@huai_xin/dsh-workbuddy 0.1.3 → 0.1.5

package/README.md

@@ -323,6 +323,35 @@ node test/live/policy-probe.mjs       # 两版白名单与准入结果对照
 - **模型不可用**：`code 11102 model [...] service info not found`（例如目录里列了但 CLI 渠道不服务的 `glm-4.6` 等）→ `INVALID_REQUEST`，不重试。
 - **额度/限流**：其他 429 → `RATE_LIMIT`；401/403 → 先续期再重试一次；5xx → `SERVER`。
 
+### 流式回答怎么算"正常结束"（2026-10-22 起）
+
+判据是机械的：**只有带 `finish_reason`（且流走到 `data: [DONE]`）或交付了工具调用，才算正常结束**；其余一律视为异常，并按下表处理。这样处理的起因是一次真实故障排查：模型"话说一半就停"看起来像正常结束，实际可能是连接被掐断，而旧实现把它当成了 `stop` → 既不报错也不重试。
+
+| 上游怎么结束 | 插件上报 | harness 会做什么 | 日志里能看到 |
+| --- | --- | --- | --- |
+| 没有 `finish_reason`、也没有 `[DONE]`（连接被掐断） | `TRANSPORT` 错误 | **自动退避重试**（默认策略含 `TRANSPORT`） | `… 的响应在 finish_reason/[DONE] 之前中断（收到 … kB，用时 …s，最后一段数据在 …s 前，中断时正在输出思考；可重试的传输错误）` |
+| 同样的断流，但断在工具调用参数中间 | `TRANSPORT` 错误 | 自动重试 | `… 的工具调用参数在传输中被截断（…）` |
+| `[DONE]` 但全程没有 `finish_reason` | `stop`（+ 记一笔） | 正常结束 | `… 的响应以 [DONE] 收尾但没有 finish_reason，按 stop 处理（输出 N tokens）` |
+| 输出打满预算 / 工具参数被输出上限截断 | `max-tokens` | 由 harness 决定续跑 | `… 的输出达到上限，本步被截断（输出 N tokens）` |
+| 正常 `stop` / `tool_calls` | 原样 | 正常 | 无 |
+
+重试本身由 harness 执行，插件只是把它记进日志：
+
+```
+[workbuddy] intl: 第 2/5 次重试（TRANSPORT） — 上游没有给出结束原因就断开了响应…；2.1s 后重试
+```
+
+另外每个 finish 帧都带一个 `response` 诊断块（`provider` / `model` / `responseId` / `stopReason` / `outputTokens` / `blocks`），会话数据诊断里会原样显示，方便一眼看出"这一步是谁答的、上游叫它什么 id"。它不是 harness 的契约字段，harness 不会据此改变行为。
+
+排查用探针：
+
+```powershell
+node test/live/stream-cut-probe.mjs cn --selftest     # 离线验证"断流"分类
+node test/live/stream-cut-probe.mjs intl 10 --long    # 真实压测断流率（免费模型零消耗）
+node test/live/find-message.mjs "关键词" <会话前缀>     # 按文本定位某一步，并打出前后事件
+node test/live/dump-stream.mjs <会话前缀> <seq,…>      # 打印那一步存下来的原始流帧
+```
+
 ## 许可
 
 MIT，见 [`LICENSE`](LICENSE)。再次说明：本项目为第三方非官方插件，与腾讯 / WorkBuddy 无关联。

package/docs/workbuddy-protocol.md

@@ -248,6 +248,11 @@ data: [DONE]
   频率实测工具：`node test/live/stream-cut-probe.mjs [cn|intl] [次数] [模型] [--long] [--selftest]`
   （2026-10-22 实测：大陆版短问答 4/4 正常、海外版 `deepseek-v4.1-flash` 长回答 10/10 正常，
   即断流是间歇性的，常规探测不易复现）
+- **finish 帧带一个 `response` 诊断块**（`kind`/`version`/`api`/`provider`/`model`/`responseId`/
+  `stopReason`/`outputTokens`/`blocks`）。它不是 harness 的契约字段（`dsh-llm` 的类型里没有
+  `response` / `stopReason`），纯属遥测：会话诊断里会原样显示，用来一眼回答"这一步是谁答的、
+  上游叫它什么 id"，不必再从 `request/header` 反推。`responseId` 取自上游流里的 `id`
+  （形如 `chatcmpl-…`），可以直接和上游日志对账；harness 不会据此改变行为 ✅
 - `usage`（末帧携带）：`prompt_tokens` / `completion_tokens` / `total_tokens` / `prompt_tokens_details.cached_tokens` / `completion_tokens_details.reasoning_tokens` / `prompt_cache_hit_tokens` / `prompt_cache_miss_tokens` / `credit` ✅
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@huai_xin/dsh-workbuddy",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "description": "WorkBuddy model provider for DeepSeek Harness (international + China deployments)",
   "type": "module",
   "main": "./src/index.js",

package/src/adapter.js

@@ -789,6 +789,31 @@ export class WorkBuddyAdapter {
     let lastDelta = '无内容'
     /** Output tokens the last usage frame reported, for the truncation log. */
     let outputTokens
+    /** The gateway's own response id, for correlating with upstream logs. */
+    let responseId
+    /**
+     * The finish chunk's diagnostics block.
+     *
+     * Not part of the harness contract — the other adapters attach their own and
+     * the session diagnostics show it verbatim, which is how a "who answered this,
+     * and what did upstream call it" question gets answered without reconstructing
+     * it from the request headers. Carries nothing the harness acts on.
+     */
+    const finishChunk = (reason) => ({
+      type: 'finish',
+      reason,
+      response: {
+        kind: 'workbuddy',
+        version: 1,
+        api: 'openai-completions',
+        provider: this.region.provider,
+        model: options.model,
+        ...(responseId === undefined ? {} : { responseId }),
+        stopReason: finishReason ?? reason.kind,
+        ...(outputTokens === undefined ? {} : { outputTokens }),
+        blocks: blocks.map((block) => ({ type: block.kind }))
+      }
+    })
 
     const textBlock = () => {
       let block = blocks.find((candidate) => candidate.kind === 'text')
@@ -838,6 +863,7 @@ export class WorkBuddyAdapter {
           }
           const choice = data.choices?.[0]
           const delta = choice?.delta
+          if (responseId === undefined && typeof data.id === 'string' && data.id.length > 0) responseId = data.id
           if (typeof choice?.finish_reason === 'string' && choice.finish_reason.length > 0) finishReason = choice.finish_reason
 
           if (typeof delta?.content === 'string' && delta.content.length > 0) {
@@ -946,31 +972,25 @@ export class WorkBuddyAdapter {
     if (!streamEnded && finishReason === undefined) {
       const detail = describeCut({ receivedBytes, startedAt, lastDataAt, lastDelta })
       this.ctx.logger.warn(`[workbuddy] ${this.region.id}: ${options.model} 的响应在 finish_reason/[DONE] 之前中断（${detail}），按传输错误上报，可自动重试`)
-      yield {
-        type: 'finish',
-        reason: {
-          kind: 'error',
-          failure: {
-            message: `${this.region.provider}: 上游没有给出结束原因就断开了响应（${detail}；可重试的传输错误）`,
-            code: 'TRANSPORT'
-          }
+      yield finishChunk({
+        kind: 'error',
+        failure: {
+          message: `${this.region.provider}: 上游没有给出结束原因就断开了响应（${detail}；可重试的传输错误）`,
+          code: 'TRANSPORT'
         }
-      }
+      })
       return
     }
     if (argsTruncated && !streamEnded) {
       const detail = describeCut({ receivedBytes, startedAt, lastDataAt, lastDelta })
       this.ctx.logger.warn(`[workbuddy] ${this.region.id}: ${options.model} 的工具调用参数在传输中被截断（${detail}），按传输错误上报，可自动重试`)
-      yield {
-        type: 'finish',
-        reason: {
-          kind: 'error',
-          failure: {
-            message: `${this.region.provider}: 工具调用的参数在传输中被截断（${detail}；可重试的传输错误）`,
-            code: 'TRANSPORT'
-          }
+      yield finishChunk({
+        kind: 'error',
+        failure: {
+          message: `${this.region.provider}: 工具调用的参数在传输中被截断（${detail}；可重试的传输错误）`,
+          code: 'TRANSPORT'
         }
-      }
+      })
       return
     }
     // Truncated arguments are checked before the empty-response rule: a step whose
@@ -978,11 +998,11 @@ export class WorkBuddyAdapter {
     // that "empty" would hide what happened.
     if (argsTruncated) {
       this.ctx.logger.warn(`[workbuddy] ${this.region.id}: ${options.model} 的工具调用参数被输出上限截断，本步按 max-tokens 上报（harness 可续跑）`)
-      yield { type: 'finish', reason: { kind: 'max-tokens' } }
+      yield finishChunk({ kind: 'max-tokens' })
       return
     }
     if (blockCount === 0) {
-      yield { type: 'finish', reason: { kind: 'error', failure: { message: '模型返回了空响应', code: 'EMPTY_RESPONSE' } } }
+      yield finishChunk({ kind: 'error', failure: { message: '模型返回了空响应', code: 'EMPTY_RESPONSE' } })
       return
     }
     const reason = finishReason === 'tool_calls' || toolOrder.length > 0
@@ -999,7 +1019,7 @@ export class WorkBuddyAdapter {
     } else if (reason.kind === 'stop' && finishReason === undefined) {
       this.ctx.logger.warn(`[workbuddy] ${this.region.id}: ${options.model} 的响应以 [DONE] 收尾但没有 finish_reason，按 stop 处理（输出 ${outputTokens ?? '未知'} tokens）`)
     }
-    yield { type: 'finish', reason }
+    yield finishChunk(reason)
   }
 }