Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Reading a new release v2.1.280 First look · 1/6 0 findings $0.00 so far
One change · claude-code

Agent SDK reference - TypeScript changed

agent-sdk/typescript

Nearest release: v2.1.273, published 2 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+8added
Lines−8removed
From line 428 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits50to this page, all time

The whole hunk

from line 428, old and new numbered
/
lines

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 428
428428| `executable` | `'bun' \| 'deno' \| 'node'` | Auto-detected | JavaScript runtime to use |
429429| `executableArgs` | `string[]` | `[]` | Arguments to pass to the executable |
430430| `extraArgs` | `Record<string, string \| null>` | `{}` | Additional arguments |
431| `fallbackModel` | `string` | `undefined` | Model to use if primary fails |
431| `fallbackModel` | `string` | `undefined` | Model to use if the primary model fails. Accepts a comma-separated list. For the order and the cap, see [Fallback model chains](/docs/en/model-config#fallback-model-chains). For guidance, see [Choose a model](/docs/en/agent-sdk/configuration#choose-a-model) |
432432| `forkSession` | `boolean` | `false` | When resuming with `resume`, fork to a new session ID instead of continuing the original session |
433433| `forwardSubagentText` | `boolean` | `false` | Forward subagent text and thinking blocks as assistant and user messages with `parent_tool_use_id` set, so consumers can render a nested transcript. Without this option, Claude Code emits subagent `tool_use` and `tool_result` blocks but not text or thinking. Messages from subagents at every nesting depth are forwarded on Claude Code v2.1.219 and later; before v2.1.219, only messages from depth-1 subagents appeared |
434434| `hooks` | `Partial<Record<`[`HookEvent`](#hookevent)`, `[`HookCallbackMatcher`](#hookcallbackmatcher)`[]>>` | `{}` | Hook callbacks for events |
from line 436
436436| `includePartialMessages` | `boolean` | `false` | Include partial message events |
437437| `loadTimeoutMs` | `number` | `60000` | *Alpha.* Timeout in milliseconds for each `sessionStore.load()` and `sessionStore.listSubkeys()` call during resume materialization. If the adapter doesn't settle within this window, the query fails instead of hanging. Ignored when `sessionStore` is not set |
438438| `managedSettings` | `Settings` | `undefined` | Policy-tier settings your host process supplies to the spawned session. On machines with admin-deployed managed settings, Claude Code ignores these unless the admin's highest-priority managed source sets `parentSettingsBehavior: 'merge'`, and never merges them while a [`policyHelper`](/docs/en/settings-reference#policyhelper) supplies managed settings. Merged values pass through a restrictive-only filter; [Restrict parent settings](/docs/en/claude-apps-gateway#restrict-parent-settings) covers what the filter admits and the `allowManaged*Only` locks. A host that sets [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](/docs/en/env-vars) has three keys read straight from this payload instead: its [model configuration](/docs/en/model-config#restrict-model-selection) on Claude Code v2.1.222 or later, [`modelPricing`](/docs/en/settings-reference#modelpricing) when no managed source sets it on v2.1.246 or later, and its `ENABLE_TOOL_SEARCH` env entry on v2.1.247 or later |
439| `maxBudgetUsd` | `number` | `undefined` | Stop the query when the client-side cost estimate reaches this USD value. Compared against the same estimate as `total_cost_usd`; see [Track cost and usage](/docs/en/agent-sdk/cost-tracking) for accuracy caveats |
439| `maxBudgetUsd` | `number` | `undefined` | Stop the query when the client-side cost estimate reaches this USD value. Compared against the same estimate as `total_cost_usd`. For accuracy caveats and reset behavior, see [Track cost and usage](/docs/en/agent-sdk/cost-tracking) |
440440| `maxThinkingTokens` | `number` | `undefined` | *Deprecated:* Use `thinking` instead. Maximum tokens for thinking process |
441441| `maxTurns` | `number` | `undefined` | Maximum agentic turns (tool-use round trips) |
442442| `mcpServers` | `Record<string, [`McpServerConfig`](#mcpserverconfig)>` | `{}` | MCP server configurations |
from line 459
459459| `sessionId` | `string` | Auto-generated | Use a specific UUID for the session instead of auto-generating one |
460460| `sessionStore` | [`SessionStore`](/docs/en/agent-sdk/session-storage#the-sessionstore-interface) | `undefined` | Mirror session transcripts to an external backend so another host can resume them. See [Persist sessions to external storage](/docs/en/agent-sdk/session-storage) |
461461| `sessionStoreFlush` | `'batched' \| 'eager'` | `'batched'` | *Alpha.* Flush mode for `sessionStore`. Ignored when `sessionStore` is not set |
462| `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) |
462| `settings` | `string \| Settings` | `undefined` | Inline [settings](/docs/en/settings) object, a settings file path, or an inline JSON string. Populates the flag-settings layer in the [precedence order](/docs/en/settings#settings-precedence). Change at runtime with [`applyFlagSettings()`](#applyflagsettings) |
463463| `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) |
464464| `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) |
465465| `spawnClaudeCodeProcess` | `(options: SpawnOptions) => SpawnedProcess` | `undefined` | Custom function to spawn the Claude Code process. Use to run Claude Code in VMs, containers, or remote environments |
from line 556
556556| `interrupt()` | Interrupts the query. Only available in streaming input mode. When the CLI advertises the `interrupt_receipt_v1` capability in [`SDKSystemMessage.capabilities`](#sdksystemmessage), resolves with an [`SDKControlInterruptResponse`](#sdkcontrolinterruptresponse) listing the messages that were pending when the interrupt arrived. Resolves `undefined` on CLIs before v2.1.205 |
557557| `rewindFiles(userMessageId, options?)` | Restores files to their state at the specified user message. Pass `{ dryRun: true }` to preview changes. Requires `enableFileCheckpointing: true`. See [File checkpointing](/docs/en/agent-sdk/file-checkpointing) |
558558| `setPermissionMode()` | Changes the permission mode (only available in streaming input mode) |
559| `setModel()` | Changes the model (only available in streaming input mode). Passing `undefined` or the string `"default"` resets to the session default model |
559| `setModel()` | Changes the model (only available in streaming input mode). Passing `undefined` or the string `"default"` resets to [Claude Code's default model](/docs/en/model-config) |
560560| `setMaxThinkingTokens()` | *Deprecated:* Use the `thinking` option instead. Changes the maximum thinking tokens. Passing `null` resets thinking to the session default: a mid-session override is cleared, and thinking stays off for sessions that have it disabled |
561561| `applyFlagSettings(settings)` | Merges settings into the session's flag settings layer at runtime (only available in streaming input mode). See [`applyFlagSettings()`](#applyflagsettings) |
562562| `updateSettings(source, settings)` | Merges settings into the project's local settings file, `.claude/settings.local.json`; they take effect on the next request. Accepts only `source: 'localSettings'` and an allowlisted key set, currently `outputStyle`, with string values; deleting a key isn't supported. Rejects on remote transports and in sessions whose [`settingSources`](#options) exclude `local`. Requires TypeScript SDK v0.3.257 or later, which bundles Claude Code v2.1.257 |
from line 591
591591 
592592The 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.
593593 
594Successive calls shallow-merge top-level keys. A second call with `{ permissions: {...} }` replaces the entire `permissions` object from the prior call rather than deep-merging into it. To clear a key from the flag layer and fall back to lower-precedence sources, pass `null` for that key. Passing `undefined` has no effect because JSON serialization drops it.
594Successive calls shallow-merge top-level keys. A second call with `{ permissions: {...} }` replaces the entire `permissions` object from the prior call rather than deep-merging into it. To clear a key from the flag layer, pass `null` for that key. Most keys then fall back to lower-precedence sources. A cleared `model` resets to [Claude Code's default model](/docs/en/model-config), even when a settings file sets `model`. Passing `undefined` has no effect because JSON serialization drops it.
595595 
596596Only available in streaming input mode, the same constraint as `setModel()` and `setPermissionMode()`.
597597 
598The example below switches the active model mid-session, then clears the override so the model falls back to whatever the user or project settings specify.
598The example below switches the active model mid-session, then clears the override so the model resets to [Claude Code's default model](/docs/en/model-config).
599599 
600600```typescript theme={null}
601601import { query } from "@anthropic-ai/claude-agent-sdk";
from line 605
605605// Override the model for the rest of the session
606606await q.applyFlagSettings({ model: "claude-opus-4-6" });
607607 
608// Later: clear the override and fall back to lower-precedence settings
608// Later: clear the override; the model resets to Claude Code's default
609609await q.applyFlagSettings({ model: null });
610610```
611611 
from line 2973
29732973 
29742974Schedules a prompt to run on a 5-field cron schedule in local time. Set `recurring` to `false` to fire once at the next match. Jobs are session-scoped by default: starting a fresh conversation clears them, and resuming with `--resume` or `--continue` restores jobs that haven't expired. See [Scheduled tasks](/docs/en/scheduled-tasks).
29752975 
2976Setting `durable` to `true` requests persistence to `.claude/scheduled_tasks.json` so the job survives restarts. Durable scheduling isn't available in every session: when it isn't, Claude Code accepts `durable: true` but creates the job session-only. Read the output's `durable` field to see whether the job persisted.
2977 
2978### CronDelete
2979 
2980**Tool name:** `CronDelete`
2981 
2982```typescript theme={null}
2983type CronDeleteInput = {
2984 id: string;
2985};
2986```
2987 
2988Deletes
2976Setting `durable` to `true` requests persistence to `.claude/scheduled_tasks.json` so the job survives restarts. Durable scheduling isn't available in every session: when it isn't, Claude Code accepts `durable: true` but creates the job session-only. Read the output's `durable` field to see whe