From 55a8c2e9f2c50ae2680c71229c4127e2a1a9ed13 Mon Sep 17 00:00:00 2001 From: pku-xht Date: Mon, 24 Aug 2026 17:59:48 +0800 Subject: [PATCH] chore(subagent): refresh Codex runtime --- ...code-and-codex-subagent-backends.i18n.yaml | 4 +- ...claude-code-and-codex-subagent-backends.md | 8 +-- ...ude-code-and-codex-subagent-backends.zh.md | 8 +-- ...agent-noninteractive-permissions.i18n.yaml | 4 +- ...uct-subagent-noninteractive-permissions.md | 4 +- ...-subagent-noninteractive-permissions.zh.md | 4 +- ...8-native-windows-pull-request-ci.i18n.yaml | 4 +- ...26-08-08-native-windows-pull-request-ci.md | 2 +- ...08-08-native-windows-pull-request-ci.zh.md | 2 +- ...ludes-product-subagent-providers.i18n.yaml | 4 +- ...dsh-excludes-product-subagent-providers.md | 2 +- ...-excludes-product-subagent-providers.zh.md | 2 +- ...uct-subagent-minimal-diagnostics.i18n.yaml | 4 +- ...21-product-subagent-minimal-diagnostics.md | 2 +- ...product-subagent-minimal-diagnostics.zh.md | 2 +- .../session.jsonl | 8 +-- .../stdout.expected.jsonl | 4 +- .../subagent/subagent-codex/README.i18n.yaml | 4 +- packages/subagent/subagent-codex/README.md | 8 +-- packages/subagent/subagent-codex/README.zh.md | 8 +-- packages/subagent/subagent-codex/package.json | 2 +- packages/subagent/subagent-codex/src/wire.ts | 2 +- .../subagent-codex/tests/real-deepseek.e2e.ts | 4 +- .../subagent-codex/tests/real-product.spec.ts | 8 +-- .../subagent-codex/tests/responses-fixture.ts | 2 +- .../tests/subagent-codex.spec.ts | 30 +++++----- pnpm-lock.yaml | 58 +++++++++---------- pnpm-workspace.yaml | 3 + 28 files changed, 100 insertions(+), 97 deletions(-) diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml index e5c8b676af..8a9c235a3b 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.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 .agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md -2026-08-04-claude-code-and-codex-subagent-backends.md: 467115a0e6c2d44091e54ac0466a535196698bf4 -2026-08-04-claude-code-and-codex-subagent-backends.zh.md: 39ace0bc033e314709a50b5f4da79e9636caae61 +2026-08-04-claude-code-and-codex-subagent-backends.md: 04b8fcb9c3fd899a485a12ce9c002b8ab5d6bbb3 +2026-08-04-claude-code-and-codex-subagent-backends.zh.md: de9248ed7c82266bd6083020ab32190a3dfd8d1f diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md index 467115a0e6..04b8fcb9c3 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md @@ -34,17 +34,17 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro ## Codex provider -`@deepseek-ai/dsh-subagent-codex` registers a Profile-selected provider name that defaults to `codex`, resolves the `codex` bin declared by its pinned `@openai/codex@0.148.0` package, and starts that wrapper through the current Node executable with `app-server --stdio`. The wrapper selects the private native platform payload; the provider neither resolves nor falls back to a host `codex`. Its public configuration contains a non-empty `providerName`, an optional non-empty `model`, an explicit `env` overlay, a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`, and a three-value native `permissionMode` that defaults to `never`. Each named instance retains those resolved values for its own runs. An explicit model is passed unchanged on every ephemeral `thread/start`; omission leaves native Codex settings authoritative. Installation, login, `CODEX_HOME`, model discovery or fallback, base URL, and product-session settings remain native Codex or deployment responsibilities; the selected mode owns only the thread approval/reviewer/sandbox fields described by the non-interactive permissions decision. +`@deepseek-ai/dsh-subagent-codex` registers a Profile-selected provider name that defaults to `codex`, resolves the `codex` bin declared by its pinned `@openai/codex@0.149.1` package, and starts that wrapper through the current Node executable with `app-server --stdio`. The wrapper selects the private native platform payload; the provider neither resolves nor falls back to a host `codex`. Its public configuration contains a non-empty `providerName`, an optional non-empty `model`, an explicit `env` overlay, a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`, and a three-value native `permissionMode` that defaults to `never`. Each named instance retains those resolved values for its own runs. An explicit model is passed unchanged on every ephemeral `thread/start`; omission leaves native Codex settings authoritative. Installation, login, `CODEX_HOME`, model discovery or fallback, base URL, and product-session settings remain native Codex or deployment responsibilities; the selected mode owns only the thread approval/reviewer/sandbox fields described by the non-interactive permissions decision. Before publication, the provider validates a non-empty text-only task, starts the managed app-server in the parent workspace, completes `initialize` → `initialized`, maps the optional model and resolved mode into official `thread/start` fields, and creates an `ephemeral: true` thread. The fixed app-server argv contains no model, mode, or task text. The published run owns exactly one `turn/start`; its thread and turn ids remain private and are never persisted in the parent Session. `turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns Codex action categories, HTTP status, lifecycle stages, process outcomes, and stop-reason preservation. Local cancellation remains `aborted` without a failure diagnostic. -For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.148.0 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is neither classified nor copied into the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply. +For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.149.1 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is neither classified nor copied into the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply. An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, detaches the stderr observer, and then rejects `start()` with its fixed operation stage. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, waits for whole-tree exit, and detaches the observer. Independent cleanup failure reports `teardown`; when startup and rollback both fail, the aggregate's top message retains both safe stage lines while the underlying causes remain internal. -Codex 0.148.0 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively. +Codex 0.149.1 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively. ## Claude Code provider @@ -62,7 +62,7 @@ The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract Each product owns branch-complete package tests, a required keyless real-product spec, a Loader composition e2e, and a credentialed DeepSeek e2e. The keyless product tier uses the exact official distribution under test, a non-empty fake product key, an isolated temporary workspace and product home, and a loopback fixed-answer model. Missing product requests, wrong authentication, altered task text, a non-exact answer, a skipped real product, or a surviving managed handle fails the required test. The Codex Loader fixture exposes two named Codex instances and tools; the Claude Code Loader fixture exposes the default Codex tool plus two named Claude Code instances and tools. Both fixtures include generic Job controls and start neither product process. The credentialed tier starts the same production provider and real product with a runtime-only key, requires a unique nonce from the fixed official DeepSeek service, and proves quiescence again; it self-skips only when a local operator supplied no key, while trusted CI preflights the secret. -The Codex evidence pins `@openai/codex@0.148.0`, `codex-cli 0.148.0`, and all six optional platform aliases. Its generated schema proves optional `ThreadStartParams.model`; the real-product spec observes omitted-model inheritance, two explicit instance models, the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, named instances retain separate models, environments, and modes, and production never resolves a host `codex` from `PATH`. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns failure, process-outcome, and final presentation evidence. +The Codex evidence pins `@openai/codex@0.149.1`, `codex-cli 0.149.1`, and all six optional platform aliases. Its generated schema proves optional `ThreadStartParams.model`; the real-product spec observes omitted-model inheritance, two explicit instance models, the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, named instances retain separate models, environments, and modes, and production never resolves a host `codex` from `PATH`. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns failure, process-outcome, and final presentation evidence. The Codex credentialed e2e registers the production provider, starts the same real app-server, and requests one random nonce through the test-private bridge described above. It fixes the external endpoint and model, stores no credential or request payload, requires exactly one completed upstream response, compares the trimmed product answer byte-for-byte with the nonce, and waits for every managed handle to exit. diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md index 39ace0bc03..de9248ed7c 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md @@ -34,17 +34,17 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro ## Codex 提供方 -`@deepseek-ai/dsh-subagent-codex` 注册由 Profile 选择、默认值为 `codex` 的提供方名称，解析锁定的 `@openai/codex@0.148.0` 包所声明的 `codex` bin，并使用当前 Node 可执行文件加 `app-server --stdio` 启动该 wrapper。Wrapper 会选择私有原生平台载荷；提供方既不解析也不回退宿主 `codex`。其公开配置包含非空的 `providerName`、可选的非空 `model`、显式的 `env` 覆盖项、须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`，以及默认使用 `never` 的三值原生 `permissionMode`。每个命名实例会为自己的运行保留这些已解析值。显式模型会原样传给每个临时 `thread/start`；省略时仍以 Codex 原生设置为权威。安装、登录、`CODEX_HOME`、模型发现或 fallback、基础 URL 和产品会话设置仍由 Codex 原生机制或部署环境负责；所选模式只拥有非交互权限决策中描述的线程 approval／reviewer／sandbox 字段。 +`@deepseek-ai/dsh-subagent-codex` 注册由 Profile 选择、默认值为 `codex` 的提供方名称，解析锁定的 `@openai/codex@0.149.1` 包所声明的 `codex` bin，并使用当前 Node 可执行文件加 `app-server --stdio` 启动该 wrapper。Wrapper 会选择私有原生平台载荷；提供方既不解析也不回退宿主 `codex`。其公开配置包含非空的 `providerName`、可选的非空 `model`、显式的 `env` 覆盖项、须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`，以及默认使用 `never` 的三值原生 `permissionMode`。每个命名实例会为自己的运行保留这些已解析值。显式模型会原样传给每个临时 `thread/start`；省略时仍以 Codex 原生设置为权威。安装、登录、`CODEX_HOME`、模型发现或 fallback、基础 URL 和产品会话设置仍由 Codex 原生机制或部署环境负责；所选模式只拥有非交互权限决策中描述的线程 approval／reviewer／sandbox 字段。 发布前，提供方会验证非空的纯文本任务，在父级工作区中启动受管的 app-server，完成 `initialize` → `initialized` 握手，把可选模型与已解析模式映射为官方 `thread/start` 字段，并创建一个 `ephemeral: true` 线程。固定 app-server argv 不包含模型、模式或任务文本。已发布的运行只拥有一次 `turn/start`；其线程 ID 与轮次 ID 保持私有，绝不会持久化到父会话。 `turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责 Codex 行动类别、HTTP status、生命周期阶段、进程结果与终止原因保持。本地取消仍是 `aborted` 且不附带失败诊断。 -对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.148.0 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与结构化 `sandboxError` 终态的安全类别。产品 stderr 会原样转发给 Host，但既不会被分类，也不会复制进诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。 +对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.149.1 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与结构化 `sandboxError` 终态的安全类别。产品 stderr 会原样转发给 Host，但既不会被分类，也不会复制进诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。 若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树、等待其退出、移除 stderr observer，然后用固定操作阶段拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，等待整棵进程树退出，并移除 observer。独立清理失败会报告 `teardown`；启动与回滚同时失败时，聚合的顶层消息会保留两条安全阶段说明，而底层 cause 仍只在内部可见。 -Codex 0.148.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。 +Codex 0.149.1 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。 ## Claude Code 提供方 @@ -62,7 +62,7 @@ Codex 0.148.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端 每个产品都负责覆盖所有分支的包测试、一项必跑的无密钥真实产品测试、一项 Loader 组合 e2e 和一项带密钥 DeepSeek e2e。无密钥产品层级使用被测的确切官方发行版、非空的伪产品密钥、隔离的临时工作区与产品主目录，以及能返回固定答案的回环模型。产品请求缺失、身份验证错误、任务文本被改动、答案不完全一致、真实产品被跳过或受管句柄仍存活，都会使这项必跑测试失败。Codex Loader fixture 会公开两个命名 Codex 实例与工具；Claude Code Loader fixture 会公开默认 Codex 工具以及两个命名 Claude Code 实例与工具。两个 fixture 都包含通用 Job 控制工具，而且不会启动任何产品进程。带密钥层级会使用仅在运行时提供的密钥启动同一生产提供方与真实产品，要求从固定的 DeepSeek 官方服务取得唯一随机数，并再次证明完全停稳；仅当本地操作者未提供密钥时才会自行跳过，而受信任的 CI 会预检该 secret。 -Codex 证据会锁定 `@openai/codex@0.148.0`、`codex-cli 0.148.0` 与六个平台 alias。生成 schema 会证明可选的 `ThreadStartParams.model`；真实产品测试会观测省略模型继承、两个显式实例模型、包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，命名实例会保留彼此独立的模型、环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责失败、进程结果与最终呈现证据。 +Codex 证据会锁定 `@openai/codex@0.149.1`、`codex-cli 0.149.1` 与六个平台 alias。生成 schema 会证明可选的 `ThreadStartParams.model`；真实产品测试会观测省略模型继承、两个显式实例模型、包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，命名实例会保留彼此独立的模型、环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责失败、进程结果与最终呈现证据。 带密钥 Codex e2e 会注册生产提供方，启动同样的真实 app-server，并通过上述测试专用桥接层请求一个随机数。该测试固定外部端点与模型，不存储任何凭据或请求载荷，要求上游恰好完成一次响应，将去除首尾空白后的产品答案与该随机数逐字节比较，并等待所有受管句柄退出。 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml index 8016061d4c..bcefa42504 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.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 .agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md -2026-08-15-product-subagent-noninteractive-permissions.md: d49b7b9cadc378d29d3d4bc2110b1a2655d0f2c6 -2026-08-15-product-subagent-noninteractive-permissions.zh.md: bbcf9e53c45564f971c31c64e341dd1b0c4735ca +2026-08-15-product-subagent-noninteractive-permissions.md: 8ce71cbf156d3e22a22fa8ad526b838ec1a5effe +2026-08-15-product-subagent-noninteractive-permissions.zh.md: e6471b2ce1c8ebbb767254df2426969a3da36f78 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md index d49b7b9cad..8ce71cbf15 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md @@ -32,7 +32,7 @@ Every query disables `AskUserQuestion`. Non-bypass permission callbacks deny ins ### Codex -Codex defaults to `never` and accepts the three native non-interactive modes exposed by Codex 0.148.0. The Provider starts the fixed app-server command, then maps the selected mode into official `thread/start` fields because CLI-global permission flags do not configure threads created later by an app-server client: +Codex defaults to `never` and accepts the three native non-interactive modes exposed by Codex 0.149.1. The Provider starts the fixed app-server command, then maps the selected mode into official `thread/start` fields because CLI-global permission flags do not configure threads created later by an app-server client: | Value | `thread/start` fields | Native behavior | | --- | --- | --- | @@ -63,7 +63,7 @@ The foreground consumer presents the stop-reason headline, then the optional dia ## Verification -Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK 0.3.241 and Claude Code 2.1.241 fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex 0.148.0 app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, a rejected escalation leaves no side effect or raw command or path in the diagnostic, stderr remains Host-only, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. +Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK 0.3.241 and Claude Code 2.1.241 fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex 0.149.1 app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, a rejected escalation leaves no side effect or raw command or path in the diagnostic, stderr remains Host-only, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md index bbcf9e53c4..e6471b2ce1 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md @@ -32,7 +32,7 @@ Claude Code 默认使用 `dontAsk`，而且只接受锁定版本 Agent SDK 支 ### Codex -Codex 默认使用 `never`，并接受 Codex 0.148.0 公开的三种原生非交互模式。提供方启动固定的 app-server 命令，再把所选模式映射为官方 `thread/start` 字段，因为 CLI 全局权限 flag 不会配置之后由 app-server 客户端创建的线程： +Codex 默认使用 `never`，并接受 Codex 0.149.1 公开的三种原生非交互模式。提供方启动固定的 app-server 命令，再把所选模式映射为官方 `thread/start` 字段，因为 CLI 全局权限 flag 不会配置之后由 app-server 客户端创建的线程： | 值 | `thread/start` 字段 | 原生行为 | | --- | --- | --- | @@ -63,7 +63,7 @@ Codex 默认使用 `never`，并接受 Codex 0.148.0 公开的三种原生非交 ## Verification -包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex 0.148.0 app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、被拒绝的提权不会留下副作用且诊断不含原始命令或路径、stderr 只供 Host 观测，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 +包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex 0.149.1 app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、被拒绝的提权不会留下副作用且诊断不含原始命令或路径、stderr 只供 Host 观测，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml index 6e51b8241f..6d24a3ca22 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.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 .agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md -2026-08-08-native-windows-pull-request-ci.md: 5d18c8787fbeb8908cdbd2d5f53c9985b6e90a79 -2026-08-08-native-windows-pull-request-ci.zh.md: 456cc57a45820e8ba768ea49243c1f997fd7cb2e +2026-08-08-native-windows-pull-request-ci.md: d690cfdf59a57847d9c4a962d733a021db468910 +2026-08-08-native-windows-pull-request-ci.zh.md: 5ac74e6bd5a8777a86247202e8edb1066a84c2d7 diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md index 5d18c8787f..d690cfdf59 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md @@ -32,7 +32,7 @@ Windows durable JSONL paths keep drive roots in native spelling and apply the ex Post-boot profile watcher setup proceeds only while the root fiber and Loader are both live. A concurrent setup error is contained only when the same invocation's recorded signal already owns shutdown; unrelated HMR failures remain loud. The [process-shutdown controller](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.md) lets a successful one-shot completion drain Node's remaining handles after root disposal, while teardown failure, deadline, and signal escalation retain forced exit. The vendored Include serializes debounced writes, retries only transient access or busy failures with bounded backoff, and observes every timer rejection. A terminal persistence failure remains on the queue and is rethrown to the teardown owner, while successful teardown drains the latest write. -Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.148.0 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and whole-tree exit on each host. +Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.149.1 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and whole-tree exit on each host. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md index 456cc57a45..5ac74e6bd5 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md @@ -32,7 +32,7 @@ Windows 的持久 JSONL 路径会保留驱动器根目录的原生写法，并 启动后，只有根 fiber 与 Loader 均处于活跃状态时，系统才会继续设置 profile watcher。只有当同一次调用所记录的信号已取得关闭流程所有权时，系统才会隔离并发设置错误；无关 HMR 故障仍会响亮失败。[进程关闭控制器](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.zh.md)会在根级 dispose 成功后让单次任务的正常完成流程排空 Node 剩余句柄，同时让拆卸失败、截止时间到期和信号升级继续强制退出。vendored Include 会串行化防抖写入，只对瞬时访问或忙碌故障执行有界退避重试，并确保每个由计时器触发的拒绝都得到观察。持久化最终失败后，该故障会保留在队列中，并重新抛给拆卸责任方；成功拆卸则会排空最新写入。 -Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.148.0 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和整棵进程树退出。 +Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.149.1 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和整棵进程树退出。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml index 7b1b304531..a017cbbc22 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.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 .agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md -2026-08-12-production-dsh-excludes-product-subagent-providers.md: d0da33a025d4909b5f8cf27ad0c502fb8ffbeb37 -2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: df7955a8b93146007582c0149d26cdb07abd3a75 +2026-08-12-production-dsh-excludes-product-subagent-providers.md: 551cf86bd0d1901e5ad8e33588b7bf274cb2c8fe +2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: 611c6192c501f6289911c18c36ca21a31c57e2cd diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md index d0da33a025..551cf86bd0 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md @@ -16,7 +16,7 @@ The two Bundles remain independent. The Codex Bundle owns the pinned official wr ## Verification -Package tests pin both Bundle manifests, published patches, exact self-provider rows, and product runtime dependencies. Claude coverage pins Agent SDK 0.3.241, Claude Code 2.1.241, all eight platform packages, SDK-selected execution, and missing-payload failure without host fallback. Codex coverage pins wrapper 0.148.0, all six platform aliases, package-declared execution, native descendant quiescence, and the same missing-payload behavior. Workspace validation derives each published patch from its Bundle declaration rather than a package catalog. Package/base assertions plus actual pnpm production evidence prove the default and selected-product dependency boundaries, while real Bundle-patch and Agent-Preset composition covers none, either product, both, the tool-grant intersection, later-Session adoption, and zero startup processes. +Package tests pin both Bundle manifests, published patches, exact self-provider rows, and product runtime dependencies. Claude coverage pins Agent SDK 0.3.241, Claude Code 2.1.241, all eight platform packages, SDK-selected execution, and missing-payload failure without host fallback. Codex coverage pins wrapper 0.149.1, all six platform aliases, package-declared execution, native descendant quiescence, and the same missing-payload behavior. Workspace validation derives each published patch from its Bundle declaration rather than a package catalog. Package/base assertions plus actual pnpm production evidence prove the default and selected-product dependency boundaries, while real Bundle-patch and Agent-Preset composition covers none, either product, both, the tool-grant intersection, later-Session adoption, and zero startup processes. ## Alternatives considered diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md index df7955a8b9..611c6192c5 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md @@ -16,7 +16,7 @@ Status: implemented ## 验证 -包测试会固定两个 Bundle 的 manifest、发布 patch、准确的自身提供方行与产品运行时依赖。Claude 覆盖会固定 Agent SDK 0.3.241、Claude Code 2.1.241、八个平台包、SDK 所选执行路径，以及载荷缺失时不回退宿主命令的失败。Codex 覆盖会固定 wrapper 0.148.0、六个平台 alias、包声明的执行路径、原生后代进程停稳，以及同样的载荷缺失行为。工作区验证会从 Bundle 声明派生每份发布 patch，而非维护包目录。包与 base 断言加上实际 pnpm 生产证据会证明默认与所选产品的依赖边界；真实 Bundle patch 与 Agent Preset 组装则覆盖未安装、任一单包、双包、工具授权交集、后续 Session 采纳以及零启动进程。 +包测试会固定两个 Bundle 的 manifest、发布 patch、准确的自身提供方行与产品运行时依赖。Claude 覆盖会固定 Agent SDK 0.3.241、Claude Code 2.1.241、八个平台包、SDK 所选执行路径，以及载荷缺失时不回退宿主命令的失败。Codex 覆盖会固定 wrapper 0.149.1、六个平台 alias、包声明的执行路径、原生后代进程停稳，以及同样的载荷缺失行为。工作区验证会从 Bundle 声明派生每份发布 patch，而非维护包目录。包与 base 断言加上实际 pnpm 生产证据会证明默认与所选产品的依赖边界；真实 Bundle patch 与 Agent Preset 组装则覆盖未安装、任一单包、双包、工具授权交集、后续 Session 采纳以及零启动进程。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml index dabbf049ab..9aaf9322f1 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.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 .agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md -2026-08-21-product-subagent-minimal-diagnostics.md: a5b65608cb256485881f2750ce2351c702383875 -2026-08-21-product-subagent-minimal-diagnostics.zh.md: c46c7bde1accbc0e192d66a3ef4db9ceaf122a11 +2026-08-21-product-subagent-minimal-diagnostics.md: b99ed487911a7ac9bf7c0751ea02290ff92cad6a +2026-08-21-product-subagent-minimal-diagnostics.zh.md: 46f948334df0268a095f8cb34ab1a7707eee811b diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md index a5b65608cb..b99ed48791 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md @@ -53,7 +53,7 @@ The Codex diagnostic retains `initialize`, `thread-start`, `turn-start`, `turn`, ## Verification -Claude Code package tests cover every coarse category, all four stages, unknown structured values, permission ordering, raw-text exclusion, success and cancellation omission, concurrent-run isolation, and independent exit code and signal fields. The real Agent SDK 0.3.241 and Claude Code 2.1.241 fixture produces an actual max-turns limit, process failure, permission denial, strict final answer, cancellation, and whole-tree quiescence. Codex package tests cover every coarse category, all six stages, applicable HTTP status, structured permission ordering, stderr exclusion, success and cancellation omission, concurrency, and cleanup aggregation. The real 0.148.0 app-server fixture produces service, product-error, process, final-answer, model-isolation, cancellation, and quiescence evidence. Loader and keyless product compositions continue to expose static tools without a diagnostic parser or model-visible category input. +Claude Code package tests cover every coarse category, all four stages, unknown structured values, permission ordering, raw-text exclusion, success and cancellation omission, concurrent-run isolation, and independent exit code and signal fields. The real Agent SDK 0.3.241 and Claude Code 2.1.241 fixture produces an actual max-turns limit, process failure, permission denial, strict final answer, cancellation, and whole-tree quiescence. Codex package tests cover every coarse category, all six stages, applicable HTTP status, structured permission ordering, stderr exclusion, success and cancellation omission, concurrency, and cleanup aggregation. The real 0.149.1 app-server fixture produces service, product-error, process, final-answer, model-isolation, cancellation, and quiescence evidence. Loader and keyless product compositions continue to expose static tools without a diagnostic parser or model-visible category input. ## Alternatives considered diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md index c46c7bde1a..46f948334d 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md @@ -53,7 +53,7 @@ Codex 诊断会保留 `initialize`、`thread-start`、`turn-start`、`turn`、`p ## Verification -Claude Code 包测试覆盖全部粗粒度类别、四个阶段、未知结构化值、权限顺序、原始文本排除、成功与取消时省略、并发运行隔离，以及彼此独立的退出码与信号字段。真实 Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 会产生实际 max-turns 限制、进程失败、权限拒绝、严格最终答案、取消与整棵进程树完全停稳。Codex 包测试覆盖全部粗粒度类别、六个阶段、适用 HTTP status、结构化权限顺序、stderr 排除、成功与取消时省略、并发及清理聚合。真实 0.148.0 app-server fixture 会产生服务、产品错误、进程、最终答案、模型隔离、取消与完全停稳证据。Loader 与无密钥产品组合继续公开静态工具，不增加诊断解析器或模型可见类别输入。 +Claude Code 包测试覆盖全部粗粒度类别、四个阶段、未知结构化值、权限顺序、原始文本排除、成功与取消时省略、并发运行隔离，以及彼此独立的退出码与信号字段。真实 Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 会产生实际 max-turns 限制、进程失败、权限拒绝、严格最终答案、取消与整棵进程树完全停稳。Codex 包测试覆盖全部粗粒度类别、六个阶段、适用 HTTP status、结构化权限顺序、stderr 排除、成功与取消时省略、并发及清理聚合。真实 0.149.1 app-server fixture 会产生服务、产品错误、进程、最终答案、模型隔离、取消与完全停稳证据。Loader 与无密钥产品组合继续公开静态工具，不增加诊断解析器或模型可见类别输入。 ## Alternatives considered diff --git a/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/session.jsonl b/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/session.jsonl index a340b26734..60527346e0 100644 --- a/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/session.jsonl +++ b/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/session.jsonl @@ -51,7 +51,7 @@ {"type":"assistant/chunk","data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"89ab3728-fc3f-4825-97e5-383d46568d8c"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":4,"callId":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}} -{"type":"tool/result","data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"call_codex_foreground"},"content":[{"type":"tool-result","toolCallId":"call_codex_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"5203aefd-6d83-4220-9ad5-0d33635fa79a"}},"sourceEventSeqs":[51],"surfaceOp":"append"} +{"type":"tool/result","data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"call_codex_foreground"},"content":[{"type":"tool-result","toolCallId":"call_codex_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"de1f2980-db1f-416c-8373-5ba5329b9835"}},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":4}} {"type":"step/start","data":{"turn":1,"step":5}} {"type":"assistant/chunk","data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -61,12 +61,12 @@ {"type":"assistant/chunk","data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"996da601-acb8-49c9-8dd7-e60a88a8f1a2"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":5,"callId":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}} -{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"94b0c135-958e-48de-bea6-95106f0e6bc6"}]}} +{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"d16457d9-737d-4a1b-a530-f01811d88dba"}]}} {"type":"tool/result","data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"call_codex_background"},"content":[{"type":"tool-result","toolCallId":"call_codex_background","content":[{"type":"text","text":"started background subagent job subagent-2"}],"isError":false}],"role":"user","id":"684012b7-0ea4-4717-9d87-a800465001b1"}},"sourceEventSeqs":[61],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":5}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","data":{"turn":1,"step":6}} -{"type":"user/message","data":{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"94b0c135-958e-48de-bea6-95106f0e6bc6"},"surfaceOp":"append"} +{"type":"user/message","data":{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"d16457d9-737d-4a1b-a530-f01811d88dba"},"surfaceOp":"append"} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"tool-call-delta","index":0,"id":"call_codex_output","name":"job_output","argumentsDelta":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}}} @@ -74,7 +74,7 @@ {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"cfc1726c-5d9e-486a-aa0f-057219e16dfd"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[68,69,70,71,72],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":6,"callId":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}} -{"type":"tool/result","data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"call_codex_output"},"content":[{"type":"tool-result","toolCallId":"call_codex_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]"}],"isError":false}],"role":"user","id":"c60f2896-4fbb-4326-8452-8f0aa588827d"}},"sourceEventSeqs":[74],"surfaceOp":"append"} +{"type":"tool/result","data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"call_codex_output"},"content":[{"type":"tool-result","toolCallId":"call_codex_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]"}],"isError":false}],"role":"user","id":"677fb95e-e62e-4623-8c22-a62675e6b262"}},"sourceEventSeqs":[74],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":6}} {"type":"step/start","data":{"turn":1,"step":7}} {"type":"assistant/chunk","data":{"turn":1,"step":7,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/stdout.expected.jsonl index e365ee3c05..a826ab7f9f 100644 --- a/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/stdout.expected.jsonl +++ b/examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/stdout.expected.jsonl @@ -7,10 +7,10 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_claude_output","title":"job_output","kind":"other","status":"in_progress","rawInput":{"job_id":"subagent-1","wait":true}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_claude_output","status":"completed","content":[{"type":"content","content":{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Claude Code; stage: query-run; category: limit)]"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_codex_foreground","title":"subagent_codex","kind":"other","status":"in_progress","rawInput":{"description":"Observe Codex foreground diagnostic","prompt":"Return the Codex diagnostic failure.","run_in_background":false}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_codex_foreground","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_codex_foreground","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_codex_background","title":"subagent_codex","kind":"other","status":"in_progress","rawInput":{"description":"Observe Codex background diagnostic","prompt":"Return the Codex diagnostic failure.","run_in_background":true}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_codex_background","status":"completed","content":[{"type":"content","content":{"type":"text","text":"started background subagent job subagent-2"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_codex_output","title":"job_output","kind":"other","status":"in_progress","rawInput":{"job_id":"subagent-2","wait":true}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_codex_output","status":"completed","content":[{"type":"content","content":{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_codex_output","status":"completed","content":[{"type":"content","content":{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","messageId":"{{messageId}}","content":{"type":"text","text":"PARENT_OBSERVED_DIAGNOSTICS"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/packages/subagent/subagent-codex/README.i18n.yaml b/packages/subagent/subagent-codex/README.i18n.yaml index c16c4d6c35..b4cb448bd2 100644 --- a/packages/subagent/subagent-codex/README.i18n.yaml +++ b/packages/subagent/subagent-codex/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/subagent/subagent-codex/README.md -README.md: 2467daebeb2dda1541c86606ec794ab6cbed092b -README.zh.md: dd9596e9d88059f6415adfb7001407cd554f5f17 +README.md: 7ff5e1dd06f18cc5e313cca1a84576e976e96454 +README.zh.md: 8532f6cfb5ece282aa916771eb971d0f3edfab53 diff --git a/packages/subagent/subagent-codex/README.md b/packages/subagent/subagent-codex/README.md index 2467daebeb..7ff5e1dd06 100644 --- a/packages/subagent/subagent-codex/README.md +++ b/packages/subagent/subagent-codex/README.md @@ -10,7 +10,7 @@ This package registers a Profile-named Codex subagent provider whose default nam The published `run.result` starts exactly one turn. It accepts only notifications for that run's thread and turn, then waits for the authoritative `turn/completed` terminal notification. The latest `agentMessage` with `phase: "final_answer"` wins; when Codex emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback. Commentary never replaces either answer, and a successful turn with no nonblank answer settles as an error. -For command and file approvals, the unattended provider selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.148.0 request shape without an offered-decision list falls back to `decline`. It answers permission requests with an empty turn-scoped permission set, answers user-input requests with no answers, and declines MCP elicitation. A request with no legal unattended response, or any unknown server request, fails the run. The wire records only the effective mode, request category, decision, and fixed safe reason. It also recognizes declined command/file items and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is never classified or copied into the diagnostic. +For command and file approvals, the unattended provider selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.149.1 request shape without an offered-decision list falls back to `decline`. It answers permission requests with an empty turn-scoped permission set, answers user-input requests with no answers, and declines MCP elicitation. A request with no legal unattended response, or any unknown server request, fails the run. The wire records only the effective mode, request category, decision, and fixed safe reason. It also recognizes declined command/file items and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is never classified or copied into the diagnostic. Local cancellation wins the result race and maps to `aborted`. Failed turns use the coarse categories `limit`, `access-policy`, `service`, `transport`, `product-error`, `invalid-result`, or `unknown`; an early app-server exit uses `process`. Applicable connection and stream failures retain a numeric `httpStatusCode`. The diagnostic also names `turn-start`, `turn`, or `process` and independently includes available exit code and signal without copying raw fields. `contextWindowExceeded` remains `max-tokens`; every other remote interruption or failure remains `error`, and the provider produces no `refusal`. A contributing structured permission decision follows the failure line. Successful and locally cancelled runs omit both facts. @@ -36,7 +36,7 @@ The provider advertises no optional start-time capabilities and reports `inherit | `approve-for-me` | `approvalPolicy: on-request`, `approvalsReviewer: auto_review`, `sandbox: workspace-write` | Route permission requests through Codex automatic review without a human. | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`, `sandbox: danger-full-access` | Skip approval and sandbox enforcement; this value must be selected explicitly. | -Production resolves the `codex` bin declared by its pinned `@openai/codex@0.148.0` dependency and launches that JavaScript wrapper with the current Node executable. The wrapper selects the matching native platform payload; the provider neither inspects nor falls back to a host `codex` on `PATH`. Native Codex configuration and authentication remain authoritative through the parent cwd, `HOME`, and `CODEX_HOME`. A configured `model` is passed unchanged on each ephemeral `thread/start`; omission leaves the field absent, and the Provider does not discover models, rewrite aliases, select `modelProvider` or `serviceTier`, or set a fallback. The selected permission mode remains the only other thread-level override. The plugin does not create `CODEX_HOME`, log in, or probe an account. Credential-shaped ambient variables are removed by the subprocess seam before the explicit `env` overlay is applied. +Production resolves the `codex` bin declared by its pinned `@openai/codex@0.149.1` dependency and launches that JavaScript wrapper with the current Node executable. The wrapper selects the matching native platform payload; the provider neither inspects nor falls back to a host `codex` on `PATH`. Native Codex configuration and authentication remain authoritative through the parent cwd, `HOME`, and `CODEX_HOME`. A configured `model` is passed unchanged on each ephemeral `thread/start`; omission leaves the field absent, and the Provider does not discover models, rewrite aliases, select `modelProvider` or `serviceTier`, or set a fallback. The selected permission mode remains the only other thread-level override. The plugin does not create `CODEX_HOME`, log in, or probe an account. Credential-shaped ambient variables are removed by the subprocess seam before the explicit `env` overlay is applied. This package is an optional Profile Bundle. Install it into the target Profile, then restart that Profile; installation brings the official wrapper and one compatible native platform payload into that Profile, while the declared `cordis.patch.yml` layer registers only the dormant `codex` Host provider and starts no Codex process. Removing the package withdraws that provider and its private runtime closure on the next Profile start. @@ -97,7 +97,7 @@ The standalone composition below shows the complete explicit capability. A Profi ## Product compatibility and evidence -The production wire intentionally implements only the app-server methods required by this one-shot contract. The runtime dependency and all six optional-dependency aliases are pinned to `@openai/codex@0.148.0` / `codex-cli 0.148.0`. A normal install selects one payload for the current OS and CPU. For the current darwin-arm64 payload, `npm pack --dry-run --json @openai/codex@0.148.0-darwin-arm64` reports 105,734,658 packed bytes and 271,015,475 unpacked bytes. That package contains native `codex`, `codex-code-mode-host`, `rg`, and `zsh` resources; other platforms may differ, and these values are disclosure rather than an installation threshold. +The production wire intentionally implements only the app-server methods required by this one-shot contract. The runtime dependency and all six optional-dependency aliases are pinned to `@openai/codex@0.149.1` / `codex-cli 0.149.1`. A normal install selects one payload for the current OS and CPU. For the current darwin-arm64 payload, `npm pack --dry-run --json @openai/codex@0.149.1-darwin-arm64` reports 114,152,335 packed bytes and 282,491,555 unpacked bytes. That package contains native `codex`, `codex-code-mode-host`, `rg`, and `zsh` resources; other platforms may differ, and these values are disclosure rather than an installation threshold. Generated schema evidence pins the optional `ThreadStartParams.model` field, while package tests cover representative error groups, applicable HTTP status, six lifecycle stages, process outcomes, stop-reason mapping, unknown fallback, sanitization, structured permission ordering, cancellation, concurrency, and cleanup aggregation. The keyless real-product test drives the package wrapper against a loopback Responses fixture and observes the package-local argv, omitted-model inheritance, two explicit instance models, exact Bearer key, original task, byte-exact final answer, thread-level `never` overriding ambient `on-request`, automatic-review startup, unattended rejection without file side effects, a real service failure, explicit dangerous-bypass writing in suite-owned temporary storage, process/protocol failure with safe exit facts, and wrapper/native quiescence. @@ -139,7 +139,7 @@ Append-only: foreground adds one result after the reusable parent prefix, while - **Static instance selection** — Profile rows fix provider names, optional models, and tool bindings; calls cannot choose or change either a provider or model dynamically, and every exposed tool needs a unique `toolName`. - **Authentication and account state remain native** — the Bundle supplies the CLI but does not create an account, log in, trust a project, or rewrite Codex settings; configuration and authentication failures surface with their lifecycle stage and the safe `unknown` fallback rather than a separate public taxonomy. - **The native platform payload is required at delegation time** — installs that omit optional dependencies, unsupported platforms, and missing or damaged payloads fail at the first run; there is no host-CLI fallback. -- **Compatibility is pinned by development evidence** — upgrading from the verified 0.148.0 protocol baseline requires regenerating upstream schema evidence and rerunning handshake, answer-selection, approval, cancellation, keyless real-product, and credentialed DeepSeek nonce tests. +- **Compatibility is pinned by development evidence** — upgrading from the verified 0.149.1 protocol baseline requires regenerating upstream schema evidence and rerunning handshake, answer-selection, approval, cancellation, keyless real-product, and credentialed DeepSeek nonce tests. - **No human approval path** — known unattended approval requests are denied and unknown server requests fail closed; the three Profile modes never create a DSH interaction channel or per-call allow policy. - **Assistant payload is final text only** — a failed run may additionally expose the separate safe diagnostic; reasoning, commentary, intermediate messages, tool traffic, usage, raw stderr, and workspace diffs remain outside the parent Session, while generic Job ids, notices, and status come from the shared job runtime. - **No optional shared capabilities** — `agentOptions`, output schemas, child personas, tool filtering, and harness depth enforcement are rejected by the shared service for this provider. diff --git a/packages/subagent/subagent-codex/README.zh.md b/packages/subagent/subagent-codex/README.zh.md index dd9596e9d8..8532f6cfb5 100644 --- a/packages/subagent/subagent-codex/README.zh.md +++ b/packages/subagent/subagent-codex/README.zh.md @@ -10,7 +10,7 @@ 已发布的 `run.result` 恰好启动一个轮次。它只接受与此次运行的线程和轮次匹配的通知，随后等待权威的终止通知 `turn/completed`。以最后一条 `phase: "final_answer"` 的 `agentMessage` 为准；若 Codex 没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退。过程说明绝不会取代上述任一答案；成功完成的轮次若没有非空白答案，结果也会判为错误。 -对于命令与文件审批，无人值守的提供方会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.148.0 请求形态没有决策选项列表，因此回退到 `decline`。它对权限请求返回作用域限于当前轮次的空权限集，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败。wire 只记录有效模式、请求类别、决定与固定的安全原因，也会识别被拒绝的命令／文件 item 和结构化 `sandboxError` 终态。产品 stderr 会原样转发给 Host，但绝不会被分类或复制进诊断。 +对于命令与文件审批，无人值守的提供方会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.149.1 请求形态没有决策选项列表，因此回退到 `decline`。它对权限请求返回作用域限于当前轮次的空权限集，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败。wire 只记录有效模式、请求类别、决定与固定的安全原因，也会识别被拒绝的命令／文件 item 和结构化 `sandboxError` 终态。产品 stderr 会原样转发给 Host，但绝不会被分类或复制进诊断。 本地取消会在结果竞态中胜出并映射为 `aborted`。失败轮次使用粗粒度类别 `limit`、`access-policy`、`service`、`transport`、`product-error`、`invalid-result` 或 `unknown`；app-server 提前退出使用 `process`。适用的连接与 stream 失败会保留数值 `httpStatusCode`。诊断还会注明 `turn-start`、`turn` 或 `process`，分别包含可用的退出码与信号，且不复制原始字段。`contextWindowExceeded` 仍映射为 `max-tokens`；其他任何远端中断或失败仍映射为 `error`，且该提供方不会产生 `refusal`。参与失败的结构化权限决定会跟在失败行之后。成功与本地取消都不附带这两类事实。 @@ -36,7 +36,7 @@ | `approve-for-me` | `approvalPolicy: on-request`、`approvalsReviewer: auto_review`、`sandbox: workspace-write` | 由 Codex 自动评审权限请求，不等待人工。 | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`、`sandbox: danger-full-access` | 跳过审批与 sandbox；必须显式选择该值。 | -生产环境会解析锁定的 `@openai/codex@0.148.0` 依赖所声明的 `codex` bin，并使用当前 Node 可执行文件启动该 JavaScript wrapper。Wrapper 会选择匹配的原生平台载荷；提供方既不检查也不回退 `PATH` 中的宿主 `codex`。父会话 cwd、`HOME` 与 `CODEX_HOME` 继续让原生 Codex 配置和身份验证保持权威。已配置的 `model` 会原样传给每个临时 `thread/start`；省略时不设置该字段，且提供方不会发现模型、改写别名、选择 `modelProvider` 或 `serviceTier`，也不会设置 fallback。所选权限模式仍是唯一的另一项线程级覆盖。本插件不创建 `CODEX_HOME`、不执行登录，也不探测账户。子进程 seam 会先移除具有凭证特征的环境变量，再应用显式 `env` 覆盖。 +生产环境会解析锁定的 `@openai/codex@0.149.1` 依赖所声明的 `codex` bin，并使用当前 Node 可执行文件启动该 JavaScript wrapper。Wrapper 会选择匹配的原生平台载荷；提供方既不检查也不回退 `PATH` 中的宿主 `codex`。父会话 cwd、`HOME` 与 `CODEX_HOME` 继续让原生 Codex 配置和身份验证保持权威。已配置的 `model` 会原样传给每个临时 `thread/start`；省略时不设置该字段，且提供方不会发现模型、改写别名、选择 `modelProvider` 或 `serviceTier`，也不会设置 fallback。所选权限模式仍是唯一的另一项线程级覆盖。本插件不创建 `CODEX_HOME`、不执行登录，也不探测账户。子进程 seam 会先移除具有凭证特征的环境变量，再应用显式 `env` 覆盖。 本包是可选的 Profile Bundle。将它安装进目标 Profile 后重启该 Profile；安装会把官方 wrapper 与一个兼容的原生平台载荷带入该 Profile，而包所声明的 `cordis.patch.yml` 层只注册休眠的 `codex` Host provider，不会启动 Codex 进程。移除该包后，下一次 Profile 启动会撤回这一 provider 及其私有运行时闭包。 @@ -97,7 +97,7 @@ dsh --profile ## 产品兼容性与证据 -生产环境的协议层有意只实现这一单次执行约定所需的 app-server 方法。运行时依赖与六个 optional-dependency alias 均锁定到 `@openai/codex@0.148.0` / `codex-cli 0.148.0`。普通安装会按当前操作系统与 CPU 选择一个载荷。对于当前 darwin-arm64 载荷，`npm pack --dry-run --json @openai/codex@0.148.0-darwin-arm64` 报告压缩包为 105,734,658 字节、解包后为 271,015,475 字节。该包包含原生 `codex`、`codex-code-mode-host`、`rg` 与 `zsh` 资源；其他平台可能不同，这些数值只用于披露而不是安装阈值。 +生产环境的协议层有意只实现这一单次执行约定所需的 app-server 方法。运行时依赖与六个 optional-dependency alias 均锁定到 `@openai/codex@0.149.1` / `codex-cli 0.149.1`。普通安装会按当前操作系统与 CPU 选择一个载荷。对于当前 darwin-arm64 载荷，`npm pack --dry-run --json @openai/codex@0.149.1-darwin-arm64` 报告压缩包为 114,152,335 字节、解包后为 282,491,555 字节。该包包含原生 `codex`、`codex-code-mode-host`、`rg` 与 `zsh` 资源；其他平台可能不同，这些数值只用于披露而不是安装阈值。 生成的 schema 证据会固定可选的 `ThreadStartParams.model` 字段，包测试则覆盖代表性的错误分组、适用 HTTP status、六个生命周期阶段、进程结果、终止原因映射、unknown 回退、脱敏、结构化权限顺序、取消、并发与清理聚合。无密钥真实产品测试会驱动包内 wrapper 连接回环 Responses fixture，并观测包内 argv、省略模型继承、两个显式实例模型、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、线程级 `never` 对环境中 `on-request` 的覆盖、自动评审启动、不产生文件副作用的无人值守拒绝、真实服务失败、测试拥有临时存储中的显式危险绕过写入、携带安全退出事实的进程／协议失败，以及 wrapper／原生进程完全停稳。 @@ -139,7 +139,7 @@ Codex 子级会在一个全新的临时线程中，以单个轮次接收这些 - **静态选择实例**：Profile 配置项固定提供方名称、可选模型与工具绑定；调用无法动态选择或修改提供方与模型，而且每个公开工具都需要唯一的 `toolName`。 - **身份验证与账户状态仍由原生机制管理**：Bundle 会提供 CLI，但不会创建账户、登录、信任项目或改写 Codex 设置；配置与身份验证失败会公开其生命周期阶段与安全的 `unknown` 回退，而不会增加单独的公开分类体系。 - **委派时必须存在原生平台载荷**：省略 optional dependencies 的安装、不受支持的平台以及缺失或损坏的载荷都会在第一次运行时失败；不会回退到宿主 CLI。 -- **兼容性由开发证据锁定**：若要从已验证的 0.148.0 协议基线升级，必须重新生成上游 schema 证据，并重新运行握手、答案选择、审批、取消、无密钥真实产品以及带密钥的 DeepSeek 随机数测试。 +- **兼容性由开发证据锁定**：若要从已验证的 0.149.1 协议基线升级，必须重新生成上游 schema 证据，并重新运行握手、答案选择、审批、取消、无密钥真实产品以及带密钥的 DeepSeek 随机数测试。 - **没有人工审批路径**：已知的无人值守审批请求会被拒绝，未知服务器请求会以默认拒绝方式使运行失败；三种 Profile 模式都不会创建 DSH 交互通道或逐次调用 allow 策略。 - **assistant 载荷仅包含最终文本**：失败运行可以额外公开独立的安全诊断；推理、过程说明、中间消息、工具通信、用量信息、原始 stderr 和工作区差异不会进入父会话，通用 Job id、通知与状态来自共享作业运行时。 - **没有可选的共享能力**：对于本提供方，共享服务会拒绝 `agentOptions`、输出 schema、子任务角色设定、工具筛选和 harness 深度强制约束。 diff --git a/packages/subagent/subagent-codex/package.json b/packages/subagent/subagent-codex/package.json index c08fd9ea27..2d7e30dc2a 100644 --- a/packages/subagent/subagent-codex/package.json +++ b/packages/subagent/subagent-codex/package.json @@ -49,7 +49,7 @@ "dependencies": { "@deepseek-ai/dsh-sdk-protocol": "workspace:^", "@deepseek-ai/schemastery": "workspace:^", - "@openai/codex": "0.148.0" + "@openai/codex": "0.149.1" }, "devDependencies": { "@deepseek-ai/cordis-plugin-loader": "workspace:^", diff --git a/packages/subagent/subagent-codex/src/wire.ts b/packages/subagent/subagent-codex/src/wire.ts index deb80d4c5f..474d7a9a32 100644 --- a/packages/subagent/subagent-codex/src/wire.ts +++ b/packages/subagent/subagent-codex/src/wire.ts @@ -1,5 +1,5 @@ /** - * Minimal Codex app-server 0.148.0 protocol adapter. The shared JSON-RPC + * Minimal Codex app-server 0.149.1 protocol adapter. The shared JSON-RPC * transport owns framing and request correlation; this module owns only the * product methods, current thread/turn association, unattended approval * responses, and terminal-answer selection. diff --git a/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts b/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts index 0a2925166c..a7014070a0 100644 --- a/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts +++ b/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts @@ -109,8 +109,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)( const version = await execFileAsync(process.execPath, [codexEntry, '--version'], { env: { ...process.env, ...env }, }) - expect(codexPackage.version).toBe('0.148.0') - expect(version.stdout.trim()).toBe('codex-cli 0.148.0') + expect(codexPackage.version).toBe('0.149.1') + expect(version.stdout.trim()).toBe('codex-cli 0.149.1') const parent = { id: 'deepseek-e2e-parent', diff --git a/packages/subagent/subagent-codex/tests/real-product.spec.ts b/packages/subagent/subagent-codex/tests/real-product.spec.ts index af44598195..77e1102d63 100644 --- a/packages/subagent/subagent-codex/tests/real-product.spec.ts +++ b/packages/subagent/subagent-codex/tests/real-product.spec.ts @@ -212,18 +212,18 @@ function responseInputTexts(body: Record): string[] { }) } -describe('real @openai/codex 0.148.0 product', () => { +describe('real @openai/codex 0.149.1 product', () => { it('starts approve-for-me through the real app-server and returns exact text', async () => { - const sentinel = 'REAL_CODEX_SENTINEL_0_148_0' + const sentinel = 'REAL_CODEX_SENTINEL_0_149_1' const task = 'Return the fixture sentinel exactly.' const { harness, fixture } = await realHarness([ { kind: 'complete', text: sentinel }, ], 'approve-for-me') - expect(codexPackage.version).toBe('0.148.0') + expect(codexPackage.version).toBe('0.149.1') const version = await execFileAsync(process.execPath, [codexEntry, '--version'], { env: { ...process.env, ...harness.env }, }) - expect(version.stdout.trim()).toBe('codex-cli 0.148.0') + expect(version.stdout.trim()).toBe('codex-cli 0.149.1') const schemaRoot = mkdtempSync(join(tmpdir(), 'dsh-codex-schema-')) roots.push(schemaRoot) await execFileAsync(process.execPath, [ diff --git a/packages/subagent/subagent-codex/tests/responses-fixture.ts b/packages/subagent/subagent-codex/tests/responses-fixture.ts index 679c18ef1e..e960f36bb2 100644 --- a/packages/subagent/subagent-codex/tests/responses-fixture.ts +++ b/packages/subagent/subagent-codex/tests/responses-fixture.ts @@ -94,7 +94,7 @@ function responseObject(text: string): Record { } /** - * Build the minimal Responses SSE event sequence consumed by Codex 0.148.0. + * Build the minimal Responses SSE event sequence consumed by Codex 0.149.1. * @param text - exact assistant answer. * @returns ordered response lifecycle events. */ diff --git a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts index e6cf696aa7..80a286274b 100644 --- a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts +++ b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts @@ -65,7 +65,7 @@ vi.mock('node:fs', async (importOriginal) => { type JsonObject = Record -const CODEX_VERSION = '0.148.0' +const CODEX_VERSION = '0.149.1' const CODEX_PLATFORM_PACKAGES = [ '@openai/codex-darwin-arm64', '@openai/codex-darwin-x64', @@ -266,7 +266,7 @@ async function initializeWire(): Promise<{ wire.start() const initializing = wire.initialize(new AbortController().signal) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing expect(await child.peer.nextMethod('initialized')).toEqual({ jsonrpc: '2.0', @@ -286,7 +286,7 @@ async function publishRun( ) { const starting = startCodexRun(request(undefined, signal), runSpec(child, specOverrides)) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true } }) @@ -505,7 +505,7 @@ describe('task admission and package contracts', () => { [bypassChild, 'codex-bypass-model'], ] as const) { const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).toMatchObject({ model }) @@ -603,7 +603,7 @@ describe('task admission and package contracts', () => { expect(ctx.subagents.getProvider('codex')).toBeDefined() const starting = ctx.subagents.start('codex', request()) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).not.toHaveProperty('model') @@ -644,7 +644,7 @@ describe('task admission and package contracts', () => { wire.start() const initializing = wire.initialize(new AbortController().signal) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing await child.peer.nextMethod('initialized') const starting = wire.startThread('/workspace', new AbortController().signal) @@ -671,7 +671,7 @@ describe('task admission and package contracts', () => { wire.start() const initializing = wire.initialize(new AbortController().signal) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing await child.peer.nextMethod('initialized') const starting = wire.startThread('/workspace', new AbortController().signal) @@ -753,7 +753,7 @@ describe('CodexAppServerWire', () => { requestAttestation: false, }, }) - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing await child.peer.nextMethod('initialized') @@ -1503,7 +1503,7 @@ describe('run lifecycle and quiescence', () => { void starting.then(() => { published = true }) const initialize = await child.peer.nextMethod('initialize') expect(published).toBe(false) - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(published).toBe(false) @@ -1954,7 +1954,7 @@ describe('run lifecycle and quiescence', () => { const threadChild = fakeChild() const threadStarting = startCodexRun(request(), runSpec(threadChild)) const threadInitialize = await threadChild.peer.nextMethod('initialize') - threadChild.peer.respond(threadInitialize, { userAgent: 'codex-cli 0.148.0' }) + threadChild.peer.respond(threadInitialize, { userAgent: 'codex-cli 0.149.1' }) await threadChild.peer.nextMethod('initialized') const invalidThread = await threadChild.peer.nextMethod('thread/start') threadChild.peer.respond(invalidThread, { thread: { id: '', ephemeral: true } }) @@ -1969,7 +1969,7 @@ describe('run lifecycle and quiescence', () => { ) const exitedThreadInitialize = await exitedThreadChild.peer.nextMethod('initialize') exitedThreadChild.peer.respond(exitedThreadInitialize, { - userAgent: 'codex-cli 0.148.0', + userAgent: 'codex-cli 0.149.1', }) await exitedThreadChild.peer.nextMethod('initialized') await exitedThreadChild.peer.nextMethod('thread/start') @@ -1988,7 +1988,7 @@ describe('run lifecycle and quiescence', () => { const eofBeforeCloseInitialize = await eofBeforeCloseChild.peer .nextMethod('initialize') eofBeforeCloseChild.peer.respond(eofBeforeCloseInitialize, { - userAgent: 'codex-cli 0.148.0', + userAgent: 'codex-cli 0.149.1', }) await eofBeforeCloseChild.peer.nextMethod('initialized') await eofBeforeCloseChild.peer.nextMethod('thread/start') @@ -2006,7 +2006,7 @@ describe('run lifecycle and quiescence', () => { const stderrStarting = startCodexRun(request(), runSpec(stderrChild)) const stderrInitialize = await stderrChild.peer.nextMethod('initialize') stderrChild.stderr.emit('error', new Error('startup stderr broke')) - stderrChild.peer.respond(stderrInitialize, { userAgent: 'codex-cli 0.148.0' }) + stderrChild.peer.respond(stderrInitialize, { userAgent: 'codex-cli 0.149.1' }) await stderrChild.peer.nextMethod('initialized') const stderrThreadStart = await stderrChild.peer.nextMethod('thread/start') stderrChild.peer.respond(stderrThreadStart, { @@ -2032,7 +2032,7 @@ describe('run lifecycle and quiescence', () => { runSpec(child), ) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).toEqual({ @@ -2187,7 +2187,7 @@ describe('run lifecycle and quiescence', () => { signal: new AbortController().signal, }) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.148.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).toEqual({ diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index bf4d444c42..4c4323e98a 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -8316,8 +8316,8 @@ importers: specifier: link:../../../vendor/schemastery version: link:../../../vendor/schemastery '@openai/codex': - specifier: 0.148.0 - version: 0.148.0 + specifier: 0.149.1 + version: 0.149.1 devDependencies: '@deepseek-ai/cordis': specifier: workspace:^ @@ -11545,43 +11545,43 @@ packages: resolution: {integrity: sha512-da6KbdNCV5sr1/txD896V+6W0iamFWrvVl8cHkBSPT+YlvmT3DwXa4jxZnQc+gnuTEqSWbBeoSZYTayXH9wXcw==} engines: {node: '>= 20'} - '@openai/codex@0.148.0': - resolution: {integrity: sha512-bh5kH9+BMrFaHGmLeoSansPdfRksvr4UXzjQInns/KRO7r8VJ+6AAW+SqUsE8XcG3+OW/mI4EEy8Gpo9UDXGvQ==} + '@openai/codex@0.149.1': + resolution: {integrity: sha512-6q5pbcpFbJbqOpkubSDBwXmktQ55aD8eUzGzBF1zASob2DjwhBKDSNGtdZKalfrNJUdTDTPDMmzCXEXs5tMBYA==} engines: {node: '>=16'} hasBin: true - '@openai/codex@0.148.0-darwin-arm64': - resolution: {integrity: sha512-xgBPFiF1fHUlRS7HE6wGB56LjBJh16kGD7b4TTbwdVBZNB4QDkTok+vdkAGrfpVkfKcwGNhPSKDgCw+KMZOVug==} + '@openai/codex@0.149.1-darwin-arm64': + resolution: {integrity: sha512-6X84kTCbnTgPIJ2EdcPsrvwS0Wxsqpa+bCswGmRf4BjhcQ5nPMnBC6yCAaCMj+vrbXQHj+L6sa9FaR4QkmA1qw==} engines: {node: '>=16'} cpu: [arm64] os: [darwin] - '@openai/codex@0.148.0-darwin-x64': - resolution: {integrity: sha512-qepQolhJutfOp+e9i7L3xsi8aoWeCUiiRq274WMWqRj50rKTrXxsuAgkAwDbqEfT3G5VynhYZuQvDsW37JgdNQ==} + '@openai/codex@0.149.1-darwin-x64': + resolution: {integrity: sha512-MfLBQLfcElJL9tvj6y45qVHHMGSXCPnQOixuD3/Zq0g1BW/eFizkrGLdn48cFpc+l8cK+gt5nYG5pQYwVs6g4A==} engines: {node: '>=16'} cpu: [x64] os: [darwin] - '@openai/codex@0.148.0-linux-arm64': - resolution: {integrity: sha512-51DCd+izzk6n4mMh4w2utWj3lTLhSTnCOEJQfRh0LS9nBDkcYZcK3iSKOST6fByRIlLSXuLO33LlYYA1VPot6A==} + '@openai/codex@0.149.1-linux-arm64': + resolution: {integrity: sha512-OqxUfZ1TVvHd18zHPKK/8ZRlpk8Vy11mg5CMHaLxNWldTbwVImDKtSLWT+m8m4NM5Sz4PbjtZMrVT/RfpBW/mQ==} engines: {node: '>=16'} cpu: [arm64] os: [linux] - '@openai/codex@0.148.0-linux-x64': - resolution: {integrity: sha512-uDT9s7AfMr9xLuJX3ZLVWHgHkUpCnZ33CZjZEdVQhrYCIErkDHsCW5TG290nNjaKngK0WxGt5uCcxeUHv9MWWA==} + '@openai/codex@0.149.1-linux-x64': + resolution: {integrity: sha512-Of5fGYgr7tAMsyj6vhXb4/RM/UoA3Zq8BLegUBDC09UNy1XTLGYP/2XD+UX8z3qh0NDwxYdCjFIWdDNijKZggQ==} engines: {node: '>=16'} cpu: [x64] os: [linux] - '@openai/codex@0.148.0-win32-arm64': - resolution: {integrity: sha512-a8iOwLzs8UdnlWDHjgK3W/YSBBsUImG8X5XLBjengp3XGJRruhiIsQtUDUOYimCmotKPM4aX7Ub6zjl/KPxMQQ==} + '@openai/codex@0.149.1-win32-arm64': + resolution: {integrity: sha512-5K0DmOKGK9Bos627p8sK8ATHjovPK0sDyT6h9Cb+4v+5CW5SGw1HLgjGxoLfJ8g3cg6mtg/pRCXXo2L/j71UVA==} engines: {node: '>=16'} cpu: [arm64] os: [win32] - '@openai/codex@0.148.0-win32-x64': - resolution: {integrity: sha512-/Jg8eYw0BqTGNUpnrzzWlK2kbu29NWg7t6pnUDEfxqpTUf+mK8r3okXQn60Zjbk9InYZ4d8SwSjrtOa+i5hSPw==} + '@openai/codex@0.149.1-win32-x64': + resolution: {integrity: sha512-G3QXGAg7nyyhqOeooAMUekBCeHd8a1QByhKcVAFyzNBaI06t6Ft7nsF+1SzFS0spuIdU4YyMi5YD26ukADBQUQ==} engines: {node: '>=16'} cpu: [x64] os: [win32] @@ -17134,31 +17134,31 @@ snapshots: '@octokit/request-error': 7.1.1 '@octokit/webhooks-methods': 6.0.0 - '@openai/codex@0.148.0': + '@openai/codex@0.149.1': optionalDependencies: - '@openai/codex-darwin-arm64': '@openai/codex@0.148.0-darwin-arm64' - '@openai/codex-darwin-x64': '@openai/codex@0.148.0-darwin-x64' - '@openai/codex-linux-arm64': '@openai/codex@0.148.0-linux-arm64' - '@openai/codex-linux-x64': '@openai/codex@0.148.0-linux-x64' - '@openai/codex-win32-arm64': '@openai/codex@0.148.0-win32-arm64' - '@openai/codex-win32-x64': '@openai/codex@0.148.0-win32-x64' + '@openai/codex-darwin-arm64': '@openai/codex@0.149.1-darwin-arm64' + '@openai/codex-darwin-x64': '@openai/codex@0.149.1-darwin-x64' + '@openai/codex-linux-arm64': '@openai/codex@0.149.1-linux-arm64' + '@openai/codex-linux-x64': '@openai/codex@0.149.1-linux-x64' + '@openai/codex-win32-arm64': '@openai/codex@0.149.1-win32-arm64' + '@openai/codex-win32-x64': '@openai/codex@0.149.1-win32-x64' - '@openai/codex@0.148.0-darwin-arm64': + '@openai/codex@0.149.1-darwin-arm64': optional: true - '@openai/codex@0.148.0-darwin-x64': + '@openai/codex@0.149.1-darwin-x64': optional: true - '@openai/codex@0.148.0-linux-arm64': + '@openai/codex@0.149.1-linux-arm64': optional: true - '@openai/codex@0.148.0-linux-x64': + '@openai/codex@0.149.1-linux-x64': optional: true - '@openai/codex@0.148.0-win32-arm64': + '@openai/codex@0.149.1-win32-arm64': optional: true - '@openai/codex@0.148.0-win32-x64': + '@openai/codex@0.149.1-win32-x64': optional: true '@opentelemetry/api-logs@0.220.0': diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml index a73f95d927..45ac3677f7 100644 --- a/pnpm-workspace.yaml +++ b/pnpm-workspace.yaml @@ -78,6 +78,9 @@ minimumReleaseAgeExclude: - '@anthropic-ai/claude-agent-sdk-win32-arm64@0.3.241' - '@anthropic-ai/claude-agent-sdk-win32-x64@0.3.241' - '@anthropic-ai/claude-agent-sdk@0.3.241' + # All platform aliases resolve to the @openai/codex package name, so their + # reviewed exact versions must share one version-union policy entry. + - '@openai/codex@0.149.1||0.149.1-darwin-arm64||0.149.1-darwin-x64||0.149.1-linux-arm64||0.149.1-linux-x64||0.149.1-win32-arm64||0.149.1-win32-x64' patchedDependencies: node-pty@1.2.0-beta.15: patches/node-pty@1.2.0-beta.15.patch