feat: display thinking content in web console

agent/chat/service.py

@@ -57,7 +57,16 @@ class ChatService:
             event_type = event.get("type")
             data = event.get("data", {})
 
-            if event_type == "message_update":
+            if event_type == "reasoning_update":
+                delta = data.get("delta", "")
+                if delta:
+                    send_chunk_fn({
+                        "chunk_type": "reasoning",
+                        "delta": delta,
+                        "segment_id": state.segment_id,
+                    })
+
+            elif event_type == "message_update":
                 # Incremental text delta
                 delta = data.get("delta", "")
                 if delta:

agent/memory/conversation_store.py

@@ -188,8 +188,9 @@ def _group_into_display_turns(
             if text:
                 turns.append({"role": "user", "content": text, "created_at": created_at})
 
-        # Collect all tool_calls and tool_results from the rest of the group
-        all_tool_calls: List[Dict[str, Any]] = []
+        # Build an ordered list of steps preserving the original sequence:
+        #   thinking → content → tool_call → content → ...
+        steps: List[Dict[str, Any]] = []
         tool_results: Dict[str, str] = {}
         final_text = ""
         final_ts: Optional[int] = None
@@ -198,24 +199,46 @@ def _group_into_display_turns(
             if role == "user":
                 tool_results.update(_extract_tool_results(content))
             elif role == "assistant":
-                tcs = _extract_tool_calls(content)
-                all_tool_calls.extend(tcs)
-                t = _extract_display_text(content)
-                if t:
-                    final_text = t
+                # Walk content blocks in order to preserve interleaving
+                if isinstance(content, list):
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        btype = block.get("type")
+                        if btype == "thinking":
+                            txt = block.get("thinking", "").strip()
+                            if txt:
+                                steps.append({"type": "thinking", "content": txt})
+                        elif btype == "text":
+                            txt = block.get("text", "").strip()
+                            if txt:
+                                steps.append({"type": "content", "content": txt})
+                                final_text = txt
+                        elif btype == "tool_use":
+                            steps.append({
+                                "type": "tool",
+                                "id": block.get("id", ""),
+                                "name": block.get("name", ""),
+                                "arguments": block.get("input", {}),
+                            })
+                elif isinstance(content, str) and content.strip():
+                    steps.append({"type": "content", "content": content.strip()})
+                    final_text = content.strip()
                 final_ts = created_at
 
-        # Attach tool results to their matching tool_call entries
-        for tc in all_tool_calls:
-            tc["result"] = tool_results.get(tc.get("id", ""), "")
+        # Attach tool results to tool steps
+        for step in steps:
+            if step["type"] == "tool":
+                step["result"] = tool_results.get(step.get("id", ""), "")
 
-        if final_text or all_tool_calls:
-            turns.append({
+        if steps or final_text:
+            turn = {
                 "role": "assistant",
                 "content": final_text,
-                "tool_calls": all_tool_calls,
+                "steps": steps,
                 "created_at": final_ts or (user_row[1] if user_row else 0),
-            })
+            }
+            turns.append(turn)
 
     return turns
 
@@ -312,6 +335,9 @@ class ConversationStore:
                 content = json.loads(raw_content)
             except Exception:
                 content = raw_content
+            # Strip thinking blocks — they are stored for UI display only
+            if role == "assistant" and isinstance(content, list):
+                content = [b for b in content if b.get("type") != "thinking"]
             result.append({"role": role, "content": content})
         return result
 

agent/protocol/agent_stream.py

@@ -527,6 +527,7 @@ class AgentStreamExecutor:
 
         # Streaming response
         full_content = ""
+        full_reasoning = ""
         tool_calls_buffer = {}  # {index: {id, name, arguments}}
         gemini_raw_parts = None  # Preserve Gemini thoughtSignature for round-trip
         stop_reason = None  # Track why the stream stopped
@@ -584,10 +585,10 @@ class AgentStreamExecutor:
                     if finish_reason:
                         stop_reason = finish_reason
 
-                    # Skip reasoning_content (internal thinking from models like GLM-5)
                     reasoning_delta = delta.get("reasoning_content") or ""
-                    # if reasoning_delta:
-                    #     logger.debug(f"🧠 [thinking] {reasoning_delta[:100]}...")
+                    if reasoning_delta:
+                        full_reasoning += reasoning_delta
+                        self._emit_event("reasoning_update", {"delta": reasoning_delta})
 
                     # Handle text content
                     content_delta = delta.get("content") or ""
@@ -788,7 +789,12 @@ class AgentStreamExecutor:
         # Add assistant message to history (Claude format uses content blocks)
         assistant_msg = {"role": "assistant", "content": []}
 
-        # Add text content block if present
+        if full_reasoning:
+            assistant_msg["content"].append({
+                "type": "thinking",
+                "thinking": full_reasoning
+            })
+
         if full_content:
             assistant_msg["content"].append({
                 "type": "text",