@deepseek-ai/dsh-llm-mock-server 0.2.0-rc.2 → 0.2.1-alpha.2

package/README.i18n.yaml

@@ -9,8 +9,8 @@
   en: bf31466ee0c85b69
   zh: 77ac4edc39b8fc19
 /deepseek-ai-dsh-llm-mock-server/summary:
-  en: a9e09bb7e96cc08a
-  zh: a317c2318fda0b60
+  en: 1cfa2887c40b3229
+  zh: 14963d3d17f980f9
 /deepseek-ai-dsh-llm-mock-server/table-of-contents:
   en: d152484eb41ac6b4
   zh: 09388d293f9be9cb
@@ -39,8 +39,8 @@
   en: 393a6ca8f1eb021e
   zh: d71bc369d550b527
 /deepseek-ai-dsh-llm-mock-server/understand-the-implementation/source-map:
-  en: ac683a0f364b53e4
-  zh: 3b4c782b56e024db
+  en: 893c33eff2af34d1
+  zh: 44eed7b3810023a9
 /deepseek-ai-dsh-llm-mock-server/understand-the-implementation/wire-flow:
   en: 34abeb79b2e0cdcd
   zh: d175185e4f1cc190

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-This package gives tests and demos a scriptable Messages-compatible HTTP/SSE endpoint, so they can exercise model-provider failures and successes without a provider key. Each accepted `/v1/messages` request consumes the next scripted behavior, including resets, stalls, malformed chunks, rate limits, server errors, completions, and tool calls. Test authors can run it with `pnpm run mock:llm` or call `startMockLlmServer`, which returns captured requests for assertions. Seeded `random` behavior supports reproducible mixed-failure stress runs.
+This package gives tests and demos a scriptable Messages-compatible HTTP/SSE endpoint with named events for native SDK consumers, so they can exercise model-provider failures and successes without a provider key. Each accepted `/v1/messages` request consumes the next scripted behavior, including resets, stalls, malformed chunks, rate limits, server errors, completions, and tool calls. Test authors can run it with `pnpm run mock:llm` or call `startMockLlmServer`, which returns captured requests for assertions. Seeded `random` behavior supports reproducible mixed-failure stress runs.
 
 ## Table of Contents
 
@@ -117,7 +117,6 @@ The server is built on one rule: each accepted Messages request consumes exactly
 | [`src/index.ts`](src/index.ts) | `startMockLlmServer`: listener, behavior table, seeded randomness, telemetry, captured request records |
 | [`src/cli.ts`](src/cli.ts) | `--sequence` and timing/content option parsing, JSONL stdout telemetry |
 | [`src/bin.ts`](src/bin.ts) | The `pnpm run mock:llm` source entry |
-| — | No runtime invariant companion is published; this standalone test server owns no Cordis event stream or shared data; its wire behavior and lifecycle are exercised through direct HTTP and assembled-loop tests. |
 
 ### Wire flow
 

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-library"
 
 ## 概述
 
-本包为测试与演示提供可编脚本的 Messages 兼容 HTTP／SSE（Server-Sent Events）端点，使其无需提供方密钥即可检验模型提供方的失败与成功。每个已接受的 `/v1/messages` 请求依次消费下一个脚本行为，包括重置、停滞、畸形分片、限流、服务器错误、补全与工具调用。测试作者可以通过 `pnpm run mock:llm` 运行服务器，也可以调用 `startMockLlmServer`，后者会返回捕获的请求供断言使用。带种子的 `random` 行为支持可复现的混合故障压力运行。
+本包为测试与演示提供可编脚本的 Messages 兼容 HTTP／SSE（Server-Sent Events）端点，并为原生 SDK 消费方发送具名事件，使其无需提供方密钥即可检验模型提供方的失败与成功。每个已接受的 `/v1/messages` 请求依次消费下一个脚本行为，包括重置、停滞、畸形分片、限流、服务器错误、补全与工具调用。测试作者可以通过 `pnpm run mock:llm` 运行服务器，也可以调用 `startMockLlmServer`，后者会返回捕获的请求供断言使用。带种子的 `random` 行为支持可复现的混合故障压力运行。
 
 ## 目录
 
@@ -117,7 +117,6 @@ CLI 公开 `--success-text`、`--partial-text`、`--reasoning-text`、`--chunk-s
 | [`src/index.ts`](src/index.ts) | `startMockLlmServer`：listener、行为表、种子随机、遥测（telemetry）、捕获的请求记录 |
 | [`src/cli.ts`](src/cli.ts) | `--sequence` 与时序/内容选项解析、JSONL stdout 遥测 |
 | [`src/bin.ts`](src/bin.ts) | `pnpm run mock:llm` 源入口 |
-| — | 不发布运行时不变式伴生组件；该独立测试服务器不拥有 Cordis 事件流或共享数据；其协议行为和生命周期通过直接 HTTP 测试及组装后的循环测试进行检验。 |
 
 ### 协议流程
 

package/lib/index.js

@@ -149,7 +149,8 @@ function openSse(response, contentType = "text/event-stream; charset=utf-8") {
 	response.flushHeaders();
 }
 function writeSse(record, response, payload) {
-	response.write(`data: ${typeof payload === "string" ? payload : JSON.stringify(payload)}\n\n`);
+	const event = typeof payload === "string" ? "" : `event: ${payload.type}\n`;
+	response.write(`${event}data: ${typeof payload === "string" ? payload : JSON.stringify(payload)}\n\n`);
 	record.chunksSent += 1;
 }
 function writeDone(record, response) {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-llm-mock-server",
   "description": "Scriptable Messages HTTP/SSE fault server for LLM recovery tests",
-  "version": "0.2.0-rc.2",
+  "version": "0.2.1-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -27,9 +27,9 @@
   ],
   "license": "MIT",
   "peerDependencies": {
-    "@deepseek-ai/cordis": "~4.0.4"
+    "@deepseek-ai/cordis": "~4.0.5-alpha.1"
   },
   "devDependencies": {
-    "@deepseek-ai/cordis": "~4.0.4"
+    "@deepseek-ai/cordis": "~4.0.5-alpha.1"
   }
 }