perf(scheduler): bound isolated session context to agent_max_context_turns/5

bridge/agent_bridge.py

@@ -418,6 +418,18 @@ class AgentBridge:
             # Store session_id on agent so executor can clear DB on fatal errors
             agent._current_session_id = session_id
 
+            # Bound the in-memory context for scheduler sessions before each run.
+            # Scheduler sessions are stable per-task and append every trigger,
+            # so without trimming they would grow unbounded across runs and
+            # blow up prompt cost. Regular user chats are not touched here —
+            # the agent's own context manager handles that path.
+            if session_id and session_id.startswith("scheduler_"):
+                from config import conf
+                scheduler_keep_turns = max(
+                    1, int(conf().get("agent_max_context_turns", 20)) // 5
+                )
+                self._trim_in_memory_to_turns(agent, scheduler_keep_turns)
+
             try:
                 # Use agent's run_stream method with event handler
                 response = agent.run_stream(
@@ -717,6 +729,61 @@ class AgentBridge:
                     f"for session={session_id}: {e}"
                 )
 
+    @staticmethod
+    def _trim_in_memory_to_turns(agent, keep_turns: int) -> None:
+        """Bound ``agent.messages`` to the most recent ``keep_turns`` real
+        user/assistant turns, dropping older history together with any
+        intermediate tool_use/tool_result blocks that belonged to it.
+
+        A "real" user message is any user message whose content is not solely a
+        tool_result block — matches the heuristic used elsewhere when filtering
+        history (see ``AgentInitializer._filter_text_only_messages``).
+
+        No-op when the session is already within budget. Caller does not need
+        to hold the lock; this method acquires it itself.
+        """
+        if keep_turns <= 0:
+            return
+
+        def _is_real_user(msg) -> bool:
+            if not isinstance(msg, dict) or msg.get("role") != "user":
+                return False
+            content = msg.get("content")
+            if isinstance(content, list):
+                if any(
+                    isinstance(b, dict) and b.get("type") == "tool_result"
+                    for b in content
+                ):
+                    return False
+                return any(
+                    isinstance(b, dict) and b.get("type") == "text" and b.get("text")
+                    for b in content
+                )
+            if isinstance(content, str):
+                return bool(content.strip())
+            return False
+
+        with agent.messages_lock:
+            msgs = agent.messages
+            real_user_indices = [i for i, m in enumerate(msgs) if _is_real_user(m)]
+            if len(real_user_indices) <= keep_turns:
+                return
+
+            # Cut at the (k-th from the end) real user message; keep everything
+            # from there onwards so the surviving slice is still a valid
+            # user/assistant sequence.
+            cut_idx = real_user_indices[-keep_turns]
+            if cut_idx == 0:
+                return
+
+            kept = msgs[cut_idx:]
+            msgs.clear()
+            msgs.extend(kept)
+            logger.debug(
+                f"[AgentBridge] Trimmed in-memory messages to last "
+                f"{keep_turns} turns ({len(kept)} messages remain)"
+            )
+
     @classmethod
     def _prune_scheduled_in_memory(cls, agent, keep_last_n: int) -> None:
         """Mirror conversation_store.prune_scheduled_messages on agent.messages.

bridge/agent_initializer.py

@@ -144,7 +144,15 @@ class AgentInitializer:
             from agent.memory import get_conversation_store
             store = get_conversation_store()
             max_turns = conf().get("agent_max_context_turns", 20)
-            restore_turns = max(3, max_turns // 6)
+            # Scheduler tasks run on a stable isolated session per task and
+            # can fire many times a day; a smaller restore window keeps prompt
+            # cost bounded while still letting the agent see "last few" runs
+            # for trend / dedup style logic. Regular chat sessions keep the
+            # original heuristic so user dialogues feel continuous.
+            if session_id.startswith("scheduler_"):
+                restore_turns = max(1, max_turns // 5)
+            else:
+                restore_turns = max(3, max_turns // 6)
             saved = store.load_messages(session_id, max_turns=restore_turns)
             if saved:
                 filtered = self._filter_text_only_messages(saved)

docs/tools/scheduler.mdx

@@ -65,6 +65,16 @@ description: 创建和管理定时任务
 }
 ```
 
+## 任务执行时的上下文
+
+定时任务的隔离 session 会保留最近几次执行的对话历史，便于做"对比上次"、"延续之前结论"等操作；但为了避免高频任务（如每 5 分钟监控）prompt 越积越长，会按公式自动裁剪：
+
+```
+scheduler_keep_turns = max(1, agent_max_context_turns / 5)
+```
+
+`agent_max_context_turns` 默认为 `20`，所以定时任务每次执行默认带最近 **4 轮**历史。需要更长记忆可调大 `agent_max_context_turns`。
+
 <Note>
 群聊场景（飞书 / 企微群机器人 / 钉钉等）下用户的真实 session_id 形如 `user_id:group_id`，与 receiver 不同。创建任务时会自动记录正确的 session_id；老的 `tasks.json` 缺该字段时回落到 receiver，行为与历史版本一致。
 </Note>