diff --git a/apps/cli/tests/profiles/acp/tests/stdout.expected.e2e.ts b/apps/cli/tests/profiles/acp/tests/stdout.expected.e2e.ts
new file mode 100644
index 0000000000..9468f874cc
--- /dev/null
+++ b/apps/cli/tests/profiles/acp/tests/stdout.expected.e2e.ts
@@ -0,0 +1,102 @@
+/** Account catalog diagnostics preserve the shipped ACP profile's JSON-RPC stream. */
+import { once } from 'node:events'
+import { mkdir, mkdtemp, writeFile } from 'node:fs/promises'
+import { createServer } from 'node:http'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
+import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } from '@deepseek-ai/dsh-session-snapshot'
+import { expect, it } from 'vitest'
+import { cleanupAcpExampleTest } from './cleanup.ts'
+
+it('keeps account model-listing diagnostics on stderr during API-key session creation', async () => {
+  const cwd = await mkdtemp(join(tmpdir(), 'dsh-acp-stdout-'))
+  const token = 'acp-catalog-fixture-token'
+  const requests: Array<{ method: string | undefined; path: string | undefined; token: string | string[] | undefined }> = []
+  const server = createServer((request, response) => {
+    requests.push({ method: request.method, path: request.url, token: request.headers['x-dsh-auth-token'] })
+    request.resume()
+    if (request.method !== 'GET' || request.url !== '/models') {
+      response.writeHead(500).end('unexpected request')
+      return
+    }
+    response.writeHead(200, { 'content-type': 'application/json' }).end(JSON.stringify({
+      data: [
+        {
+          id: 'deepseek-flash', name: 'Account fixture model', input_modalities: ['text'], output_modalities: ['text'],
+          context_window: 1_048_576, max_output_tokens: 393_216, api_capabilities: { anthropic_messages: {} },
+        },
+        { id: 'deepseek-v4-pro' },
+      ],
+    }))
+  })
+  let launched: LaunchedAcpTestAgent | undefined
+  try {
+    server.listen(0, '127.0.0.1')
+    await once(server, 'listening')
+    const address = server.address()
+    if (address === null || typeof address === 'string') throw new Error('account catalog server has no port')
+    const origin = `http://127.0.0.1:${address.port}`
+    await mkdir(join(cwd, '.dsh'))
+    await writeFile(join(cwd, '.dsh', '.credentials.yaml'), JSON.stringify({
+      version: 1,
+      records: {
+        'deepseek-account-platform/default': { kind: 'grant', payload: { version: 1, token, issuer: origin } },
+      },
+    }) + '\n', { mode: 0o600 })
+    const configPath = join(cwd, 'catalog.patch.yml')
+    await writeFile(configPath, JSON.stringify([
+      { id: 'deepseek-account', config: { platformOrigin: origin, inferenceOrigin: origin, allowLoopbackHttp: true } },
+      { id: 'llm-deepseek-account', config: { baseURL: `${origin}/anthropic` } },
+      { id: 'llm-deepseek', config: { baseURL: `${origin}/anthropic`, models: [{ id: 'fixture-api-key-model' }] } },
+      // Catalog discovery requires the account service to have loaded the stored grant.
+      {
+        id: 'acp', inject: ['acpAppStartup', 'deepseekAccount'],
+        config: { provider: 'deepseek-official', model: 'fixture-api-key-model' },
+      },
+      { id: 'session-persistence-jsonl', config: { root: join(cwd, 'sessions'), compression: 'none' } },
+    ]) + '\n')
+    const agent: AgentUnderTest = {
+      binScript: fileURLToPath(new URL('../../../../src/bin.ts', import.meta.url)),
+      configPath,
+      profile: 'acp',
+      tsconfigPath: fileURLToPath(new URL('../../../../../../tsconfig.json', import.meta.url)),
+    }
+    launched = launchAcpTestAgent({
+      agent,
+      cwd,
+      env: { DEEPSEEK_API_KEY: 'acp-fixture-api-key', DEEPSEEK_BASE_URL: `${origin}/anthropic`, DSH_TELEMETRY_DISABLED: '1' },
+    })
+    await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} })
+    const created = await launched.client.newSession({ cwd, mcpServers: [] })
+    expect(created.configOptions).toContainEqual(expect.objectContaining({
+      id: 'model', currentValue: JSON.stringify(['deepseek-official', 'fixture-api-key-model']),
+    }))
+    await launched.client.closeSession({ sessionId: created.sessionId })
+    // Closing joins both pipes; receiving a stdout response alone does not drain stderr.
+    await launched.close()
+
+    expect(launched.child.signalCode).toBeNull()
+    expect(launched.child.exitCode).toBe(0)
+    expect(requests).toEqual([{ method: 'GET', path: '/models', token }])
+    const frames = launched.rawStdout().trim().split('\n').map(line => JSON.parse(line) as Record<string, unknown>)
+    expect(frames.length).toBeGreaterThanOrEqual(3)
+    for (const frame of frames) expect(frame).toMatchObject({ jsonrpc: '2.0' })
+    expect(launched.stderr()).toContain(`[llm-deepseek-account] model listing from ${origin}/models loaded 2 model(s), skipped 0 row(s)`)
+    expect(launched.stderr()).toContain('[llm-deepseek-account] model "deepseek-v4-pro" declares no api_capabilities.anthropic_messages')
+    expect(launched.stderr()).not.toContain(token)
+  } finally {
+    const cleanup = await Promise.allSettled([cleanupAcpExampleTest(launched, cwd)])
+    server.closeAllConnections()
+    cleanup.push(...await Promise.allSettled([
+      server.listening ? new Promise<void>((resolve, reject) => server.close((error) => {
+        if (error === undefined) resolve()
+        else reject(error)
+      })) : undefined,
+    ]))
+    const failures: unknown[] = []
+    for (const result of cleanup) if (result.status === 'rejected') failures.push(result.reason)
+    if (failures.length > 0) throw new AggregateError(failures, 'ACP catalog test cleanup failed')
+  }
+})
diff --git a/packages/llm/llm-deepseek-account/README.i18n.yaml b/packages/llm/llm-deepseek-account/README.i18n.yaml
index 355018a3c4..a1482909bd 100644
--- a/packages/llm/llm-deepseek-account/README.i18n.yaml
+++ b/packages/llm/llm-deepseek-account/README.i18n.yaml
@@ -15,8 +15,8 @@
   en: 23386452a66b2fbd
   zh: 4cf93c4bf17b3da2
 /deepseek-ai-dsh-llm-deepseek-account/use-this-package:
-  en: f0ac16310ce5a5c4
-  zh: 6929f80d830c18df
+  en: d6fcd541fcd882ac
+  zh: c859dff4d6cd36d4
 /deepseek-ai-dsh-llm-deepseek-account/understand-the-implementation:
   en: 8e8d8e4f786e03c3
   zh: 7b32d8cea29d2b1a
diff --git a/packages/llm/llm-deepseek-account/README.md b/packages/llm/llm-deepseek-account/README.md
index 223640859b..6ceafc3bc9 100644
--- a/packages/llm/llm-deepseek-account/README.md
+++ b/packages/llm/llm-deepseek-account/README.md
@@ -29,7 +29,7 @@ Only `deepseekAccount.resolveToken(url)` supplies the token; the account service
 
 The route's catalog comes from the account's `GET /models` listing at the origin of the Messages `baseURL` (`https://api.deepseek.com/models` for the official endpoint); the listing endpoint is not configurable. Listing requests carry the account token in `x-dsh-auth-token` and the harness `User-Agent`, and reject redirects.
 
-The first access of a credential waits for the listing up to `modelsTimeoutMs`. Later accesses use the loaded listing and refresh it in the background once it is older than `modelsMaxAgeMs`. A failed or empty listing keeps the previous one; before any listing loads, the route serves the built-in catalog of the current version (`deepseek-flash` and `deepseek-v4-pro`). A listing HTTP 401 does not remove the stored login. Each loaded listing, the first failure of a failing streak with the catalog it falls back to, and each hidden listing entry are written to the console with the `[llm-deepseek-account]` tag; secrets are never logged. Each account token has its own listing, so the service can roll a model out to some accounts first.
+The first access of a credential waits for the listing up to `modelsTimeoutMs`. Later accesses use the loaded listing and refresh it in the background once it is older than `modelsMaxAgeMs`. A failed or empty listing keeps the previous one; before any listing loads, the route serves the built-in catalog of the current version (`deepseek-flash` and `deepseek-v4-pro`). A listing HTTP 401 does not remove the stored login. Each loaded listing, the first failure of a failing streak with the catalog it falls back to, and each hidden listing entry are written to stderr with the `[llm-deepseek-account]` tag; stdout remains available for protocol messages, and secrets are never logged. Each account token has its own listing, so the service can roll a model out to some accounts first.
 
 A listed model is offered only when the current DeepSeek Harness version can serve it. A model that declares `client_requirements["deepseek-harness"].min_version` is offered when the current version is at least that version in semantic-version order, including prerelease tags such as `0.2.0-alpha.1` and `0.2.0-rc.1`. A prerelease orders below its release: `min_version: 0.2.1` refuses `0.2.1-alpha.2`, so a listing that admits prereleases declares the earliest one it admits, such as `0.2.1-alpha.0`. A model without that declaration is offered only when the built-in catalog knows its id; other listed models stay hidden. A request for a listed model the current version cannot serve fails before network I/O with `CLIENT_UPGRADE_REQUIRED`, which names the required and current versions, or with `MODEL_UNSUPPORTED`. Model ids the listing does not name pass through unchanged.
 
diff --git a/packages/llm/llm-deepseek-account/README.zh.md b/packages/llm/llm-deepseek-account/README.zh.md
index 382c09a908..09954ce198 100644
--- a/packages/llm/llm-deepseek-account/README.zh.md
+++ b/packages/llm/llm-deepseek-account/README.zh.md
@@ -29,7 +29,7 @@ kind: "package-reference"
 
 路由的目录来自账号的 `GET /models` 列表，地址为 Messages `baseURL` 的 origin 加 `/models`（官方端点即 `https://api.deepseek.com/models`），不可配置。列表请求用 `x-dsh-auth-token` 携带账号 token，带上 harness 的 `User-Agent`，并拒绝重定向。
 
-同一凭据的第一次访问会等待列表，最长 `modelsTimeoutMs`。之后的访问直接使用已加载的列表，列表超过 `modelsMaxAgeMs` 后在后台刷新。获取失败或得到空列表时保留上一份；还没有加载到任何列表时，路由提供当前版本内置的目录（`deepseek-flash` 与 `deepseek-v4-pro`）。列表请求返回 HTTP 401 不会清除已保存的登录。每次加载成功、连续失败中的第一次失败及其退回的目录、以及每个被隐藏的列表条目，都会以 `[llm-deepseek-account]` 标签写到控制台日志；不记录任何密钥。每个账号 token 有自己的列表，因此服务端可以先对部分账号开放某个模型。
+同一凭据的第一次访问会等待列表，最长 `modelsTimeoutMs`。之后的访问直接使用已加载的列表，列表超过 `modelsMaxAgeMs` 后在后台刷新。获取失败或得到空列表时保留上一份；还没有加载到任何列表时，路由提供当前版本内置的目录（`deepseek-flash` 与 `deepseek-v4-pro`）。列表请求返回 HTTP 401 不会清除已保存的登录。每次加载成功、连续失败中的第一次失败及其退回的目录、以及每个被隐藏的列表条目，都会以 `[llm-deepseek-account]` 标签写到 stderr；stdout 保留给协议消息，且不记录任何密钥。每个账号 token 有自己的列表，因此服务端可以先对部分账号开放某个模型。
 
 只有当前版本的 DeepSeek Harness 能用的模型才会出现在目录里。声明了 `client_requirements["deepseek-harness"].min_version` 的模型，在当前版本号按 semver 顺序不低于该版本时提供，预发布号（如 `0.2.0-alpha.1`、`0.2.0-rc.1`）同样参与比较。预发布版本低于同号的正式版本：`min_version: 0.2.1` 会拒绝 `0.2.1-alpha.2`，因此要放行预发布版本的列表应声明它允许的最早一个，如 `0.2.1-alpha.0`。没有这个声明的模型，只有内置目录认识它的 id 时才提供；其余列出的模型保持隐藏。请求一个当前版本不能用的已列出模型时，会在网络请求之前失败：`CLIENT_UPGRADE_REQUIRED` 会写明所需版本和当前版本，否则为 `MODEL_UNSUPPORTED`。列表没有列出的模型 id 照常透传。
 
diff --git a/packages/llm/llm-deepseek-account/src/index.ts b/packages/llm/llm-deepseek-account/src/index.ts
index 4303a0e407..79feb7994c 100644
--- a/packages/llm/llm-deepseek-account/src/index.ts
+++ b/packages/llm/llm-deepseek-account/src/index.ts
@@ -75,7 +75,8 @@ export function apply(ctx: Context, config: Config): void {
     token: async url => account()?.resolveToken(url),
     load: (url, token, signal) => requestModelListing(url, { [TOKEN_HEADER]: token }, signal),
     now: () => Date.now(),
-    info: (message) => { console.info(LOG_TAG, message) },
+    // ACP reserves stdout for protocol messages, including during successful catalog loads.
+    info: (message) => { console.error(LOG_TAG, message) },
     warn: (message) => { console.warn(LOG_TAG, message) },
   })
   let loggedListing: ModelListing | undefined
diff --git a/packages/llm/llm-deepseek-account/tests/provider.spec.ts b/packages/llm/llm-deepseek-account/tests/provider.spec.ts
index 7a0dc604df..d4a75057d2 100644
--- a/packages/llm/llm-deepseek-account/tests/provider.spec.ts
+++ b/packages/llm/llm-deepseek-account/tests/provider.spec.ts
@@ -109,7 +109,7 @@ it('falls back to the bundled catalog when the listing fails', async () => {
 })
 
 it('hides and refuses listed models this build cannot serve before any inference request', async () => {
-  const info = vi.spyOn(console, 'info').mockImplementation(() => {})
+  const diagnostic = vi.spyOn(console, 'error').mockImplementation(() => {})
   const warn = vi.spyOn(console, 'warn').mockImplementation(() => {})
   const server = await listing(json({ data: [
     FLASH,
@@ -127,7 +127,7 @@ it('hides and refuses listed models this build cannot serve before any inference
     .rejects.toMatchObject({ code: 'CLIENT_UPGRADE_REQUIRED', message: expect.stringMatching(/requires DeepSeek Harness 99\.0\.0-alpha\.1 or later; current version is /) as string })
   await expect(ctx.llm.prepareCall({ provider: 'deepseek-account', model: 'unlisted-pass-through' })).resolves.toBeDefined()
   expect(server.requests.map(request => request.url)).toEqual(['/models'])
-  expect(info).toHaveBeenCalledExactlyOnceWith('[llm-deepseek-account]', expect.stringContaining('loaded 5 model(s), skipped 0 row(s)') as string)
+  expect(diagnostic).toHaveBeenCalledExactlyOnceWith('[llm-deepseek-account]', expect.stringContaining('loaded 5 model(s), skipped 0 row(s)') as string)
   expect(warn).toHaveBeenCalledExactlyOnceWith('[llm-deepseek-account]', 'model "deepseek-v4-pro" declares no api_capabilities.anthropic_messages')
 })