support batch tests

.github/workflows/test_04.abstract_base.yml

@@ -0,0 +1,83 @@
+name: 'Reusable Test Runner | RAG + CoT | Generic'
+on:
+  workflow_call:
+    inputs:
+      batch_offset:
+        description: 'Starting prompt index offset'
+        required: true
+        type: number
+      range_name:
+        description: 'Human readable range name (e.g., "1-20")'
+        required: true
+        type: string
+      test_file_path:
+        description: 'Path to the test file to run'
+        required: true
+        type: string
+      model_display_name:
+        description: 'Human readable model name for workflow title'
+        required: true
+        type: string
+      batch_size:
+        description: 'Number of prompts per batch'
+        required: false
+        type: number
+        default: 2
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 55 # Set max runtime for each job
+    continue-on-error: true
+    strategy:
+      # Always 10 batches per workflow
+      matrix:
+        batch: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+      fail-fast: false
+    steps:
+      - name: 'checkout'
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+      
+      - name: 'set up Python'
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.12'
+      
+      - name: 'set up Python dependencies'
+        shell: bash
+        run: |
+          pip install -r ${{ github.workspace }}/requirements.txt
+          
+      - name: 'set up Microsoft Phi-3 Mini 4k LLM from HuggingFace'
+        shell: bash
+        run: |
+          pip install huggingface-hub[cli]
+          huggingface-cli download microsoft/Phi-3-mini-4k-instruct-onnx --include cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/* --local-dir ${{ github.workspace }}/infrastructure/foundation_model
+      
+      - name: 'run text generation tests - ${{ inputs.model_display_name }} - range ${{ inputs.range_name }} batch ${{ matrix.batch }}'
+        shell: bash
+        env:
+          PROMPT_BATCH: ${{ matrix.batch }}
+          BATCH_SIZE: ${{ inputs.batch_size }}
+          BATCH_OFFSET: ${{ inputs.batch_offset }}
+        run: pytest ${{ inputs.test_file_path }} -s --disable-warnings
+      
+      - name: Check for changes
+        id: verify-changed-files
+        run: |
+          if [ -n "$(git status --porcelain)" ]; then
+            echo "changed=true" >> $GITHUB_OUTPUT
+          else
+            echo "changed=false" >> $GITHUB_OUTPUT
+          fi
+      
+      - name: Commit and push changes
+        if: steps.verify-changed-files.outputs.changed == 'true'
+        run: |
+          git config --local user.email "42450907+lightbroker@users.noreply.github.com"
+          git config --local user.name "Adam Wilson"
+          git add .
+          git add .
+          git commit -m "Auto-generated files from microsoft/Phi-3-mini-4k-instruct range 1-20 batch 4 [skip ci]"
+          git checkout -b auto-generated-$(date +%Y%m%d-%H%M%S)
+          git push origin HEAD

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.01-20.yml

@@ -0,0 +1,14 @@
+name: '#4 (1-20) | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_dispatch:
+  schedule:
+    # Workflow 1 - Starts at hours: 0, 5, 10, 15, 20 (every 5th hour starting from midnight)
+    - cron: '0 */5 * * *'
+
+jobs:
+  test-prompts-1-20:
+    uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
+    with:
+      batch_offset: 0
+      range_name: "1-20"
+      batch_size: 2

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.21-40.yml

@@ -0,0 +1,14 @@
+name: '#4 (21-40) | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_dispatch:
+  schedule:
+    # Workflow 2 - Starts at hours: 1, 6, 11, 16, 21 (every 5th hour starting from 1 AM)
+    - cron: '0 1-23/5 * * *'
+
+jobs:
+  test-prompts-21-40:
+    uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
+    with:
+      batch_offset: 20
+      range_name: "21-40"
+      batch_size: 2

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.41-60.yml

@@ -0,0 +1,14 @@
+name: '#4 (41-60) | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_dispatch:
+  schedule:
+    # Workflow 3 - Starts at hours: 2, 7, 12, 17, 22 (every 5th hour starting from 2 AM)
+    - cron: '0 2-23/5 * * *'
+
+jobs:
+  test-prompts-41-60:
+    uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
+    with:
+      batch_offset: 40
+      range_name: "41-60"
+      batch_size: 2

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.61-80.yml

@@ -0,0 +1,14 @@
+name: '#4 (61-80) | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_dispatch:
+  schedule:
+    # Workflow 4 - Starts at hours: 3, 8, 13, 18, 23 (every 5th hour starting from 3 AM)
+    - cron: '0 3-23/5 * * *'
+
+jobs:
+  test-prompts-61-80:
+    uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
+    with:
+      batch_offset: 60
+      range_name: "61-80"
+      batch_size: 2

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.81-100.yml

@@ -0,0 +1,14 @@
+name: '#4 (81-100) | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_dispatch:
+  schedule:
+    # Workflow 5 - Starts at hours: 4, 9, 14, 19 (every 5th hour starting from 4 AM)
+    - cron: '0 4-19/5 * * *'
+
+jobs:
+  test-prompts-81-100:
+    uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
+    with:
+      batch_offset: 80
+      range_name: "81-100"
+      batch_size: 2

.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml

@@ -0,0 +1,27 @@
+name: 'Reusable Test #4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+on:
+  workflow_call:
+    inputs:
+      batch_offset:
+        description: 'Starting prompt index offset'
+        required: true
+        type: number
+      range_name:
+        description: 'Human readable range name (e.g., "1-20")'
+        required: true
+        type: string
+      batch_size:
+        description: 'Number of prompts per batch'
+        required: false
+        type: number
+        default: 2
+
+jobs:
+  test:
+    uses: ./.github/workflows/test_04.abstract_base.yml
+    with:
+      batch_offset: ${{ inputs.batch_offset }}
+      range_name: ${{ inputs.range_name }}
+      batch_size: ${{ inputs.batch_size }}
+      test_file_path: tests/integration/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.py
+      model_display_name: microsoft/Phi-3-mini-4k-instruct