Merge pull request 'ci: harden the qdrant integration job (5s client timeout + cold storage)' (#60) from ci/harden-qdrant-integration into main

Reviewed-on: #60

.gitea/workflows/docker-build.yaml

@@ -32,15 +32,32 @@ jobs:
           docker rm -f qdrant-${{ github.run_id }} 2>/dev/null || true
           docker run -d --name qdrant-${{ github.run_id }} \
             --network "container:$(hostname)" \
-            docker.io/qdrant/qdrant:latest
+            docker.io/qdrant/qdrant:v1.19
 
       - name: Wait for Qdrant
         run: |
-          for i in $(seq 1 30); do
+          # /healthz answers before the storage engine accepts writes, and a cold
-            curl -s http://localhost:6333/healthz && echo "QDRANT ready" && break
+          # container on a loaded host can take several seconds to create its
-            echo "Waiting for Qdrant... ($i/30)"
+          # first collection. Gate on a real write round-trip, not on /healthz.
+          ready=""
+          for i in $(seq 1 60); do
+            if curl -sf "http://localhost:6333/healthz" > /dev/null 2>&1 \
+              && curl -sf -X PUT "http://localhost:6333/collections/ci_readiness_probe?timeout=60" \
+                   -H 'Content-Type: application/json' \
+                   -d '{"vectors":{"size":4,"distance":"Cosine"}}' > /dev/null 2>&1; then
+              curl -sf -X DELETE "http://localhost:6333/collections/ci_readiness_probe" > /dev/null 2>&1 || true
+              ready="yes"
+              echo "QDRANT ready: write path OK (attempt $i)"
+              break
+            fi
+            echo "Waiting for Qdrant... ($i/60)"
             sleep 1
           done
+          if [ -z "$ready" ]; then
+            echo "Qdrant write path never became ready"
+            docker logs --tail 100 qdrant-${{ github.run_id }} || true
+            exit 1
+          fi
 
       - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
         with:
@@ -53,6 +70,15 @@ jobs:
         env:
           QDRANT_URL: http://localhost:6333
           COLLECTION_NAME: test_mcp_maildir
+          # The qdrant client defaults to a 5s request timeout, which a cold
+          # collection on a shared runner can exceed; this job has no SLA.
+          QDRANT_TIMEOUT: "60"
+
+      - name: Qdrant diagnostics
+        if: failure()
+        run: |
+          docker ps -a || true
+          docker logs --tail 200 qdrant-${{ github.run_id }} || true
 
       - name: Cleanup Qdrant
         if: always()

.gitea/workflows/main.yaml

@@ -45,17 +45,32 @@ jobs:
         run: |
           docker run -d --name qdrant-${{ github.run_id }} \
             --network "container:$(hostname)" \
-            docker.io/qdrant/qdrant:latest
+            docker.io/qdrant/qdrant:v1.19
 
       - name: Wait for Qdrant
         run: |
-          for i in $(seq 1 30); do
+          # /healthz answers before the storage engine accepts writes, and a cold
-            curl -s http://localhost:6333/healthz \
+          # container on a loaded host can take several seconds to create its
-              && echo "QDRANT ready" && break
+          # first collection. Gate on a real write round-trip, not on /healthz.
-            echo "Waiting for Qdrant... ($i/30)"
+          ready=""
+          for i in $(seq 1 60); do
+            if curl -sf "http://localhost:6333/healthz" > /dev/null 2>&1 \
+              && curl -sf -X PUT "http://localhost:6333/collections/ci_readiness_probe?timeout=60" \
+                   -H 'Content-Type: application/json' \
+                   -d '{"vectors":{"size":4,"distance":"Cosine"}}' > /dev/null 2>&1; then
+              curl -sf -X DELETE "http://localhost:6333/collections/ci_readiness_probe" > /dev/null 2>&1 || true
+              ready="yes"
+              echo "QDRANT ready: write path OK (attempt $i)"
+              break
+            fi
+            echo "Waiting for Qdrant... ($i/60)"
             sleep 1
           done
-          curl -s http://localhost:6333/healthz > /dev/null
+          if [ -z "$ready" ]; then
+            echo "Qdrant write path never became ready"
+            docker logs --tail 100 qdrant-${{ github.run_id }} || true
+            exit 1
+          fi
 
       - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7
         with:
@@ -67,6 +82,15 @@ jobs:
         env:
           QDRANT_URL: http://localhost:6333
           COLLECTION_NAME: test_mcp_maildir
+          # The qdrant client defaults to a 5s request timeout, which a cold
+          # collection on a shared runner can exceed; this job has no SLA.
+          QDRANT_TIMEOUT: "60"
+
+      - name: Qdrant diagnostics
+        if: failure()
+        run: |
+          docker ps -a || true
+          docker logs --tail 200 qdrant-${{ github.run_id }} || true
 
       - name: Cleanup Qdrant
         if: always()

docker-compose.yml

@@ -1,6 +1,6 @@
 services:
   qdrant:
-    image: docker.io/qdrant/qdrant:latest
+    image: docker.io/qdrant/qdrant:v1.19
     container_name: mcp_maildir_qdrant
     ports:
       - "127.0.0.1:6333:6333" # REST API

renovate.json

@@ -3,9 +3,12 @@
   "customManagers": [
     {
       "customType": "regex",
-      "description": "Track qdrant/qdrant Docker image from docker-compose.yml (native manager missed it)",
+      "description": "Track the pinned qdrant/qdrant image in docker-compose.yml and the CI workflows (native manager missed it)",
-      "managerFilePatterns": ["/^docker-compose\\.ya?ml$/"],
+      "managerFilePatterns": [
-      "matchStrings": ["image:\\s*(?:docker\\.io/)?qdrant/qdrant:(?<currentValue>[^\\s]+)"],
+        "/^docker-compose\\.ya?ml$/",
+        "/^\\.gitea/workflows/.*\\.ya?ml$/"
+      ],
+      "matchStrings": ["(?:docker\\.io/)?qdrant/qdrant:(?<currentValue>[^\\s\"']+)"],
       "depNameTemplate": "qdrant/qdrant",
       "datasourceTemplate": "docker"
     }

src/server.py

@@ -37,6 +37,10 @@ COLLECTION_NAME = os.environ.get("COLLECTION_NAME", "")
 EMBEDDING_MODEL_NAME = os.environ.get("EMBEDDING_MODEL_NAME", "BAAI/bge-small-en-v1.5")
 DEFAULT_LIMIT = int(os.environ.get("SEARCH_LIMIT", "50"))
 
+# Per-request timeout (seconds) for Qdrant. The client default is 5s, which is
+# tight for a cold collection or a busy host: unset means keep that default.
+QDRANT_TIMEOUT = int(os.environ["QDRANT_TIMEOUT"]) if os.environ.get("QDRANT_TIMEOUT") else None
+
 if not QDRANT_URL:
     raise ValueError("QDRANT_URL environment variable is required.")
 if not COLLECTION_NAME:
@@ -61,8 +65,8 @@ def get_qdrant_client() -> QdrantClient:
     """Returns a singleton Qdrant client."""
     global _qdrant_client
     if _qdrant_client is None:
-        logger.info(f"Connecting to Qdrant at {QDRANT_URL}")
+        logger.info(f"Connecting to Qdrant at {QDRANT_URL} (timeout={QDRANT_TIMEOUT})")
-        _qdrant_client = QdrantClient(url=QDRANT_URL)
+        _qdrant_client = QdrantClient(url=QDRANT_URL, timeout=QDRANT_TIMEOUT)
     return _qdrant_client