feat(acp): bridge durable image prompts and replies

packages/support/acp-snapshot/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/acp-snapshot/README.md
-README.md: 06f1cb67cfcd954254db480ea696d10d81b37438
-README.zh.md: c4a5643f8c5d7e5b62a160cd32e5969187d34046
+README.md: 31f4ec0caeb995a10202d4a452ee7e433749762f
+README.zh.md: f97bac11de690fe980595c77375aead47b3b0214

packages/support/acp-snapshot/README.md

@@ -61,7 +61,7 @@ Every scenario compares `stdout.expected.jsonl` with cwd-rooted separators canon
 
 The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log expected outputs, and owned prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md).
 
-Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the JSON-RPC and Web snapshot recorders. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.
+Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the JSON-RPC and Web snapshot recorders. Input scripts cover initialization, fresh-session creation, shorthand text prompts, exact structured ACP prompt blocks, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.
 
 ## Model Experience
 

packages/support/acp-snapshot/README.zh.md

@@ -61,7 +61,7 @@ defineAcpSnapshotSuite({
 
 示例还发布 `cordis.snapshot.yml` 回放 overlay，位于 `cordis.yml` 旁边（bin 在 `DSH_SNAPSHOT=replay` 下交换它们，见[单源回放配置 Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)）；回放 fixture 由 [`dsh-llm-replay`](../llm-replay/README.md) 提供，该包通过对子级设置的 `DSH_SNAPSHOT_*` env var 指向它。`pnpm run test:snapshot:record` 调用实时 LLM，并重写已记录场景的模型 fixture；`pnpm run test:snapshot:refresh` 保持无密钥，运行回放 overlay，并从已提交模型脚本重写 stdout、可比较会话日志预期输出，以及各 pin 自有的提示词与工具 schema sidecar。Fixture 角色、录制/回放/刷新语义和场景表字段记录在 `Scenario` 以及[快照 Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) 中。
 
-约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 JSON-RPC 和 Web 快照录制器消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once` 等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。
+约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 JSON-RPC 和 Web 快照录制器消费。输入脚本覆盖初始化、新建会话、文本提示简写、精确结构化 ACP 提示词块、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once` 等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。
 
 ## 模型体验
 

packages/support/acp-snapshot/src/harness.ts

@@ -25,6 +25,7 @@ import { vi } from 'vitest'
 import {
   ClientSideConnection,
   PROTOCOL_VERSION,
+  type ContentBlock as AcpContentBlock,
   type RequestPermissionRequest,
   type RequestPermissionResponse,
   type SessionNotification,
@@ -69,6 +70,7 @@ export type InputStep =
   | { op: 'newSession' }
   | { op: 'newSessionExpectError'; additionalDirectories?: string[] }
   | { op: 'prompt'; text: string }
+  | { op: 'promptContent'; content: AcpContentBlock[] }
   | { op: 'promptAndWaitForAgentMessage'; text: string; waitForText: string }
   | { op: 'promptExpectError'; text: string }
   | {
@@ -422,6 +424,12 @@ async function runStep(
       await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
       return
     }
+    case 'promptContent': {
+      const sessionId = getSessionId()
+      if (sessionId === undefined) throw new Error('snapshot-harness: promptContent before newSession')
+      await client.prompt({ sessionId, prompt: step.content })
+      return
+    }
     case 'promptAndWaitForAgentMessage': {
       const sessionId = getSessionId()
       if (sessionId === undefined) throw new Error('snapshot-harness: promptAndWaitForAgentMessage before newSession')

packages/support/acp-snapshot/tests/harness.spec.ts

@@ -407,6 +407,24 @@ describe('runScenario', () => {
     expect((JSON.parse(sessionLine) as { cwd?: string }).cwd).toBe(result.cwd)
   })
 
+  it('drives a structured prompt-content step without flattening its wire blocks', { timeout: 20_000 }, async () => {
+    const { fixtureFile } = await scenario({})
+    const result = await runScenario(
+      {
+        steps: [...boot, {
+          op: 'promptContent',
+          content: [
+            { type: 'text', text: 'before' },
+            { type: 'image', data: 'AQ==', mimeType: 'image/png' },
+            { type: 'text', text: 'after' },
+          ],
+        }],
+      },
+      { agent: AGENT, mode: 'replay', fixtureFile },
+    )
+    expect(result.rawStdout).toContain('"stopReason":"end_turn"')
+  })
+
   it('forwards override/child fixture paths into the child env and captures stderr', { timeout: 20_000 }, async () => {
     const { dir, fixtureFile } = await scenario({ echoEnv: true, stderrNote: 'fake bin booted' })
     const childFiles = [join(dir, 'session.1.jsonl'), join(dir, 'session.2.jsonl')]
@@ -1097,6 +1115,7 @@ describe('runScenario', () => {
 
   it.each([
     [{ op: 'prompt', text: 'x' }, /prompt before newSession/],
+    [{ op: 'promptContent', content: [{ type: 'text', text: 'x' }] }, /promptContent before newSession/],
     [{ op: 'promptAndWaitForAgentMessage', text: 'x', waitForText: 'later' }, /promptAndWaitForAgentMessage before newSession/],
     [{ op: 'promptExpectError', text: 'x' }, /promptExpectError before newSession/],
     [{ op: 'promptAndCancel', text: 'x' }, /promptAndCancel before newSession/],