fix: switch structured output to tool-call with reflection retry (#879)

* fix: switch structured output to tool-call with reflection retry

Replace the two-pass StructuredOutputWorkflow (TreeSummarize → acomplete)
with astructured_predict + reflection retry loop for structured LLM output.

- Enable function-calling mode (is_function_calling_model=True)
- Use astructured_predict with PromptTemplate for first attempt
- On ValidationError/parse failure, retry with reflection feedback
- Add min_length=10 to TopicResponse title/summary fields
- Remove dead StructuredOutputWorkflow class and its event types
- Rewrite tests to match new astructured_predict approach

* fix: include texts parameter in astructured_predict prompt

The switch to astructured_predict dropped the texts parameter entirely,
causing summary prompts (participants, subjects, action items) to be
sent without the transcript content. Combine texts with the prompt
before calling astructured_predict, mirroring what TreeSummarize did.

* fix: reduce TopicResponse min_length from 10 to 8 for title and summary

* ci: try fixing spawning job in github

* ci: fix for new arm64 builder

.github/workflows/test_server.yml

@@ -34,7 +34,7 @@ jobs:
           uv run -m pytest -v tests
 
   docker-amd64:
-    runs-on: linux-amd64
+    runs-on: [linux-amd64]
     concurrency:
       group: docker-amd64-${{ github.ref }}
       cancel-in-progress: true
@@ -52,12 +52,14 @@ jobs:
           github-token: ${{ secrets.GHA_CACHE_TOKEN }}
 
   docker-arm64:
-    runs-on: linux-arm64
+    runs-on: [linux-arm64]
     concurrency:
       group: docker-arm64-${{ github.ref }}
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v4
+      - name: Wait for Docker daemon
+        run: while ! docker version; do sleep 1; done
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
       - name: Build ARM64