diff --git a/.github/actions/run-and-record-tests/action.yml b/.github/actions/run-and-record-tests/action.yml
index ac3edba78..c85b36e08 100644
--- a/.github/actions/run-and-record-tests/action.yml
+++ b/.github/actions/run-and-record-tests/action.yml
@@ -24,21 +24,103 @@ runs:
   steps:
     - name: Check Storage and Memory Available Before Tests
       if: ${{ always() }}
+      shell: bash
       run: |
         free -h
         df -h
 
+    - name: Run Llama Stack Server
+      if: ${{ contains(inputs.stack-config, 'server:') }}
+      shell: bash
+      run: |
+        # Run this so pytest in a loop doesn't start-stop servers in a loop
+        echo "Starting Llama Stack Server"
+        nohup uv run llama stack run ci-tests --image-type venv > server.log 2>&1 &
+
+        echo "Waiting for Llama Stack Server to start"
+        for i in {1..30}; do
+          if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
+            echo "Llama Stack Server started"
+            exit 0
+          fi
+          sleep 1
+        done
+
+        echo "Llama Stack Server failed to start"
+        cat server.log
+        exit 1
+
     - name: Run Integration Tests
-      uses: ./.github/actions/run-integration-tests
-      with:
-        test-types: ${{ inputs.test-types }}
-        stack-config: ${{ inputs.stack-config }}
-        provider: ${{ inputs.provider }}
-        inference-mode: ${{ inputs.inference-mode }}
-        run-vision-tests: ${{ inputs.run-vision-tests }}
+      env:
+        LLAMA_STACK_CLIENT_TIMEOUT: "300"
+      shell: bash
+      run: |
+        stack_config="${{ inputs.stack-config }}"
+        EXCLUDE_TESTS="builtin_tool or safety_with_image or code_interpreter or test_rag"
+
+        export LLAMA_STACK_TEST_INFERENCE_MODE="${{ inputs.inference-mode }}"
+
+        # Configure provider-specific settings
+        if [ "${{ inputs.provider }}" == "ollama" ]; then
+          export OLLAMA_URL="http://0.0.0.0:11434"
+          export TEXT_MODEL="ollama/llama3.2:3b-instruct-fp16"
+          export SAFETY_MODEL="ollama/llama-guard3:1b"
+          EXTRA_PARAMS="--safety-shield=llama-guard"
+        else
+          export VLLM_URL="http://localhost:8000/v1"
+          export TEXT_MODEL="vllm/meta-llama/Llama-3.2-1B-Instruct"
+          EXTRA_PARAMS=""
+          EXCLUDE_TESTS="${EXCLUDE_TESTS} or test_inference_store_tool_calls"
+        fi
+
+        if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
+          export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings/vision"
+          if uv run pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=${stack_config} \
+            -k "not( ${EXCLUDE_TESTS} )" \
+            --vision-model=ollama/llama3.2-vision:11b \
+            --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \
+            --color=yes ${EXTRA_PARAMS} \
+            --capture=tee-sys | tee pytest-${{ inputs.inference-mode }}-vision.log; then
+            echo "✅ Tests completed for vision"
+          else
+            echo "❌ Tests failed for vision"
+            exit 1
+          fi
+
+          exit 0
+        fi
+
+        # Run non-vision tests
+        export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings"
+        TEST_TYPES='${{ inputs.test-types }}'
+        echo "Test types to run: $TEST_TYPES"
+
+        for test_type in $(echo "$TEST_TYPES" | jq -r '.[]'); do
+          # if provider is vllm, exclude the following tests: (safety, post_training, tool_runtime)
+          if [ "${{ inputs.provider }}" == "vllm" ]; then
+            if [ "$test_type" == "safety" ] || [ "$test_type" == "post_training" ] || [ "$test_type" == "tool_runtime" ]; then
+              continue
+            fi
+          fi
+
+          echo "=== Running tests for: $test_type ==="
+
+          if uv run pytest -s -v tests/integration/$test_type --stack-config=${stack_config} \
+            -k "not( ${EXCLUDE_TESTS} )" \
+            --text-model=$TEXT_MODEL \
+            --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \
+            --color=yes ${EXTRA_PARAMS} \
+            --capture=tee-sys | tee pytest-${{ inputs.inference-mode }}-$test_type.log; then
+            echo "✅ Tests completed for $test_type"
+          else
+            echo "❌ Tests failed for $test_type"
+            exit 1
+          fi
+        done
 
     - name: Check Storage and Memory Available After Tests
       if: ${{ always() }}
+      shell: bash
       run: |
         free -h
         df -h
@@ -47,11 +129,18 @@ runs:
       if: ${{ inputs.inference-mode == 'record' }}
       shell: bash
       run: |
+        echo "Checking for recording changes"
         git status --porcelain tests/integration/recordings/
+
         if [[ -n $(git status --porcelain tests/integration/recordings/) ]]; then
           echo "New recordings detected, committing and pushing"
           git add tests/integration/recordings/
-          git commit -m "Recordings update from CI"
+
+          if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
+            git commit -m "Recordings update from CI (vision)"
+          else
+            git commit -m "Recordings update from CI"
+          fi
 
           git fetch origin ${{ github.event.pull_request.head.ref }}
           git rebase origin/${{ github.event.pull_request.head.ref }}
diff --git a/.github/actions/run-integration-tests/action.yml b/.github/actions/run-integration-tests/action.yml
deleted file mode 100644
index 7d93d2a61..000000000
--- a/.github/actions/run-integration-tests/action.yml
+++ /dev/null
@@ -1,116 +0,0 @@
-name: 'Run Integration Tests'
-description: 'Run integration tests with configurable execution mode and provider settings'
-
-inputs:
-  test-types:
-    description: 'Test types to run (JSON array)'
-    required: true
-  stack-config:
-    description: 'Stack configuration: "ci-tests" or "server:ci-tests"'
-    required: true
-  provider:
-    description: 'Provider to use: "ollama" or "vllm"'
-    required: true
-  inference-mode:
-    description: 'Inference mode: "record" or "replay"'
-    required: true
-  run-vision-tests:
-    description: 'Run vision tests: "true" or "false"'
-    required: false
-    default: 'false'
-
-outputs:
-  logs-path:
-    description: 'Path to generated log files'
-    value: '*.log'
-
-runs:
-  using: 'composite'
-  steps:
-    - name: Run Llama Stack Server
-      if: ${{ contains(inputs.stack-config, 'server:') }}
-      run: |
-        # Run this so pytest in a loop doesn't start-stop servers in a loop
-        echo "Starting Llama Stack Server"
-        nohup uv run llama stack run ci-tests --image-type venv > server.log 2>&1 &
-
-        echo "Waiting for Llama Stack Server to start"
-        for i in {1..30}; do
-          if curl -s http://localhost:8321/v1/health | grep -q "OK"; then
-            echo "Llama Stack Server started"
-            exit 0
-          fi
-          sleep 1
-        done
-
-        echo "Llama Stack Server failed to start"
-        cat server.log
-        exit 1
-
-    - name: Run Integration Tests
-      env:
-        LLAMA_STACK_CLIENT_TIMEOUT: "300"
-      shell: bash
-      run: |
-        stack_config="${{ inputs.stack-config }}"
-        EXCLUDE_TESTS="builtin_tool or safety_with_image or code_interpreter or test_rag"
-
-        export LLAMA_STACK_TEST_INFERENCE_MODE="${{ inputs.inference-mode }}"
-
-        # Configure provider-specific settings
-        if [ "${{ inputs.provider }}" == "ollama" ]; then
-          export OLLAMA_URL="http://0.0.0.0:11434"
-          export TEXT_MODEL="ollama/llama3.2:3b-instruct-fp16"
-          export SAFETY_MODEL="ollama/llama-guard3:1b"
-          EXTRA_PARAMS="--safety-shield=llama-guard"
-        else
-          export VLLM_URL="http://localhost:8000/v1"
-          export TEXT_MODEL="vllm/meta-llama/Llama-3.2-1B-Instruct"
-          EXTRA_PARAMS=""
-          EXCLUDE_TESTS="${EXCLUDE_TESTS} or test_inference_store_tool_calls"
-        fi
-
-        if [ "${{ inputs.run-vision-tests }}" == "true" ]; then
-          export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings/vision"
-          if uv run pytest -s -v tests/integration/inference/test_vision_inference.py --stack-config=${stack_config} \
-            -k "not( ${EXCLUDE_TESTS} )" \
-            --vision-model=ollama/llama3.2-vision:11b \
-            --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \
-            --color=yes ${EXTRA_PARAMS} \
-            --capture=tee-sys | tee pytest-${{ inputs.inference-mode }}-vision.log; then
-            echo "✅ Tests completed for vision"
-          else
-            echo "❌ Tests failed for vision"
-            exit 1
-          fi
-
-          exit 0
-        fi
-
-        # Run non-vision tests
-        export LLAMA_STACK_TEST_RECORDING_DIR="tests/integration/recordings"
-        TEST_TYPES='${{ inputs.test-types }}'
-        echo "Test types to run: $TEST_TYPES"
-
-        for test_type in $(echo "$TEST_TYPES" | jq -r '.[]'); do
-          # if provider is vllm, exclude the following tests: (safety, post_training, tool_runtime)
-          if [ "${{ inputs.provider }}" == "vllm" ]; then
-            if [ "$test_type" == "safety" ] || [ "$test_type" == "post_training" ] || [ "$test_type" == "tool_runtime" ]; then
-              continue
-            fi
-          fi
-
-          echo "=== Running tests for: $test_type ==="
-
-          if uv run pytest -s -v tests/integration/$test_type --stack-config=${stack_config} \
-            -k "not( ${EXCLUDE_TESTS} )" \
-            --text-model=$TEXT_MODEL \
-            --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \
-            --color=yes ${EXTRA_PARAMS} \
-            --capture=tee-sys | tee pytest-${{ inputs.inference-mode }}-$test_type.log; then
-            echo "✅ Tests completed for $test_type"
-          else
-            echo "❌ Tests failed for $test_type"
-            exit 1
-          fi
-        done
diff --git a/.github/workflows/integration-tests.yml b/.github/workflows/integration-tests.yml
index cf8a09b5f..b893ce2ca 100644
--- a/.github/workflows/integration-tests.yml
+++ b/.github/workflows/integration-tests.yml
@@ -17,7 +17,6 @@ on:
       - '.github/actions/setup-ollama/action.yml'
       - '.github/actions/setup-test-environment/action.yml'
       - '.github/actions/run-and-record-tests/action.yml'
-      - '.github/actions/run-integration-tests/action.yml'
   schedule:
     # If changing the cron schedule, update the provider in the test-matrix job
     - cron: '0 0 * * *'  # (test latest client) Daily at 12 AM UTC
diff --git a/.github/workflows/integration-vision-tests.yml b/.github/workflows/integration-vision-tests.yml
index c87b25e9f..1c07d034c 100644
--- a/.github/workflows/integration-vision-tests.yml
+++ b/.github/workflows/integration-vision-tests.yml
@@ -17,7 +17,6 @@ on:
       - '.github/actions/setup-ollama/action.yml'
       - '.github/actions/setup-test-environment/action.yml'
       - '.github/actions/run-and-record-tests/action.yml'
-      - '.github/actions/run-integration-tests/action.yml'
   workflow_dispatch:
     inputs:
       test-all-client-versions: