Add LogCollector for precise test log boundaries

Problem: Tests used `docker compose logs --since=5m` which caused:
- Log overlap between tests
- Logs from previous tests included
- Missing logs if test exceeded 5 minutes

Solution:
- New LogCollector class runs `docker compose logs --follow`
- Marks test start/end boundaries
- Writes test-specific logs to /tmp/test-{testId}-logs.txt
- Test steps access via TEST_ID environment variable

Changes:
- tests/src/log-collector.ts: New LogCollector class
- tests/src/executor.ts: Integrate LogCollector, set TEST_ID env
- tests/src/cli.ts: Start/stop LogCollector for runtime/inference
- All test cases: Use log collector with fallback to docker compose

Also updated docs/CICD.md with:
- Test runner CLI documentation
- Judge modes (simple, llm, dual)
- Log collector integration
- Updated test case list (12b, 27b models)
- Model unload strategy
- Troubleshooting guide

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

tests/testcases/runtime/TC-RUNTIME-001.yml

@@ -22,12 +22,21 @@ steps:
 
   - name: Capture startup logs
     command: |
-      cd docker && docker compose logs 2>&1 | head -100
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        head -100 /tmp/test-${TEST_ID}-logs.txt
+      else
+        cd docker && docker compose logs 2>&1 | head -100
+      fi
 
   - name: Check for startup errors in logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       # Check for critical errors
       if echo "$LOGS" | grep -qE "(level=ERROR|CUBLAS_STATUS_|CUDA error|cudaMalloc failed)"; then

tests/testcases/runtime/TC-RUNTIME-002.yml

@@ -30,8 +30,12 @@ steps:
 
   - name: Verify GPU detection in Ollama logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== GPU Detection Check ==="
 
@@ -60,8 +64,12 @@ steps:
 
   - name: Check for GPU-related errors in logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== GPU Error Check ==="
 
@@ -82,8 +90,12 @@ steps:
 
   - name: Display GPU memory status from logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== GPU Memory Status ==="
       echo "$LOGS" | grep -E "gpu memory.*library=CUDA" | tail -4

tests/testcases/runtime/TC-RUNTIME-003.yml

@@ -30,8 +30,12 @@ steps:
 
   - name: Verify server listening in logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== Server Status Check ==="
 
@@ -46,8 +50,12 @@ steps:
 
   - name: Check for runtime errors in logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== Runtime Error Check ==="
 
@@ -71,8 +79,12 @@ steps:
 
   - name: Verify API request handling in logs
     command: |
-      cd docker
-      LOGS=$(docker compose logs 2>&1)
+      # Use log collector file if available, fallback to docker compose logs
+      if [ -f "/tmp/test-${TEST_ID}-logs.txt" ]; then
+        LOGS=$(cat /tmp/test-${TEST_ID}-logs.txt)
+      else
+        LOGS=$(cd docker && docker compose logs 2>&1)
+      fi
 
       echo "=== API Request Logs ==="