Agent SDK reference - TypeScript changedagent-sdk/typescript
Nearest release: v2.1.250, published 4 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+95added
Lines−15removed
From line
13
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits115to this page, all time
### `SDKControlReloadSkillsResponse` #### `user_message_uuid` #### `queued_turn_count`
The whole hunk
from line 13, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 13
1313<Note>
1414 The SDK bundles a native Claude Code binary for your platform as an optional dependency such as `@anthropic-ai/claude-agent-sdk-darwin-arm64`. Most installs need no separate Claude Code install. The SDK version tracks the bundled Claude Code version: SDK v0.3.191 bundles Claude Code v2.1.191, so a feature on this page that requires a Claude Code version needs the SDK release with the same patch number or later. If your package manager skips optional dependencies, the SDK throws `Native CLI binary for <platform> not found`; set [`pathToClaudeCodeExecutable`](#options) to a separately installed `claude` binary instead.
1515
16 If your package manager doesn't apply npm's `libc` field, as Yarn 1.x doesn't, you get both the glibc and musl platform packages on Linux, roughly doubling the install size. The SDK still launches the correct variant. To reclaim the space in a container image, delete the platform package that doesn't match the libc where your app runs; for a glibc runtime on x64, that's `rm -rf node_modules/@anthropic-ai/claude-agent-sdk-linux-x64-musl`. On a development machine the deletion is temporary, since Yarn reinstalls the package on the next dependency change.
16 If your package manager doesn't apply npm's `libc` field, as Yarn 1.x doesn't, you get both the glibc and musl platform packages on Linux, roughly doubling the install size. On Agent SDK v0.2.141 or later, the SDK still launches the correct variant. To reclaim the space in a container image, delete the platform package that doesn't match the libc where your app runs; for a glibc runtime on x64, that's `rm -rf node_modules/@anthropic-ai/claude-agent-sdk-linux-x64-musl`. On a development machine the deletion is temporary, since Yarn reinstalls the package on the next dependency change.
1717</Note>
1818
1919### Compile to a single executable
from line 452
452452| `sessionStoreFlush` | `'batched' \| 'eager'` | `'batched'` | *Alpha.* Flush mode for `sessionStore`. Ignored when `sessionStore` is not set |
453453| `settings` | `string \| Settings` | `undefined` | Inline [settings](/docs/en/settings) object or path to a settings file. Populates the flag-settings layer in the [precedence order](/docs/en/settings#settings-precedence). Change at runtime with [`applyFlagSettings()`](#applyflagsettings) |
454454| `settingSources` | [`SettingSource`](#settingsource)`[]` | CLI defaults (all sources) | Control which filesystem settings to load. Pass `[]` to disable user, project, and local settings. [Endpoint-managed policy](/docs/en/managed-settings#delivery-mechanisms) loads regardless; server-managed settings are fetched when the session authenticates with an organization credential on an [eligible configuration](/docs/en/server-managed-settings#platform-availability). See [Use Claude Code features](/docs/en/agent-sdk/claude-code-features#what-settingsources-does-not-control) |
455| `skills` | `string[] \| 'all'` | `undefined` | Skills available to the session. Pass `'all'` to enable every discovered skill, or a list of skill names. Pass exact names only. The SDK rejects malformed and wildcard-form names with an error before starting the Claude Code process. When set, the SDK adds the Skill tool to `allowedTools` automatically. If you also pass `tools`, include `'Skill'` in that list. See [Skills](/docs/en/agent-sdk/skills) |
455| `skills` | `string[] \| 'all'` | `undefined` | Skills available to the session. Pass `'all'` to enable every discovered skill, or a list of skill names. Pass exact names only. On Agent SDK v0.3.221 or later, the SDK rejects malformed and wildcard-form names with an error before starting the Claude Code process. When set, the SDK adds the Skill tool to `allowedTools` automatically. If you also pass `tools`, include `'Skill'` in that list. See [Skills](/docs/en/agent-sdk/skills) |
456456| `spawnClaudeCodeProcess` | `(options: SpawnOptions) => SpawnedProcess` | `undefined` | Custom function to spawn the Claude Code process. Use to run Claude Code in VMs, containers, or remote environments |
457457| `stderr` | `(data: string) => void` | `undefined` | Callback for stderr output |
458458| `strictMcpConfig` | `boolean` | `false` | Use only the servers passed in `mcpServers` and ignore project `.mcp.json`, user settings, plugin-provided MCP servers, and [claude.ai connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) |
from line 503
503503 setPermissionMode(mode: PermissionMode): Promise<void>;
504504 setModel(model?: string): Promise<void>;
505505 setMaxThinkingTokens(maxThinkingTokens: number | null): Promise<void>;
506 applyFlagSettings(settings: { [K in keyof Settings]?: Settings[K] | null }): Promise<void>;
506 applyFlagSettings(settings: {
507 [K in keyof Settings]?: K extends 'effortLevel'
508 ? 'low' | 'medium' | 'high' | 'xhigh' | 'max' | null
509 : Settings[K] | null;
510 }): Promise<void>;
507511 initializationResult(): Promise<SDKControlInitializeResponse>;
508512 reinitialize(): Promise<SDKControlInitializeResponse>;
509513 supportedCommands(): Promise<SlashCommand[]>;
from line 519
515519 path: string,
516520 options?: { maxBytes?: number; encoding?: 'utf-8' | 'base64' }
517521 ): Promise<SDKControlReadFileResponse | null>;
522 reloadSkills(): Promise<SDKControlReloadSkillsResponse>;
518523 accountInfo(): Promise<AccountInfo>;
519524 reconnectMcpServer(serverName: string): Promise<void>;
520525 toggleMcpServer(serverName: string, enabled: boolean): Promise<void>;
from line 548
543548| `mcpServerStatus()` | Returns status of connected MCP servers |
544549| `getContextUsage()` | Returns an [`SDKControlGetContextUsageResponse`](#sdkcontrolgetcontextusageresponse) breaking down the session's context window usage by category, skill, and tool. The same data `/context` shows in an interactive session |
545550| `readFile(path, options?)` | Reads a file from the session's filesystem. Claude Code resolves the path against `cwd` and applies the same read-permission rules as the Read tool. Pass `{ maxBytes }` to change the read cap (default 1 MB, ceiling 10 MB) and `{ encoding: 'base64' }` for binary files such as images. Resolves with an [`SDKControlReadFileResponse`](#sdkcontrolreadfileresponse), or `null` on permission denial, a missing file, or a transport error. Requires TypeScript SDK v0.2.121 or later |
551| `reloadSkills()` | Reloads skills from disk, so skills you add or edit mid-session become available to the running session. Resolves with an [`SDKControlReloadSkillsResponse`](#sdkcontrolreloadskillsresponse) listing the skills available after the reload. Requires Agent SDK v0.3.163 or later |
546552| `accountInfo()` | Returns account information |
547553| `reconnectMcpServer(serverName)` | Reconnect an MCP server by name |
548554| `toggleMcpServer(serverName, enabled)` | Enable or disable an MCP server by name |
549| `setMcpServers(servers)` | Dynamically replace the set of MCP servers for this session. Returns which servers were added and removed, and any errors. The call keeps plugin-provided servers it doesn't name; naming one replaces it. The promise resolves after newly added stdio, HTTP, and SSE servers connect or fail, so tools from servers that connected are available on the next turn. |
555| `setMcpServers(servers)` | Dynamically replace the set of MCP servers for this session. Resolves with an [`McpSetServersResult`](#mcpsetserversresult) naming which servers were added and removed, and any errors |
550556| `streamInput(stream)` | Stream input messages to the query for multi-turn conversations |
551557| `stopTask(taskId)` | Stop a running background task by ID |
552558| `close()` | Close the query and terminate the underlying process. Forcefully ends the query and cleans up all resources |
from line 567
561567* **Applied during the current turn**: `model`. If you switch `model` while Claude is working on a turn, the response Claude is already generating finishes on the old model, and the rest of the turn, starting with the next call Claude Code makes to the model, uses the new one. Subagents keep their own model. Before v2.1.212, a mid-turn switch waited for the next turn.
562568* **No effect mid-session**: the system prompt options. These are resolved once at startup, so the running session keeps the original value even though the call succeeds. To change them, start a new session.
563569
564`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which runs the session at `xhigh` effort and turns on [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode). The `Settings` type declares `effortLevel` without that value, so pass the equivalent `{ ultracode: true }` in TypeScript. The `ultracode` value requires Claude Code v2.1.203 or later and is accepted only by `applyFlagSettings()`, not by the `effortLevel` key in a settings file.
570`effortLevel` accepts an [effort level](/docs/en/model-config#adjust-effort-level) name. It also accepts `"ultracode"`, which runs the session at `xhigh` effort and turns on [ultracode](/docs/en/workflows#let-claude-decide-with-ultracode). `applyFlagSettings()` declares `effortLevel` without that value, so pass the equivalent `{ ultracode: true }` in TypeScript. The `ultracode` value requires Claude Code v2.1.203 or later and is accepted only by `applyFlagSettings()`, not by the `effortLevel` key in a settings file.
565571
566572The values are written to the flag-settings layer, the same layer the inline `settings` option of `query()` populates at startup. This is the same tier the [on-page precedence section](#settings-precedence) calls programmatic options.
567573
from line 797
791797
792798`contents` holds the file text, or base64 data when you requested `encoding: 'base64'`; the response's `encoding` field is set to `'base64'` in that case. `absPath` is the resolved absolute path. `truncated` is set when the file was longer than the `maxBytes` cap and the contents were cut at that limit.
793799
800### `SDKControlReloadSkillsResponse`
801
802Return type of [`reloadSkills()`](#query-object).
803
804```typescript theme={null}
805type SDKControlReloadSkillsResponse = {
806 skills: SlashCommand[];
807};
808```
809
810`skills` lists the skills available after the reload, in the same [`SlashCommand`](#slashcommand) shape that `supportedCommands()` returns.
811
794812### `AgentDefinition`
795813
796814Configuration for a subagent defined programmatically.
from line 1173
11551173 aborted?: true;
11561174 timestamp?: string;
11571175 context_usage?: SDKContextUsage;
1176 user_message_uuid?: string;
11581177};
11591178```
11601179
from line 1183
11641183
11651184`aborted` is `true` when an interrupt or abort truncated the assistant message before the stream completed: the message has no `stop_reason` and the content may end mid-word. The field is absent on normally completed messages. It requires Agent SDK v0.3.214 or later.
11661185
1186Claude Code sets `user_message_uuid` on the turn's first assistant message, under the conditions in [`user_message_uuid`](#user_message_uuid).
1187
11671188`timestamp` is the ISO 8601 time when the message's content finished generating on the process that produced it. The value comes from that machine's clock, so use it for display only and don't order messages by it. One API turn can produce several assistant messages that share a `message.id`, each with its own `timestamp`. When the field is absent, fall back to the time you received the message.
11681189
11691190`context_usage` is a structured copy of the `/context` report, typed as [`SDKContextUsage`](#sdkcontextusage), and requires Agent SDK v0.3.232 or later. When you send `/context` as a prompt, Claude Code delivers the report as an assistant message whose `message.content` holds the markdown table, and attaches `context_usage` to that same message. Claude Code doesn't set the field on any other assistant message, and earlier versions deliver the `/context` table without it, so read the breakdown from the field when it's present and fall back to the markdown text when it isn't.
from line 1259
12381259 usage: NonNullableUsage;
12391260 modelUsage: { [modelName: string]: ModelUsage };
12401261 permission_denials: SDKPermissionDenial[];
1262 queued_turn_count?: number;
12411263 structured_output?: unknown;
12421264 deferred_tool_use?: { id: string; name: string; input: Record<string, unknown> };
12431265 terminal_reason?: TerminalReason;
from line 1285
12631285 usage: NonNullableUsage;
12641286 modelUsage: { [modelName: string]: ModelUsage };
12651287 permission_denials: SDKPermissionDenial[];
1288 queued_turn_count?: number;
12661289 errors: string[];
1290 user_message_uuid?: string;
12671291 terminal_reason?: TerminalReason;
12681292 fast_mode_state?: FastModeState;
12691293 fast_mode_disabled_reason?: FastModeDisabledReason;
from line 1300
12761300* `api_error_status`: the HTTP status code of the API error that terminated the conversation. Absent or `null` when the turn ended without an API error.
12771301* `ttft_ms`: time to first token in milliseconds, measured when the first complete assistant message arrives. Present on the success arm only.
12781302* `ttft_stream_ms`: time in milliseconds until the first `message_start` stream event, when the response stream opens. Lower than `ttft_ms`; the gap between the two is time spent streaming the first message. Present on the success arm only.
1279* `user_message_uuid`: the `uuid` of the [`SDKUserMessage`](#sdkusermessage) that started this turn, echoed back so you can match the result to the message you sent. Requires Claude Code v2.1.216 or later. Present on the success arm only, together with `request_sent_wall_ms`; absent on API-error results, subagent calls, and synthetic turns such as scheduled ones.
1280* `request_sent_wall_ms`: epoch milliseconds at which Claude Code dispatched the API request, for joins against server-side timestamps. Present only together with `user_message_uuid`.
1303* `user_message_uuid`: the `uuid` of the message you sent that started this turn. See [`user_message_uuid`](#user_message_uuid) for which results carry it.
1304* `request_sent_wall_ms`: epoch milliseconds at which Claude Code dispatched the API request, for joins against server-side timestamps. Present on the success arm only, together with `user_message_uuid`, when `is_error` is false.
12811305* `usage`: main agent loop only. Excludes subagent and auxiliary model calls, and is per-turn in streaming-input sessions. Prefer `modelUsage` for token/cost accounting.
12821306* `modelUsage`: per-model totals for every model call made through the query pipeline during this `query()` call, including the main loop, subagents, and internal calls such as compaction and Workflow agents. Helper calls outside that pipeline, such as the permission classifier and token-counting requests, are excluded. In streaming-input sessions the totals are cumulative across turns, so read the latest result rather than summing across results. See [Track costs in streaming input mode](/docs/en/agent-sdk/cost-tracking#track-costs-in-streaming-input-mode) for resets and [Recover totals after a session crash](/docs/en/agent-sdk/cost-tracking#recover-totals-after-a-session-crash) for zeroed results.
12831307* `total_cost_usd`: cumulative estimated cost in USD for this `query()` call, covering the same calls as `modelUsage` and reset at the same points. It is an estimate, not a billing statement. See [Track cost and usage](/docs/en/agent-sdk/cost-tracking) for accuracy caveats.
1308* `queued_turn_count`: the number of messages you sent with `origin: { kind: "human" }` that are still waiting when Claude Code produced the result. See [`queued_turn_count`](#queued_turn_count) for what `0` and an absent field tell you.
12841309* `terminal_reason`: why the loop ended. One of `"completed"`, `"max_turns"`, `"tool_deferred"`, `"aborted_streaming"`, `"aborted_tools"`, `"hook_stopped"`, `"stop_hook_prevented"`, `"background_requested"`, `"blocking_limit"`, `"rapid_refill_breaker"`, `"prompt_too_long"`, `"image_error"`, `"model_error"`, `"api_error"`, `"malformed_tool_use_exhausted"`, `"budget_exhausted"`, `"structured_output_retry_exhausted"`, `"tool_deferred_unavailable"`, or `"turn_setup_failed"`.
12851310* `fast_mode_state`: one of `"on"`, `"off"`, or `"cooldown"`.
12861311* `fast_mode_disabled_reason`: why [fast mode](/docs/en/fast-mode) isn't available right now. Absent when nothing blocks fast mode, though a request may still run at standard speed. During the cooldown after a fast mode rate limit, Claude Code reports `fast_mode_state: "cooldown"` with no reason code and re-enables fast mode when the cooldown expires. Requires Claude Code v2.1.219 or later.
from line 1333
13081333
13091334When a `PreToolUse` hook returns `permissionDecision: "defer"`, the result has `stop_reason: "tool_deferred"` and `deferred_tool_use` carries the pending tool's `id`, `name`, and `input`. Read this field to surface the request in your own UI, then resume with the same `session_id` to continue. See [Defer a tool call for later](/docs/en/hooks#defer-a-tool-call-for-later) for the full round trip.
13101335
1336#### `user_message_uuid`
1337
1338The `uuid` of the [`SDKUserMessage`](#sdkusermessage) that started the turn, echoed so you can match Claude Code's reply to the message you sent. Claude Code echoes it only if you set `uuid` on that message. The field is optional on `SDKUserMessage`, and a string prompt passed to `query()` carries none. When you set it, Claude Code echoes it on two kinds of frame:
1339
1340* **The result**: on the success arm with `is_error` false, together with `request_sent_wall_ms`, which requires Agent SDK v0.3.216 or later. On an error result that answers a message you sent, Claude Code echoes the field alone, which requires Agent SDK v0.3.246 or later.
1341* **The turn's first reply**: the first [assistant message](#sdkassistantmessage), or with `includePartialMessages` the first [stream event](#sdkpartialassistantmessage) whose `event.type` isn't `ping`, so you can bind the reply before the result arrives. When a turn streams nothing, Claude Code sets it on the first assistant message instead. One frame per turn carries it. Requires Agent SDK v0.3.246 or later.
1342
1343Claude Code omits the field in these cases:
1344
1345* Later assistant messages and stream events of the same turn
1346* Subagent frames
1347* Synthetic turns, such as scheduled ones
1348* Results with no single triggering message, such as the zeroed result after a crashed worker process
1349
1350#### `queued_turn_count`
1351
1352The number of messages you sent with [`origin: { kind: "human" }`](#sdkmessageorigin) that are still waiting in the command queue when Claude Code produced the result. Requires Agent SDK v0.3.242 or later.
1353
1354What `0` and an absent field tell you:
1355
1356* **`0`**: Claude Code doesn't count messages you sent without that `origin`, and doesn't count task notifications, so a turn can still follow.
1357* **Absent**: the final result that Claude Code emits after a crash or fatal startup error omits the field, and [may carry zeroed totals](/docs/en/agent-sdk/cost-tracking#recover-totals-after-a-session-crash).
1358
13111359### `SDKSystemMessage`
13121360
13131361System initialization message.
from line 1415
13671415 uuid: UUID;
13681416 session_id: string;
13691417 ttft_ms?: number; // Time to first token in ms, present only on message_start events
1418 user_message_uuid?: string; // Present on at most one stream event per turn
13701419};
13711420```
13721421
1422Claude Code sets `user_message_uuid` on one stream event per turn, under the conditions in [`user_message_uuid`](#user_message_uuid).
1423
13731424### `SDKCompactBoundaryMessage`
13741425
13751426Message indicating a conversation compaction boundary.
from line 1667
16161667
16171668### Peer origin fields
16181669
1619A `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:
1670A `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. Cross-session peers require Claude Code v2.1.224 or later on macOS and Linux; see [cross-session messaging availability](/docs/en/cross-session-messaging#availability) for the native Windows requirement. 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:
16201671
16211672* `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.
16221673* `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.
from line 2409
23582409**Tool name:** `Agent`. The previous name `Task` is still accepted as an alias, and the `tools` array in the [`SDKSystemMessage`](#sdksystemmessage) init message currently lists this tool as `Task` for backward compatibility.
23592410
23602411<Note>
2361 The `mode` field is deprecated and ignored on Claude Code v2.1.212 or later: subagents [inherit the parent session's permission mode](/docs/en/agent-sdk/permissions#available-modes), and a subagent definition's [`permissionMode`](#agentdefinition) can override it, except when the parent uses `bypassPermissions`, `acceptEdits`, or `auto`, and Claude Code ignores a definition's `permissionMode: "bypassPermissions"` when bypass mode is disabled by [`permissions.disableBypassPermissionsMode`](/docs/en/permissions#managed-settings).
2412 The `mode` field is deprecated and ignored on Claude Code v2.1.212 or later: subagents [inherit the parent session's permission mode](/docs/en/agent-sdk/permissions#available-modes), and a subagent definition's [`permissionMode`](#agentdefinition) can override it, except when the parent uses `bypassPermissions`, `acceptEdits`, or `auto`. On v2.1.223 or later, Claude Code ignores a definition's `permissionMode: "bypassPermissions"` when bypass mode is disabled by [`permissions.disableBypassPermissionsMode`](/docs/en/permissions#managed-settings).
23622413</Note>
23632414
23642415```typescript theme={null}
from line 2531
24802531
24812532Reads files from the local filesystem, including text, images, PDFs, and Jupyter notebooks. Use `pages` for PDF page ranges (for example, `"1-5"`).
24822533
2534For a PDF, Claude receives the file's contents inside the Read call's `tool_result` content. A read that returns the `pdf` [output](#tool-output-types) carries a summary `text` block followed by a `document` block. One that returns the `parts` output carries the summary `text` block followed by one block per extracted page: an `image` block, or a `text` block naming the page when Claude Code couldn't render it as an image. Before Agent SDK v0.3.242, Claude Code delivered the file's contents as a separate `user` message after the tool result.
2535
24832536### Write
24842537
24852538**Tool name:** `Write`
from line 2886
28332886};
28342887```
28352888
2836Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 seconds. The `delaySeconds`, `reason`, and `prompt` fields are required unless `stop` is true. Setting `stop: true` cancels the pending wakeup and ends the self-paced `/loop`. The `stop` field requires Claude Code v2.1.202 or later. See the [ScheduleWakeup row in the tools reference](/docs/en/tools-reference) for availability; it isn't available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry, nor when you turn off [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching).
2889Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 seconds. The `delaySeconds`, `reason`, and `prompt` fields are required unless `stop` is true. Setting `stop: true` cancels the pending wakeup and ends the self-paced `/loop`. The `stop` field requires Claude Code v2.1.202 or later. See the [ScheduleWakeup row in the tools reference](/docs/en/tools-reference).
28372890
28382891### RemoteTrigger
28392892
from line 3397
33443397 count: number;
33453398 outputDir: string;
33463399 };
3400 /** Document page number of the first extracted page; labels the page images in the tool_result content. */
3401 firstPage?: number;
3402 /** In-process only: the page-image bytes are delivered as image blocks in the tool_result content and aren't retained on the emitted tool_use_result, so this key is absent there. */
3403 pages?: {
3404 base64: string;
3405 mediaType: "image/jpeg" | "image/png" | "image/gif" | "image/webp";
3406 error?: string;
3407 }[];
33473408 }
33483409 | {
33493410 type: "file_unchanged";
from line 3448
33873448};
33883449```
33893450
3390Returns the write result with structured diff information.
3451Returns the write result with structured diff information. What `originalFile` and `structuredPatch` hold depends on the write:
33913452
3453* For a newly created file, `originalFile` is null and `structuredPatch` is empty
3454* On an overwrite, `originalFile` carries the previous content, except when that content is larger than about 10 MB: Claude Code then skips the diff and returns `originalFile` null and `structuredPatch` empty
3455* `structuredPatch` is also empty when the write changed nothing or the diff timed out
3456
33923457### Glob
33933458
33943459**Tool name:** `Glob`
from line 4239
41744239```typescript theme={null}
41754240type SlashCommand = {
41764241 name: string;
4177 description: string;
4178 argumentHint: string;
4179 aliases?: string[];
4180};
4181```
4182
4183### `ModelInfo`
4184
4185Information about an available model.
4186
4187```typescript theme={null}
4188type ModelInfo = {
4189 value: string;
4190 resolvedModel?: string;
4191 displayName: string;
4192 description: string;
4193 supportsEffort?: boolean;
4194 supportedEffortLevels?: ("low" | "medium" | "high" | "xhigh" | "max")[];
4195 supportsAdaptiveThinking?: boolean;
4196 supportsFastMode?: boolean;
4197 supportsAutoMode?: boolean;
4198};
4199```
4200
4201| Field | Type | Description |
4202| :------------------------- | :----------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
4203| `value` | `string` | Model identifier to pass in API calls |
4204| `resolvedModel` | `string \| undefined` | Canonical wire model ID that this entry's `value` resolves to. An alias entry such as `sonnet` resolves to an explicit model ID such as `claude-sonnet-5`, so a host can match a stored explicit model ID against the alias entry that covers it. Requires Claude Code v2.1.197 or later. |
4205| `displayName` | `string` | Human-readable display name |
4206| `description` | `string` | Description of the model's capabilities |
4207| `supportsEffort` | `boolean \| undefined` | Whether this model supports effort levels |
4208| `supportedEffortLevels` | `("low" \| "medium" \| "high" \| "xhigh" \| "max")[] \| undefined` | Effort levels this model accepts |
4209| `supportsAdaptiveThinking` | `boolean \| undefined` | Whether this model supports adaptive thinking, where Claude decides when and how much to think |
4210| `supportsFastMode` | `boolean \| undefined` | Whether this model supports fast mode |
4211| `supportsAutoMode` | `boolean \| undefined` | Whether this model supports auto mode |
4212
4213### `AgentInfo`
4214
4215Information about an available subagent that can be invoked via the Agent tool.
4216
4217```typescript theme={null}
4218type AgentInfo = {
4219 name: string;
4220 description: string;
4221 model?: string;
4222};
4223```
4224
4225| Field | Type | Description |
4226| :------------ | :-------------
4242 descripti
No line in this hunk matches that.