feat: enhanced token probe with diagnostics - tests Azure and GitHub endpoints, logs token source

.github/workflows/llm-hello-world.yaml

@@ -155,20 +155,39 @@ jobs:
     steps:
       - name: Probe token limits
         env:
-          GITHUB_TOKEN: ${{ secrets.COPILOT_PAT || secrets.GITHUB_TOKEN }}
+          AUTH_TOKEN: ${{ secrets.COPILOT_PAT }}
+          FALLBACK_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          # Try Azure endpoint (Gemini's suggestion) - deprecated Oct 2025 but may have different limits
+          LLM_ENDPOINT_AZURE: "https://models.inference.ai.azure.com/chat/completions"
+          LLM_ENDPOINT_GITHUB: "https://models.github.ai/inference/chat/completions"
         run: |
           echo "=== Token Limit Probe ==="
-          echo "Testing progressively larger payloads to find the ceiling"
+
+          # Diagnostic: which token are we using?
+          if [ -n "$AUTH_TOKEN" ]; then
+            echo "Using: COPILOT_PAT (length: ${#AUTH_TOKEN} chars)"
+            TOKEN="$AUTH_TOKEN"
+          else
+            echo "Using: GITHUB_TOKEN (fallback)"
+            TOKEN="$FALLBACK_TOKEN"
+          fi
+
+          # Test both endpoints
+          for ENDPOINT_NAME in "AZURE" "GITHUB"; do
+            if [ "$ENDPOINT_NAME" = "AZURE" ]; then
+              ENDPOINT="$LLM_ENDPOINT_AZURE"
+            else
+              ENDPOINT="$LLM_ENDPOINT_GITHUB"
+            fi
+
+            echo ""
+            echo "=== Testing $ENDPOINT_NAME endpoint ==="
+            echo "URL: $ENDPOINT"
+            echo "Model: gpt-4o"
             echo ""
 
             # Test sizes in characters (roughly 4 chars per token)
-          SIZES=(2000 4000 8000 16000 32000 64000)
+            SIZES=(2000 4000 8000 16000 32000 64000 128000)
-
-          # Generate filler text (lorem ipsum style)
-          generate_filler() {
-            local size=$1
-            python3 -c "print(('The quick brown fox jumps over the lazy dog. ' * ($size // 45 + 1))[:$size])"
-          }
 
             echo "| Size (chars) | ~Tokens | HTTP Status | Result |"
             echo "|--------------|---------|-------------|--------|"
@@ -176,18 +195,17 @@ jobs:
             for SIZE in "${SIZES[@]}"; do
               APPROX_TOKENS=$((SIZE / 4))
 
-            # Generate payload of specified size
+              # Generate filler
-            FILLER=$(generate_filler $SIZE)
+              FILLER=$(python3 -c "print(('The quick brown fox jumps over the lazy dog. ' * ($SIZE // 45 + 1))[:$SIZE])")
 
               PROMPT="Respond with exactly one word: 'received'. Here is padding text to test token limits: $FILLER"
               PROMPT_ESCAPED=$(echo "$PROMPT" | jq -Rs .)
 
-            # Call the LLM
+              RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$ENDPOINT" \
-            RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$LLM_ENDPOINT" \
+                -H "Authorization: Bearer $TOKEN" \
-              -H "Authorization: Bearer $GITHUB_TOKEN" \
                 -H "Content-Type: application/json" \
                 -d "{
-                \"model\": \"$LLM_MODEL\",
+                  \"model\": \"gpt-4o\",
                   \"messages\": [
                     {\"role\": \"user\", \"content\": $PROMPT_ESCAPED}
                   ],
@@ -200,32 +218,25 @@ jobs:
               if [ "$HTTP_CODE" = "200" ]; then
                 RESULT="OK"
               else
-              # Extract error message if present
                 ERROR_MSG=$(echo "$BODY" | jq -r '.error.message // .message // "Unknown error"' 2>/dev/null | head -c 50)
                 RESULT="FAIL: $ERROR_MSG"
-
-              # Log full error for debugging
                 echo ""
-              echo "::warning::Failed at ${SIZE} chars (~${APPROX_TOKENS} tokens)"
+                echo "::warning::Failed at ${SIZE} chars (~${APPROX_TOKENS} tokens) on $ENDPOINT_NAME"
-              echo "Full error response:"
+                echo "Full error: $BODY"
-              echo "$BODY" | jq . 2>/dev/null || echo "$BODY"
                 echo ""
               fi
 
               echo "| $SIZE | ~$APPROX_TOKENS | $HTTP_CODE | $RESULT |"
 
-            # Stop probing after first failure to avoid hammering the API
               if [ "$HTTP_CODE" != "200" ]; then
                 echo ""
-              echo "=== Ceiling Found ==="
+                echo "=== $ENDPOINT_NAME Ceiling: ~$((SIZE / 8)) tokens ==="
-              echo "Last successful size: $((SIZE / 2)) chars (~$((SIZE / 8)) tokens)"
-              echo "First failure at: $SIZE chars (~$APPROX_TOKENS tokens)"
                 break
               fi
 
-            # Small delay to avoid rate limiting
               sleep 1
             done
+          done
 
           echo ""
           echo "=== Probe Complete ==="