Merge pull request #24 from lightbroker/model-support-expansion

fix test number file path; support smaller runs

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

@@ -1,25 +1,11 @@
-name: 'Test #4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct'
+name: '#4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct (1-20)'
 on:
   workflow_dispatch:
 
 jobs:
-  test-all-ranges:
-    strategy:
-      matrix:
-        include:
-          - offset: 0
-            range: "1-20"
-          - offset: 20
-            range: "21-40"
-          - offset: 40
-            range: "41-60"
-          - offset: 60
-            range: "61-80"
-          - offset: 80
-            range: "81-100"
-      fail-fast: false
+  test-prompts-1-20:
     uses: ./.github/workflows/test_04_malicious_prompts_rag_and_cot_microsoft_phi_3_mini4k_instruct.base.yml
     with:
-      batch_offset: ${{ matrix.offset }}
-      range_name: ${{ matrix.range }}
+      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 +1,11 @@
+name: '#4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct (21-40)'
+on:
+  workflow_dispatch:
+
+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 +1,11 @@
+name: '#4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct (41-60)'
+on:
+  workflow_dispatch:
+
+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 +1,11 @@
+name: '#4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct (61-80)'
+on:
+  workflow_dispatch:
+
+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 +1,11 @@
+name: '#4 | RAG + CoT | microsoft/Phi-3-mini-4k-instruct (81-100)'
+on:
+  workflow_dispatch:
+
+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

tests/integration/test_utils.py

@@ -33,7 +33,7 @@ def get_prompt_batch(prompts: List[str], batch_size=10, env_var='PROMPT_BATCH'):
     
     print(f"Running batch {batch_num} (range offset {offset}): prompts {start_idx+1}-{end_idx} ({len(prompt_subset)} prompts)")
     
-    return prompt_subset, start_idx, end_idx
+    return prompt_subset, (start_idx+1), end_idx
 
 
 def run_prompt_analysis_test(