refactor: centralize turn input preparation

docs/ARCHITECTURE.md

@@ -183,7 +183,7 @@ Session ID 格式为：
 5. 持久化写入由 `persistence_lock` 串行化；多条相关记录应使用 Storage 的原子接口。
 6. 内存先变更但持久化失败时，必须回滚精确匹配的消息后缀，不能删除无关的新状态。
 
-SessionManager 负责组装会话上下文：系统提示、Skills、召回的 Knowledge、压缩后的 Timeline、可选的 active plan 摘要和当前消息历史。普通闲聊 session 没有 plan 摘要；计划状态由 `WorkManager` 从 SQLite 读取，在历史压缩之后追加，因此不以自然语言摘要作为权威来源。`AgentLoop` 接收完整输入执行一次模型/工具循环，本身不拥有会话状态。
+SessionManager 负责组装会话上下文：系统提示、Skills、召回的 Knowledge、压缩后的 Timeline、可选的 active plan 摘要和当前消息历史。`session::turn_input` 在 Session 锁外并行读取 Knowledge、active plan 并压缩历史，然后通过同一个 assembly 路径生成首次请求和 context-overflow 重试输入；重试不得复制系统提示或 runtime context 拼接逻辑。普通闲聊 session 没有 plan 摘要；计划状态由 `WorkManager` 从 SQLite 读取，因此不以自然语言摘要作为权威来源。`AgentLoop` 接收完整输入执行一次模型/工具循环，本身不拥有会话状态。
 
 每个 session 最多有一个 active plan，但 plan 内多个 item 可以分别绑定不同子 Agent 并行执行。主 Agent 通过 `todo` 创建和维护计划，通过 `delegate.plan_item_id` 委托；子 Agent 不获得 `todo` 或 `delegate`。领取 item 使用条件更新防止重复执行，迟到结果只有在 plan 仍 active 且 execution ID 匹配时才允许提交。
 

src/session/mod.rs

@@ -3,6 +3,7 @@ pub mod error;
 pub mod events;
 mod messenger;
 mod persistence;
+mod turn_input;
 // The public `session::session` path is retained for API compatibility.
 #[allow(clippy::module_inception)]
 pub mod session;

src/session/session.rs

@@ -5,6 +5,7 @@ use tokio::sync::{Mutex, mpsc, oneshot};
 
 use super::persistence::{append_persisted_messages, finalize_turn_after_persistence};
 use super::turn::{TurnBlock, TurnController, TurnSnapshot};
+use super::turn_input::prepare_turn_input;
 use crate::bus::{
     ChatMessage, CompletionStatus, MediaItem, MediaRef, MessageSource, OutboundMessage, SourceKind,
 };
@@ -48,7 +49,7 @@ pub enum HandleResult {
     AgentProcessing,
 }
 use crate::agent::context_compressor::ContextCompressionConfig;
-use crate::agent::system_prompt::{build_runtime_context, build_system_prompt};
+use crate::agent::system_prompt::build_system_prompt;
 use crate::agent::{AgentError, AgentLoop, AgentTurnContext, ContextCompressor, TurnEmitter};
 use crate::channels::slash_command::parse_slash_command;
 use crate::config::BrowserConfig;
@@ -791,18 +792,6 @@ impl Session {
         }
     }
 
-    fn append_runtime_context_to_user_message(message: &mut ChatMessage, runtime_context: &str) {
-        if runtime_context.trim().is_empty() {
-            return;
-        }
-
-        if message.content.trim().is_empty() {
-            message.content = runtime_context.to_string();
-        } else {
-            message.content = format!("{}\n\n{}", message.content, runtime_context);
-        }
-    }
-
     pub fn create_user_message_with_source(
         &self,
         content: &str,
@@ -2584,7 +2573,14 @@ fn spawn_agent_worker(
                     continue 'tasks;
                 }
 
-                let (agent, history_raw, mut compressor, base_version, cancel_rx) = {
+                let (
+                    agent,
+                    history_raw,
+                    mut compressor,
+                    system_prompt_out,
+                    base_version,
+                    cancel_rx,
+                ) = {
                     let mut guard = session.lock().await;
 
                     if guard.worker_generation != worker_gen {
@@ -2623,59 +2619,22 @@ fn spawn_agent_worker(
                         agent,
                         history_raw,
                         guard.fresh_context_compressor(),
+                        guard.build_system_prompt(&skills_prompt),
                         guard.state_version,
                         cancel_rx,
                     )
                 }; // lock released
 
-                let memory_context = match memory_manager
+                let prepared_input = prepare_turn_input(
-                    .recall(
+                    memory_manager.clone(),
+                    work_manager.clone(),
+                    &unified_str,
                     &task.content,
-                        5,
+                    system_prompt_out,
-                        Some(crate::memory::MemoryCategory::Knowledge),
+                    &mut compressor,
-                        None,
+                    history_raw,
                 )
-                    .await
+                .await;
-                {
-                    Ok(entries) if !entries.is_empty() => Some(
-                        entries
-                            .iter()
-                            .map(|e| format!("- {}: {}", e.key, e.content))
-                            .collect::<Vec<_>>()
-                            .join("\n"),
-                    ),
-                    Err(e) => {
-                        tracing::warn!(error = %e, "Failed to fetch memory context");
-                        None
-                    }
-                    _ => None,
-                };
-
-                let work_context = match work_manager.active_plan(&unified_str).await {
-                    Ok(Some(plan)) => Some(plan.compact_context()),
-                    Ok(None) => None,
-                    Err(error) => {
-                        tracing::warn!(error = %error, "Failed to load active task plan");
-                        None
-                    }
-                };
-                let runtime_context = build_runtime_context(
-                    Some(unified_str.as_str()),
-                    memory_context.as_deref(),
-                    work_context.as_deref(),
-                );
-
-                let system_prompt_out = {
-                    let guard = session.lock().await;
-                    if guard.worker_generation != worker_gen {
-                        return;
-                    }
-                    guard.build_system_prompt(&skills_prompt)
-                };
-
-                let compression_result = compressor.compress_if_needed(history_raw).await;
-                let mut history_out = match compression_result {
-                    Ok(result) => {
                 let meta_snapshot = {
                     let mut guard = session.lock().await;
                     if guard.worker_generation != worker_gen {
@@ -2689,12 +2648,11 @@ fn spawn_agent_worker(
                         guard.current_cancel = None;
                         continue 'tasks;
                     }
-                            if result.created_timelines {
+                    if prepared_input.created_timelines {
                         guard.last_compressed_message_at =
                             Some(chrono::Utc::now().timestamp_millis());
                     }
-                            guard.last_consolidated_at =
+                    guard.last_consolidated_at = Some(chrono::Utc::now().timestamp_millis());
-                                Some(chrono::Utc::now().timestamp_millis());
                     guard.session_meta_snapshot()
                 };
                 if let Some((storage, meta)) = meta_snapshot
@@ -2702,21 +2660,8 @@ fn spawn_agent_worker(
                 {
                     tracing::warn!(error = %e, "Failed to persist session meta after compression");
                 }
-                        result.history
+                let history_out = prepared_input.messages;
-                    }
+                let runtime_context = prepared_input.runtime;
-                    Err(e) => {
-                        tracing::warn!(error = %e, "Context compression failed in worker");
-                        let guard = session.lock().await;
-                        if guard.worker_generation != worker_gen {
-                            return;
-                        }
-                        guard.get_history().to_vec()
-                    }
-                };
-                history_out.insert(0, ChatMessage::system(system_prompt_out.clone()));
-                if let Some(last_msg) = history_out.iter_mut().rev().find(|m| m.role == "user") {
-                    Session::append_runtime_context_to_user_message(last_msg, &runtime_context);
-                }
 
                 let (turn_controller, turn_emitter, turn_receiver) = TurnController::start(
                     unified_str.clone(),
@@ -2867,21 +2812,7 @@ fn spawn_agent_worker(
                                 tracing::warn!(error = %e, "Failed to persist session meta after retry compression");
                             }
 
-                            let retry_history = {
+                            let retry_history = runtime_context.assemble(retry_result.history);
-                                let mut retry = retry_result.history;
-                                retry.insert(
-                                    0,
-                                    ChatMessage::system(system_prompt_out.clone()),
-                                );
-                                if let Some(last_msg) = retry.iter_mut().rev().find(|m| m.role == "user")
-                                {
-                                    Session::append_runtime_context_to_user_message(
-                                        last_msg,
-                                        &runtime_context,
-                                    );
-                                }
-                                retry
-                            };
 
                             match agent
                                 .process_streaming(retry_history, agent_turn.clone())

src/session/turn_input.rs

@@ -0,0 +1,148 @@
+use std::sync::Arc;
+
+use crate::agent::ContextCompressor;
+use crate::agent::system_prompt::build_runtime_context;
+use crate::bus::ChatMessage;
+use crate::memory::{MemoryCategory, MemoryManager};
+use crate::work::WorkManager;
+
+/// Immutable context used to assemble provider input for both the initial call
+/// and context-overflow recovery.
+pub(super) struct TurnRuntimeContext {
+    system_prompt: String,
+    runtime_context: String,
+}
+
+impl TurnRuntimeContext {
+    pub(super) fn assemble(&self, mut history: Vec<ChatMessage>) -> Vec<ChatMessage> {
+        history.insert(0, ChatMessage::system(self.system_prompt.clone()));
+        if let Some(last_user) = history
+            .iter_mut()
+            .rev()
+            .find(|message| message.role == "user")
+        {
+            append_runtime_context(last_user, &self.runtime_context);
+        }
+        history
+    }
+}
+
+pub(super) struct PreparedTurnInput {
+    pub(super) messages: Vec<ChatMessage>,
+    pub(super) runtime: TurnRuntimeContext,
+    pub(super) created_timelines: bool,
+}
+
+/// Builds the complete cross-turn provider input outside the Session lock.
+/// Independent context sources and compression are fetched concurrently.
+pub(super) async fn prepare_turn_input(
+    memory_manager: Arc<MemoryManager>,
+    work_manager: Arc<WorkManager>,
+    session_id: &str,
+    query: &str,
+    system_prompt: String,
+    compressor: &mut ContextCompressor,
+    history: Vec<ChatMessage>,
+) -> PreparedTurnInput {
+    let memory_future = memory_manager.recall(query, 5, Some(MemoryCategory::Knowledge), None);
+    let work_future = work_manager.active_plan(session_id);
+    let compression_future = compressor.compress_if_needed(history.clone());
+    let (memory_result, work_result, compression_result) =
+        tokio::join!(memory_future, work_future, compression_future);
+
+    let memory_context = match memory_result {
+        Ok(entries) if !entries.is_empty() => Some(
+            entries
+                .iter()
+                .map(|entry| format!("- {}: {}", entry.key, entry.content))
+                .collect::<Vec<_>>()
+                .join("\n"),
+        ),
+        Err(error) => {
+            tracing::warn!(error = %error, "Failed to fetch memory context");
+            None
+        }
+        _ => None,
+    };
+    let work_context = match work_result {
+        Ok(Some(plan)) => Some(plan.compact_context()),
+        Ok(None) => None,
+        Err(error) => {
+            tracing::warn!(error = %error, "Failed to load active task plan");
+            None
+        }
+    };
+    let compression = match compression_result {
+        Ok(result) => result,
+        Err(error) => {
+            tracing::warn!(error = %error, "Context compression failed while preparing turn input");
+            crate::agent::context_compressor::CompressionResult {
+                history,
+                created_timelines: false,
+            }
+        }
+    };
+    let runtime = TurnRuntimeContext {
+        system_prompt,
+        runtime_context: build_runtime_context(
+            Some(session_id),
+            memory_context.as_deref(),
+            work_context.as_deref(),
+        ),
+    };
+
+    PreparedTurnInput {
+        messages: runtime.assemble(compression.history),
+        runtime,
+        created_timelines: compression.created_timelines,
+    }
+}
+
+fn append_runtime_context(message: &mut ChatMessage, runtime_context: &str) {
+    if runtime_context.trim().is_empty() {
+        return;
+    }
+    if message.content.trim().is_empty() {
+        message.content = runtime_context.to_string();
+    } else {
+        message.content = format!("{}\n\n{}", message.content, runtime_context);
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn runtime_context_is_added_only_to_latest_user_message() {
+        let runtime = TurnRuntimeContext {
+            system_prompt: "system".to_string(),
+            runtime_context: "runtime".to_string(),
+        };
+        let messages = runtime.assemble(vec![
+            ChatMessage::user("old"),
+            ChatMessage::assistant("answer"),
+            ChatMessage::user("new"),
+        ]);
+
+        assert_eq!(messages[0].role, "system");
+        assert_eq!(messages[1].content, "old");
+        assert_eq!(messages[3].content, "new\n\nruntime");
+    }
+
+    #[test]
+    fn overflow_reassembly_does_not_duplicate_runtime_context() {
+        let runtime = TurnRuntimeContext {
+            system_prompt: "system".to_string(),
+            runtime_context: "runtime".to_string(),
+        };
+
+        let first = runtime.assemble(vec![ChatMessage::user("question")]);
+        let recovered = runtime.assemble(vec![ChatMessage::user("question")]);
+
+        assert_eq!(first.len(), recovered.len());
+        assert_eq!(first[0].content, recovered[0].content);
+        assert_eq!(first[1].content, recovered[1].content);
+        assert_eq!(recovered.len(), 2);
+    }
+}