bfd6a15b0b24d5e68e05e3975e4dbdc3cea6ec4f96e060/opentelemetry_instrumentation_httpx-0.60b0-py3-none-any.whl", hash = "sha256:3f5e6fc4ddf1d9de2aaddb5255110827154dbd4de9187da906c8c2a3cc2219e9", size = 15702, upload-time = "2025-12-03T13:21:20.667Z" },
+    { url = "https://files.pythonhosted.org/packages/43/59/b98e84eebf745ffc75397eaad4763795bff8a30cbf2373a50ed4e70646c5/opentelemetry_instrumentation_httpx-0.60b1-py3-none-any.whl", hash = "sha256:f37636dd742ad2af83d896ba69601ed28da51fa4e25d1ab62fde89ce413e275b", size = 15701, upload-time = "2025-12-11T13:36:04.56Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-logging"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-instrumentation" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/5b/8b/a1aed0b695a58a1f0bdcf90fae5e468cc0fd7de2b74b9816b17e45c38e43/opentelemetry_instrumentation_logging-0.60b0.tar.gz", hash = "sha256:6d87840666669cbbcd53d2230c7a33476862d0bf7f1adc67a95519c6ccfc8281", size = 9969, upload-time = "2025-12-03T13:22:22.608Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/60/a6/4515895b383113677fd2ad21813df5e56108a2df14ebb7916c962c9a0234/opentelemetry_instrumentation_logging-0.60b1.tar.gz", hash = "sha256:98f4b9c7aeb9314a30feee7c002c7ea9abea07c90df5f97fb058b850bc45b89a", size = 9968, upload-time = "2025-12-11T13:37:03.974Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/00/89/6d4f5d8d03376637bff5b8d9e91356104a6f1ce9a34a2099bb2f4bf5e2b5/opentelemetry_instrumentation_logging-0.60b0-py3-none-any.whl", hash = "sha256:af75b3020911b9b6a1b4b19819a165eb131ce9bfdd313062d578fc2dc9a5cd0f", size = 12576, upload-time = "2025-12-03T13:21:24.797Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/f9/8a4ce3901bc52277794e4b18c4ac43dc5929806eff01d22812364132f45f/opentelemetry_instrumentation_logging-0.60b1-py3-none-any.whl", hash = "sha256:f2e18cbc7e1dd3628c80e30d243897fdc93c5b7e0c8ae60abd2b9b6a99f82343", size = 12577, upload-time = "2025-12-11T13:36:08.123Z" },
 ]
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/48/b5/64d2f8c3393cd13ea2092106118f7b98461ba09333d40179a31444c6f176/opentelemetry_proto-1.39.0.tar.gz", hash = "sha256:c1fa48678ad1a1624258698e59be73f990b7fc1f39e73e16a9d08eef65dd838c", size = 46153, upload-time = "2025-12-03T13:20:08.729Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/49/1d/f25d76d8260c156c40c97c9ed4511ec0f9ce353f8108ca6e7561f82a06b2/opentelemetry_proto-1.39.1.tar.gz", hash = "sha256:6c8e05144fc0d3ed4d22c2289c6b126e03bcd0e6a7da0f16cedd2e1c2772e2c8", size = 46152, upload-time = "2025-12-11T13:32:48.681Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e3/4d/d500e1862beed68318705732d1976c390f4a72ca8009c4983ff627acff20/opentelemetry_proto-1.39.0-py3-none-any.whl", hash = "sha256:1e086552ac79acb501485ff0ce75533f70f3382d43d0a30728eeee594f7bf818", size = 72534, upload-time = "2025-12-03T13:19:50.251Z" },
+    { url = "https://files.pythonhosted.org/packages/51/95/b40c96a7b5203005a0b03d8ce8cd212ff23f1793d5ba289c87a097571b18/opentelemetry_proto-1.39.1-py3-none-any.whl", hash = "sha256:22cdc78efd3b3765d09e68bfbd010d4fc254c9818afd0b6b423387d9dee46007", size = 72535, upload-time = "2025-12-11T13:32:33.866Z" },
 ]
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.39.0"
+version = "1.39.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-semantic-conventions" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/51/e3/7cd989003e7cde72e0becfe830abff0df55c69d237ee7961a541e0167833/opentelemetry_sdk-1.39.0.tar.gz", hash = "sha256:c22204f12a0529e07aa4d985f1bca9d6b0e7b29fe7f03e923548ae52e0e15dde", size = 171322, upload-time = "2025-12-03T13:20:09.651Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/eb/fb/c76080c9ba07e1e8235d24cdcc4d125ef7aa3edf23eb4e497c2e50889adc/opentelemetry_sdk-1.39.1.tar.gz", hash = "sha256:cf4d4563caf7bff906c9f7967e2be22d0d6b349b908be0d90fb21c8e9c995cc6", size = 171460, upload-time = "2025-12-11T13:32:49.369Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a4/b4/2adc8bc83eb1055ecb592708efb6f0c520cc2eb68970b02b0f6ecda149cf/opentelemetry_sdk-1.39.0-py3-none-any.whl", hash = "sha256:90cfb07600dfc0d2de26120cebc0c8f27e69bf77cd80ef96645232372709a514", size = 132413, upload-time = "2025-12-03T13:19:51.364Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/98/e91cf858f203d86f4eccdf763dcf01cf03f1dae80c3750f7e635bfa206b6/opentelemetry_sdk-1.39.1-py3-none-any.whl", hash = "sha256:4d5482c478513ecb0a5d938dcc61394e647066e0cc2676bee9f3af3f3f45f01c", size = 132565, upload-time = "2025-12-11T13:32:35.069Z" },
 ]
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/71/0e/176a7844fe4e3cb5de604212094dffaed4e18b32f1c56b5258bcbcba85c2/opentelemetry_semantic_conventions-0.60b0.tar.gz", hash = "sha256:227d7aa73cbb8a2e418029d6b6465553aa01cf7e78ec9d0bc3255c7b3ac5bf8f", size = 137935, upload-time = "2025-12-03T13:20:12.395Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/91/df/553f93ed38bf22f4b999d9be9c185adb558982214f33eae539d3b5cd0858/opentelemetry_semantic_conventions-0.60b1.tar.gz", hash = "sha256:87c228b5a0669b748c76d76df6c364c369c28f1c465e50f661e39737e84bc953", size = 137935, upload-time = "2025-12-11T13:32:50.487Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d0/56/af0306666f91bae47db14d620775604688361f0f76a872e0005277311131/opentelemetry_semantic_conventions-0.60b0-py3-none-any.whl", hash = "sha256:069530852691136018087b52688857d97bba61cd641d0f8628d2d92788c4f78a", size = 219981, upload-time = "2025-12-03T13:19:53.585Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/5e/5958555e09635d09b75de3c4f8b9cae7335ca545d77392ffe7331534c402/opentelemetry_semantic_conventions-0.60b1-py3-none-any.whl", hash = "sha256:9fa8c8b0c110da289809292b0591220d3a7b53c1526a23021e977d68597893fb", size = 219982, upload-time = "2025-12-11T13:32:36.955Z" },
 ]
 
 [[package]]
 name = "opentelemetry-util-http"
-version = "0.60b0"
+version = "0.60b1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/38/0d/786a713445cf338131fef3a84fab1378e4b2ef3c3ea348eeb0c915eb804a/opentelemetry_util_http-0.60b0.tar.gz", hash = "sha256:e42b7bb49bba43b6f34390327d97e5016eb1c47949ceaf37c4795472a4e3a82d", size = 10576, upload-time = "2025-12-03T13:22:41.224Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/50/fc/c47bb04a1d8a941a4061307e1eddfa331ed4d0ab13d8a9781e6db256940a/opentelemetry_util_http-0.60b1.tar.gz", hash = "sha256:0d97152ca8c8a41ced7172d29d3622a219317f74ae6bb3027cfbdcf22c3cc0d6", size = 11053, upload-time = "2025-12-11T13:37:25.115Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/53/5d/a448862f6d10c95685ed0e703596b6bd1784074e7ad90bffdc550abb7b68/opentelemetry_util_http-0.60b0-py3-none-any.whl", hash = "sha256:4f366f1a48adb74ffa6f80aee26f96882e767e01b03cd1cfb948b6e1020341fe", size = 8742, upload-time = "2025-12-03T13:21:54.553Z" },
+    { url = "https://files.pythonhosted.org/packages/16/5c/d3f1733665f7cd582ef0842fb1d2ed0bc1fba10875160593342d22bba375/opentelemetry_util_http-0.60b1-py3-none-any.whl", hash = "sha256:66381ba28550c91bee14dcba8979ace443444af1ed609226634596b4b0faf199", size = 8947, upload-time = "2025-12-11T13:36:37.151Z" },
 ]
 
 [[package]]
@@ -3314,7 +3353,7 @@ wheels = [
 
 [[package]]
 name = "pytest-otel"
-version = "2.0.1"
+version = "2.0.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -3322,9 +3361,9 @@ dependencies = [
     { name = "opentelemetry-sdk" },
     { name = "pytest" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ca/5e/771f8dbdf55ae57603d89bb26e046c13e8bee3492c74cb3afb6044166e9a/pytest_otel-2.0.1.tar.gz", hash = "sha256:3d529dc34105862cca39fd1258d00dd3d17f3b7d92ebf0953d55326bb017af3d", size = 17880, upload-time = "2025-12-08T14:56:40.393Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/14/e4f7cb90c4c93dbdd85034fd65e7a16da328bd71c6ca5270e4f8d37fa4ba/pytest_otel-2.0.3.tar.gz", hash = "sha256:782985fef50acc6922db5e69da4584b384d785c863a96ebc11eaf2a7fef5189c", size = 18587, upload-time = "2026-01-02T16:12:20.394Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/16/fa/0cfe23bac571f68b4f427ad7ae313ddd8de881ec2ff49dcea196a2a96592/pytest_otel-2.0.1-py2.py3-none-any.whl", hash = "sha256:501f36f02f55578ca34c3ccbe55e81cc1e14bb130da13f7cf0b6480d54a9e5db", size = 14530, upload-time = "2025-12-08T14:56:41.731Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/f8/d9b93b41b299c7e14b47887eb31fb4cb77d771c2e9f3e0bcac0750f62699/pytest_otel-2.0.3-py2.py3-none-any.whl", hash = "sha256:3c6c331e943609ad7df7c718714090dee91211340f133a8798217e72e3b2cd67", size = 14914, upload-time = "2026-01-02T16:12:21.946Z" },
 ]
 
 [[package]]