@huai_xin/dsh-workbuddy 0.1.13 → 0.1.14

package/docs/workbuddy-protocol.md

@@ -394,7 +394,7 @@ data: [DONE]
 | INTL scoped → `500`（openresty/APISIX，HTML 错误页） | 2026-10-21 起持续；`/v3/config` 正常 ✅ |
 | `glm-5.1` 图片能力两个端点矛盾 | scoped 报 `false`、`/v3/config` 报 `true`，实测能看图（📖 参考实现据此写了覆盖白名单） |
 | 目录包含渠道不服务的模型 | 见 `11102`（§6）✅ |
-| 长上下文下"说话说一半就收尾"（`finish_reason: stop`，无工具调用） | 上游/模型行为，**不是插件问题**。实测：同一提示、同一套工具、只改前面的对话长度 —— 0k 2/2 正常、30k 1/2（一次 181 字后 `stop`）、89k 1/2；每次 finish 诊断块都标 `workbuddy-intl/deepseek-v4.1-flash`。判据：流里**没有任何 tool-call 分片**、`finish_reason` 就是 `stop`（若丢帧会是 `tool_calls` 且能看到分片）。已排除：采样（四档温度 16/16 正常）、工具 schema/数量（70 个 / 单个 / 简化 schema 9/9 正常）、提示词校验（海外版无此错误，请求体按原样转发）。复现：`node test/live/long-context-probe.mjs 2`；排查：`node test/live/toolcall-audit.mjs <会话前缀>`、`long-context-probe.mjs`、`repro-probe.mjs`。缓解只有换模型/压缩上下文/回一句"继续" —— 合法的 `stop` 不能当错误重试。 |
+| 长上下文下"说话说一半就收尾"（`finish_reason: stop`，无工具调用） | 上游/模型行为，**不是插件问题**。对外跟踪入口：[issue #1](https://github.com/2424830124/dsh-workbuddy/issues/1)（含两次真实截断的 `responseId`/`outputTokens` 与已排除项）。实测：同一提示、同一套工具、只改前面的对话长度 —— 0k 2/2 正常、30k 1/2（一次 181 字后 `stop`）、89k 1/2；每次 finish 诊断块都标 `workbuddy-intl/deepseek-v4.1-flash`。判据：流里**没有任何 tool-call 分片**、`finish_reason` 就是 `stop`（若丢帧会是 `tool_calls` 且能看到分片）。已排除：采样（五档 16/16 与 2–3/8 两个实验都无差别）、工具 schema/数量（70 个 / 单个 / 简化 schema 9/9 正常）、`prompt_cache_key` 与 `stream_options`（去掉后 1/8 vs 2/8）、提示词校验（海外版无 11128 之外的拦截，请求体按原样转发）。复现：`node test/live/long-context-probe.mjs 2`、`node test/live/repro-probe.mjs 3 deepseek-v4.1-flash 280000`；取证：`node test/live/session-tail-live.mjs <会话前缀> 8 dsh-model-picker`（读 `response.stopReason` 原话）。缓解只有换模型/压缩上下文/回一句"继续" —— 合法的 `stop` 不能当错误重试。 |
 
 ### 4.7 模型选择器里每一项元数据的来源
 
@@ -694,6 +694,22 @@ POST /v2/chat/completions {"model":"glm-4.6", …}
 
 结论：这是**行首锚定的品牌指纹**（「某 AI agent powered by &lt;品牌&gt; Harness」），不是内容审查。规避方式：把这一句改写成中性表述（本插件统一改写为 `You are an AI agent.`，两个部署都改）✅。
 
+#### 7.1.1 规则扩大：整段 DSH 提示词被拦（2026-10-23）
+
+同一天再次实测：**完整的 DSH 系统提示词（5.7k 字符）整段被拦**，而短提示词通过。二分结果：
+
+| 送什么 | 结果 |
+| --- | --- |
+| 完整 DSH 提示词（只做 7.1 的开头改写） | **拦（11128）** |
+| 同一份，只去掉最后那段 Web GUI 开发指引 | 过 ✅ |
+| 只送那一段（1002 字符） | 过 ✅ |
+| 那一段的每一句单独送 | 全都过 ✅ |
+| 中性提示词填充到 5.7k / 10k 字符 | 过 ✅（不是长度） |
+
+所以**不是一个词、也不是长度**，而是「提示词整体 + 那段开发指引」的组合命中。那段内容是 `pnpm run dev:web` / `apps/web` / HMR / "do not start a replacement server" —— **给改 harness 自身的人看的**，对一次聊天补全毫无用处，所以插件直接**整行删掉**，并把 `DeepSeek Harness` 统一改写成 `this harness`（顺序很重要：先删行再改名，否则模式匹配不到原文）。
+
+> 注意：这条规则**会继续扩大**。再遇到 11128 时，用 `node test/live/cn-prompt-fingerprint.mjs` 二分定位新命中的段落，再决定删还是改，别猜。
+
 ### 7.2 其它渠道相关事实
 
 - `X-Conversation-ID` 可复用；一旦被判定为异常渠道，**换新会话标识无效**（实测：换标识 + 切备用主机仍被拒），但换一个**合法 system 提示词**立刻恢复 ✅。
@@ -930,6 +946,8 @@ provider 与全部 HTTP 路由都没注册，设置面板只剩一个 `HTTP 404`
 | `test/live/long-context-probe.mjs [次数] [模型]` | 只改上下文长度，看提前收尾率（可复现的对照实验） |
 | `test/live/context-size-probe.mjs [字符数…]` | 填充上下文实际值多少 token（网关 `inputTokens` 为准） |
 | `test/live/thinking-field-probe.mjs [次数] [模型] [部署]` | 带/不带 `thinking` 字段时思考量对比（档位才是开关） |
+| `test/live/dsh-prompt-probe.mjs [次数] [字符数…]` | **用会话里存的 DSH 原版系统提示词** + 真实 70 工具集跑长上下文，看会不会调用工具（2026-10-23：0k/90k/280k 各 3 次，9/9 都调用 `read`） |
+| `test/live/system-prompt-probe.mjs [次数]` | 判定上游是否注入/覆盖 system：两个代号实验 + 不给 system 时它自认是谁（答「DeepSeek」= 无厂商注入）+ 语言服从性 |
 | `test/live/request-structure.mjs` / `test/live/free-models.mjs` | 各厂商请求结构、免费档清单的逐字段试探 |
 | `test/live/verify-policy.mjs` | 实时目录扣掉台账里 `dead` 的判定后，两版的条目数对照 |
 | **契约与 UI 参考（写 UI 插件用）** | |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@huai_xin/dsh-workbuddy",
-  "version": "0.1.13",
+  "version": "0.1.14",
   "description": "WorkBuddy model provider for DeepSeek Harness (international + China deployments)",
   "type": "module",
   "main": "./src/index.js",

package/src/adapter.js

@@ -607,23 +607,34 @@ export class WorkBuddyAdapter {
   }
 
   /**
-   * Neutralise the one system-prompt fingerprint the China gateway blocks.
+   * Neutralise the system-prompt fingerprints the China gateway blocks.
    *
-   * Verified 2026-10-21 against `copilot.tencent.com`: a system message whose
-   * text *begins* with `You are an AI agent powered by DeepSeek Harness`
-   * (case-insensitive, trailing period optional) is answered with
-   * `code 11128 Illegal API invocation from an unapproved channel`. The bare
-   * phrase, a leading word, and the same sentence with another noun all pass,
-   * so the rule is an anchored brand fingerprint rather than a content filter.
-   * Rewriting that opening keeps every other instruction intact.
+   * Verified 2026-10-21 against `copilot.tencent.com`: a system message whose text
+   * *begins* with `You are an AI agent powered by DeepSeek Harness` is answered with
+   * `code 11128 Illegal API invocation from an unapproved channel`.
    *
-   * Applied to both deployments: the international gateway accepts the
-   * original wording, but one prompt shape for both routes is simpler to
-   * reason about and cannot regress when the rule spreads.
+   * Verified again 2026-10-23: the rule now catches more of the harness prompt. The
+   * whole 5.7k-character prompt is rejected while a short one passes, and bisecting it
+   * shows the harness's Web-GUI development guidance at the end is part of what
+   * trips the check (dropping that paragraph unblocks the same prompt). That guidance
+   * is instructions for a coding session about the harness's own web shell — useless
+   * to a chat completion — so it is dropped for this route rather than rewritten.
+   * Brand mentions are generalised for the same reason.
+   *
+   * Applied to both deployments: the international gateway accepts the original
+   * wording, but one prompt shape for both routes is simpler to reason about.
    */
   sanitizeSystem(text) {
     if (typeof text !== 'string') return text
-    return text.replace(/^[ \t\r\n]*you are an ai agent powered by deepseek harness\.?/i, 'You are an AI agent.')
+    return text
+      .replace(/^[ \t\r\n]*you are an ai agent powered by deepseek harness\.?/i, 'You are an AI agent.')
+      // Drop the Web-GUI development paragraphs: `pnpm run dev:web`, `apps/web`,
+      // the HMR receiver and the "do not start a replacement server" advice are all
+      // for editing the harness itself, and this route never needs them. This runs
+      // before the brand rename below, or the pattern would no longer match.
+      .replace(/[^\n]*(?:pnpm run dev:web|apps\/web|client-plugin HMR|DeepSeek Harness Web GUI|replacement server)[^\n]*\n?/gi, '')
+      .replace(/DeepSeek Harness/g, 'this harness')
+      .replace(/\n{3,}/g, '\n\n')
   }
 
   buildBody(options, model, entry, imageUrls) {