improve runtest, optimize CI batching (#210)

agents/codex.ts

@@ -246,6 +246,11 @@ const messageHandlers: {
     } else if (item.type === "mcp_tool_call") {
       if (item.status === "failed" && item.error) {
         log.warning(`MCP tool call failed: ${item.error.message}`);
+      } else if ((item as any).output) {
+        // log successful MCP tool call output so it appears in captured output
+        const output = (item as any).output;
+        const outputStr = typeof output === "string" ? output : JSON.stringify(output);
+        log.debug(`tool output: ${outputStr}`);
       }
     } else if (item.type === "reasoning") {
       // Display reasoning in a human-readable format

agents/cursor.ts

@@ -199,9 +199,12 @@ export const cursor = agent({
             log.warning("Tool call failed");
           } else {
             // log successful tool result so it appears in output
-            const text = result?.content?.[0]?.text?.text;
+            // handle both formats: { text: string } or { text: { text: string } }
+            const contentItem = result?.content?.[0];
+            const textValue = contentItem?.text;
+            const text = typeof textValue === "string" ? textValue : textValue?.text;
             if (text) {
-              console.log(text);
+              log.debug(`tool output: ${text}`);
             }
           }
         }

agents/gemini.ts

@@ -126,6 +126,11 @@ const messageHandlers = {
       const errorMsg =
         typeof event.output === "string" ? event.output : JSON.stringify(event.output);
       log.warning(`Tool call failed: ${errorMsg}`);
+    } else if (event.output) {
+      // log successful tool result so it appears in output
+      const outputStr =
+        typeof event.output === "string" ? event.output : JSON.stringify(event.output);
+      log.debug(`tool output: ${outputStr}`);
     }
   },
   result: async (event: GeminiResultEvent) => {

agents/opencode.ts

@@ -498,6 +498,10 @@ const messageHandlers = {
     if (status === "error") {
       const errorMsg = typeof output === "string" ? output : JSON.stringify(output);
       log.error(`» ❌ tool call failed: ${errorMsg}`);
+    } else if (output) {
+      // log successful tool result so it appears in captured output
+      const outputStr = typeof output === "string" ? output : JSON.stringify(output);
+      log.debug(`tool output: ${outputStr}`);
     }
   },
   result: async (event: OpenCodeResultEvent) => {