refactor(session): remove synthetic log-only turns

packages/session-title/session-title-llm/README.i18n.yaml

@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: 5d004b634e6242a8a558182e6c953e4c43b25e1f
-README.zh.md: 36567d950e612561d8af804eca64ac6f9f3cd788
+#   pnpm run verify-translation-pairing --write packages/session-title/session-title-llm/README.md
+README.md: 342687b5aa0cd35a70abf8cc66b3fe80342bce0b
+README.zh.md: 2bb48b52ae6298c5c895ef99ff54cf5f1d7a6d8c

packages/session-title/session-title-llm/README.md

@@ -10,7 +10,7 @@ This package is a library, not a Cordis plugin. The provider plugins call `regis
 
 `provider` and `model` overrides are optional but must be supplied together as non-empty strings. Without that pair, the helper uses the exact provider/model route captured from the current session's logged `request/header`; an explicit refresh before any route exists therefore needs overrides. The helper measures the final JSON-framed user prompt, including seq fields, wrappers, and JSON escaping, against `maxInputBytes` before logging or dispatch instead of truncating it. Timeout and caller cancellation are rechecked while consuming the stream and after it completes, so a late successful result cannot be accepted even if an interceptor or adapter ignores abort. Malformed or empty output, tool calls, and non-stop finish reasons also reject; the session-title service decides whether that rejection is an automatic warning or an explicit caller failure.
 
-After route and input validation, the helper appends a log-only `session/title-llm-request` event before model dispatch. It contains the title-provider id, exact source seqs, route, system prompt, message list, and output-token cap used by the call. The append shares the title capability's per-session settlement queue, so a superseding request cannot collide with an earlier fallback, request record, or accepted-title flush. The dispatched envelope is deep-frozen, carries `purpose: 'session-title'`, and deliberately lacks dsh-agent-loop's process-local request identity. Interceptors stay aligned with the record while loop-only reconstruction observers do not compare it with the conversation header. The DeepSeek adapter maps that purpose to thinking-disabled so the small output budget is reserved for visible title text; other adapters own their purpose-specific behavior. A later model failure leaves the request record intact; validation failures that never become dispatchable requests do not create one. The event stays outside derived model history.
+After route and input validation, the helper appends a log-only `session/title-llm-request` event directly through `Session` before model dispatch. It contains the title-provider id, exact source seqs, route, system prompt, message list, and output-token cap used by the call. Persistence observes the record eagerly; the append does not need a title-specific marker, cast, settlement queue, or flush. The dispatched envelope is deep-frozen, carries `purpose: 'session-title'`, and deliberately lacks dsh-agent-loop's process-local request identity. Interceptors stay aligned with the record while loop-only reconstruction observers do not compare it with the conversation header. The DeepSeek adapter maps that purpose to thinking-disabled so the small output budget is reserved for visible title text; other adapters own their purpose-specific behavior. A later model failure leaves the request record intact; validation failures that never become dispatchable requests do not create one. The event stays outside derived model history.
 
 ## Configuration
 

packages/session-title/session-title-llm/README.zh.md

@@ -10,7 +10,7 @@
 
 `provider` 和 `model` 覆盖项都是可选的，但必须同时作为非空字符串提供。如果没有这一对取值，辅助模块会使用当前会话已记录 `request/header` 中捕获的确切提供方／模型路由；因此，在任何路由出现前显式刷新时必须提供覆盖项。辅助模块在记录或分发前，以 `maxInputBytes` 测量最终 JSON 封装的用户提示词，包括 seq 字段、包装层与 JSON 转义，而不是将其截断。消费流期间和流完成后都会重新检查超时与调用方取消，因此即使 interceptor 或适配器忽略 abort，也不能接受迟到的成功结果。格式错误或空输出、工具调用和非 stop 结束原因同样会 reject；会话标题服务决定该 reject 属于自动警告还是显式调用方失败。
 
-路由与输入验证完成后，辅助模块会在模型分发前追加仅写入日志的 `session/title-llm-request` 事件。它包含标题提供方 id、确切来源 seq、路由、系统提示词、消息列表，以及该调用使用的输出 token 上限。追加操作共享标题能力的逐会话结算队列，因此取代当前请求的新请求不会与更早回退、请求记录或已接受标题的 flush 冲突。分发的 envelope 会深度冻结，携带 `purpose: 'session-title'`，且有意不包含 dsh-agent-loop 的进程本地请求身份。Interceptor 会与记录保持一致，而循环专用重建观察者不会把它与对话 header 比较。DeepSeek 适配器会将该 purpose 映射为关闭 thinking，使少量输出预算全部用于可见标题文本；其他适配器负责自身 purpose 专用行为。后续模型失败会保留请求记录；从未成为可分发请求的验证失败不会创建记录。该事件始终位于派生模型历史之外。
+路由与输入验证完成后，辅助模块会在模型分发前直接通过 `Session` 追加仅写入日志的 `session/title-llm-request` 事件。它包含标题提供方 id、确切来源 seq、路由、系统提示词、消息列表，以及该调用使用的输出 token 上限。持久化会尽快观察该记录；追加不需要标题专属标记、类型断言、结算队列或 flush。分发的 envelope 会深度冻结，携带 `purpose: 'session-title'`，且有意不包含 dsh-agent-loop 的进程本地请求身份。Interceptor 会与记录保持一致，而循环专用重建观察者不会把它与对话 header 比较。DeepSeek 适配器会将该 purpose 映射为关闭 thinking，使少量输出预算全部用于可见标题文本；其他适配器负责自身 purpose 专用行为。后续模型失败会保留请求记录；从未成为可分发请求的验证失败不会创建记录。该事件始终位于派生模型历史之外。
 
 ## 配置
 

packages/session-title/session-title-llm/src/index.ts

@@ -10,7 +10,6 @@ import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm'
 import type { FinishReason, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
 import { deadline, MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
 import {
-  appendSessionTitleOutOfBand,
   normalizeSessionTitle,
   SessionTitleProviderId,
 } from '@deepseek-ai/dsh-session-title'
@@ -43,10 +42,6 @@ declare module '@deepseek-ai/dsh-session' {
     /** Log-only pre-dispatch record of one session-title model request. */
     'session/title-llm-request': SessionTitleLlmRequestEventData
   }
-
-  interface OutOfBandSessionEventMap {
-    'session/title-llm-request': true
-  }
 }
 
 /** Capability-owned timeout reason code for auxiliary title requests. */
@@ -264,14 +259,14 @@ export async function generateSessionTitleWithLlm(
     purpose: 'session-title',
     signal: callDeadline.signal,
   })
-  await appendSessionTitleOutOfBand(ctx, request.session, 'session/title-llm-request', {
+  request.session.append('session/title-llm-request', {
     titleProvider,
     messageSeqs: selectedMessages.map(message => message.seq),
     route,
     system,
     messages,
     maxTokens: config.maxOutputTokens,
-  }, callDeadline.signal)
+  })
   callDeadline.signal.throwIfAborted()
   const assembler = new BlockAssembler()
   for await (const chunk of ctx.llm.stream(options)) {