Merge commit '7baf2c33efb98eeea690c5ac58579c95dc52edd1' into feat/subagent-report-semantics

packages/support/llm-mock-server/README.i18n.yaml

@@ -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 packages/support/llm-mock-server/README.md
-README.md: a535c086bf688ad48b1a3bb19c7b81da21cbad92
-README.zh.md: d814d8815b38bb34bd0d871d552e6f3ec75e042a
+README.md: 919bbc923110459e9ee4fc26f6db7e8b35ab1abb
+README.zh.md: d60c6b2395c14c0cf690c2a94e902eb1cfeffa94

packages/support/llm-mock-server/README.md

@@ -23,7 +23,7 @@ Point the shipping DeepSeek adapter at the server; it appends `/chat/completions
 ```sh
 DEEPSEEK_BASE_URL=http://127.0.0.1:8000/v1 \
 DEEPSEEK_API_KEY=mock-key \
-pnpm run demo:headless "test provider recovery"
+pnpm dsh --profile headless "test provider recovery"
 ```
 
 The repository script writes JSONL to stdout: a `ready` record carries the `/v1` base URL and random seed, followed by request/result records that name both the scripted behavior and the concrete selected behavior. The private support package exposes no installable binary.

packages/support/llm-mock-server/README.zh.md

@@ -23,7 +23,7 @@ pnpm run mock:llm -- \
 ```sh
 DEEPSEEK_BASE_URL=http://127.0.0.1:8000/v1 \
 DEEPSEEK_API_KEY=mock-key \
-pnpm run demo:headless "test provider recovery"
+pnpm dsh --profile headless "test provider recovery"
 ```
 
 仓库脚本将 JSONL 写入 stdout：`ready` 记录携带以 `/v1` 结尾的基础 URL 和随机种子，后续请求/结果记录同时命名脚本行为和实际选中的具体行为。这个私有支持包不公开可安装的二进制命令。

packages/support/llm-replay/README.i18n.yaml

@@ -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 packages/support/llm-replay/README.md
-README.md: ae7cb5414a28bcf33f9878f6f02220861df9a0d5
-README.zh.md: 2acc0ff8e8c011126452ba3458aaeb0800d9d8f3
+README.md: 6119407c06cf734166300f5f70a3fe65d026d08d
+README.zh.md: 75d74b654a9a53e7ada5cc854e275eadcbe01284

packages/support/llm-replay/README.md

@@ -29,7 +29,7 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s
 | `file` | string | `$DSH_SNAPSHOT_FILE` | Path to the primary (parent) `session.jsonl` fixture. Required (config or env). |
 | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | Optional `ReplayOverrideDoc` sidecar for the primary session: a bare `ReplayEntry[]` replaces its derived script, while `{ patches }` augments it by call index. |
 | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES` (path-delimited) | Recorded subagent child-session logs for a nested scenario; empty for a single-session scenario. |
-| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Each provider may set `retryPolicy`, and each model may publish `contextWindow`; configured routes dispatch through the replay adapter and never perform provider I/O. |
+| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Each provider may set `retryPolicy`, and each model may publish `contextWindow` and an `inputModalities` array containing only `text` and `image`; invalid modalities fail during plugin loading. Configured routes dispatch through the replay adapter and never perform provider I/O. |
 | `paceMs` | number | — (burst) | Optional per-chunk delay in ms so downstream transports (e.g. the web SSE mux observed by a real browser) see genuinely incremental delivery. A realism knob only — tests must not depend on it for correctness. Non-negative integer; abort during a pace wait cancels the stream promptly. |
 
 ```yaml

packages/support/llm-replay/README.zh.md

@@ -29,7 +29,7 @@ fixture 就是持久化的会话日志（`<scenario>/session.jsonl`）。其 `as
 | `file` | string | `$DSH_SNAPSHOT_FILE` | 主（父）`session.jsonl` fixture 的路径。必需（配置或 env）。 |
 | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | 主会话的可选 `ReplayOverrideDoc` 伴随文件：裸 `ReplayEntry[]` 替换其派生脚本，`{ patches }` 则按调用索引增补该脚本。 |
 | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES`（以路径分隔符分隔） | 嵌套场景中已记录的 subagent 子会话日志；单会话场景为空。 |
-| `providers` | `ReplayProviderConfig[]` | 无 | 可选的仅回放提供方和模型目录。每个提供方可以设置 `retryPolicy`，每个模型可以发布 `contextWindow`；已配置路由通过回放适配器分派，绝不执行提供方 I/O。 |
+| `providers` | `ReplayProviderConfig[]` | 无 | 可选的仅回放提供方和模型目录。每个提供方可以设置 `retryPolicy`，每个模型可以发布 `contextWindow` 和仅包含 `text`、`image` 的 `inputModalities` 数组；模态配置无效时，插件加载会失败。已配置路由通过回放适配器分派，绝不执行提供方 I/O。 |
 | `paceMs` | number | 无（突发） | 可选的每分片毫秒延迟，使下游传输（例如真实浏览器观察到的 Web SSE（Server-Sent Events）多路复用器）看到真正的增量传递。它只是仿真开关，测试不得依赖它保证正确性。值必须是非负整数；pace 等待期间中止会迅速取消流。 |
 
 ```yaml

packages/support/llm-replay/src/index.ts

@@ -19,6 +19,7 @@ import type {
   LlmModelInfo,
   LlmProviderInfo,
   LlmResolvedModelInfo,
+  ModelModality,
   ResolvedRetryPolicy,
   RetryPolicyConfig,
   StreamChunk,
@@ -51,6 +52,8 @@ export interface ReplayModelConfig {
   description?: string
   /** Optional positive integer context capacity published by the replay adapter. */
   contextWindow?: number
+  /** Optional declared input modalities, so a scenario can exercise capability gates (e.g. image-capable `read_image`). */
+  inputModalities?: readonly ModelModality[]
   /**
    * Optional per-request output cap the replay route materializes when callers
    * omit one, so replay reconstructs the request header a live catalog produced.
@@ -581,6 +584,7 @@ class ReplayAdapter extends LlmAdapter {
       id: model.id,
       name: model.name ?? model.id,
       ...model.description === undefined ? {} : { description: model.description },
+      ...model.inputModalities === undefined ? {} : { inputModalities: [...model.inputModalities] },
     })))
   }
 
@@ -594,6 +598,9 @@ class ReplayAdapter extends LlmAdapter {
       id: model,
       name: configuredModel?.name ?? model,
       ...configuredModel?.description === undefined ? {} : { description: configuredModel.description },
+      ...configuredModel?.inputModalities === undefined
+        ? {}
+        : { inputModalities: [...configuredModel.inputModalities] },
       ...configuredModel?.contextWindow === undefined
         ? {}
         : { context: { contextWindow: configuredModel.contextWindow } },
@@ -783,11 +790,28 @@ export interface Config {
   paceMs?: number
 }
 
+function validateConfiguredModalities(providers: ReplayProviderConfig[] | undefined): void {
+  for (const provider of providers ?? []) {
+    for (const model of provider.models ?? []) {
+      const modalities: unknown = model.inputModalities
+      if (modalities === undefined) continue
+      if (!Array.isArray(modalities)
+        || !modalities.every((modality: unknown) => modality === 'text' || modality === 'image')) {
+        throw new Error(
+          `llm-replay: provider "${provider.id}" model "${model.id}" inputModalities `
+          + 'must be an array containing only "text" and "image"',
+        )
+      }
+    }
+  }
+}
+
 export function apply(ctx: Context, config: Config = {}): void {
   const file = config.file ?? process.env.DSH_SNAPSHOT_FILE
   if (file === undefined || file.length === 0) {
     throw new Error('llm-replay: a fixture path is required (Config.file or $DSH_SNAPSHOT_FILE)')
   }
+  validateConfiguredModalities(config.providers)
   const overrideFile = config.overrideFile ?? process.env.DSH_SNAPSHOT_OVERRIDE
   const childEnv = process.env.DSH_SNAPSHOT_CHILD_FILES
   const childFiles = config.childFiles

packages/support/llm-replay/tests/llm-replay.spec.ts

@@ -7,6 +7,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session'
 import { CompactionId } from '@deepseek-ai/dsh-compact'
 import LlmService, { CallId, createUserMessage, GenerateOptions, LlmAdapter, StreamChunk } from '@deepseek-ai/dsh-llm'
 import {
+  type Config,
   type ReplayEntry,
   type SessionScript,
   apply,
@@ -595,6 +596,7 @@ describe('installLlmReplay (through the real LlmService)', () => {
             {
               id: 'flash',
               contextWindow: 128_000,
+              inputModalities: ['text', 'image'],
               defaultMaxTokens: 64_000,
               reasoningEfforts: ['off', 'max'],
               defaultReasoningEffort: 'max',
@@ -611,18 +613,20 @@ describe('installLlmReplay (through the real LlmService)', () => {
       { id: 'empty', name: 'empty' },
     ])
     await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
-      { provider: 'deepseek', id: 'flash', name: 'flash' },
+      { provider: 'deepseek', id: 'flash', name: 'flash', inputModalities: ['text', 'image'] },
       { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' },
     ])
     await expect(ctx.llm.listModels('empty')).resolves.toEqual([])
     await expect(ctx.llm.resolveModelInfo('deepseek', 'flash')).resolves.toMatchObject({
       context: { contextWindow: 128_000 },
+      inputModalities: ['text', 'image'],
       defaultMaxTokens: 64_000,
       reasoning: {
         efforts: [{ id: 'off', name: 'off' }, { id: 'max', name: 'max' }],
         defaultEffort: 'max',
       },
     })
+    await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('inputModalities')
     await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('context')
     // Efforts without a configured default preserve the provider's own default.
     await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.toMatchObject({
@@ -1111,11 +1115,31 @@ describe('apply (the plugin entry)', () => {
     writeFileSync(file, sessionJsonl(TEXT_CHUNKS.map((c, i) => chunkEvent(i + 1, 1, 1, c))), 'utf8')
     const ctx = new Context()
     await ctx.plugin(LlmService)
-    apply(ctx, { file, providers: [{ id: 'm', models: [{ id: 'm' }] }], paceMs: 1 })
-    expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }])
+    apply(ctx, {
+      file,
+      providers: [
+        { id: 'm', models: [{ id: 'm', inputModalities: ['image'] }, { id: 'text' }] },
+        { id: 'empty' },
+      ],
+      paceMs: 1,
+    })
+    expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }, { id: 'empty', name: 'empty' }])
+    await expect(ctx.llm.resolveModelInfo('m', 'm')).resolves.toMatchObject({ inputModalities: ['image'] })
     expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS)
   })
 
+  it.each([
+    ['a string', 'image'],
+    ['an unknown modality', ['audio']],
+  ])('rejects inputModalities configured as %s during load', (_case, inputModalities) => {
+    const ctx = new Context()
+    const providers = [{ id: 'm', models: [{ id: 'm', inputModalities }] }] as unknown as
+      NonNullable<Config['providers']>
+    expect(() => { apply(ctx, { file, providers }) }).toThrow(
+      'llm-replay: provider "m" model "m" inputModalities must be an array containing only "text" and "image"',
+    )
+  })
+
   it('falls back to $DSH_SNAPSHOT_FILE / $DSH_SNAPSHOT_OVERRIDE when config is empty', async () => {
     writeFileSync(file, sessionJsonl([]), 'utf8')
     const overrideFile = join(dir, 'replay.override.json')