bump: version 0.48.3 → 0.48.4

Add exponential backoff retry handling for OpenAI API rate limits
(429 errors). This is needed for GitHub Models API which has stricter
rate limits than standard OpenAI API.

- Add retry_on_rate_limit decorator with exponential backoff
- Max 5 retries with delays: 2s → 4s → 8s → 16s → 32s
- Apply to embed(), _embed_batch_request(), and generate() methods

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/rag-evaluation.yml

@@ -29,16 +29,17 @@ jobs:
       - name: Run docker compose with vector sync
         uses: hoverkraft-tech/compose-action@3846bcd61da338e9eaaf83e7ed0234a12b099b72 # v2.4.1
         with:
-          compose-file: "./docker-compose.yml"
+          compose-file: |
+            ./docker-compose.yml
+            ./docker-compose.ci.yml
           up-flags: "--build"
         env:
-          # Override MCP container environment for OpenAI + vector sync
-          VECTOR_SYNC_ENABLED: "true"
-          VECTOR_SYNC_SCAN_INTERVAL: "5"
+          # Environment variables passed to docker-compose.ci.yml
           OPENAI_API_KEY: ${{ secrets.GITHUB_TOKEN }}
           OPENAI_BASE_URL: "https://models.github.ai/inference"
           OPENAI_EMBEDDING_MODEL: ${{ inputs.embedding_model }}
           OPENAI_GENERATION_MODEL: ${{ inputs.generation_model }}
+          VECTOR_SYNC_SCAN_INTERVAL: "5"
 
       - name: Install the latest version of uv
         uses: astral-sh/setup-uv@1e862dfacbd1d6d858c55d9b792c756523627244 # v7.1.4
@@ -86,11 +87,17 @@ jobs:
           OPENAI_EMBEDDING_MODEL: ${{ inputs.embedding_model }}
           OPENAI_GENERATION_MODEL: ${{ inputs.generation_model }}
         run: |
-          uv run pytest tests/integration/test_rag_openai.py -v --log-cli-level=INFO --provider openai
+          uv run pytest tests/integration/test_rag.py -v --log-cli-level=INFO --provider openai
+
+      - name: Capture MCP container logs
+        if: always()
+        run: |
+          echo "=== MCP Container Logs ==="
+          docker compose logs mcp --tail=500
 
       - name: Upload test results
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5
         with:
           name: rag-evaluation-results
           path: |

CHANGELOG.md

@@ -1,3 +1,9 @@
+## v0.48.4 (2025-11-23)
+
+### Fix
+
+- Add rate limit retry logic to OpenAI provider
+
 ## v0.48.3 (2025-11-23)
 
 ### Fix

charts/nextcloud-mcp-server/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: nextcloud-mcp-server
 description: A Helm chart for Nextcloud MCP Server - enables AI assistants to interact with Nextcloud
 type: application
-version: 0.48.3
-appVersion: "0.48.3"
+version: 0.48.4
+appVersion: "0.48.4"
 keywords:
   - nextcloud
   - mcp

docker-compose.ci.yml

@@ -0,0 +1,25 @@
+# CI-specific overrides for RAG evaluation pipeline
+# This file is used by the rag-evaluation.yml workflow to configure the MCP
+# container with OpenAI/GitHub Models API for vector embeddings.
+#
+# Usage:
+#   docker compose -f docker-compose.yml -f docker-compose.ci.yml up
+#
+# Environment variables (set in CI workflow):
+#   OPENAI_API_KEY - API key for embeddings (GitHub Models uses GITHUB_TOKEN)
+#   OPENAI_BASE_URL - API endpoint (e.g., https://models.github.ai/inference)
+#   OPENAI_EMBEDDING_MODEL - Model name (e.g., openai/text-embedding-3-small)
+#   OPENAI_GENERATION_MODEL - Model name for generation (e.g., openai/gpt-4o-mini)
+
+services:
+  mcp:
+    environment:
+      # OpenAI provider configuration (required for CI vector sync)
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - OPENAI_BASE_URL=${OPENAI_BASE_URL:-https://models.github.ai/inference}
+      - OPENAI_EMBEDDING_MODEL=${OPENAI_EMBEDDING_MODEL:-openai/text-embedding-3-small}
+      - OPENAI_GENERATION_MODEL=${OPENAI_GENERATION_MODEL:-openai/gpt-4o-mini}
+      # Faster sync for CI
+      - VECTOR_SYNC_SCAN_INTERVAL=${VECTOR_SYNC_SCAN_INTERVAL:-5}
+      # Enable document processing for PDF parsing
+      - ENABLE_DOCUMENT_PROCESSING=true

docker-compose.yml

@@ -34,7 +34,7 @@ services:
       - ./app-hooks:/docker-entrypoint-hooks.d:ro
       # Mount OIDC development directory outside /var/www/html to avoid rsync conflicts
       # The post-installation hook will register /opt/apps as an additional app directory
-      - ./third_party:/opt/apps:ro
+      #- ./third_party:/opt/apps:ro
     environment:
       - NEXTCLOUD_TRUSTED_DOMAINS=app
       - NEXTCLOUD_ADMIN_USER=admin

nextcloud_mcp_server/providers/openai.py

@@ -7,13 +7,48 @@ Supports:
 """
 
 import logging
+from functools import wraps
 
-from openai import AsyncOpenAI
+import anyio
+from openai import AsyncOpenAI, RateLimitError
 
 from .base import Provider
 
 logger = logging.getLogger(__name__)
 
+# Rate limit retry configuration
+MAX_RETRIES = 5
+INITIAL_RETRY_DELAY = 2.0  # seconds
+MAX_RETRY_DELAY = 60.0  # seconds
+
+
+def retry_on_rate_limit(func):
+    """Decorator to retry on OpenAI rate limit errors 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 RateLimitError as e:
+                last_error = e
+                if attempt < MAX_RETRIES:
+                    logger.warning(
+                        f"Rate limit hit (attempt {attempt}/{MAX_RETRIES}), "
+                        f"retrying in {retry_delay:.1f}s..."
+                    )
+                    await anyio.sleep(retry_delay)
+                    retry_delay = min(retry_delay * 2, MAX_RETRY_DELAY)
+
+        logger.error(f"Rate limit exceeded after {MAX_RETRIES} attempts")
+        raise last_error  # type: ignore[misc]
+
+    return wrapper
+
+
 # Well-known embedding dimensions for OpenAI models
 OPENAI_EMBEDDING_DIMENSIONS: dict[str, int] = {
     "text-embedding-3-small": 1536,
@@ -86,6 +121,7 @@ class OpenAIProvider(Provider):
         """Whether this provider supports text generation."""
         return self.generation_model is not None
 
+    @retry_on_rate_limit
     async def embed(self, text: str) -> list[float]:
         """
         Generate embedding vector for text.
@@ -151,14 +187,8 @@ class OpenAIProvider(Provider):
         for i in range(0, len(texts), batch_size):
             batch = texts[i : i + batch_size]
 
-            response = await self.client.embeddings.create(
-                input=batch,
-                model=self.embedding_model,
-            )
-
-            # Sort by index to maintain order
-            sorted_data = sorted(response.data, key=lambda x: x.index)
-            batch_embeddings = [item.embedding for item in sorted_data]
+            # Use helper method with retry logic for each batch
+            batch_embeddings = await self._embed_batch_request(batch)
             all_embeddings.extend(batch_embeddings)
 
             # Update dimension if not set
@@ -171,6 +201,17 @@ class OpenAIProvider(Provider):
 
         return all_embeddings
 
+    @retry_on_rate_limit
+    async def _embed_batch_request(self, batch: list[str]) -> list[list[float]]:
+        """Make a single batch embedding request with retry logic."""
+        response = await self.client.embeddings.create(
+            input=batch,
+            model=self.embedding_model,
+        )
+        # Sort by index to maintain order
+        sorted_data = sorted(response.data, key=lambda x: x.index)
+        return [item.embedding for item in sorted_data]
+
     def get_dimension(self) -> int:
         """
         Get embedding dimension.
@@ -194,6 +235,7 @@ class OpenAIProvider(Provider):
             )
         return self._dimension
 
+    @retry_on_rate_limit
     async def generate(self, prompt: str, max_tokens: int = 500) -> str:
         """
         Generate text from a prompt.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nextcloud-mcp-server"
-version = "0.48.3"
+version = "0.48.4"
 description = "Model Context Protocol (MCP) server for Nextcloud integration - enables AI assistants to interact with Nextcloud data"
 authors = [
     {name = "Chris Coutinho", email = "chris@coutinho.io"}

uv.lock

@@ -1936,7 +1936,7 @@ wheels = [
 
 [[package]]
 name = "nextcloud-mcp-server"
-version = "0.48.3"
+version = "0.48.4"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },