perf: improve tool calls in reasoning and multiple tool calls display (#7742)

* perf: improve tool calls in reasoning and multiple tool calls display

- Updated LiveChatRoute and OpenApiRoute to replace manual message accumulation with BotMessageAccumulator.
- Simplified message saving logic by using build_bot_history_content and collect_plain_text_from_message_parts.
- Enhanced message processing to handle various message types (plain, image, record, file, video) more efficiently.
- Improved reasoning handling by extracting thinking parts and displaying them correctly in the UI components.
- Refactored message normalization and reasoning extraction logic in useMessages composable for better clarity and maintainability.
- Updated ChatMessageList, MessageList, StandaloneChat, and ReasoningBlock components to accommodate new message structure and rendering logic.

* feat(chat): reasoning activity panel

- Introduced a new ReasoningSidebar component for displaying reasoning details.
- Refactored MessageList and StandaloneChat components to utilize renderBlocks for improved message part handling.
- Added ReasoningTimeline component to visualize reasoning steps.
- Updated message handling logic to differentiate between thinking and content blocks.
- Enhanced localization for reasoning-related terms in English, Russian, and Chinese.
- Improved styling for various components to ensure consistency and readability.

* Update astrbot/dashboard/routes/chat.py

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

---------

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Author: Soulter

astrbot/core/agent/runners/tool_loop_agent_runner.py

@@ -717,6 +717,15 @@ async def step(self):
                 if self.stats.time_to_first_token == 0:
                     self.stats.time_to_first_token = time.time() - self.stats.start_time
 
+                if llm_response.reasoning_content:
+                    yield AgentResponse(
+                        type="streaming_delta",
+                        data=AgentResponseData(
+                            chain=MessageChain(type="reasoning").message(
+                                llm_response.reasoning_content,
+                            ),
+                        ),
+                    )
                 if llm_response.result_chain:
                     yield AgentResponse(
                         type="streaming_delta",
@@ -729,15 +738,6 @@ async def step(self):
                             chain=MessageChain().message(llm_response.completion_text),
                         ),
                     )
-                if llm_response.reasoning_content:
-                    yield AgentResponse(
-                        type="streaming_delta",
-                        data=AgentResponseData(
-                            chain=MessageChain(type="reasoning").message(
-                                llm_response.reasoning_content,
-                            ),
-                        ),
-                    )
                 if self._is_stop_requested():
                     llm_resp_result = LLMResponse(
                         role="assistant",
@@ -791,6 +791,15 @@ async def step(self):
             await self._complete_with_assistant_response(llm_resp)
 
         # 返回 LLM 结果
+        if llm_resp.reasoning_content:
+            yield AgentResponse(
+                type="llm_result",
+                data=AgentResponseData(
+                    chain=MessageChain(type="reasoning").message(
+                        llm_resp.reasoning_content,
+                    ),
+                ),
+            )
         if llm_resp.result_chain:
             yield AgentResponse(
                 type="llm_result",
@@ -803,15 +812,6 @@ async def step(self):
                     chain=MessageChain().message(llm_resp.completion_text),
                 ),
             )
-        if llm_resp.reasoning_content:
-            yield AgentResponse(
-                type="llm_result",
-                data=AgentResponseData(
-                    chain=MessageChain(type="reasoning").message(
-                        llm_resp.reasoning_content,
-                    ),
-                ),
-            )
 
         # 如果有工具调用，还需处理工具调用
         if llm_resp.tools_call_name:
@@ -821,6 +821,15 @@ async def step(self):
                     logger.warning(
                         "skills_like tool re-query returned no tool calls; fallback to assistant response."
                     )
+                    if llm_resp.reasoning_content:
+                        yield AgentResponse(
+                            type="llm_result",
+                            data=AgentResponseData(
+                                chain=MessageChain(type="reasoning").message(
+                                    llm_resp.reasoning_content,
+                                ),
+                            ),
+                        )
                     if llm_resp.result_chain:
                         yield AgentResponse(
                             type="llm_result",
@@ -833,15 +842,7 @@ async def step(self):
                                 chain=MessageChain().message(llm_resp.completion_text),
                             ),
                         )
-                    if llm_resp.reasoning_content:
-                        yield AgentResponse(
-                            type="llm_result",
-                            data=AgentResponseData(
-                                chain=MessageChain(type="reasoning").message(
-                                    llm_resp.reasoning_content,
-                                ),
-                            ),
-                        )
+
                     await self._complete_with_assistant_response(llm_resp)
                     return
 
@@ -988,6 +989,7 @@ def _append_tool_call_result(tool_call_id: str, content: str) -> None:
             llm_response.tools_call_args,
             llm_response.tools_call_ids,
         ):
+            tool_result_blocks_start = len(tool_call_result_blocks)
             tool_call_streak = self._track_tool_call_streak(func_tool_name)
             yield _HandleFunctionToolsResult.from_message_chain(
                 MessageChain(
@@ -1201,24 +1203,23 @@ def _append_tool_call_result(tool_call_id: str, content: str) -> None:
                     ),
                 )
 
-        # yield the last tool call result
-        if tool_call_result_blocks:
-            last_tcr_content = str(tool_call_result_blocks[-1].content)
-            yield _HandleFunctionToolsResult.from_message_chain(
-                MessageChain(
-                    type="tool_call_result",
-                    chain=[
-                        Json(
-                            data={
-                                "id": func_tool_id,
-                                "ts": time.time(),
-                                "result": last_tcr_content,
-                            }
-                        )
-                    ],
+            if len(tool_call_result_blocks) > tool_result_blocks_start:
+                tool_result_content = str(tool_call_result_blocks[-1].content)
+                yield _HandleFunctionToolsResult.from_message_chain(
+                    MessageChain(
+                        type="tool_call_result",
+                        chain=[
+                            Json(
+                                data={
+                                    "id": func_tool_id,
+                                    "ts": time.time(),
+                                    "result": tool_result_content,
+                                }
+                            )
+                        ],
+                    )
                 )
-            )
-            logger.info(f"Tool `{func_tool_name}` Result: {last_tcr_content}")
+                logger.info(f"Tool `{func_tool_name}` Result: {tool_result_content}")
 
         # 处理函数调用响应
         if tool_call_result_blocks:

astrbot/core/astr_agent_run_util.py

@@ -235,6 +235,12 @@ async def run_agent(
                         )
                         await astr_event.send(chain)
                     continue
+                elif resp.type == "llm_result":
+                    chain = resp.data["chain"]
+                    if chain.type == "reasoning":
+                        # For non-streaming mode, we handle reasoning in astrbot/core/astr_agent_hooks.py.
+                        # For streaming mode, we yield content immediately when received a reasoning chunk but not in here, see below.
+                        continue
 
                 if stream_to_general and resp.type == "streaming_delta":
                     continue

astrbot/core/provider/sources/openai_source.py

@@ -652,6 +652,8 @@ async def _query_stream(
             reasoning = self._extract_reasoning_content(chunk)
             _y = False
             llm_response.id = chunk.id
+            llm_response.reasoning_content = ""
+            llm_response.completion_text = ""
             if reasoning:
                 llm_response.reasoning_content = reasoning
                 _y = True