Documentation 2026-08-19 17:02 UTC to 2026-08-20 01:57 UTC

267 267 

268* Pass `settingSources: []` in TypeScript or `setting_sources=[]` in Python so no filesystem settings load.268* Pass `settingSources: []` in TypeScript or `setting_sources=[]` in Python so no filesystem settings load.

269* Set `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1` in `env`. [Auto memory](/docs/en/memory#auto-memory) at `~/.claude/projects/<project>/memory/` loads into the system prompt regardless of `settingSources`. See [What settingSources does not control](/docs/en/agent-sdk/claude-code-features#what-settingsources-does-not-control) for the other inputs that load unconditionally.269* Set `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1` in `env`. [Auto memory](/docs/en/memory#auto-memory) at `~/.claude/projects/<project>/memory/` loads into the system prompt regardless of `settingSources`. See [What settingSources does not control](/docs/en/agent-sdk/claude-code-features#what-settingsources-does-not-control) for the other inputs that load unconditionally.

270* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config.270* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory, you can also set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) in `env` to keep the transcript paths under it short. Requires TypeScript Agent SDK v0.3.234 or later.

271* Use a per-tenant working directory. Pass `cwd` explicitly on every `query()` call.271* Use a per-tenant working directory. Pass `cwd` explicitly on every `query()` call.

272* Apply per-tenant egress rules at your proxy, such as distinct outbound IPs, credentials, or domain allowlists, so a compromised tenant cannot exfiltrate data via another tenant's outbound policy.272* Apply per-tenant egress rules at your proxy, such as distinct outbound IPs, credentials, or domain allowlists, so a compromised tenant cannot exfiltrate data via another tenant's outbound policy.

273 273 

274The example below applies the four SDK-level options together. Construct `tenantDir` and `configDir` so each tenant gets a path no other tenant can read. In TypeScript, `env` replaces the subprocess environment, so spread `...process.env` to keep inherited variables like `PATH` and `ANTHROPIC_API_KEY`. In Python, `env` is merged on top of the inherited environment.274The example below applies the settings, auto memory, config directory, and working directory options together. Construct `tenantDir` and `configDir` so each tenant gets a path no other tenant can read. In TypeScript, `env` replaces the subprocess environment, so spread `...process.env` to keep inherited variables like `PATH` and `ANTHROPIC_API_KEY`. In Python, `env` is merged on top of the inherited environment.

275 275 

276<CodeGroup>276<CodeGroup>

277 ```typescript TypeScript theme={null}277 ```typescript TypeScript theme={null}

86 ```86 ```

87</CodeGroup>87</CodeGroup>

88 88 

89`SessionKey` addresses one transcript. `projectKey` is a stable, filesystem-safe encoding of the working directory, `sessionId` is the session UUID, and `subpath` is set when the entry belongs to a subagent transcript or sidecar file rather than the main conversation. Because `projectKey` encodes the working directory, resume or continue from the store from a working directory matching the original run's. Treat `subpath` as an opaque key suffix; it follows the on-disk layout, for example `subagents/agent-<id>`. When `subpath` is undefined the key refers to the main transcript.89`SessionKey` addresses one transcript. `projectKey` is a stable, filesystem-safe encoding of the working directory, `sessionId` is the session UUID, and `subpath` is set when the entry belongs to a subagent transcript or sidecar file rather than the main conversation.

90 

91Because `projectKey` encodes the working directory, resume or continue from the store from a working directory matching the original run's. In TypeScript, if you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR` in a query's [`env` option](/docs/en/agent-sdk/typescript#options), the SDK keys that query's entries, and its `resume` and `continue` lookups, by that name instead. Requires Agent SDK v0.3.234 or later.

92 

93Treat `subpath` as an opaque key suffix; it follows the on-disk layout, for example `subagents/agent-<id>`. When `subpath` is undefined the key refers to the main transcript.

90 94 

91| Method | Required | Called when |95| Method | Required | Called when |

92| :--------------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |96| :--------------------- | :------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

269You should see a response that builds on the earlier analysis instead of starting fresh. That confirms the agent resumed the session with its prior context intact.269You should see a response that builds on the earlier analysis instead of starting fresh. That confirms the agent resumed the session with its prior context intact.

270 270 

271<Tip>271<Tip>

272 Claude Code stores sessions under `~/.claude/projects/<encoded-cwd>/*.jsonl`. If you set the `CLAUDE_CONFIG_DIR` environment variable, look under `$CLAUDE_CONFIG_DIR/projects/` instead. To find your session's directory, replace every non-alphanumeric character in the absolute working directory with `-`: `/Users/me/proj` becomes `-Users-me-proj`. For a working directory whose converted name exceeds 200 characters, Claude Code [truncates the name and appends a hash](/docs/en/sessions#where-transcripts-are-stored), so match the first 200 characters of the converted name when you list `projects/`.272 Claude Code stores sessions under `~/.claude/projects/<encoded-cwd>/*.jsonl`. If you set the `CLAUDE_CONFIG_DIR` environment variable, look under `$CLAUDE_CONFIG_DIR/projects/` instead.

273 

274 To find your session's directory, replace every non-alphanumeric character in the absolute working directory with `-`: `/Users/me/proj` becomes `-Users-me-proj`. For a working directory whose converted name exceeds 200 characters, Claude Code [truncates the name and appends a hash](/docs/en/sessions#where-transcripts-are-stored), so match the first 200 characters of the converted name when you list `projects/`.

275 

276 If you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR`, look under that name in `projects/` instead. Requires TypeScript Agent SDK v0.3.234 or later.

273 277 

274 You can resume from any working directory:278 You can resume from any working directory:

275 279 

1331 plugins: { name: string; path: string }[];1331 plugins: { name: string; path: string }[];

1332 fast_mode_state?: FastModeState;1332 fast_mode_state?: FastModeState;

1333 fast_mode_disabled_reason?: FastModeDisabledReason;1333 fast_mode_disabled_reason?: FastModeDisabledReason;

1334 effort?: "low" | "medium" | "high" | "xhigh" | "max" | null;

1334 capabilities?: string[];1335 capabilities?: string[];

1335};1336};

1336```1337```

1339 1340 

1340`terminal_slash_commands` names the entries in `slash_commands` whose interface is bound to the local terminal, such as `exit`. You can send them like any other entry in `slash_commands`; the field exists so a remote or mobile client can hide them from its command menus. The field is present only when non-empty, and requires Agent SDK v0.3.229 or later.1341`terminal_slash_commands` names the entries in `slash_commands` whose interface is bound to the local terminal, such as `exit`. You can send them like any other entry in `slash_commands`; the field exists so a remote or mobile client can hide them from its command menus. The field is present only when non-empty, and requires Agent SDK v0.3.229 or later.

1341 1342 

1343* `effort`: the [effort level](/docs/en/model-config#adjust-effort-level) Claude Code sends on the session's next request, or `null` when it sends none. Claude Code sets the field only on the init message it sends to [Remote Control](/docs/en/remote-control) clients, and omits it from the init message your application reads. Requires Agent SDK v0.3.234 or later.

1344 

1342The `capabilities` array names the protocol behaviors this CLI implements, so you can feature-detect instead of comparing `claude_code_version` strings. It is an open set: ignore values you don't recognize, and check for the specific capability whose behavior you rely on. The field requires Claude Code v2.1.205 or later and is absent on earlier CLIs.1345The `capabilities` array names the protocol behaviors this CLI implements, so you can feature-detect instead of comparing `claude_code_version` strings. It is an open set: ignore values you don't recognize, and check for the specific capability whose behavior you rely on. The field requires Claude Code v2.1.205 or later and is absent on earlier CLIs.

1343 1346 

1344| Capability | Meaning |1347| Capability | Meaning |

1570 | {1573 | {

1571 kind: "peer";1574 kind: "peer";

1572 from: string;1575 from: string;

1576 fromMode?: "bypass" | "prompting";

1573 name?: string;1577 name?: string;

1574 fromSession?: string;1578 fromSession?: string;

1575 senderTaskId?: string;1579 senderTaskId?: string;

1609A `peer` origin identifies which agent sent the message: an in-process [teammate](/docs/en/agent-teams) sending to `main` with `SendMessage`, or a [cross-session peer](/docs/en/cross-session-messaging), another of your Claude Code sessions. A cross-session peer can run on the same machine, or on [another of your machines](/docs/en/cross-session-messaging#message-sessions-on-other-machines) or [Claude Code on the web](/docs/en/claude-code-on-the-web) when its message arrives through Remote Control. The two kinds of sender fill the fields differently:1613A `peer` origin identifies which agent sent the message: an in-process [teammate](/docs/en/agent-teams) sending to `main` with `SendMessage`, or a [cross-session peer](/docs/en/cross-session-messaging), another of your Claude Code sessions. A cross-session peer can run on the same machine, or on [another of your machines](/docs/en/cross-session-messaging#message-sessions-on-other-machines) or [Claude Code on the web](/docs/en/claude-code-on-the-web) when its message arrives through Remote Control. The two kinds of sender fill the fields differently:

1610 1614 

1611* `from`: the teammate's name, or the sender address for a cross-session peer. For a [one-way cross-machine message](/docs/en/cross-session-messaging#message-sessions-on-other-machines), the sender has no reply address and `from` is `"unknown"`. The value is sender-authored; `verifiedPeerPid` is the verified identity.1615* `from`: the teammate's name, or the sender address for a cross-session peer. For a [one-way cross-machine message](/docs/en/cross-session-messaging#message-sessions-on-other-machines), the sender has no reply address and `from` is `"unknown"`. The value is sender-authored; `verifiedPeerPid` is the verified identity.

1616* `fromMode`: the sending session's permission class, `bypass` or `prompting`, declared by a host that relays a peer message between your sessions, such as the [desktop app](/docs/en/desktop#work-across-sessions). Claude Code reads it in the receiving session when it applies the [inbound controls](/docs/en/cross-session-messaging#control-inbound-messages). Requires Agent SDK v0.3.234 or later.

1612* `senderTaskId`: the teammate's task ID. Absent for a cross-session peer.1617* `senderTaskId`: the teammate's task ID. Absent for a cross-session peer.

1613* `name`: the sender's display name, normalized by Claude Code: it strips Unicode control, format, surrogate, and line or paragraph separator code points, then trims the result and caps it at 64 code points with an ellipsis. Requires Claude Code v2.1.205 or later.1618* `name`: the sender's display name, normalized by Claude Code: it strips Unicode control, format, surrogate, and line or paragraph separator code points, then trims the result and caps it at 64 code points with an ellipsis. Requires Claude Code v2.1.205 or later.

1614* `body`: the decoded message body with the peer envelope stripped, byte-exact with what the model sees. Always present for a teammate message; for a cross-session peer, present only when the turn is exactly one peer envelope formed by Claude Code. Render `name` and `body` instead of re-parsing the message text. Requires Claude Code v2.1.205 or later.1619* `body`: the decoded message body with the peer envelope stripped, byte-exact with what the model sees. Always present for a teammate message; for a cross-session peer, present only when the turn is exactly one peer envelope formed by Claude Code. Render `name` and `body` instead of re-parsing the message text. Requires Claude Code v2.1.205 or later.

2925 label?: string;2930 label?: string;

2926 url?: string;2931 url?: string;

2927 force?: boolean;2932 force?: boolean;

2933 capabilities?: Record<string, unknown>;

2934 contract?: "latest" | string;

2928};2935};

2929```2936```

2930 2937 

2932 2939 

2933Pass `"list"` to enumerate the user's published artifacts; only `limit` and `scope` may accompany it. `scope` defaults to `"mine"`, which lists artifacts the user owns; `"shared"` lists artifacts other people shared with the user, and `"all"` lists both.2940Pass `"list"` to enumerate the user's published artifacts; only `limit` and `scope` may accompany it. `scope` defaults to `"mine"`, which lists artifacts the user owns; `"shared"` lists artifacts other people shared with the user, and `"all"` lists both.

2934 2941 

2942* `capabilities`: the runtime capabilities the published page uses, keyed by capability name, such as the [connectors the page may call](/docs/en/artifacts#pull-live-data-with-mcp-connectors). The artifact service validates the declaration and rejects a publish that names a capability the account can't use or gives one an invalid config. Pass `{}` to clear a stored declaration, and omit the field on a redeploy to keep it. Requires Agent SDK v0.3.235 or later.

2943* `contract`: the runtime version the published page runs against. Omit it to keep the artifact's current version, pass `"latest"` to upgrade, or pass a specific version to pin or roll back. Requires Agent SDK v0.3.235 or later.

2944 

2935The types are exported, but the tool is off by default in Agent SDK sessions. Publishing also requires every condition in the [artifacts availability table](/docs/en/artifacts#availability), which sessions authenticated with an API key don't meet.2945The types are exported, but the tool is off by default in Agent SDK sessions. Publishing also requires every condition in the [artifacts availability table](/docs/en/artifacts#availability), which sessions authenticated with an API key don't meet.

2936 2946 

2937### Projects2947### Projects

3191 staleReadFileStateHint?: string;3201 staleReadFileStateHint?: string;

3192 ghRateLimitHint?: string;3202 ghRateLimitHint?: string;

3193 gitOperation?: {3203 gitOperation?: {

3194 commit?: { sha: string; kind: "committed" | "amended" | "cherry-picked" };3204 commit?: { sha: string; kind: "committed" | "amended" | "cherry-picked"; branch?: string };

3195 push?: { branch: string };3205 push?: { branch: string };

3196 branch?: { ref: string; action: "merged" | "rebased" };3206 branch?: { ref: string; action: "merged" | "rebased" };

3197 pr?: {3207 pr?: {

3198 number: number;3208 number: number;

3199 url?: string;3209 url?: string;

3200 action: "created" | "edited" | "merged" | "commented" | "closed" | "ready" | "draft" | "auto-merge-enabled" | "auto-merge-disabled";3210 action: "created" | "edited" | "merged" | "commented" | "closed" | "reopened" | "ready" | "draft" | "auto-merge-enabled" | "auto-merge-disabled";

3201 };3211 };

3202 };3212 };

3203};3213};

3215 3225 

3216When a subagent running in the foreground owns a backgrounded command, Claude Code terminates the command when that subagent gives its final response. Claude Code sets `backgroundEndsWithFinalResponse` to `true` on such commands, and omits the field when the command survives the turn, as commands started by the main conversation or by background subagents do. The field requires Claude Code v2.1.227 or later.3226When a subagent running in the foreground owns a backgrounded command, Claude Code terminates the command when that subagent gives its final response. Claude Code sets `backgroundEndsWithFinalResponse` to `true` on such commands, and omits the field when the command survives the turn, as commands started by the main conversation or by background subagents do. The field requires Claude Code v2.1.227 or later.

3217 3227 

3228Claude Code sets `gitOperation.commit.branch` to the branch named in git's commit summary line, and omits it for a commit made on a detached HEAD. The field requires Agent SDK v0.3.227 or later. Claude Code reports a `gh pr reopen` command as the `reopened` PR action, which requires Agent SDK v0.3.234 or later.

3229 

3218### Monitor3230### Monitor

3219 3231 

3220**Tool name:** `Monitor`3232**Tool name:** `Monitor`

4097 4109 

4098### `ApiKeySource`4110### `ApiKeySource`

4099 4111 

4112Where the API key for the session's requests came from, reported as `apiKeySource` on the [`SDKSystemMessage`](#sdksystemmessage) init message.

4113 

4100```typescript theme={null}4114```typescript theme={null}

4101type ApiKeySource = "user" | "project" | "org" | "temporary" | "oauth";4115type ApiKeySource =

4116 | "ANTHROPIC_API_KEY"

4117 | "apiKeyHelper"

4118 | "/login managed key"

4119 | "none"

4120 | "user"

4121 | "project"

4122 | "org"

4123 | "temporary"

4124 | "oauth";

4102```4125```

4103 4126 

4104<Note>4127Claude Code reports one of four values:

4105 At runtime, the `apiKeySource` field on the [`SDKSystemMessage`](#sdksystemmessage) init message can also be the string `"none"` when no API key is in use, for example when the session authenticates with an OAuth token. Handle values outside this union defensively.4128 

4106</Note>4129| Value | Key in use |

4130| -------------------- | ------------------------------------------------------------------------------------------------------------------------------- |

4131| `ANTHROPIC_API_KEY` | The key in the `ANTHROPIC_API_KEY` environment variable |

4132| `apiKeyHelper` | The key returned by your [`apiKeyHelper`](/docs/en/settings#available-settings) command |

4133| `/login managed key` | The key Claude Code stored when you logged in with a [Claude Console account](/docs/en/authentication#claude-console-authentication) |

4134| `none` | No API key. The session authenticates another way, such as a claude.ai login, a bearer token, or a cloud provider |

4135 

4136Agent SDK v0.3.234 and later list these four values in the type. The type also keeps `user`, `project`, `org`, `temporary`, and `oauth` so older code still compiles, and Claude Code doesn't report them.

4107 4137 

4108### `SdkBeta`4138### `SdkBeta`

4109 4139 

100 100 

101## Precedence101## Precedence

102 102 

103Some behaviors have both an environment variable and a dedicated settings key. If you set both, the environment variable takes precedence. For example, `ANTHROPIC_MODEL` overrides the `model` setting, and `CLAUDE_CODE_AUTO_CONNECT_IDE` overrides `autoConnectIde`. Claude Code uses the settings key only when the environment variable is unset.103Some behaviors have both an environment variable and a dedicated settings key. If you set both, the environment variable takes precedence, except for [`ANTHROPIC_DEFAULT_MODEL`](/docs/en/model-config#set-a-default-model-for-new-sessions). For example, `ANTHROPIC_MODEL` overrides the `model` setting, and `CLAUDE_CODE_AUTO_CONNECT_IDE` overrides `autoConnectIde`.

104 104 

105When the same variable is set in both your shell and a settings file `env` block, the settings file value applies. Claude Code writes each `env` entry into the process environment at startup and again when the file changes, replacing the value inherited from the shell. A few variables are special-cased; the [`env` setting](/docs/en/settings#available-settings) lists the exceptions.105When the same variable is set in both your shell and a settings file `env` block, the settings file value applies. Claude Code writes each `env` entry into the process environment at startup and again when the file changes, replacing the value inherited from the shell. A few variables are special-cased; the [`env` setting](/docs/en/settings#available-settings) lists the exceptions.

106 106 

157| `ANTHROPIC_DEFAULT_HAIKU_MODEL_DESCRIPTION` | Display description for the pinned Haiku model in the `/model` picker. Defaults to `Custom Haiku model` when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |157| `ANTHROPIC_DEFAULT_HAIKU_MODEL_DESCRIPTION` | Display description for the pinned Haiku model in the `/model` picker. Defaults to `Custom Haiku model` when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

158| `ANTHROPIC_DEFAULT_HAIKU_MODEL_NAME` | Display name for the pinned Haiku model in the `/model` picker. Defaults to the model ID when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |158| `ANTHROPIC_DEFAULT_HAIKU_MODEL_NAME` | Display name for the pinned Haiku model in the `/model` picker. Defaults to the model ID when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

159| `ANTHROPIC_DEFAULT_HAIKU_MODEL_SUPPORTED_CAPABILITIES` | Comma-separated list of [capabilities](/docs/en/model-config#customize-pinned-model-display-and-capabilities) the pinned Haiku model supports, for example `effort,thinking`. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |159| `ANTHROPIC_DEFAULT_HAIKU_MODEL_SUPPORTED_CAPABILITIES` | Comma-separated list of [capabilities](/docs/en/model-config#customize-pinned-model-display-and-capabilities) the pinned Haiku model supports, for example `effort,thinking`. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

160| `ANTHROPIC_DEFAULT_MODEL` | Model that new sessions start on by default. Requires Claude Code v2.1.236 or later. See [Set a default model for new sessions](/docs/en/model-config#set-a-default-model-for-new-sessions) |

160| `ANTHROPIC_DEFAULT_OPUS_MODEL` | Model ID that the `opus` alias resolves to, and that `opusplan` uses while Plan Mode is active. See [Model configuration](/docs/en/model-config#environment-variables) |161| `ANTHROPIC_DEFAULT_OPUS_MODEL` | Model ID that the `opus` alias resolves to, and that `opusplan` uses while Plan Mode is active. See [Model configuration](/docs/en/model-config#environment-variables) |

161| `ANTHROPIC_DEFAULT_OPUS_MODEL_DESCRIPTION` | Display description for the pinned Opus model in the `/model` picker. When not set, defaults to `Custom Opus model`, or `Custom Opus model (1M context)` if the pinned model ID has the `[1m]` suffix and `CLAUDE_CODE_DISABLE_1M_CONTEXT` isn't turned on. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |162| `ANTHROPIC_DEFAULT_OPUS_MODEL_DESCRIPTION` | Display description for the pinned Opus model in the `/model` picker. When not set, defaults to `Custom Opus model`, or `Custom Opus model (1M context)` if the pinned model ID has the `[1m]` suffix and `CLAUDE_CODE_DISABLE_1M_CONTEXT` isn't turned on. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

162| `ANTHROPIC_DEFAULT_OPUS_MODEL_NAME` | Display name for the pinned Opus model in the `/model` picker. Defaults to the model ID when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |163| `ANTHROPIC_DEFAULT_OPUS_MODEL_NAME` | Display name for the pinned Opus model in the `/model` picker. Defaults to the model ID when not set. See [Model configuration](/docs/en/model-config#customize-pinned-model-display-and-capabilities) |

322| `CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY` | Set to `1` to stop Claude Code from passing `-ExecutionPolicy Bypass` when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so `.ps1` scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy `MachinePolicy` or `UserPolicy` regardless of this setting |323| `CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY` | Set to `1` to stop Claude Code from passing `-ExecutionPolicy Bypass` when spawning PowerShell for tool calls, hooks, and status line commands, and respect the machine's effective execution policy instead. By default Claude Code bypasses execution policy at process scope so `.ps1` scripts and module imports work on default-Restricted Windows installs. Process-scope bypass never overrides Group Policy `MachinePolicy` or `UserPolicy` regardless of this setting |

323| `CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS` | Maximum time in milliseconds that [non-interactive mode](/docs/en/headless#background-tasks-at-exit) with the `-p` flag waits after the final turn for background subagents and workflows whose result is part of the output. Default: `600000`, or 10 minutes. When the cap is exceeded, remaining background tasks are terminated and the process exits. Set to `0` to wait indefinitely. This cap is separate from the five-second grace period that applies to plain background shells |324| `CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS` | Maximum time in milliseconds that [non-interactive mode](/docs/en/headless#background-tasks-at-exit) with the `-p` flag waits after the final turn for background subagents and workflows whose result is part of the output. Default: `600000`, or 10 minutes. When the cap is exceeded, remaining background tasks are terminated and the process exits. Set to `0` to wait indefinitely. This cap is separate from the five-second grace period that applies to plain background shells |

324| `CLAUDE_CODE_PROCESS_WRAPPER` | Launch the processes Claude Code starts from its own binary, such as the background service that hosts [agent view](/docs/en/agent-view) sessions, through a corporate launcher given as an argv prefix like `/opt/corp/launcher`. Set it in the `env` block of user or [managed settings](/docs/en/permissions#managed-settings), not as a shell export, so the detached background service inherits it; project and local settings can't set it. Equivalent to the [`processWrapper` setting](/docs/en/settings#available-settings), which requires Claude Code v2.1.210 or later; this variable takes precedence when both are set. The VS Code extension configures its own launcher separately through its `claudeProcessWrapper` setting. Ignored on Windows. See [Run Claude Code behind a corporate launcher](/docs/en/corporate-launcher) for the value format, what the launcher covers, and the contract the launcher must satisfy. Requires Claude Code v2.1.208 or later |325| `CLAUDE_CODE_PROCESS_WRAPPER` | Launch the processes Claude Code starts from its own binary, such as the background service that hosts [agent view](/docs/en/agent-view) sessions, through a corporate launcher given as an argv prefix like `/opt/corp/launcher`. Set it in the `env` block of user or [managed settings](/docs/en/permissions#managed-settings), not as a shell export, so the detached background service inherits it; project and local settings can't set it. Equivalent to the [`processWrapper` setting](/docs/en/settings#available-settings), which requires Claude Code v2.1.210 or later; this variable takes precedence when both are set. The VS Code extension configures its own launcher separately through its `claudeProcessWrapper` setting. Ignored on Windows. See [Run Claude Code behind a corporate launcher](/docs/en/corporate-launcher) for the value format, what the launcher covers, and the contract the launcher must satisfy. Requires Claude Code v2.1.208 or later |

326| `CLAUDE_CODE_PROJECT_DIR_NAME` | Set together with `CLAUDE_CONFIG_DIR` to choose the `projects/` directory name Claude Code stores that session's transcripts and auto memory under, in place of one derived from the working directory path. For example, starting Claude Code with `CLAUDE_CONFIG_DIR=/srv/tenant-a CLAUDE_CODE_PROJECT_DIR_NAME=work claude` stores them under `/srv/tenant-a/projects/work/`. Claude Code ignores this variable when `CLAUDE_CONFIG_DIR` is unset, and reads it only from the environment you start `claude` from, never from a [settings file `env` block](#in-settings-files). See [Name the project directory yourself](/docs/en/sessions#name-the-project-directory-yourself). Requires Claude Code v2.1.234 or later |

325| `CLAUDE_CODE_PROPAGATE_TRACEPARENT` | Set to `1` to propagate W3C trace context when `ANTHROPIC_BASE_URL` points at a custom proxy. Propagation covers the `traceparent` header on model and HTTP MCP requests and the `TRACEPARENT` environment variable for Bash, PowerShell, and hook subprocesses. By default, propagation is enabled only when connected directly to the Anthropic API. Added in v2.1.152. See [Traces (beta)](/docs/en/monitoring-usage#traces-beta) |327| `CLAUDE_CODE_PROPAGATE_TRACEPARENT` | Set to `1` to propagate W3C trace context when `ANTHROPIC_BASE_URL` points at a custom proxy. Propagation covers the `traceparent` header on model and HTTP MCP requests and the `TRACEPARENT` environment variable for Bash, PowerShell, and hook subprocesses. By default, propagation is enabled only when connected directly to the Anthropic API. Added in v2.1.152. See [Traces (beta)](/docs/en/monitoring-usage#traces-beta) |

326| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, Claude Code ignores provider-selection, endpoint, and authentication variables such as `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, and `ANTHROPIC_API_KEY` in settings files, so user settings can't override the host's routing. Claude Code also ignores model-selection keys such as `model`, `fallbackModel`, and `modelOverrides` in [managed settings](/docs/en/permissions#managed-settings), whichever managed source delivers them, so the host's model configuration takes precedence over an out-of-date managed model pin; an [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist in managed settings still applies unless the host supplies its own. Claude Code also skips the automatic telemetry opt-out it otherwise applies on third-party providers such as Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out. See [Default behaviors by API provider](/docs/en/data-usage#default-behaviors-by-api-provider) |328| `CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST` | Set by host platforms that embed Claude Code and manage model provider routing on its behalf. When set, Claude Code ignores provider-selection, endpoint, and authentication variables such as `CLAUDE_CODE_USE_BEDROCK`, `ANTHROPIC_BASE_URL`, and `ANTHROPIC_API_KEY` in settings files, so user settings can't override the host's routing. Claude Code also ignores model-selection keys such as `model`, `fallbackModel`, and `modelOverrides` in [managed settings](/docs/en/permissions#managed-settings), whichever managed source delivers them, so the host's model configuration takes precedence over an out-of-date managed model pin; an [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist in managed settings still applies unless the host supplies its own. Claude Code also skips the automatic telemetry opt-out it otherwise applies on third-party providers such as Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, so telemetry follows the standard `DISABLE_TELEMETRY` opt-out. See [Default behaviors by API provider](/docs/en/data-usage#default-behaviors-by-api-provider) |

327| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `1` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |329| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `1` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |

434 434 

435* Run `/model` and select the variant without the `[1m]` suffix to fall back to the standard context window435* Run `/model` and select the variant without the `[1m]` suffix to fall back to the standard context window

436* Run `/usage-credits` to turn on metered billing for the 1M variant on Pro and Max, or to request it from your admin on Team and Enterprise436* Run `/usage-credits` to turn on metered billing for the 1M variant on Pro and Max, or to request it from your admin on Team and Enterprise

437* If the error persists after `/model`, a 1M model ID may be set elsewhere. See [There's an issue with the selected model](#theres-an-issue-with-the-selected-model) for the configuration locations to check in priority order.437* If the error persists after `/model`, a 1M model ID may be set elsewhere. See [Setting your model](/docs/en/model-config#setting-your-model) for the configuration locations to check in priority order.

438* To remove 1M variants from the model picker entirely, set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/docs/en/env-vars)438* To remove 1M variants from the model picker entirely, set [`CLAUDE_CODE_DISABLE_1M_CONTEXT=1`](/docs/en/env-vars)

439 439 

440### Server is temporarily limiting requests440### Server is temporarily limiting requests

1336* **Non-interactive mode (`-p`)**: pass `--model` with a valid alias or ID, or set [`ANTHROPIC_MODEL`](/docs/en/env-vars). The error text shows `Run --model` on this surface.1336* **Non-interactive mode (`-p`)**: pass `--model` with a valid alias or ID, or set [`ANTHROPIC_MODEL`](/docs/en/env-vars). The error text shows `Run --model` on this surface.

1337* **Agent SDK**: the error text omits the hint because the model is set programmatically. Set [`model` on `Options`](/docs/en/agent-sdk/typescript#options) in TypeScript or [`ClaudeAgentOptions(model=...)`](/docs/en/agent-sdk/python#claudeagentoptions) in Python, and handle the structured `model_not_found` error to surface your own retry or model picker.1337* **Agent SDK**: the error text omits the hint because the model is set programmatically. Set [`model` on `Options`](/docs/en/agent-sdk/typescript#options) in TypeScript or [`ClaudeAgentOptions(model=...)`](/docs/en/agent-sdk/python#claudeagentoptions) in Python, and handle the structured `model_not_found` error to surface your own retry or model picker.

1338* Use an alias such as `sonnet` or `opus` instead of a full versioned ID. Aliases resolve to a maintained default so they don't go stale. See [Model configuration](/docs/en/model-config).1338* Use an alias such as `sonnet` or `opus` instead of a full versioned ID. Aliases resolve to a maintained default so they don't go stale. See [Model configuration](/docs/en/model-config).

1339* If the wrong model keeps coming back in the CLI, a stale ID is set somewhere. Check in [priority order](/docs/en/model-config#setting-your-model): the `--model` flag, the `ANTHROPIC_MODEL` environment variable, then the `model` field in `.claude/settings.local.json`, your project's `.claude/settings.json`, and `~/.claude/settings.json`. Remove the stale value and Claude Code falls back to your account default.1339* If the wrong model keeps coming back in the CLI, a stale ID is set somewhere. Check the places you can set a model in [priority order](/docs/en/model-config#setting-your-model) and remove the stale value.

1340* A newly launched model can be available on the Anthropic API before Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry offers it. If you pinned a new model ID on one of those providers and see this error, check your provider's model catalog for availability in your region, and keep the previous version pinned until the new one appears there.1340* A newly launched model can be available on the Anthropic API before Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry offers it. If you pinned a new model ID on one of those providers and see this error, check your provider's model catalog for availability in your region, and keep the previous version pinned until the new one appears there.

1341* Claude Code reports an expired claude.ai login as [Login expired](#login-expired), not as this error. Before v2.1.206, an expired login that could no longer be refreshed failed every model with this error; run `/login` if you see that on an older version.1341* Claude Code reports an expired claude.ai login as [Login expired](#login-expired), not as this error. Before v2.1.206, an expired login that could no longer be refreshed failed every model with this error; run `/login` if you see that on an older version.

1342* For Google Cloud's Agent Platform deployments, see [Google Cloud's Agent Platform troubleshooting](/docs/en/google-vertex-ai#troubleshooting).1342* For Google Cloud's Agent Platform deployments, see [Google Cloud's Agent Platform troubleshooting](/docs/en/google-vertex-ai#troubleshooting).

1357 1357 

1358* Run `/model` with no argument to open the picker and choose from the models available to your account, then pass the alias or ID shown there1358* Run `/model` with no argument to open the picker and choose from the models available to your account, then pass the alias or ID shown there

1359* If you used an alias that a newer Claude Code version supports, run `claude update`. A full ID that starts with `claude-` passes this check even when the model is newer than your Claude Code version, so upgrading isn't needed for those.1359* If you used an alias that a newer Claude Code version supports, run `claude update`. A full ID that starts with `claude-` passes this check even when the model is newer than your Claude Code version, so upgrading isn't needed for those.

1360* A model saved before v2.1.200 isn't repaired by this check. If a stale value keeps coming back, remove it from the locations listed under [There's an issue with the selected model](#theres-an-issue-with-the-selected-model).1360* A model saved before v2.1.200 isn't repaired by this check. If a stale value keeps coming back, remove it from the locations listed under [Setting your model](/docs/en/model-config#setting-your-model).

1361* The check runs only on the Anthropic API. On any other provider or gateway, including a custom `ANTHROPIC_BASE_URL`, the provider defines the model names, so Claude Code accepts any string and passes it through. Claude Code can still write the [unrecognized-model diagnostic line](#unrecognized-model-id-on-a-request) at request time, on every provider.1361* The check runs only on the Anthropic API. On any other provider or gateway, including a custom `ANTHROPIC_BASE_URL`, the provider defines the model names, so Claude Code accepts any string and passes it through. Claude Code can still write the [unrecognized-model diagnostic line](#unrecognized-model-id-on-a-request) at request time, on every provider.

1362 1362 

1363### Claude Opus is not available with the Claude Pro plan1363### Claude Opus is not available with the Claude Pro plan

2372 2372 

2373* If the ID names a model newer than your Claude Code version, run `claude update`2373* If the ID names a model newer than your Claude Code version, run `claude update`

2374 2374 

2375* If the ID is a typo, fix it where you set it: the `--model` flag, the `ANTHROPIC_MODEL` or `ANTHROPIC_DEFAULT_*_MODEL` environment variables, or the `model` setting. If `query_source` starts with `agent:`, fix it where you set the [subagent's model](/docs/en/sub-agents#choose-a-model) instead.2375* If the ID is a typo, fix it in whichever of the [places you can set a model](/docs/en/model-config#setting-your-model) or [alias variables](/docs/en/model-config#environment-variables) holds it. If `query_source` starts with `agent:`, fix it where you set the [subagent's model](/docs/en/sub-agents#choose-a-model) instead.

2376 2376 

2377Before v2.1.233, Claude Code wrote no line when it sent a request for a model ID it didn't recognize.2377Before v2.1.233, Claude Code wrote no line when it sent a request for a model ID it didn't recognize.

2378 2378 

88 88 

89With a selection active, hold `Shift` and press the arrow keys to extend it from the keyboard. `Shift+↑` and `Shift+↓` scroll the viewport when the selection reaches the top or bottom edge. `Shift+Home` and `Shift+End` extend to the start or end of the current line.89With a selection active, hold `Shift` and press the arrow keys to extend it from the keyboard. `Shift+↑` and `Shift+↓` scroll the viewport when the selection reaches the top or bottom edge. `Shift+Home` and `Shift+End` extend to the start or end of the current line.

90 90 

91In the normal prompt view, what happens to an active selection depends on the key you press:

92 

93* **`Esc`**: Claude Code performs the key's usual action, such as interrupting the running response or dismissing an open dialog, and the selection stays highlighted.

94* **`PgUp`, `PgDn`, `Ctrl+Home`, `Ctrl+End`, or `Shift`, `Alt` or `Option`, or `Cmd`, `Win`, or `Super` with an arrow, `Home`, or `End` key**: the selection stays.

95* **Any other key, including plain arrow keys, `Enter`, and typed characters**: Claude Code clears the selection.

96* **A key bound to [`selection:clear`](/docs/en/keybindings#scroll-actions)**: Claude Code clears the selection, even when the key is `Esc` or another key that otherwise keeps it. The action has no default binding.

97 

98In [transcript mode](#search-and-review-the-conversation), the navigation and search keys listed there also keep the selection.

99 

91## Scroll the conversation100## Scroll the conversation

92 101 

93Fullscreen rendering handles scrolling inside the app. Use these shortcuts to navigate:102Fullscreen rendering handles scrolling inside the app. Use these shortcuts to navigate:

337| `scroll:fullPageUp` | (unbound) | Scroll up the full viewport height |337| `scroll:fullPageUp` | (unbound) | Scroll up the full viewport height |

338| `scroll:fullPageDown` | (unbound) | Scroll down the full viewport height |338| `scroll:fullPageDown` | (unbound) | Scroll down the full viewport height |

339| `selection:copy` | Ctrl+Shift+C / Cmd+C | Copy the selected text to the clipboard |339| `selection:copy` | Ctrl+Shift+C / Cmd+C | Copy the selected text to the clipboard |

340| `selection:clear` | (unbound) | Clear the active text selection |340| `selection:clear` | (unbound) | Clear the active text selection. Requires v2.1.234 or later |

341| `selection:extendLeft` | Shift+Left | Extend the active selection one column left |341| `selection:extendLeft` | Shift+Left | Extend the active selection one column left |

342| `selection:extendRight` | Shift+Right | Extend the active selection one column right |342| `selection:extendRight` | Shift+Right | Extend the active selection one column right |

343| `selection:extendUp` | Shift+Up | Extend the active selection one row up. Scrolls the viewport when the selection reaches the top edge |343| `selection:extendUp` | Shift+Up | Extend the active selection one row up. Scrolls the viewport when the selection reaches the top edge |

357 357 

358Each project gets its own memory directory at `~/.claude/projects/<project>/memory/`. The `<project>` path is derived from the git repository, so all worktrees and subdirectories within the same repo share one auto memory directory. Outside a git repo, the project root is used instead.358Each project gets its own memory directory at `~/.claude/projects/<project>/memory/`. The `<project>` path is derived from the git repository, so all worktrees and subdirectories within the same repo share one auto memory directory. Outside a git repo, the project root is used instead.

359 359 

360If you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR`, Claude Code uses that name as the `<project>` directory under `<config dir>/projects/` instead, whichever repository you launch it in, so projects launched with that config directory share one auto memory directory. Requires Claude Code v2.1.234 or later.

361 

360To store auto memory in a different location, set `autoMemoryDirectory` in your `settings.json`. It is read from any [settings scope](/docs/en/settings#settings-precedence): user, project, local, policy, or `--settings`.362To store auto memory in a different location, set `autoMemoryDirectory` in your `settings.json`. It is read from any [settings scope](/docs/en/settings#settings-precedence): user, project, local, policy, or `--settings`.

361 363 

362```json theme={null}364```json theme={null}

29 29 

30| Model alias | Behavior |30| Model alias | Behavior |

31| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |31| ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

32| **`default`** | Special value that clears any model override and reverts to the recommended model for your account type, or to the [organization default model](#organization-default-model) when an admin has set one. Not itself a model alias |32| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias |

33| **`best`** | Uses Fable 5 where your organization has access to it, otherwise the latest Opus model |33| **`best`** | Uses Fable 5 where your organization has access to it, otherwise the latest Opus model |

34| **`fable`** | Uses Claude Fable 5 for your hardest and longest-running tasks |34| **`fable`** | Uses Claude Fable 5 for your hardest and longest-running tasks |

35| **`sonnet`** | Uses the latest Sonnet model for daily coding tasks |35| **`sonnet`** | Uses the latest Sonnet model for daily coding tasks |

982. **At startup**: launch with `claude --model <alias|name>`982. **At startup**: launch with `claude --model <alias|name>`

993. **Environment variable**: set `ANTHROPIC_MODEL=<alias|name>`993. **Environment variable**: set `ANTHROPIC_MODEL=<alias|name>`

1004. **Settings**: configure permanently in your settings file using the `model` field1004. **Settings**: configure permanently in your settings file using the `model` field

1015. **[Default for new sessions](#set-a-default-model-for-new-sessions)**: set `ANTHROPIC_DEFAULT_MODEL=<alias|name>`

101 102 

102As of v2.1.153, `/model` saves your choice as the default for new sessions by writing the `model` field in your user settings. In the picker:103As of v2.1.153, `/model` saves your choice as the default for new sessions by writing the `model` field in your user settings. In the picker:

103 104 

114 115 

115Resumed sessions started with `claude --resume`, `--continue`, or the `/resume` picker keep the model they were using when the transcript was saved, regardless of the current `model` setting. If the restored model has been retired or is excluded by [`availableModels`](#restrict-model-selection), the session falls through to the normal precedence order. This prevents another session's `/model` choice from changing the model on resume. On providers that use provider-specific deployment IDs rather than Anthropic model IDs, such as Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, the transcript model isn't restored at all and the session resolves its model through the normal precedence order.116Resumed sessions started with `claude --resume`, `--continue`, or the `/resume` picker keep the model they were using when the transcript was saved, regardless of the current `model` setting. If the restored model has been retired or is excluded by [`availableModels`](#restrict-model-selection), the session falls through to the normal precedence order. This prevents another session's `/model` choice from changing the model on resume. On providers that use provider-specific deployment IDs rather than Anthropic model IDs, such as Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, the transcript model isn't restored at all and the session resolves its model through the normal precedence order.

116 117 

117A model you pick for the new launch with `--model` or `ANTHROPIC_MODEL` still takes precedence over the restored model. As of v2.1.195, so does an [`ANTHROPIC_DEFAULT_OPUS_MODEL`](#environment-variables) family variable.118A model you pick for the new launch with `--model` or `ANTHROPIC_MODEL` still takes precedence over the restored model. As of v2.1.195, so does an [`ANTHROPIC_DEFAULT_OPUS_MODEL`](#environment-variables) family variable. [`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions) can too, under the conditions listed in its section.

118 119 

119When the active model at startup comes from project or managed settings rather than your own selection, the startup header shows which settings file set it. Run `/model` to override; the project or managed setting reapplies on the next launch. On platforms that embed Claude Code and set [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](/docs/en/env-vars), the host's model configuration takes precedence over managed model settings, while a managed `availableModels` allowlist stays in force unless the host supplies its own; the key-level enumeration is under [Settings precedence](/docs/en/settings#settings-precedence).120When the active model at startup comes from project or managed settings rather than your own selection, the startup header shows which settings file set it. Run `/model` to override; the project or managed setting reapplies on the next launch. On platforms that embed Claude Code and set [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](/docs/en/env-vars), the host's model configuration takes precedence over managed model settings, while a managed `availableModels` allowlist stays in force unless the host supplies its own; the key-level enumeration is under [Settings precedence](/docs/en/settings#settings-precedence).

120 121 

154}155}

155```156```

156 157 

158#### Set a default model for new sessions

159 

160Set `ANTHROPIC_DEFAULT_MODEL=<alias|name>` to choose the model your sessions start on by default. Requires Claude Code v2.1.236 or later.

161 

162Claude Code starts a new session on the variable's model only when none of these selects a model:

163 

164* The `--model` flag

165* `ANTHROPIC_MODEL`

166* A `model` value in any settings file, including the choice you save with `/model`

167* An [organization default model](#organization-default-model)

168 

169A choice you save with `/model` takes precedence over the variable on later launches too. With `ANTHROPIC_MODEL` set instead, Claude Code returns to that variable's model on the next launch, whatever you saved with `/model`.

170 

171Claude Code also resolves the Default option to the variable's model, unless an organization default model applies. When the Default option resolves to the variable's model, the Default row in the `/model` picker shows the label Set by ANTHROPIC\_DEFAULT\_MODEL.

172 

173Claude Code ignores the variable in these cases, and the Default option resolves as if you hadn't set it:

174 

175* You set it to `default`, `inherit`, `opusplan`, or `haiku`

176* [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model) is on

177* [`availableModels`](#restrict-model-selection) or [organization model restrictions](#organization-model-restrictions) exclude the model

178* The model isn't available to your account

179 

180When a new session would start on the variable's model, a session you resume with `claude --resume`, `--continue`, or the `/resume` picker starts on it too. Claude Code doesn't restore the model saved in that session's transcript. Otherwise Claude Code doesn't use the variable when you [resume a session](#setting-your-model).

181 

157## Restrict model selection182## Restrict model selection

158 183 

159Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/settings#settings-files) to restrict which models users can select. Entries match a model family such as `sonnet`, a version prefix such as `claude-sonnet-4-5`, or a full model ID such as `claude-sonnet-4-5-20250929`.184Enterprise administrators can use `availableModels` in [managed or policy settings](/docs/en/settings#settings-files) to restrict which models users can select. Entries match a model family such as `sonnet`, a version prefix such as `claude-sonnet-4-5`, or a full model ID such as `claude-sonnet-4-5-20250929`.

162 187 

163When `availableModels` is set, the allowlist applies everywhere a user can specify a model:188When `availableModels` is set, the allowlist applies everywhere a user can specify a model:

164 189 

165* **Main session model**: `/model`, the `--model` flag, the `ANTHROPIC_MODEL` environment variable, the `model` setting, and the model restored when [resuming a session](#setting-your-model)190* **Main session model**: `/model`, the `--model` flag, the `ANTHROPIC_MODEL` environment variable, the `model` setting, [`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions), and the model restored when [resuming a session](#setting-your-model)

166* **Alias resolution**: the `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, `ANTHROPIC_DEFAULT_HAIKU_MODEL`, and `ANTHROPIC_DEFAULT_FABLE_MODEL` environment variables cannot redirect an allowed alias to a model outside the list191* **Alias resolution**: the `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, `ANTHROPIC_DEFAULT_HAIKU_MODEL`, and `ANTHROPIC_DEFAULT_FABLE_MODEL` environment variables cannot redirect an allowed alias to a model outside the list

167* **Fast mode**: `/fast` refuses to toggle when it would implicitly switch to an Opus model outside the list, with the message "is not in your organization's allowed models"192* **Fast mode**: `/fast` refuses to toggle when it would implicitly switch to an Opus model outside the list, with the message "is not in your organization's allowed models"

168* **Subagent and teammate models**: the `model` field in [subagent](/docs/en/sub-agents#choose-a-model) frontmatter, the Agent tool's `model` parameter, [agent team](/docs/en/agent-teams#specify-teammates-and-models) teammate models, `CLAUDE_CODE_SUBAGENT_MODEL`, and, on v2.1.197 and earlier, the model picker in the `/agents` wizard 193* **Subagent and teammate models**: the `model` field in [subagent](/docs/en/sub-agents#choose-a-model) frontmatter, the Agent tool's `model` parameter, [agent team](/docs/en/agent-teams#specify-teammates-and-models) teammate models, `CLAUDE_CODE_SUBAGENT_MODEL`, and, on v2.1.197 and earlier, the model picker in the `/agents` wizard 

178 203 

179* **`/model`**: Claude Code rejects the switch with an error204* **`/model`**: Claude Code rejects the switch with an error

180* **`--model` flag, `ANTHROPIC_MODEL`, or the `model` setting**: Claude Code replaces the value at startup with a warning naming both the requested and substituted models, and the session starts on the default model205* **`--model` flag, `ANTHROPIC_MODEL`, or the `model` setting**: Claude Code replaces the value at startup with a warning naming both the requested and substituted models, and the session starts on the default model

206* **[`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions)**: Claude Code ignores the variable

181* **Subagent or teammate override**: Claude Code falls back to the [subagent's inherited model](/docs/en/sub-agents#choose-a-model) or the [lead's model for a teammate](/docs/en/agent-teams#specify-teammates-and-models) rather than failing the request. In interactive sessions, Claude Code warns you when it substitutes a subagent's model, by this fallback or by the newest-permitted-version substitution above, naming the requested and substituted models; it doesn't report a teammate's fallback. Where the newest-permitted-version substitution above operates, a blocked family alias follows it instead; before v2.1.222, an alias fell back like any other blocked value on every provider207* **Subagent or teammate override**: Claude Code falls back to the [subagent's inherited model](/docs/en/sub-agents#choose-a-model) or the [lead's model for a teammate](/docs/en/agent-teams#specify-teammates-and-models) rather than failing the request. In interactive sessions, Claude Code warns you when it substitutes a subagent's model, by this fallback or by the newest-permitted-version substitution above, naming the requested and substituted models; it doesn't report a teammate's fallback. Where the newest-permitted-version substitution above operates, a blocked family alias follows it instead; before v2.1.222, an alias fell back like any other blocked value on every provider

182* **Skill or command override**: Claude Code ignores the override, including a blocked family alias, and the skill or command runs on the session model. A skill or command that [runs in a subagent](/docs/en/skills#run-skills-in-a-subagent) follows the subagent behavior above instead208* **Skill or command override**: Claude Code ignores the override, including a blocked family alias, and the skill or command runs on the session model. A skill or command that [runs in a subagent](/docs/en/skills#run-skills-in-a-subagent) follows the subagent behavior above instead

183* **`advisorModel` setting**: the advisor is disabled for the session209* **`advisorModel` setting**: the advisor is disabled for the session

217 243 

218### Default model behavior244### Default model behavior

219 245 

220The Default option in the model picker is not affected by `availableModels` unless [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model) is also set. On its own, `availableModels` leaves Default available, resolving to the system's [runtime default](#default-model-setting) for the account. If that default is a model you intend to restrict, set `enforceAvailableModels` as well.246On its own, `availableModels` leaves the Default option on the system's [runtime default](#default-model-setting) for the account until you also set [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model). If that default is a model you intend to restrict, set `enforceAvailableModels` as well.

221 247 

222An empty `availableModels` array never engages the Default-model enforcement: with `availableModels: []`, named model selections are blocked but the Default model for the account type remains usable regardless of `enforceAvailableModels`.248An empty `availableModels` array never engages the Default-model enforcement: with `availableModels: []`, named model selections are blocked but the Default model for the account type remains usable regardless of `enforceAvailableModels`.

223 249 

234 260 

235The Default option resolves to the account-type default, or to the [organization default model](#organization-default-model) when an admin has set one. When that model is not in the allowlist, the Default option instead resolves to the first `availableModels` entry that names an allowed, available model, and the `/model` picker's Default row shows that model. This applies everywhere the default is reached: session startup, selecting Default in `/model`, the `"default"` keyword in [fallback model chains](#fallback-model-chains), and the fallback used when an excluded selection is dropped.261The Default option resolves to the account-type default, or to the [organization default model](#organization-default-model) when an admin has set one. When that model is not in the allowlist, the Default option instead resolves to the first `availableModels` entry that names an allowed, available model, and the `/model` picker's Default row shows that model. This applies everywhere the default is reached: session startup, selecting Default in `/model`, the `"default"` keyword in [fallback model chains](#fallback-model-chains), and the fallback used when an excluded selection is dropped.

236 262 

237`enforceAvailableModels` has no effect when `availableModels` is unset or empty: with `availableModels: []`, the Default model for the account type remains usable, so the setting cannot lock users out of every model. When `availableModels` is non-empty but no entry resolves to an allowed and available model, enforcement is skipped and Default resolves to the account-type default, with a warning visible only under `--debug`. Keep at least one guaranteed-available entry in the list to avoid this.263`enforceAvailableModels` remaps the Default option only when `availableModels` is non-empty. With `availableModels: []`, the Default model for the account type remains usable, so the setting cannot lock users out of every model. When `availableModels` is non-empty but no entry resolves to an allowed and available model, enforcement is skipped and Default resolves to the account-type default, with a warning visible only under `--debug`. Keep at least one guaranteed-available entry in the list to avoid this.

238 264 

239Deploy both keys in the [highest-precedence managed source](/docs/en/settings#precedence-within-the-managed-tier): these keys don't merge across managed sources, so a pair placed in a managed settings file is ignored when the admin console delivers any settings.265Deploy both keys in the [highest-precedence managed source](/docs/en/settings#precedence-within-the-managed-tier): these keys don't merge across managed sources, so a pair placed in a managed settings file is ignored when the admin console delivers any settings.

240 266 

247* **`availableModels`**: restricts which named models users can switch to273* **`availableModels`**: restricts which named models users can switch to

248* **`enforceAvailableModels`**: extends the `availableModels` allowlist to the Default option, so Default cannot resolve to a model outside the list274* **`enforceAvailableModels`**: extends the `availableModels` allowlist to the Default option, so Default cannot resolve to a model outside the list

249* **`model`**: sets the initial model selection when a session starts275* **`model`**: sets the initial model selection when a session starts

250* **`ANTHROPIC_DEFAULT_SONNET_MODEL`** / **`ANTHROPIC_DEFAULT_OPUS_MODEL`** / **`ANTHROPIC_DEFAULT_HAIKU_MODEL`** / **`ANTHROPIC_DEFAULT_FABLE_MODEL`**: control what the Default option and the `sonnet`, `opus`, `haiku`, and `fable` aliases resolve to276* **`ANTHROPIC_DEFAULT_SONNET_MODEL`** / **`ANTHROPIC_DEFAULT_OPUS_MODEL`** / **`ANTHROPIC_DEFAULT_HAIKU_MODEL`** / **`ANTHROPIC_DEFAULT_FABLE_MODEL`**: control what the `sonnet`, `opus`, `haiku`, and `fable` aliases resolve to, and which version the [account-type default](#default-model-setting) uses

251 277 

252This example starts users on Sonnet 4.5, limits the picker to Sonnet and Haiku, and ensures Default resolves to a model on the allowlist rather than the tier default:278This example starts users on Sonnet 4.5, limits the picker to Sonnet and Haiku, and ensures Default resolves to a model on the allowlist rather than the tier default:

253 279 

262}288}

263```289```

264 290 

265Without `enforceAvailableModels` or the `env` block, a user who selects Default in the picker would get the latest release for their tier, bypassing the version pin in `model` and `availableModels`. The two settings cover different scopes: `enforceAvailableModels` makes Default obey the allowlist, while the `env` block pins which version a permitted alias such as `sonnet` resolves to. Use `enforceAvailableModels` alone when restricting model families is enough; add the `env` block when you also need to pin a specific version.291Without `enforceAvailableModels` or the `env` block, a user who selects Default in the picker gets the [runtime default](#default-model-setting) rather than the version pinned in `model`. The two settings cover different scopes: `enforceAvailableModels` makes Default obey the allowlist, while the `env` block pins which version a permitted alias such as `sonnet` resolves to. Use `enforceAvailableModels` alone when restricting model families is enough; add the `env` block when you also need to pin a specific version.

266 292 

267### Merge behavior293### Merge behavior

268 294 

297 323 

298## Organization default model324## Organization default model

299 325 

300Organization admins on Claude Enterprise plans can set a default model for Claude Code members from the claude.ai admin console, for the whole organization or per custom role. When one is set, the Default option resolves to that model instead of the [account-type default](#default-model-setting). Requires Claude Code v2.1.196 or later.326Organization admins on Claude Enterprise plans can set a default model for Claude Code members from the claude.ai admin console, for the whole organization or per custom role. When one is set, the Default option resolves to that model. Requires Claude Code v2.1.196 or later.

301 327 

302The Default row in the `/model` picker shows the organization default's name with the label Org default. The label reads Org default whether the admin set the default for the whole organization or for your role. A role default covers members of that custom role and takes precedence over the organization-wide default; when several of your roles set different defaults, the most capable model applies.328The Default row in the `/model` picker shows the organization default's name with the label Org default. The label reads Org default whether the admin set the default for the whole organization or for your role. A role default covers members of that custom role and takes precedence over the organization-wide default; when several of your roles set different defaults, the most capable model applies.

303 329 

304The organization default is a starting point, not a restriction, and any other model selection takes precedence over it:330The organization default is a starting point, not a restriction. These selections take precedence over it:

305 331 

306* the `--model` flag and the `ANTHROPIC_MODEL` environment variable332* the `--model` flag and the `ANTHROPIC_MODEL` environment variable

307* a `model` value in [managed settings](/docs/en/settings#settings-files) or supplied through `--settings`333* a `model` value in [managed settings](/docs/en/settings#settings-files) or supplied through `--settings`

315 341 

316When the organization default doesn't override user selection, the first interactive launch after the admin changes it clears the `model` key from your user settings once, so the new default applies. It changes nothing else in the file, and a model you save with `/model` after that launch is kept.342When the organization default doesn't override user selection, the first interactive launch after the admin changes it clears the `model` key from your user settings once, so the new default applies. It changes nothing else in the file, and a model you save with `/model` after that launch is kept.

317 343 

318The organization default passes through the same restriction checks as any other Default model before it is adopted:344The organization default passes through these restriction checks before it is adopted:

319 345 

320* [`availableModels`](#restrict-model-selection) on its own never constrains the Default option, so an organization default outside the allowlist still applies. When [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model) is also set, an organization default outside the allowlist is remapped to the first allowlist entry, like any other Default346* [`availableModels`](#restrict-model-selection) on its own doesn't apply to the organization default, so an organization default outside the allowlist still applies. When [`enforceAvailableModels`](#enforce-the-allowlist-for-the-default-model) is also set, an organization default outside the allowlist is remapped to the first allowlist entry, like any other Default

321* an organization default that [organization model restrictions](#organization-model-restrictions) deny for your account is replaced by the newest allowed model in its family, or a lower-cost family when every version of it is restricted347* an organization default that [organization model restrictions](#organization-model-restrictions) deny for your account is replaced by the newest allowed model in its family, or a lower-cost family when every version of it is restricted

322* an organization default that isn't available to your account at all, such as Fable 5 under [zero data retention](/docs/en/zero-data-retention), is skipped, and the Default option resolves to the account-type default348* an organization default that isn't available to your account at all, such as Fable 5 under [zero data retention](/docs/en/zero-data-retention), is skipped, and the Default option resolves as it would [without an organization default](#default-model-setting)

323 349 

324As of v2.1.199, when the organization default is a different model family from your account type's usual default, the `/model` picker keeps a separate row for that usual family, so you can still switch to it for a session. In v2.1.196 through v2.1.198 that row is missing from the picker.350As of v2.1.199, when the organization default is a different model family from your account type's usual default, the `/model` picker keeps a separate row for that usual family, so you can still switch to it for a session. In v2.1.196 through v2.1.198 that row is missing from the picker.

325 351 

346 372 

347Before v2.1.219, `default` resolved to Opus 4.8 on the Anthropic API, Max, Team Premium, and Enterprise pay-as-you-go from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `default` resolved to Opus 4.7 on Claude Platform on AWS and to Sonnet 4.5 on Amazon Bedrock and Google Cloud's Agent Platform.373Before v2.1.219, `default` resolved to Opus 4.8 on the Anthropic API, Max, Team Premium, and Enterprise pay-as-you-go from v2.1.154, and on Claude Platform on AWS, Amazon Bedrock, and Google Cloud's Agent Platform from v2.1.207. Before v2.1.207, `default` resolved to Opus 4.7 on Claude Platform on AWS and to Sonnet 4.5 on Amazon Bedrock and Google Cloud's Agent Platform.

348 374 

349When an admin has set an [organization default model](#organization-default-model), `default` resolves to that model instead of the account-type default above. Requires Claude Code v2.1.196 or later.375When an admin has set an [organization default model](#organization-default-model), `default` resolves to that model instead of the account-type default above. Requires Claude Code v2.1.196 or later. `default` can also resolve to the model you set with [`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions), under the conditions listed in its section.

350 376 

351When managed settings [enforce the allowlist for the Default model](#enforce-the-allowlist-for-the-default-model) and the account-type default is not in `availableModels`, `default` resolves to the enforced Default instead of the account-type default above. When both apply, the organization default replaces the account-type default first and enforcement then applies to it: an allowlisted organization default is kept, while one outside the list resolves to the enforced Default.377When managed settings [enforce the allowlist for the Default model](#enforce-the-allowlist-for-the-default-model) and the account-type default is not in `availableModels`, `default` resolves to the enforced Default instead of the account-type default above. When both apply, the organization default replaces the account-type default first and enforcement then applies to it: an allowlisted organization default is kept, while one outside the list resolves to the enforced Default.

352 378 

353Fable 5 is not the default model on any account type. Sessions use Fable 5 only after you choose it, with `/model fable`, a `model` setting, or the `best` alias where Fable 5 is available. Choosing it with `/model` saves it as the selected model in your user settings, so later sessions start on Fable 5 until you change models.379Fable 5 is not the default model on any account type. Sessions use Fable 5 only after you choose it, for example with `/model fable`, a `model` setting, or the `best` alias where Fable 5 is available. Choosing it with `/model` saves it as the selected model in your user settings, so later sessions start on Fable 5 until you change models.

354 380 

355### `opusplan` model setting381### `opusplan` model setting

356 382 

663 689 

664## Environment variables690## Environment variables

665 691 

666Use the following environment variables to control the model names that the aliases map to. Each value must be a full model name, or the equivalent identifier for your API provider.692Use the following environment variables to control the model names that the aliases map to. Each value must be a full model name, or the equivalent identifier for your API provider. To choose the model your sessions start on, set [`ANTHROPIC_DEFAULT_MODEL`](#set-a-default-model-for-new-sessions), which this table omits.

667 693 

668| Environment variable | Description |694| Environment variable | Description |

669| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |695| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

682 708 

683Without pinning, Claude Code uses model aliases such as `fable`, `opus`, `sonnet`, and `haiku` that resolve to a built-in default model ID for each provider. That default can lag the newest Anthropic release, and the model it points to may not yet be enabled in a user's account. When the default is unavailable, Amazon Bedrock and Google Cloud's Agent Platform users see a notice and the session falls back to an earlier version of the default model, or to the default Sonnet model when the default is an Opus model and no Opus version is available. Microsoft Foundry users see errors instead, because Microsoft Foundry has no equivalent startup check.709Without pinning, Claude Code uses model aliases such as `fable`, `opus`, `sonnet`, and `haiku` that resolve to a built-in default model ID for each provider. That default can lag the newest Anthropic release, and the model it points to may not yet be enabled in a user's account. When the default is unavailable, Amazon Bedrock and Google Cloud's Agent Platform users see a notice and the session falls back to an earlier version of the default model, or to the default Sonnet model when the default is an Opus model and no Opus version is available. Microsoft Foundry users see errors instead, because Microsoft Foundry has no equivalent startup check.

684 710 

685On Amazon Bedrock and Google Cloud's Agent Platform, a user who starts the session on a specific Sonnet or Opus version, with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, pins that version as the session's default for the matching alias: the startup check skips the built-in default it replaces and shows no fallback notice. Before v2.1.211, the check ran and could show a notice even when a session model was explicitly configured.711On Amazon Bedrock and Google Cloud's Agent Platform, a user who starts the session on a specific Sonnet or Opus version, for example with `--model`, `ANTHROPIC_MODEL`, or the `model` setting, pins that version as the session's default for the matching alias: the startup check skips the built-in default it replaces and shows no fallback notice. Before v2.1.211, the check ran and could show a notice even when a session model was explicitly configured.

686 712 

687<Warning>713<Warning>

688 Set the model environment variables to specific version IDs as part of your initial setup. Pinning lets you control when your users move to a new model.714 Set the model environment variables to specific version IDs as part of your initial setup. Pinning lets you control when your users move to a new model.

1194 1194 

1195* Verify the marketplace URL is accessible1195* Verify the marketplace URL is accessible

1196* Check that `.claude-plugin/marketplace.json` exists at the specified path1196* Check that `.claude-plugin/marketplace.json` exists at the specified path

1197* Ensure JSON syntax is valid using `claude plugin validate .` or `/plugin validate .` from the marketplace directory. To check skill, agent, and command frontmatter, run the command against each plugin directory1197* Ensure JSON syntax is valid using `claude plugin validate .` or `/plugin validate .` from the marketplace directory. To check skill, agent, and command frontmatter, see [Validate a plugin or a directory without a manifest](#validate-a-plugin-or-a-directory-without-a-manifest)

1198* For private repositories, confirm you have access permissions1198* For private repositories, confirm you have access permissions

1199 1199 

1200### Marketplace validation errors1200### Marketplace validation errors

1209 1209 

1210Earlier versions skip plugins at the marketplace root and only descend from a `.claude-plugin/marketplace.json`.1210Earlier versions skip plugins at the marketplace root and only descend from a `.claude-plugin/marketplace.json`.

1211 1211 

1212To validate an individual plugin's `plugin.json` and its skill, agent, command, and hook files, run the command against the plugin directory itself, for example `claude plugin validate ./plugins/my-plugin`. Common errors:1212From a marketplace directory, Claude Code doesn't open the plugins' skill, agent, command, or hook files. To find errors in those files, see [Validate a plugin or a directory without a manifest](#validate-a-plugin-or-a-directory-without-a-manifest). The table below lists the most common errors from a marketplace directory, with the cause and fix for each:

1213 1213 

1214| Error | Cause | Solution |1214| Error | Cause | Solution |

1215| :------------------------------------------------ | :---------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------ |1215| :------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------- |

1216| `File not found: .claude-plugin/marketplace.json` | Missing manifest | Create `.claude-plugin/marketplace.json` with required fields |1216| `No manifest found in directory. Expected .claude-plugin/marketplace.json or .claude-plugin/plugin.json` | The directory you named has no `.claude-plugin/marketplace.json` or `plugin.json`, and no skill, agent, or command files to check | Run from the marketplace root, or create `.claude-plugin/marketplace.json` with the required fields |

1217| `Invalid JSON syntax: Unexpected token...` | JSON syntax error in marketplace.json | Check for missing commas, extra commas, or unquoted strings |1217| `Invalid JSON syntax: Unexpected token...` | JSON syntax error in marketplace.json | Check for missing commas, extra commas, or unquoted strings |

1218| `Duplicate plugin name "x" found in marketplace` | Two plugins share the same name | Give each plugin a unique `name` value |1218| `Duplicate plugin name "x" found in marketplace` | Two plugins share the same name | Give each plugin a unique `name` value |

1219| `plugins[0].source: Path contains ".."` | Source path contains `..` | Use paths relative to the marketplace root without `..`. See [Relative paths](#relative-paths) |1219| `plugins[0].source: Path contains ".."` | Source path contains `..` | Use paths relative to the marketplace root without `..`. See [Relative paths](#relative-paths) |

1220| `YAML frontmatter failed to parse: ...` | Invalid YAML in a skill, agent, or command file | Fix the YAML syntax in the frontmatter block. At runtime this file loads with no metadata. Reported only when validating a plugin directory |

1221| `Invalid JSON syntax: ...` (hooks.json) | Malformed `hooks/hooks.json` | Fix JSON syntax. A malformed `hooks/hooks.json` prevents the entire plugin from loading. Reported only when validating a plugin directory |

1222 1220 

1223**Warnings** (non-blocking):1221**Warnings** (non-blocking):

1224 1222 

1228* `Marketplace name "x" is reserved in Claude Desktop`: the marketplace is named `org`, `org-provisioned`, or `unknown`, in any casing. Claude Code accepts these names, but Claude Desktop's managed marketplace sync rejects the whole marketplace. Rename the marketplace. Before v2.1.221, `claude plugin validate` didn't run this check.1226* `Marketplace name "x" is reserved in Claude Desktop`: the marketplace is named `org`, `org-provisioned`, or `unknown`, in any casing. Claude Code accepts these names, but Claude Desktop's managed marketplace sync rejects the whole marketplace. Rename the marketplace. Before v2.1.221, `claude plugin validate` didn't run this check.

1229* `Marketplace name "x" is not accepted by Claude Desktop` or `Plugin name "x" is not accepted by Claude Desktop`: Claude Desktop accepts names of up to 128 characters made of letters, digits, `.`, `_`, and `-`, starting with a letter or digit. Claude Code accepts other forms, but Claude Desktop's managed marketplace sync rejects a marketplace whose name fails the check and silently drops a plugin entry whose name does. Rename the marketplace or plugin. Before v2.1.221, `claude plugin validate` didn't run these checks.1227* `Marketplace name "x" is not accepted by Claude Desktop` or `Plugin name "x" is not accepted by Claude Desktop`: Claude Desktop accepts names of up to 128 characters made of letters, digits, `.`, `_`, and `-`, starting with a letter or digit. Claude Code accepts other forms, but Claude Desktop's managed marketplace sync rejects a marketplace whose name fails the check and silently drops a plugin entry whose name does. Rename the marketplace or plugin. Before v2.1.221, `claude plugin validate` didn't run these checks.

1230 1228 

1229#### Validate a plugin or a directory without a manifest

1230 

1231To find skill, agent, and command files whose frontmatter doesn't parse, run `claude plugin validate` and name the directory that holds them. Claude Code doesn't look outside the directory you name. Every run except one against a plugin that has a `plugin.json` requires Claude Code v2.1.233 or later.

1232 

1233Pick the directory by what you want to check:

1234 

1235| To check | Run | Claude Code checks |

1236| :------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

1237| A plugin that has a `plugin.json` | `claude plugin validate ./plugins/my-plugin` | `plugin.json`, `hooks/hooks.json`, and the `skills`, `agents`, and `commands` directories at the plugin root |

1238| One directory of skills, agents, or commands, such as a plugin that has no `plugin.json` yet | `claude plugin validate .claude/skills`, `~/.claude/agents`, or `./my-plugin/agents` | Every skill, agent, or command file in that directory |

1239| A folder whose skill is its root `SKILL.md` | `claude plugin validate ./skills`, naming the `skills` directory that holds the folder | Each folder's root `SKILL.md`. The holding directory must be named `skills`; a folder under another name, such as `plugins/`, has no run that checks its root `SKILL.md` |

1240| A project's three directories at once | `claude plugin validate .claude`, or the project root when it has no `.claude-plugin/` manifest | `.claude/skills`, `.claude/agents`, and `.claude/commands` |

1241| Your user-level directories | `claude plugin validate ~/.claude` | `~/.claude/skills`, `~/.claude/agents`, and `~/.claude/commands` |

1242 

1243A plugin run also warns about a `CLAUDE.md` at the plugin root. For paths you set through the [component path fields](/docs/en/plugins-reference#component-path-fields) in `plugin.json`, it checks that each path exists but doesn't read the files there, and it doesn't check a `SKILL.md` at the plugin root. To check a plugin whose skill is its root `SKILL.md`, run the command twice when the plugin sits in a directory named `skills`: name that `skills` directory to check the root `SKILL.md`, and name the plugin directory to check the rest. When the plugin sits under another name, such as `plugins/`, only the second run is available, and no run checks its root `SKILL.md`.

1244 

1245Claude Code doesn't follow symlinks inside the directory you name. What it does depends on where the link is:

1246 

1247* **A linked `skills`, `agents`, or `commands` directory under the plugin or `.claude` root**: Claude Code warns that nothing in it was read.

1248* **A linked entry inside a `skills`, `agents`, or `commands` directory**: Claude Code skips it and warns, per directory, how many entries it skipped that a session would load. A plugin whose `skills` directory [links to a sibling plugin's skills](/docs/en/plugins-reference#share-files-within-a-marketplace-with-symlinks) passes with warnings; to check the linked skills, name the sibling plugin's directory. The same applies to a [symlinked skill entry](/docs/en/skills#where-skills-live) in `~/.claude/skills` or `.claude/skills`, which a session does follow; to check it, name a directory called `skills` that holds the real folder.

1249* **The `skills`, `agents`, or `commands` directory you name is itself a symlink, or its parent `.claude` directory is**: Claude Code reports an error and checks nothing in it. Name the real directory instead.

1250 

1251A clean run ends with `Validation passed`. `No manifest found in directory` means Claude Code found no `plugin.json` or `marketplace.json` there, and no skill, agent, or command file in the directories it probes under it. Name the `skills`, `agents`, or `commands` directory that holds your files instead.

1252 

1253Two of the errors Claude Code reports from these runs, with the fix for each:

1254 

1255* `YAML frontmatter failed to parse: ...`: fix the YAML in the frontmatter block of the skill, agent, or command file. Until you do, a session reads no frontmatter fields from the file

1256* `Invalid JSON syntax: ...` on `hooks/hooks.json`: fix the JSON syntax. Until you do, a session loads the plugin without the hooks in that file. Claude Code reports this error only in a plugin run

1257 

1231### Plugin installation failures1258### Plugin installation failures

1232 1259 

1233**Symptoms**: Marketplace appears but plugin installation fails1260**Symptoms**: Marketplace appears but plugin installation fails

1211### Common issues1211### Common issues

1212 1212 

1213| Issue | Cause | Solution |1213| Issue | Cause | Solution |

1214| :---------------------------------- | :------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |1214| :---------------------------------- | :------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

1215| Plugin not loading | Invalid `plugin.json` | Run `claude plugin validate ./my-plugin` or `/plugin validate ./my-plugin`, where `./my-plugin` is your plugin directory, to check `plugin.json`, skill/agent/command frontmatter, and `hooks/hooks.json` for syntax and schema errors |1215| Plugin not loading | Invalid `plugin.json` | Run `claude plugin validate ./my-plugin` or `/plugin validate ./my-plugin`, where `./my-plugin` is your plugin directory, to check `plugin.json`, `hooks/hooks.json`, and the frontmatter of the skills, agents, and commands in the plugin's default directories for syntax and schema errors. See [Validate a plugin or a directory without a manifest](/docs/en/plugin-marketplaces#validate-a-plugin-or-a-directory-without-a-manifest) for what a run covers |

1216| Skills not appearing | Wrong directory structure | Ensure `skills/` or `commands/` is at the plugin root, not inside `.claude-plugin/` |1216| Skills not appearing | Wrong directory structure | Ensure `skills/` or `commands/` is at the plugin root, not inside `.claude-plugin/` |

1217| Hooks not firing | Script not executable | Run `chmod +x script.sh` |1217| Hooks not firing | Script not executable | Run `chmod +x script.sh` |

1218| MCP server fails | Missing `${CLAUDE_PLUGIN_ROOT}` | Use variable for all plugin paths |1218| MCP server fails | Missing `${CLAUDE_PLUGIN_ROOT}` | Use variable for all plugin paths |

197The location, retention, and write behavior are configurable:197The location, retention, and write behavior are configurable:

198 198 

199| To | Set | Where |199| To | Set | Where |

200| ------------------------------------------- | ------------------------------------------------------ | ------------------------- |200| ------------------------------------------------------------------------------- | ------------------------------------------------------ | ------------------------- |

201| Move storage off `~/.claude` | [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) | Environment variable |201| Move storage off `~/.claude` | [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) | Environment variable |

202| [Name the `<project>` directory yourself](#name-the-project-directory-yourself) | [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/env-vars) | Environment variable |

202| Change the 30-day retention | [`cleanupPeriodDays`](/docs/en/settings#available-settings) | `settings.json` |203| Change the 30-day retention | [`cleanupPeriodDays`](/docs/en/settings#available-settings) | `settings.json` |

203| Suppress transcript writes in all modes | [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/docs/en/env-vars) | Environment variable |204| Suppress transcript writes in all modes | [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/docs/en/env-vars) | Environment variable |

204| Suppress writes for one non-interactive run | [`--no-session-persistence`](/docs/en/cli-reference) | CLI flag with `claude -p` |205| Suppress writes for one non-interactive run | [`--no-session-persistence`](/docs/en/cli-reference) | CLI flag with `claude -p` |

205 206 

207### Name the project directory yourself

208 

209By default, Claude Code derives the `<project>` name from the whole working directory path. To choose the name yourself, set `CLAUDE_CODE_PROJECT_DIR_NAME` alongside `CLAUDE_CONFIG_DIR`. Claude Code then stores that session's transcripts and [auto memory](/docs/en/memory#auto-memory) under your name. This suits a host that embeds Claude Code and gives each session its own config directory. Requires Claude Code v2.1.234 or later.

210 

211For example, this launch keeps tenant A's data under `/srv/tenant-a` and names its project directory `work`:

212 

213```bash theme={null}

214CLAUDE_CONFIG_DIR=/srv/tenant-a CLAUDE_CODE_PROJECT_DIR_NAME=work claude

215```

216 

217Claude Code writes the session's transcripts to `/srv/tenant-a/projects/work/` and its auto memory to `/srv/tenant-a/projects/work/memory/`, whatever the working directory is.

218 

219Three rules apply when you set it:

220 

221* **Set `CLAUDE_CONFIG_DIR` too**: the name doesn't vary with the working directory, so under the default `~/.claude` it would merge every project's transcripts and auto memory into one directory. Claude Code ignores `CLAUDE_CODE_PROJECT_DIR_NAME` when `CLAUDE_CONFIG_DIR` is unset.

222* **Use 1-64 letters, digits, hyphens, or underscores**: don't use a Windows device name such as `con`. Claude Code ignores any other value and uses the derived name.

223* **Set it in the shell environment that starts `claude`**: Claude Code reads it once at startup from that environment, so an `env` block in a settings file can't set it.

224 

225Once you've named a config directory's project directory, keep launching with that name. If you start Claude Code with the same `CLAUDE_CONFIG_DIR` but without `CLAUDE_CODE_PROJECT_DIR_NAME`, it reads and writes the derived directory again. The sessions stored under your name stay on disk: press `Ctrl+A` in the [session picker](#use-the-session-picker) to list sessions from every project directory under that config directory, the pinned one included, and whichever way you launch, [`claude --resume <session-id>`](#resume-a-session) finds a session stored under either name.

226 

206## See also227## See also

207 228 

208* [Worktrees](/docs/en/worktrees): run isolated parallel sessions on separate branches229* [Worktrees](/docs/en/worktrees): run isolated parallel sessions on separate branches

241| `autoMode.classifyAllShell` | **Default**: `false`. When `true`, suspends every Bash and PowerShell allow rule while auto mode is active so all shell commands route through the classifier, not only rules that match arbitrary-code-execution patterns. See [Route all shell commands through the classifier](/docs/en/auto-mode-config#route-all-shell-commands-through-the-classifier). Requires Claude Code v2.1.193 or later | `true` |241| `autoMode.classifyAllShell` | **Default**: `false`. When `true`, suspends every Bash and PowerShell allow rule while auto mode is active so all shell commands route through the classifier, not only rules that match arbitrary-code-execution patterns. See [Route all shell commands through the classifier](/docs/en/auto-mode-config#route-all-shell-commands-through-the-classifier). Requires Claude Code v2.1.193 or later | `true` |

242| `autoScrollEnabled` | **Default**: `true`. In [fullscreen rendering](/docs/en/fullscreen), follow new output to the bottom of the conversation. Appears in `/config` as **Auto-scroll**. Permission prompts still scroll into view when this is off | `false` |242| `autoScrollEnabled` | **Default**: `true`. In [fullscreen rendering](/docs/en/fullscreen), follow new output to the bottom of the conversation. Appears in `/config` as **Auto-scroll**. Permission prompts still scroll into view when this is off | `false` |

243| `autoUpdatesChannel` | **Default**: `"latest"`. Release channel to follow for updates. Use `"stable"` for a version that is typically about one week old and skips versions with major regressions, or `"latest"` for the most recent release. To disable auto-updates entirely, set [`DISABLE_AUTOUPDATER`](/docs/en/setup#disable-auto-updates) in `env` | `"stable"` |243| `autoUpdatesChannel` | **Default**: `"latest"`. Release channel to follow for updates. Use `"stable"` for a version that is typically about one week old and skips versions with major regressions, or `"latest"` for the most recent release. To disable auto-updates entirely, set [`DISABLE_AUTOUPDATER`](/docs/en/setup#disable-auto-updates) in `env` | `"stable"` |

244| `availableModels` | Restrict which models users can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/docs/en/advisor). Does not affect the Default option unless `enforceAvailableModels` is also set. See [Restrict model selection](/docs/en/model-config#restrict-model-selection) | `["sonnet", "haiku"]` |244| `availableModels` | Restrict which models users can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/docs/en/advisor). See [Default model behavior](/docs/en/model-config#default-model-behavior) for the Default option. See [Restrict model selection](/docs/en/model-config#restrict-model-selection) | `["sonnet", "haiku"]` |

245| `awaySummaryEnabled` | Show a one-line session recap when you return to the terminal after a few minutes away. Set to `false` or turn off Session recap in `/config` to disable. Same as [`CLAUDE_CODE_ENABLE_AWAY_SUMMARY`](/docs/en/env-vars) | `true` |245| `awaySummaryEnabled` | Show a one-line session recap when you return to the terminal after a few minutes away. Set to `false` or turn off Session recap in `/config` to disable. Same as [`CLAUDE_CODE_ENABLE_AWAY_SUMMARY`](/docs/en/env-vars) | `true` |

246| `awsAuthRefresh` | Custom script that modifies the `.aws` directory (see [advanced credential configuration](/docs/en/amazon-bedrock#advanced-credential-configuration)) | `aws sso login --profile myprofile` |246| `awsAuthRefresh` | Custom script that modifies the `.aws` directory (see [advanced credential configuration](/docs/en/amazon-bedrock#advanced-credential-configuration)) | `aws sso login --profile myprofile` |

247| `awsCredentialExport` | Custom script that outputs JSON with AWS credentials (see [advanced credential configuration](/docs/en/amazon-bedrock#advanced-credential-configuration)) | `/bin/generate_aws_grant.sh` |247| `awsCredentialExport` | Custom script that outputs JSON with AWS credentials (see [advanced credential configuration](/docs/en/amazon-bedrock#advanced-credential-configuration)) | `/bin/generate_aws_grant.sh` |

278| `enableAllProjectMcpServers` | Automatically approve all MCP servers defined in project `.mcp.json` files. As of v2.1.196, `claude mcp list` and `claude mcp get` honor this key in an untrusted folder only from [settings files that aren't checked into the repository](/docs/en/mcp#managing-your-servers) | `true` |278| `enableAllProjectMcpServers` | Automatically approve all MCP servers defined in project `.mcp.json` files. As of v2.1.196, `claude mcp list` and `claude mcp get` honor this key in an untrusted folder only from [settings files that aren't checked into the repository](/docs/en/mcp#managing-your-servers) | `true` |

279| `enableArtifact` | Enable or disable the [Artifact](/docs/en/artifacts) tool for this user. When unset, the default follows the feature's [availability](/docs/en/artifacts#availability) for your account. The **Artifacts** row in `/config` writes this key. A managed `disableArtifact` and your organization's [admin setting](/docs/en/artifacts#manage-artifacts-for-your-organization) take precedence, and the key is ignored in project and local settings (`.claude/settings.json`, `.claude/settings.local.json`), which a repository could otherwise commit. Requires Claude Code v2.1.196 or later | `true` |279| `enableArtifact` | Enable or disable the [Artifact](/docs/en/artifacts) tool for this user. When unset, the default follows the feature's [availability](/docs/en/artifacts#availability) for your account. The **Artifacts** row in `/config` writes this key. A managed `disableArtifact` and your organization's [admin setting](/docs/en/artifacts#manage-artifacts-for-your-organization) take precedence, and the key is ignored in project and local settings (`.claude/settings.json`, `.claude/settings.local.json`), which a repository could otherwise commit. Requires Claude Code v2.1.196 or later | `true` |

280| `enabledMcpjsonServers` | List of specific MCP servers from `.mcp.json` files to approve. As of v2.1.196, `claude mcp list` and `claude mcp get` honor this key in an untrusted folder only from [settings files that aren't checked into the repository](/docs/en/mcp#managing-your-servers) | `["memory", "github"]` |280| `enabledMcpjsonServers` | List of specific MCP servers from `.mcp.json` files to approve. As of v2.1.196, `claude mcp list` and `claude mcp get` honor this key in an untrusted folder only from [settings files that aren't checked into the repository](/docs/en/mcp#managing-your-servers) | `["memory", "github"]` |

281| `enforceAvailableModels` | Extend the `availableModels` allowlist to the Default model. When `true` in managed settings and `availableModels` is a non-empty array, the Default option falls back to the first allowlisted entry that is available, but only when the model Default would resolve to (the [organization default](/docs/en/model-config#organization-default-model) when one applies, otherwise the account-type default) is not in the allowlist; an allowlisted default is kept as-is. Has no effect when `availableModels` is unset or empty. See [Enforce the allowlist for the Default model](/docs/en/model-config#enforce-the-allowlist-for-the-default-model). Requires Claude Code v2.1.175 or later | `true` |281| `enforceAvailableModels` | Extend the `availableModels` allowlist to the Default model. When `true` in managed settings and `availableModels` is a non-empty array, a Default model outside the allowlist falls back to the first allowlisted entry that is available. See [Enforce the allowlist for the Default model](/docs/en/model-config#enforce-the-allowlist-for-the-default-model). Requires Claude Code v2.1.175 or later | `true` |

282| `env` | Environment variables applied to every session and to subprocesses Claude Code spawns from it. Set a variable to `""` to override a shell export with an empty string, which Claude Code treats as unset for provider selection. Subprocesses still inherit the empty value. `NO_COLOR` and `FORCE_COLOR` set here reach only subprocesses; to change Claude Code's own interface colors, set them in your shell before launching `claude`. Claude Code ignores identity variables set here that its hosting environments own, such as `CLAUDE_CODE_REMOTE` and `CLAUDE_CODE_ACCOUNT_UUID`. It also ignores [`CLAUDE_CODE_MESSAGING_SOCKET` and `CLAUDE_CODE_MESSAGING_TOKEN`](/docs/en/env-vars#variables), which it exports itself. Ignoring the socket variable requires Claude Code v2.1.224 or later, and ignoring the token requires v2.1.228 or later | `{"FOO": "bar"}` |282| `env` | Environment variables Claude Code sets in every session and passes to the processes it starts, such as Bash commands and hooks. To override a shell export you can't unset, set that variable to `""` here; Claude Code treats the empty value as unset for provider selection, and processes it starts still inherit the empty value. `NO_COLOR` and `FORCE_COLOR` set here reach only subprocesses; to change Claude Code's own interface colors, set them in your shell before launching `claude`. Claude Code ignores identity variables set here that its hosting environments own, such as `CLAUDE_CODE_REMOTE` and `CLAUDE_CODE_ACCOUNT_UUID`. It also ignores [`CLAUDE_CODE_MESSAGING_SOCKET` and `CLAUDE_CODE_MESSAGING_TOKEN`](/docs/en/env-vars#variables), which it exports itself. Ignoring the socket variable requires Claude Code v2.1.224 or later, and ignoring the token requires v2.1.228 or later. Ignoring [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself), which it reads from the launch environment only, requires v2.1.234 or later | `{"FOO": "bar"}` |

283| `fallbackModel` | Fallback model(s) to try in order when the primary model is overloaded or unavailable. Claude Code switches to the next available model in the chain for the rest of the turn and shows a notice. `"default"` expands to the default model. Chains are capped at three models; extra entries are ignored. Unlike most array settings, this key does not merge across settings files: the highest-precedence file that defines it supplies the entire chain. The [`--fallback-model`](/docs/en/cli-reference#cli-flags) flag overrides this for one session. See [Fallback model chains](/docs/en/model-config#fallback-model-chains) | `["claude-sonnet-5", "claude-haiku-4-5"]` |283| `fallbackModel` | Fallback model(s) to try in order when the primary model is overloaded or unavailable. Claude Code switches to the next available model in the chain for the rest of the turn and shows a notice. `"default"` expands to the default model. Chains are capped at three models; extra entries are ignored. Unlike most array settings, this key does not merge across settings files: the highest-precedence file that defines it supplies the entire chain. The [`--fallback-model`](/docs/en/cli-reference#cli-flags) flag overrides this for one session. See [Fallback model chains](/docs/en/model-config#fallback-model-chains) | `["claude-sonnet-5", "claude-haiku-4-5"]` |

284| `fastMode` | Turn [fast mode](/docs/en/fast-mode) on for sessions where it's available. Toggling with `/fast` writes `true` here in user settings and removes the key when you turn fast mode off | `true` |284| `fastMode` | Turn [fast mode](/docs/en/fast-mode) on for sessions where it's available. Toggling with `/fast` writes `true` here in user settings and removes the key when you turn fast mode off | `true` |

285| `fastModePerSessionOptIn` | When `true`, fast mode does not persist across sessions. Each session starts with fast mode off, requiring users to enable it with `/fast`. The user's fast mode preference is still saved. See [Require per-session opt-in](/docs/en/fast-mode#require-per-session-opt-in) | `true` |285| `fastModePerSessionOptIn` | When `true`, fast mode does not persist across sessions. Each session starts with fast mode off, requiring users to enable it with `/fast`. The user's fast mode preference is still saved. See [Require per-session opt-in](/docs/en/fast-mode#require-per-session-opt-in) | `true` |

302| `color` | No | Display color for the subagent in the task list and transcript. Accepts `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan` |302| `color` | No | Display color for the subagent in the task list and transcript. Accepts `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan` |

303| `initialPrompt` | No | Auto-submitted as the first user turn when this agent runs as the main session agent (via `--agent` or the `agent` setting). [Commands](/docs/en/commands) and [skills](/docs/en/skills) are processed. Prepended to any user-provided prompt |303| `initialPrompt` | No | Auto-submitted as the first user turn when this agent runs as the main session agent (via `--agent` or the `agent` setting). [Commands](/docs/en/commands) and [skills](/docs/en/skills) are processed. Prepended to any user-provided prompt |

304 304 

305#### Subagent files Claude Code skips

306 

307Claude Code skips a file in a project, user, or managed `agents` directory, or in one under a directory you add with `--add-dir`, without reporting it in the session, when the frontmatter has any of these problems:

308 

309* **No `name`**: Claude Code treats the file as documentation kept beside your agents.

310* **A `name` that starts with `-` or contains `:`**: Claude Code skips the file and writes an error to the debug log. See the `name` row in the table above.

311* **A `name` but no `description`**: Claude Code skips the file and writes the reason to the debug log.

312* **YAML that doesn't parse**: Claude Code reads no fields from the file, skips it, and writes the parse error to the debug log.

313 

314To see the debug log, run Claude Code with `--debug`. A [plugin subagent](/docs/en/plugins-reference#agents) whose frontmatter has no `name` or doesn't parse still loads, under its filename.

315 

316To find files in an `agents` directory whose frontmatter doesn't parse, run `claude plugin validate` against the directory, for example `.claude/agents` or `~/.claude/agents`. Claude Code checks only [the directory you name](/docs/en/plugin-marketplaces#validate-a-plugin-or-a-directory-without-a-manifest), and doesn't flag a file whose frontmatter parses but has no `name`. Requires Claude Code v2.1.233 or later.

317 

305### Choose a model318### Choose a model

306 319 

307The `model` field controls which [AI model](/docs/en/model-config) the subagent uses:320The `model` field controls which [AI model](/docs/en/model-config) the subagent uses: