修复网页对话并接入 SearXNG 搜索

app/engine.py

@@ -26,6 +26,7 @@ from __future__ import annotations
 
 import asyncio
 import logging
+import re
 import time
 import uuid
 from dataclasses import dataclass, field
@@ -36,16 +37,27 @@ import numpy as np
 
 from .config import AppConfig
 from .identity.base import IdentityDecision, IdentityProvider
-from .llm.base import LLMProvider, ToolCall
+from .llm.base import ChunkKind, LLMProvider, ToolCall
 from .memory.base import (
     ConfirmStatus, Memory, MemoryKind, MemoryStore, Scope, Turn,
 )
 from .prompts import build_system_prompt, trim_history
+from .search import (
+    WEB_SEARCH_PROMPT,
+    WEB_SEARCH_TOOL,
+    SearchError,
+    SearXNGSearchClient,
+)
 from .voice.stt import StreamingSTT
-from .voice.tts import LocalTTS, split_sentences
+from .voice.tts import LocalTTS, split_sentences, text_for_speech
 
 log = logging.getLogger(__name__)
 
+_SOURCE_SECTION_RE = re.compile(
+    r"(?:^|\n)\s*(?:参考来源|资料来源|来源)\s*[：:]",
+    re.IGNORECASE,
+)
+
 
 class EventKind(str, Enum):
     IDENTITY = "identity"           # 本轮的身份裁决结果
@@ -84,12 +96,15 @@ class TurnMetrics:
     memories_used: int = 0
     reply_chars: int = 0
     speaks: int = 0
+    search_ms: float = 0.0
+    searches: int = 0
 
     def summary(self) -> str:
         return (f"STT {self.stt_ms:.0f}ms | 身份 {self.identity_ms:.0f}ms | "
                 f"检索 {self.retrieve_ms:.0f}ms | LLM首token {self.llm_first_content_ms:.0f}ms | "
                 f"首音 {self.first_audio_ms:.0f}ms | 总 {self.total_ms:.0f}ms | "
-                f"{self.llm_backend} | 记忆{self.memories_used}条 | {self.speaks}段音频")
+                f"{self.llm_backend} | 记忆{self.memories_used}条 | "
+                f"搜索{self.searches}次/{self.search_ms:.0f}ms | {self.speaks}段音频")
 
 
 class ConversationEngine:
@@ -101,6 +116,7 @@ class ConversationEngine:
         identity: IdentityProvider,
         tts: LocalTTS,
         stt: StreamingSTT | None = None,
+        search: SearXNGSearchClient | None = None,
     ):
         self.cfg = cfg
         self.llm = llm
@@ -108,6 +124,9 @@ class ConversationEngine:
         self.identity = identity
         self.tts = tts
         self.stt = stt
+        self.search = search or (
+            SearXNGSearchClient(cfg.search) if cfg.search.enabled else None
+        )
         #: 会话历史。切身份时会清空——方案 §8 要求切换身份
         #: 清理上一人的私有检索上下文。
         self._history: list[dict] = []
@@ -177,7 +196,11 @@ class ConversationEngine:
             yield Event(kind=EventKind.MEMORY_USED, memories=memories)
 
         # ---- 拼 system（每轮重建，单条）
-        system = build_system_prompt(identity, memories)
+        system = build_system_prompt(
+            identity,
+            memories,
+            extra=WEB_SEARCH_PROMPT if self.search is not None else "",
+        )
         history = trim_history(self._history,
                                max_turns=self.cfg.context.max_turns)
         messages = [{"role": "system", "content": system}] + history + \
@@ -186,15 +209,22 @@ class ConversationEngine:
         # ---- LLM 流式 + 逐句 TTS
         reply_parts: list[str] = []
         buffer = ""
+        speech_done = False
         speaks = 0
         async for ev in self._stream_and_speak(messages, metrics):
             if ev.kind == EventKind.RESPONSE_DELTA:
                 reply_parts.append(ev.text)
-                buffer += ev.text
                 # 增量文本必须**原样透传**给调用方（显示、字幕、日志都要用）。
                 # 这里漏掉 yield 的后果是：音频正常出来了，但上层拿到的是空回复——
                 # 因为文本只进了内部累加器，从未离开这个生成器。
                 yield ev
+                if speech_done:
+                    continue
+                buffer += ev.text
+                source_start = _SOURCE_SECTION_RE.search(buffer)
+                if source_start:
+                    buffer = buffer[:source_start.start()]
+                    speech_done = True
                 # 攒到句末就送去合成——这是提前出声的唯一手段
                 segs = split_sentences(buffer)
                 if len(segs) > 1:
@@ -278,21 +308,75 @@ class ConversationEngine:
 
     async def _stream_and_speak(self, messages: list[dict],
                                 metrics: TurnMetrics) -> AsyncIterator[Event]:
-        """只负责 LLM 流式，不做 TTS。TTS 由调用方按句驱动。"""
+        """执行 LLM/搜索工具闭环；最终文本仍然流式交给调用方做 TTS。"""
         t0 = time.perf_counter()
         try:
-            async for chunk in self.llm.stream(messages):
-                if chunk.kind.value == "content" and chunk.text:
-                    if not metrics.llm_first_content_ms:
-                        metrics.llm_first_content_ms = (time.perf_counter() - t0) * 1000
-                    yield Event(kind=EventKind.RESPONSE_DELTA, text=chunk.text)
-                elif chunk.kind.value == "tool_call" and chunk.tool_name:
-                    # 骨架阶段只上报，不执行。工具执行要配合
-                    # 方案 §9 的"执行 ID + 状态确认 + 不盲目重试"，
-                    # 留到接米家时再做。
-                    yield Event(kind=EventKind.TOOL_CALL, tool_call=ToolCall(
-                        id=chunk.tool_id, name=chunk.tool_name,
-                        arguments=chunk.tool_arguments))
+            # 最多允许连续两轮搜索；第三次请求不再暴露工具，强制形成回答，
+            # 防止模型在搜索词之间无限循环。
+            for round_index in range(3):
+                tool_defs = (
+                    [WEB_SEARCH_TOOL]
+                    if self.search is not None and round_index < 2
+                    else None
+                )
+                tool_acc: dict[int, dict[str, str]] = {}
+                assistant_parts: list[str] = []
+
+                async for chunk in self.llm.stream(messages, tools=tool_defs):
+                    if chunk.kind == ChunkKind.CONTENT and chunk.text:
+                        assistant_parts.append(chunk.text)
+                        if not metrics.llm_first_content_ms:
+                            metrics.llm_first_content_ms = (
+                                time.perf_counter() - t0
+                            ) * 1000
+                        yield Event(kind=EventKind.RESPONSE_DELTA, text=chunk.text)
+                    elif chunk.kind == ChunkKind.TOOL_CALL:
+                        slot = tool_acc.setdefault(
+                            chunk.tool_index,
+                            {"id": "", "name": "", "arguments": ""},
+                        )
+                        # base.py 传来的是截至当前分片的完整累计值，直接覆盖，
+                        # 不能再次拼接，否则参数会重复。
+                        slot["id"] = chunk.tool_id or slot["id"]
+                        slot["name"] = chunk.tool_name or slot["name"]
+                        slot["arguments"] = chunk.tool_arguments
+
+                metrics.llm_backend = getattr(
+                    self.llm, "last_backend", self.llm.name)
+                if not tool_acc:
+                    break
+
+                calls: list[ToolCall] = []
+                api_calls: list[dict] = []
+                for index, raw in sorted(tool_acc.items()):
+                    call = ToolCall(
+                        id=raw["id"] or f"call_{uuid.uuid4().hex[:12]}",
+                        name=raw["name"],
+                        arguments=raw["arguments"] or "{}",
+                    )
+                    calls.append(call)
+                    api_calls.append({
+                        "id": call.id,
+                        "type": "function",
+                        "function": {
+                            "name": call.name,
+                            "arguments": call.arguments,
+                        },
+                    })
+                    yield Event(kind=EventKind.TOOL_CALL, tool_call=call)
+
+                messages.append({
+                    "role": "assistant",
+                    "content": "".join(assistant_parts) or None,
+                    "tool_calls": api_calls,
+                })
+                for call in calls:
+                    result = await self._execute_tool(call, metrics)
+                    messages.append({
+                        "role": "tool",
+                        "tool_call_id": call.id,
+                        "content": result,
+                    })
         except asyncio.CancelledError:
             log.info("本轮被取消（打断）")
             raise
@@ -301,9 +385,32 @@ class ConversationEngine:
             yield Event(kind=EventKind.ERROR, error=f"{type(e).__name__}: {e}")
         metrics.llm_backend = getattr(self.llm, "last_backend", self.llm.name)
 
+    async def _execute_tool(self, call: ToolCall, metrics: TurnMetrics) -> str:
+        """执行只读搜索工具；错误作为工具结果回灌，不让整轮对话中断。"""
+        if call.name != "web_search" or self.search is None:
+            return "工具不可用。请不要声称已经执行。"
+        query = call.parsed_arguments().get("query")
+        if not isinstance(query, str) or not query.strip():
+            return "搜索失败：缺少有效的 query 参数。"
+
+        started = time.perf_counter()
+        metrics.searches += 1
+        try:
+            results = await self.search.search(query)
+            log.info("联网搜索 %r：返回 %d 条", query[:80], len(results))
+            return self.search.for_model(query, results)
+        except SearchError as exc:
+            log.warning("联网搜索失败：%s", exc)
+            return f"搜索失败：{exc}。请明确告知用户暂时无法取得实时资料。"
+        except Exception as exc:  # noqa: BLE001 — 工具失败不能拖垮对话
+            log.exception("联网搜索异常：%s", exc)
+            return "搜索服务发生异常。请明确告知用户暂时无法取得实时资料。"
+        finally:
+            metrics.search_ms += (time.perf_counter() - started) * 1000
+
     async def _speak(self, text: str, metrics: TurnMetrics) -> AsyncIterator[Event]:
         """合成一段并产出可播放音频。"""
-        text = text.strip()
+        text = text_for_speech(text)
         if not text:
             return
         t0 = time.perf_counter()