AI sub-agent tool not being displayed properly

src-node/claude-code-agent.js

@@ -824,7 +824,7 @@ async function _runQuery(requestId, prompt, projectPath, model, signal, locale,
         },
         allowedTools: [
             "Read", "Edit", "Write", "Glob", "Grep", "Bash",
-            "AskUserQuestion", "Task",
+            "AskUserQuestion", "Task", "Agent",
             "TodoRead", "TodoWrite",
             "TaskCreate", "TaskUpdate", "TaskList", "TaskGet",
             "WebFetch", "WebSearch",
@@ -1612,6 +1612,49 @@ async function _runQuery(requestId, prompt, projectPath, model, signal, locale,
                 _log("Session:", currentSessionId);
             }
 
+            // Subagent tool extraction. The SDK delivers the parent
+            // agent's tool calls as a stream of stream_event messages
+            // (content_block_start / content_block_delta / content_block_
+            // stop), but the new Agent dispatcher's *subagent* tool calls
+            // arrive batched on a single assistant message with
+            // parent_tool_use_id set — there is no streaming path. We have
+            // to fish them out here, otherwise the UI sees the parent
+            // Agent card finish and then nothing until the subagent
+            // returns. Each tool_use block emits aiProgress + aiToolInfo
+            // back-to-back (no streaming preview — the SDK never gave us
+            // one); the tool_use id is registered in _toolUseIdToCounter
+            // so the existing tool_result handler routes the response
+            // back to the right indicator card.
+            if (message.type === "assistant" &&
+                    message.parent_tool_use_id &&
+                    message.message && Array.isArray(message.message.content)) {
+                const parentToolId = _toolUseIdToCounter[message.parent_tool_use_id];
+                for (const block of message.message.content) {
+                    if (block && block.type === "tool_use") {
+                        toolCounter++;
+                        if (block.id) {
+                            _toolUseIdToCounter[block.id] = toolCounter;
+                        }
+                        _log("Subagent tool:", block.name, "#" + toolCounter,
+                            "parent=#" + (parentToolId !== undefined ? parentToolId : "?"));
+                        nodeConnector.triggerPeer("aiProgress", {
+                            requestId: requestId,
+                            toolName: block.name,
+                            toolId: toolCounter,
+                            parentToolId: parentToolId,
+                            phase: "tool_use"
+                        });
+                        nodeConnector.triggerPeer("aiToolInfo", {
+                            requestId: requestId,
+                            toolName: block.name,
+                            toolId: toolCounter,
+                            parentToolId: parentToolId,
+                            toolInput: block.input || {}
+                        });
+                    }
+                }
+            }
+
             // Per-turn token usage: each SDKAssistantMessage carries the
             // wrapped Anthropic API message whose `.usage` reflects what
             // that single turn consumed. Useful for diagnosing runaway

src/styles/Extn-AIChatPanel.less

@@ -1126,6 +1126,39 @@
     }
 }
 
+/* ── Subagent step rows ──────────────────────────────────────────────
+   Compact one-line entries inside an Agent dispatcher card showing
+   what the subagent is doing (Read foo.json, Searched: *.md, etc).
+   Indented with a left border so the nesting reads clearly. */
+.ai-subagent-steps {
+    margin-top: 4px;
+    padding-left: 8px;
+    border-left: 2px solid fade(@project-panel-text-2, 25%);
+}
+
+.ai-subagent-step {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    padding: 2px 0;
+    font-size: @ai-text-secondary;
+}
+
+.ai-subagent-step-icon {
+    width: 14px;
+    text-align: center;
+    flex-shrink: 0;
+    font-size: @ai-text-secondary;
+}
+
+.ai-subagent-step-label {
+    color: @project-panel-text-2;
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    min-width: 0;
+}
+
 @keyframes ai-spin {
     to { transform: rotate(360deg); }
 }

tracking-repos.json

@@ -1,5 +1,5 @@
 {
   "phoenixPro": {
-    "commitID": "21edc7c2963b6b73076dfa7b362a76ae71db7879"
+    "commitID": "79aeedfe7690aa5a166dd8e5b988900f6bf71468"
   }
 }