test(sdk): leave model surface to packaged snapshot

2026-08-29 04:26:38 +00:00 · 2026-08-25 12:21:50 +08:00
parent 43f0f07f9b
commit d0e8f5f9c4
7 changed files with 10 additions and 21 deletions
@@ -2,5 +2,5 @@
 # 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 .agents/notes/implemented/architecture/2026-08-24-standalone-sdk-minimal-profile.md
-2026-08-24-standalone-sdk-minimal-profile.md: 9cdc92248326f115cb77444531cee420507ff871
-2026-08-24-standalone-sdk-minimal-profile.zh.md: a4fa2b3d4c0941447e84347f4999c15951ad76be
+2026-08-24-standalone-sdk-minimal-profile.md: 9c8afbaaf1a8e522af119c1d42ca5ad714eaa879
+2026-08-24-standalone-sdk-minimal-profile.zh.md: b1cd2a348c4b77f197e30a658c13691b2f35d26e
@@ -40,7 +40,7 @@ It also supersedes the minimal-overlay realization in [Python SDK runtime throug

 ## Verification

-The bundle test pins the exact row and dependency roster. Profile-template and config-dump tests pin the one-bundle manifest, startup-only lifecycle, absence of `dsh-base`, and absence of module HMR. The keyless Python example test boots the real `dsh --profile sdk-minimal` process and asserts the generated manifest, complete system prompt, and two advertised tools. The installed-wheel minimal scenario exercises persistent shell state, editor effects, JSONL persistence, and the committed model-visible snapshot through the packaged executable.
+The bundle test pins the exact row and dependency roster. Profile-template and config-dump tests pin the one-bundle manifest, startup-only lifecycle, absence of `dsh-base`, and absence of module HMR. The keyless source test boots the real `dsh --profile sdk-minimal` process, completes a turn, and asserts the generated manifest. The installed-wheel minimal scenario owns the complete system prompt and two advertised tools in its committed model-visible snapshot while exercising persistent shell state, editor effects, and JSONL persistence through the packaged executable.

 ## Alternatives considered

@@ -40,7 +40,7 @@ Python 运行时继续打包 `dsh-web-app` 与前端产物。`dsh web` 会从已

 ## 验证

-组合包测试固定确切配置项与依赖清单。Profile 模板与配置 dump 测试固定单组合包 manifest、仅启动时生命周期、`dsh-base` 缺席与模块 HMR 缺席。Keyless Python 示例测试启动真实 `dsh --profile sdk-minimal` 进程，并断言生成的 manifest、完整系统提示词与两个对外公布的工具。Installed-wheel 极简场景通过打包可执行程序验证持久 shell 状态、editor 文件效果、JSONL 持久化与已提交的模型可见快照。
+组合包测试固定确切配置项与依赖清单。Profile 模板与配置 dump 测试固定单组合包 manifest、仅启动时生命周期、`dsh-base` 缺席与模块 HMR 缺席。Keyless 源码测试启动真实 `dsh --profile sdk-minimal` 进程、完成一个回合并断言生成的 manifest。Installed-wheel 极简场景通过已提交的模型可见快照固定完整系统提示词和两个对外公布的工具，同时经由打包可执行程序验证持久 shell 状态、editor 文件效果与 JSONL 持久化。

 ## 考虑过的替代方案

@@ -2,5 +2,5 @@
 # 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 .agents/notes/implemented/feature/2026-08-11-minimal-profiles-bare-two-tool-runtime.md
-2026-08-11-minimal-profiles-bare-two-tool-runtime.md: d201a7557136822d82950466e39ae0efd27a5888
-2026-08-11-minimal-profiles-bare-two-tool-runtime.zh.md: b56f5cea26bb9305ad75a10d153b64f11f841e96
+2026-08-11-minimal-profiles-bare-two-tool-runtime.md: ffe8e799e1ba5a71939e3a17d484afd209b4014f
+2026-08-11-minimal-profiles-bare-two-tool-runtime.zh.md: 587ba696382575244a75f23fe69c14252caf7544
@@ -22,7 +22,7 @@ The standalone [`@deepseek-ai/dsh-sdk-minimal` bundle](../../../../packages/bund

 The Web replay boots the complete Web host, creates the agent through the preset service, and asserts that the scoped filesystem is bare, no scoped compaction service exists, no system-prompt-owned runtime-context message was appended, and the assembled request contains exactly the fixed prompt and two tools. It then executes persistent Bash and the editor against the real scoped services.

-The SDK keyless process test boots real `dsh --profile sdk-minimal`, injects an environment-selected prompt, and asserts the generated one-bundle manifest, assembled prompt, exact two-tool catalog, and absence of every system-prompt-owned runtime-context message. Python SDK bundled-runtime coverage initializes the standalone profile through each available packaged carrier with environment-selected model, model capacity, and prompt values, then executes the selected persistent shell and editor. Cordis validation checks that both configurations resolve their declared plugins and configuration fields.
+The SDK keyless source test boots real `dsh --profile sdk-minimal`, completes a turn with an environment-selected prompt, and asserts the generated one-bundle manifest. The Python SDK bundled-runtime snapshot owns the assembled prompt, exact two-tool catalog, and absence of every system-prompt-owned runtime-context message. Packaged-runtime coverage initializes the standalone profile through each available carrier with environment-selected model, model capacity, and prompt values, then executes the selected persistent shell and editor. Cordis validation checks that both configurations resolve their declared plugins and configuration fields.

 ## Alternatives considered

@@ -22,7 +22,7 @@ Web `minimal` preset 与独立 JSON-RPC minimal 组合对外提供持久 `bash`

 Web 回放会启动完整 Web 宿主，通过 preset 服务创建 agent，并断言作用域文件系统为裸后端、不存在作用域压缩服务、没有追加 system-prompt 拥有的 runtime-context 消息，而且组装请求只包含固定提示词与两个工具。随后，它通过真实作用域服务执行持久 Bash 和编辑器。

-SDK keyless 进程测试启动真实 `dsh --profile sdk-minimal`，注入由环境选择的提示词，并断言生成的单组合包 manifest、组装提示词、精确双工具目录，以及不存在任何 system-prompt 拥有的 runtime-context 消息。Python SDK 内置运行时覆盖会通过每种可用的打包载体，使用环境选择的模型、模型容量和提示词值初始化独立 profile，然后执行所选持久 shell 与 editor。Cordis 校验会检查两份配置能否解析声明的插件和配置字段。
+SDK keyless 源码测试启动真实 `dsh --profile sdk-minimal`，使用环境选择的提示词完成一个回合，并断言生成的单组合包 manifest。Python SDK 打包运行时快照固定组装提示词、精确双工具目录，并固定不存在任何 system-prompt 所拥有的 runtime-context 消息。打包运行时覆盖会通过每种可用载体，使用环境选择的模型、模型容量和提示词值初始化独立 profile，然后执行所选持久 shell 与 editor。Cordis 校验会检查两份配置能否解析声明的插件和配置字段。

 ## 考虑过的替代方案

@@ -169,15 +169,11 @@ describe('Python SDK dsh profile keyless smoke', () => {
    }
  }, 40_000)

-  it('boots the standalone minimal profile with its exact model-facing roster', async () => {
+  it('boots the standalone minimal profile through its generated manifest', async () => {
    const root = await mkdtemp(join(tmpdir(), 'dsh-python-sdk-minimal-'))
-    const modelRequests: Record<string, unknown>[] = []
    const modelServer = createServer((request, response) => {
-      let body = ''
-      request.setEncoding('utf8')
-      request.on('data', (chunk: string) => { body += chunk })
+      request.resume()
      request.on('end', () => {
-        modelRequests.push(JSON.parse(body) as Record<string, unknown>)
        response.writeHead(200, { 'content-type': 'text/event-stream' })
        response.write('data: {"choices":[{"delta":{"role":"assistant","content":null}}]}\n\n')
        response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n')
@@ -237,13 +233,6 @@ describe('Python SDK dsh profile keyless smoke', () => {
        return params?.sessionId === 'minimal' && event?.type === 'turn/end'
      }, () => stderr)

-      const request = modelRequests[0] as {
-        messages?: Array<{ role?: string; content?: unknown }>
-        tools?: Array<{ function?: { name?: string } }>
-      }
-      expect(request.messages?.[0]).toMatchObject({ role: 'system', content: 'Minimal allowlist prompt.' })
-      const shellTool = process.platform === 'win32' ? 'pwsh' : 'bash'
-      expect(request.tools?.map(tool => tool.function?.name).sort()).toEqual([shellTool, 'str_replace_editor'].sort())
      const profile = JSON.parse(
        await readFile(join(root, '.dsh', 'profiles', 'sdk-minimal', 'package.json'), 'utf8'),
      ) as { dsh?: { profile?: { bundles?: string[]; patchReload?: string } } }