docs: document recent plan and terminal updates#411
docs: document recent plan and terminal updates#411poe-code-agent[bot] wants to merge 15 commits into
Conversation
![poe-code-agent[bot]](https://avatars.githubusercontent.com/in/2645587?s=60&v=4){kind=small}
| | Argument | Required | Description | | ||
| |----------|----------|-------------| | ||
| | `agent` | Yes | Agent to spawn: `claude-code`, `codex`, `opencode`, `kimi`, `goose` | | ||
| | `agent` | Yes | Agent to spawn, such as `claude-code`, `codex`, `cursor`, `opencode`, `kimi`, `goose`, or `poe-agent`. | |
There was a problem hiding this comment.
This changed doc no longer passes npx prettier --check docs/README_FULL.md (the base version does), so the repository format check regresses. Please run npx prettier --write docs/README_FULL.md.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 83260f253b
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| ```bash | ||
| npx poe-code@latest wrap claude | ||
| # Also available: codex, opencode, kimi, goose | ||
| # Also available: codex, cursor, opencode, kimi, goose |
There was a problem hiding this comment.
wrap cursor is advertised in the quickstart, but the wrap command requires the provider to define isolatedEnv and throws Agent "cursor" does not support isolated configuration wrappers. otherwise; src/providers/cursor.ts defines spawn/install support but no isolated wrapper config. Users following this line will get an immediate failure instead of a Poe-routed Cursor session.
Useful? React with 👍 / 👎.
|
|
||
| # Setup a specific agent | ||
| npx poe-code@latest configure codex # (or claude, opencode, kimi, goose) | ||
| npx poe-code@latest configure codex # (or claude, cursor, opencode, kimi, goose) |
There was a problem hiding this comment.
cursor is documented here as a setup target, but the provider has requiresProvider: false and an empty manifest.configure, while the agent-spawn README says Cursor uses the authenticated cursor-agent account with no environment variables injected. Running poe-code configure cursor therefore only records a no-provider config and does not route Cursor API calls through Poe, so this quickstart points users at a setup path that cannot produce the advertised behavior.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1f3372480f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
This package does not have a declarative spawn/resume mapping for poe-agent: allSpawnConfigs only registers Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose, and resolveCliConfig throws when an agent has no spawn config. Users importing @poe-code/agent-spawn and following this line with spawn("poe-agent", { resumeThreadId: ... }) will fail before launch; if the intent is to describe the root CLI/SDK custom Poe Agent handler, it should be documented separately from agent-spawn's declarative mappings.
Useful? React with 👍 / 👎.
|
|
||
| #### Run a plan with follow-up checks | ||
|
|
||
| Gaslight runs a Markdown plan, then resumes the same agent thread with configured follow-up prompts such as testing, simplification, and commit checks. |
There was a problem hiding this comment.
When users follow this new quickstart after gaslight install, the scaffolded config has follow-ups, but the CLI wrapper passes @poe-code/agent-spawn.spawn into runGaslight; that low-level spawn returns only stdout/stderr/exitCode, while runGaslight throws before the first follow-up if result.threadId is missing. In that normal CLI-agent path the documented “resumes the same agent thread” flow stops after round 1 instead of running testing/commit checks.
Useful? React with 👍 / 👎.
1f33724 to
948412b
Compare
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5. The table should also include the newer Codex model set shown later in this file.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | |
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Codex yolo no longer maps to -s danger-full-access; packages/agent-spawn/src/configs/codex.ts uses --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
This summary should match the updated MCP serialization section and supportsMcpAtSpawn(): OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so spawn-time MCP is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 948412b34e
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | `agentArgs` | No | Additional arguments forwarded directly to the agent CLI. | | ||
| | Argument | Required | Description | | ||
| | ----------- | -------- | ------------------------------------------------------------------------------------------------------ | | ||
| | `agent` | Yes | Agent to spawn, such as `claude-code`, `codex`, `cursor`, `opencode`, `kimi`, `goose`, or `poe-agent`. | |
There was a problem hiding this comment.
Including poe-agent in the generic spawn list makes the adjacent --mode read|edit|auto|yolo documentation look applicable to it, but the custom createPoeAgentSpawnHandler drops options.mode when calling spawnPoeAgentWithAcp. In particular, poe-code spawn poe-agent --mode read ... still runs without Poe Agent's read policy, so users relying on this doc for a read-only run get a less constrained session than advertised.
Useful? React with 👍 / 👎.
948412b to
48a7a2e
Compare
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn still has no poe-agent spawn config, so package consumers following this sentence with spawn("poe-agent", { resumeThreadId }) hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
Since this section now includes poe-agent as a spawn target, this overstates --mode: createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read is not constrained by the documented read mode.
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is still out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | |
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Codex yolo no longer maps to -s danger-full-access; packages/agent-spawn/src/configs/codex.ts uses --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 48a7a2e08a
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example calls startManagedProcess() without a spawnDaemon implementation, but StartManagedProcessOptions requires that callback and startManagedProcess calls options.spawnDaemon(spec.id) unconditionally. Users copying the README sample will either get a TypeScript error or a runtime options.spawnDaemon is not a function before the managed process can start, so the usage example needs to show how to provide the daemon launcher (or use an API that does not require one).
Useful? React with 👍 / 👎.
48a7a2e to
cb15c5a
Compare
poe-code-agent
Bot
changed the title
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn still has no poe-agent spawn config (allSpawnConfigs only registers Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose), so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This usage example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) unconditionally before waiting for the daemon to report the managed process state, so copying this sample fails at compile time or at runtime instead of starting the process.
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
Since this section includes poe-agent as a spawn target, this overstates --mode: createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read ... is not constrained by the documented read mode. Please either remove poe-agent from the generic target list or qualify that this mode behavior applies only to declarative agent-spawn providers.
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Codex yolo no longer maps to -s danger-full-access; packages/agent-spawn/src/configs/codex.ts uses --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
cb15c5a to
d5605cd
Compare
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
cursor is included in the Poe-routing claim, but src/providers/cursor.ts has requiresProvider: false and an empty configure manifest; Cursor spawn uses the user's authenticated cursor-agent account instead of Poe provider config.
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | |
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api), and can also spawn Cursor through the authenticated local `cursor-agent` CLI. Instead of managing multiple provider accounts for Poe-routed agents, a single Poe subscription powers those coding agents. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
This overstates --mode now that the same section lists poe-agent: createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read ... is not constrained by the documented read mode.
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | | |
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode for declarative spawn providers: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. Poe Agent uses its custom spawn path and does not currently receive this option. | |
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | | |
| | `openai/gpt-5.2-codex` | | |
| |------|------| | ||
| | Mode | Args | | ||
| | ------ | ----------------------- | | ||
| | `yolo` | `-s danger-full-access` | |
There was a problem hiding this comment.
Codex yolo no longer maps to -s danger-full-access; packages/agent-spawn/src/configs/codex.ts uses --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | `-s danger-full-access` | | |
| | `yolo` | `--dangerously-bypass-approvals-and-sandbox` | |
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Same obsolete Codex yolo flag here; the spawn config uses --dangerously-bypass-approvals-and-sandbox, not -s danger-full-access.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the managed process state, so copying this sample fails at compile time or runtime instead of starting the process.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: d5605cdd9d
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | `agentArgs` | No | Additional arguments forwarded directly to the agent CLI. | | ||
| | Argument | Required | Description | | ||
| | ----------- | -------- | ------------------------------------------------------------------------------------------------------ | | ||
| | `agent` | Yes | Agent to spawn, such as `claude-code`, `codex`, `cursor`, `opencode`, `kimi`, `goose`, or `poe-agent`. | |
There was a problem hiding this comment.
Adding poe-agent to the generic spawn list puts it under the documented “displays a resume command” behavior, but the custom Poe Agent handler currently prints poe-code spawn --agent poe-agent --resume-thread-id ... (src/cli/commands/spawn-poe-agent.ts), while the spawn command only accepts the agent as the positional <agent> argument and defines no --agent option (src/cli/commands/spawn.ts). Users who pick Poe Agent from this list and copy the emitted resume command will hit an unknown-option failure instead of resuming; the hint/docs should use poe-code spawn poe-agent ... or avoid advertising it until the command is valid.
Useful? React with 👍 / 👎.
| | `ingest --sources <sources>` | `claude,codex` collector | Comma-separated trace sources: `claude`, `codex`, or both. | | ||
| | `ingest --since <duration>` | `30d` | Only include recently updated traces. | | ||
| | `ingest --limit <number>` | `200` | Maximum extracted human prompts. | | ||
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | |
There was a problem hiding this comment.
This default is only true when .poe-code/gaslight.yaml does not already exist; resolveOutputPath() writes an agent-prefixed variant such as .poe-code/codex-gaslight.yaml when the default config file is present. In that common case users following this table will look for the generated config in the wrong file, and a later poe-code gaslight run will keep loading the existing gaslight.yaml unless they pass --config for the variant.
Useful? React with 👍 / 👎.
d5605cd to
893f216
Compare
poe-code-agent
Bot
changed the title
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
Since poe-agent is now listed as a spawn target in this section, this row implies poe-code spawn poe-agent --mode read enforces a read-only run. The custom Poe Agent handler currently drops options.mode before calling spawnPoeAgentWithAcp, so users can get a less constrained session than the docs promise. Please either exclude Poe Agent from the generic mode docs or wire/enforce the selected mode before advertising it here.
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | |
| |------|------| | ||
| | Mode | Args | | ||
| | ------ | ----------------------- | | ||
| | `yolo` | `-s danger-full-access` | |
There was a problem hiding this comment.
Codex yolo no longer maps to -s danger-full-access; packages/agent-spawn/src/configs/codex.ts uses --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | `-s danger-full-access` | | |
| | `yolo` | `--dangerously-bypass-approvals-and-sandbox` | |
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Same obsolete Codex yolo flag here; the spawn config uses --dangerously-bypass-approvals-and-sandbox, not -s danger-full-access.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the managed process state, so copying this sample fails at compile time or runtime instead of starting the process.
893f216 to
615b453
Compare
poe-code-agent
Bot
changed the title
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
Cursor is not Poe-routed: src/providers/cursor.ts has requiresProvider: false and an empty configure manifest, and agent-spawn uses the authenticated local cursor-agent account.
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | |
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api), and can also spawn Cursor through the authenticated local `cursor-agent` CLI. Instead of managing multiple provider accounts for Poe-routed agents, a single Poe subscription powers those coding agents. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
This row now sits under a target list that includes poe-agent, but createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read is not constrained by the documented read mode.
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | | |
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode for declarative spawn providers: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. Poe Agent uses its custom spawn path and does not currently receive this option. | |
| | `ingest --sources <sources>` | `claude,codex` collector | Comma-separated trace sources: `claude`, `codex`, or both. | | ||
| | `ingest --since <duration>` | `30d` | Only include recently updated traces. | | ||
| | `ingest --limit <number>` | `200` | Maximum extracted human prompts. | | ||
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | |
There was a problem hiding this comment.
This default is only used when .poe-code/gaslight.yaml does not already exist; resolveOutputPath() writes an agent-prefixed variant such as .poe-code/codex-gaslight.yaml when the default file is present.
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | | |
| | `ingest --output <path>` | `.poe-code/gaslight.yaml`, or an agent-prefixed variant when that file exists | Generated gaslight config path. | |
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This is still out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5; the current Codex model list also includes openai/gpt-5.3-codex.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | | |
| | `openai/gpt-5.3-codex` | | |
| |------|------| | ||
| | Mode | Args | | ||
| | ------ | ----------------------- | | ||
| | `yolo` | `-s danger-full-access` | |
There was a problem hiding this comment.
Codex yolo uses --dangerously-bypass-approvals-and-sandbox in packages/agent-spawn/src/configs/codex.ts, not -s danger-full-access.
| | `yolo` | `-s danger-full-access` | | |
| | `yolo` | `--dangerously-bypass-approvals-and-sandbox` | |
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
Same obsolete Codex yolo flag here; the spawn config maps both yolo and auto to --dangerously-bypass-approvals-and-sandbox.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the daemon to report state, so copying the sample fails before starting the process.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 615b453f4d
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | ||
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | |
There was a problem hiding this comment.
The updated mode table says Codex does not support auto, but the actual spawn config defines codexSpawnConfig.modes.auto and supportsSpawnMode("codex", "auto") returns true; Codex maps it to --dangerously-bypass-approvals-and-sandbox. Users reading this section will wrongly expect poe-code spawn codex --mode auto or Gaslight's default auto mode to fail instead of running in Codex's unattended mode.
Useful? React with 👍 / 👎.
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
This summary still says OpenCode has no MCP spawn support, but the same document now lists OpenCode's OPENCODE_CONFIG_CONTENT serialization and the actual openCodeSpawnConfig exposes mcpEnv, so supportsMcpAtSpawn("opencode") is true. Users relying on the summary will incorrectly avoid passing --mcp-servers to OpenCode even though the CLI can inject them.
Useful? React with 👍 / 👎.
Remove Cursor from wrap and configure quickstart targets because Cursor spawn support does not route calls through Poe provider configuration. Format docs/README_FULL.md with Prettier to restore the repository formatting check. Addresses review comments 3406958006, 3406961902, and 3406961905.
615b453 to
48d1af6
Compare
poe-code-agent
Bot
changed the title
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
Cursor is not Poe-routed: src/providers/cursor.ts has requiresProvider: false and an empty configure manifest, and agent-spawn launches the authenticated local cursor-agent account.
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | |
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api), and can also spawn Cursor through the authenticated local `cursor-agent` CLI. Instead of managing multiple provider accounts for Poe-routed agents, a single Poe subscription powers those coding agents. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
This row now sits under a target list that includes poe-agent, but createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read is not constrained by the documented read mode.
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | | |
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode for declarative spawn providers: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. Poe Agent uses its custom spawn path and does not currently receive this option. | |
| | `ingest --sources <sources>` | `claude,codex` collector | Comma-separated trace sources: `claude`, `codex`, or both. | | ||
| | `ingest --since <duration>` | `30d` | Only include recently updated traces. | | ||
| | `ingest --limit <number>` | `200` | Maximum extracted human prompts. | | ||
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | |
There was a problem hiding this comment.
This default is only used when .poe-code/gaslight.yaml does not already exist; resolveOutputPath() writes an agent-prefixed variant such as .poe-code/codex-gaslight.yaml when the default file is present.
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | | |
| | `ingest --output <path>` | `.poe-code/gaslight.yaml`, or an agent-prefixed variant when that file exists | Generated gaslight config path. | |
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5; the current Codex model set also includes openai/gpt-5.4 and openai/gpt-5.3-codex.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | | |
| | `openai/gpt-5.4` | | | |
| | `openai/gpt-5.3-codex` | | | |
| | `openai/gpt-5.2-codex` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | ||
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | |
There was a problem hiding this comment.
Codex yolo and auto are both supported by packages/agent-spawn/src/configs/codex.ts, and both map to --dangerously-bypass-approvals-and-sandbox; this table still shows the old -s danger-full-access flag and says auto is unsupported.
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the daemon to report state, so copying the sample fails before starting the process.
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
Cursor is not Poe-routed: src/providers/cursor.ts sets requiresProvider: false with an empty configure manifest, and the spawn path launches the user's local cursor-agent account.
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | |
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api), and can also spawn Cursor through the authenticated local `cursor-agent` CLI. Instead of managing multiple provider accounts for Poe-routed agents, a single Poe subscription powers those coding agents. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
This row now sits under a target list that includes poe-agent, but createPoeAgentSpawnHandler() does not pass options.mode into spawnPoeAgentWithAcp. As written, poe-code spawn poe-agent --mode read is documented as read-only but is not constrained by that mode.
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | | |
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode for declarative spawn providers: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. Poe Agent uses its custom spawn path and does not currently receive this option. | |
| | `ingest --sources <sources>` | `claude,codex` collector | Comma-separated trace sources: `claude`, `codex`, or both. | | ||
| | `ingest --since <duration>` | `30d` | Only include recently updated traces. | | ||
| | `ingest --limit <number>` | `200` | Maximum extracted human prompts. | | ||
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | |
There was a problem hiding this comment.
This default is only used when .poe-code/gaslight.yaml does not already exist; resolveOutputPath() writes an agent-prefixed variant such as .poe-code/codex-gaslight.yaml when the default file is present.
| | `ingest --output <path>` | `.poe-code/gaslight.yaml` | Generated gaslight config path. | | |
| | `ingest --output <path>` | `.poe-code/gaslight.yaml`, or an agent-prefixed variant when that file exists | Generated gaslight config path. | |
| | `openai/gpt-5.1-codex-mini` | | | ||
| | Model ID | Default | | ||
| | --------------------------- | ------- | | ||
| | `openai/gpt-5.2-codex` | Yes | |
There was a problem hiding this comment.
This default is out of sync with src/cli/constants.ts, where DEFAULT_CODEX_MODEL is openai/gpt-5.5; the current Codex model set also includes openai/gpt-5.3-codex.
| | `openai/gpt-5.2-codex` | Yes | | |
| | `openai/gpt-5.5` | Yes | | |
| | `openai/gpt-5.3-codex` | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | ||
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | |
There was a problem hiding this comment.
Codex yolo and auto are both supported by packages/agent-spawn/src/configs/codex.ts, and both map to --dangerously-bypass-approvals-and-sandbox; this table still shows the old -s danger-full-access flag and says auto is unsupported.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | `--dangerously-bypass-approvals-and-sandbox` | Not supported | Not supported | Not supported | Not supported | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the daemon to report state, so copying the sample fails before starting the process.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0d5b375dcf
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
Including Cursor in this sentence says Poe Code configures it to route API calls through the Poe API, but the Cursor provider is explicitly requiresProvider: false with an empty configure manifest in src/providers/cursor.ts, and Cursor spawns use the authenticated cursor-agent account without Poe environment injection. Users who choose Cursor from this overview will not get Poe-routed calls through their Poe subscription.
Useful? React with 👍 / 👎.
poe-code-agent
Bot
changed the title
| @@ -1,11 +1,10 @@ | |||
| import { runPreflight, formatPreflightResults } from '@poe-code/e2e-test-runner'; | |||
|
|
|||
| import { formatPreflightResults, runPreflight } from "../packages/e2e-test-runner/src/preflight.js"; | |||
There was a problem hiding this comment.
This direct source import fixes the old globalSetup/matcher problem, but it now exposes unaliased workspace deps during e2e startup. From a clean checkout after npm ci, npm run e2e -- --reporter=verbose --passWithNoTests fails resolving toolcraft-design from packages/e2e-test-runner/src/preflight.ts because e2e only aliases @poe-code/e2e-test-runner and auth-store to source while toolcraft-design (and its workspace transitive deps) still point at unbuilt dist. Please mirror the root vitest workspace-package aliases in e2e/vitest.config.ts or otherwise resolve those workspace deps to source before importing preflight here.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4a2cf2e9cd
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | `agentArgs` | No | Additional arguments forwarded directly to the agent CLI. | | ||
| | Argument | Required | Description | | ||
| | ----------- | -------- | ------------------------------------------------------------------------------------------------------ | | ||
| | `agent` | Yes | Agent to spawn, such as `claude-code`, `codex`, `cursor`, `opencode`, `kimi`, `goose`, or `poe-agent`. | |
There was a problem hiding this comment.
When users pick poe-agent from this generic spawn list and combine it with the adjacent -i, --interactive option, spawn.ts takes the interactive branch before checking custom handlers and calls resolveServiceAdapter for the agent. Poe Agent is registered only as an extraServices custom handler in src/cli/program.ts, not as a provider service, so poe-code spawn poe-agent -i ... fails instead of launching an interactive session. Please either exclude Poe Agent from the generic spawn list/options or document that it only works through the non-interactive handler until the interactive path is wired.
Useful? React with 👍 / 👎.
…ation # Conflicts: # README.md # e2e/setup.ts
| > **Audience**: AI agents and developers who need to understand and use every feature of the `poe-code` library — CLI, SDK, providers, and internals. | ||
|
|
||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | ||
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. |
There was a problem hiding this comment.
Cursor is not Poe-routed: src/providers/cursor.ts sets requiresProvider: false with an empty configure manifest, and agent-spawn launches the authenticated local cursor-agent account.
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, Cursor, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api). Instead of managing multiple provider accounts, a single Poe subscription powers all your coding agents. | |
| `poe-code` is a CLI tool and Node.js SDK that configures coding agents (Claude Code, Codex, OpenCode, Kimi, Goose) to route their API calls through the [Poe API](https://poe.com/api), and can also spawn Cursor through the authenticated local `cursor-agent` CLI. Instead of managing multiple provider accounts for Poe-routed agents, a single Poe subscription powers those coding agents. |
| | `-C, --cwd <path>` | Current dir | Working directory for the agent. | | ||
| | `--stdin` | `false` | Read the prompt from stdin. | | ||
| | `-i, --interactive` | `false` | Launch in interactive TUI mode (inherits stdio). | | ||
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | |
There was a problem hiding this comment.
Because this section lists poe-agent, this row overstates what --mode does: createPoeAgentSpawnHandler() does not pass options.mode to spawnPoeAgentWithAcp, so poe-code spawn poe-agent --mode read is not constrained by this documented mode.
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. | | |
| | `--mode <mode>` | Prompted; `--yes` uses `yolo` | Permission mode for declarative spawn providers: `yolo`, `auto`, `edit`, or `read`. Unsupported modes fail before launch with the supported-mode list. Poe Agent uses its custom spawn path and does not currently receive this option. | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | ||
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | |
There was a problem hiding this comment.
Codex yolo and auto are both supported by packages/agent-spawn/src/configs/codex.ts, and both map to --dangerously-bypass-approvals-and-sandbox; this table still shows the old flag and says auto is unsupported.
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | Not supported | Not supported | Not supported | Not supported | Not supported | | |
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `--dangerously-bypass-approvals-and-sandbox` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | | |
| | `auto` | Native safe-action auto approval when the agent supports it | `--permission-mode auto` | `--dangerously-bypass-approvals-and-sandbox` | Not supported | Not supported | Not supported | Not supported | |
| | ----------- | ------------- | ---------- | ---------- | ------------- | ----- | --------- | ----------- | ------ | | ||
| | Claude Code | `claude-code` | `claude` | `claude` | JSON | Yes | Yes | Yes | Yes | | ||
| | Codex | `codex` | — | `codex` | TOML | Yes | Yes | Yes | Yes | | ||
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | |
There was a problem hiding this comment.
OpenCode has mcpEnv: serializeOpenCodeMcpEnv, so supportsMcpAtSpawn("opencode") returns true and this summary should say MCP spawn is supported.
| | OpenCode | `opencode` | — | `opencode` | JSON | No | No | Yes | Yes | | |
| | OpenCode | `opencode` | — | `opencode` | JSON | No | Yes | Yes | Yes | |
|
|
||
| ## Resuming sessions | ||
|
|
||
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. |
There was a problem hiding this comment.
@poe-code/agent-spawn has no poe-agent entry in allSpawnConfigs, so package consumers following this with resumeThreadId hit Agent "poe-agent" has no spawn config. Poe Agent resume is handled by the top-level CLI/provider path instead.
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, Goose, and Poe Agent have resume mappings; Poe Agent persists its local message history under `~/.poe-code/sessions/`. | |
| Pass `resumeThreadId` to continue a prior provider thread/session. Declarative agent configs decide where the resume arguments are inserted and how user-facing resume hints are rendered. Claude Code, Codex, Cursor, OpenCode, Kimi, and Goose have resume mappings. |
| ```ts | ||
| import { startManagedProcess, stopManagedProcess } from "@poe-code/process-launcher"; | ||
|
|
||
| const record = await startManagedProcess({ |
There was a problem hiding this comment.
This example omits the required spawnDaemon callback. StartManagedProcessOptions requires it, and startManagedProcess() calls options.spawnDaemon(spec.id) before waiting for the daemon to report state, so copying the sample fails before starting the process.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bfe273abd3
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | `read` | Read-only, no modifications | `--permission-mode plan` | `-s read-only` | `--agent plan` | (none) | `GOOSE_MODE=chat` | | ||
| | Mode | Description | Claude Code Args | Codex Args | Cursor Args | OpenCode Args | Kimi Args | Goose | | ||
| | ------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------- | ---------------------------- | -------------- | ------------- | -------------------------- | | ||
| | `yolo` | Full access, no permission prompts | `--dangerously-skip-permissions` | `-s danger-full-access` | `--force --sandbox disabled` | (none) | `--yolo` | `GOOSE_MODE=auto` | |
There was a problem hiding this comment.
For Codex yolo runs, the actual codexSpawnConfig.modes.yolo in packages/agent-spawn/src/configs/codex.ts emits --dangerously-bypass-approvals-and-sandbox, not -s danger-full-access. Users debugging or reproducing poe-code spawn codex --mode yolo from this new table will get a command that does not match Poe Code's behavior, so this row should be updated to the configured flag.
Useful? React with 👍 / 👎.
| |--------|-------------| | ||
| | Option | Description | | ||
| | ---------------- | -------------------------------------------- | | ||
| | `--agent <name>` | Agent to configure (alias for the argument). | |
There was a problem hiding this comment.
This table advertises poe-code skill configure --agent ..., but registerSkillCommand only defines the positional [agent] plus --local, --global, and --yes for skill configure (and skill unconfigure likewise has no --agent). Users following this documented alias get an unknown-option failure instead of configuring skills, so either wire the option or document the positional argument only.
Useful? React with 👍 / 👎.
| homeDir: "/home/test", | ||
| plan: ".poe-code/pipeline/plans/plan-auth.yaml", | ||
| maxRuns: 5, | ||
| worktree: true, |
There was a problem hiding this comment.
This example imports runPipeline from @poe-code/pipeline, but the package's exported PipelineRunOptions has no worktree field; worktree support is added only by the root poe-code SDK wrapper. TypeScript users copying this hit an excess-property error, and plain JavaScript callers silently run without isolation/reconciliation; the same root-SDK-only mismatch appears in the new Gaslight/Ralph package API docs, so these package READMEs should either point to poe-code or omit worktree.
Useful? React with 👍 / 👎.
1 participant
Summary
agent/update-documentationPR for commits that landed onmainduring the last 24 hours.poe-code update, package-manager selection, version-check behavior, and dry-run behavior.poe-code worktreecommands, CLI--worktreesupport, SDK worktree helpers, and package-level worktree APIs.maininto the PR branch and kept the root README aligned with the trimmed main README while preserving the existing local skill documentation.Reviewed commits
7b0d2db8feat: add update command57ef4133test: speed up terminal-pilot process regression795d9609feat: add toolcraft markdown html rendererc385f9bbdocs: document toolcraft design exports74468b5ffeat: add managed worktree execution1cf19eb8docs: clarify toolcraft design npm install9af55c26fix: simplify worktree reconciliation surface99e66beefix: accept acp end turn stop reason6b74ceebdocs: add toolcraft markdown highlighting planacd813dbdocs: expand toolcraft markdown highlighting plan72891399docs: refine toolcraft highlighting plan constraints94d8297ffeat: add toolcraft markdown syntax highlighting4b6e3533fix: export toolcraft markdown token types1eafbd44docs: document toolcraft markdown syntax highlighting41f0fb3bfeat: expand toolcraft markdown highlighter languagesb3c8f65adocs: update toolcraft highlighter language listf638bdb1feat: broaden toolcraft markdown language highlighting73c762bffix: trim root help outputValidation
git diff --checknpx prettier --check README.md docs/README_FULL.md docs/changelog/2026-06-24-update-worktrees-toolcraft.md packages/agent-gaslight/README.md packages/experiment-loop/README.md packages/pipeline/README.md packages/poe-acp-client/README.md packages/ralph/README.md packages/superintendent/README.md packages/worktree/README.mdnpm run buildnpm run lint:packagesnpm run dev -- update --helpnpm run dev -- worktree --helpnpm run dev -- worktree reconcile --helpnpm run dev -- gaslight --help | grep -A3 -B3 -- --worktreenpm run dev -- pipeline run --help | grep -A3 -B3 -- --worktreenpm run dev -- ralph run --help | grep -A3 -B3 -- --worktreenpm run dev -- experiment run --help | grep -A3 -B3 -- --worktreenpm run dev -- harness run --help | grep -A3 -B3 -- --worktreenpm run lint:eslint(warnings only: existing_worktreeunused-var warnings insrc/sdk/experiment.tsandsrc/sdk/gaslight.ts)npm run lint:typesnpm run lint:packagesnpm test(800 files passed, 13,929 tests passed, 2 files / 7 tests skipped)guard,run,pr / test,e2e, andTruffleHog Advisory Scanpassing.e2ewas rerun once after a transient KimiInternal server error; the rerun passed.Notes
agent/update-documentation; no new PR was opened.