feat: remove restart required for auth config

.github/workflows/openapi-bundle.yml

@@ -0,0 +1,55 @@
+name: OpenAPI Bundle
+
+on:
+  push:
+    branches: ["main"]
+    paths:
+      - "docs/openapi/**"
+      - "!docs/openapi/openapi.json"
+  pull_request:
+    paths:
+      - "docs/openapi/**"
+      - "!docs/openapi/openapi.json"
+
+permissions:
+  contents: write
+
+jobs:
+  bundle-openapi:
+    name: Bundle OpenAPI Spec
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: pip install pyyaml
+
+      - name: Bundle OpenAPI spec
+        working-directory: ./docs/openapi
+        run: python bundle.py
+
+      - name: Check for changes
+        id: changes
+        run: |
+          if git diff --quiet docs/openapi/openapi.json; then
+            echo "changed=false" >> $GITHUB_OUTPUT
+          else
+            echo "changed=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push changes
+        if: steps.changes.outputs.changed == 'true' && github.event_name == 'push'
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add docs/openapi/openapi.json
+          git commit -m "chore: regenerate openapi.json --skip-pipeline"
+          git push

docs/features/mcp/agent-mode.mdx

@@ -13,6 +13,10 @@ This feature is only available on `v1.4.0-prerelease1` and above. Please check t
 
 **Agent Mode** enables Bifrost to automatically execute tool calls without requiring explicit execution API calls for each tool. This transforms Bifrost from a simple gateway into an autonomous agent runtime.
 
+<Warning>
+**Streaming Not Supported**: Agent Mode is not compatible with streaming operations (`chat_stream` and `responses_stream`). Due to architectural limitations, the autonomous tool execution loop requires complete responses before proceeding to the next iteration (we cannot store all streaming chunks in memory just "in case" we get any tool calls, this would be a big anti-pattern). Use non-streaming endpoints (`chat` and `responses`) when Agent Mode is enabled.
+</Warning>
+
 When Agent Mode is enabled:
 1. LLM returns tool calls in its response
 2. Bifrost automatically executes **auto-executable** tools