One read of Claude Developer Platformapi-20261022T020713Z

This capture is too large to show at once. Changes 126-150 of 168 are below, significant first; the rest are on the following screens.

manage-claude/wif-providers/github-actions Changed · +1 / -1 lines

from line 311

311311 

312312## Verify the setup

313313 

314A successful exchange returns an `access_token` beginning with `sk-ant-oat01-` and an `expires_in` value in seconds. A denied exchange returns an opaque `401` `authentication_error` with the fixed message `Authentication failed`, whichever check failed; in most cases the deny reason is recorded on the attempt's entry in the [authentication history page](https://platform.claude.com/settings/workload-identity-federation?tab=history) in the Claude Console, and [Troubleshoot a failed exchange](https://platform.claude.com/docs/en/manage-claude/wif-reference#troubleshoot-a-failed-exchange) walks the checks in order. The most common GitHub Actions-side cause is the `sub` claim format not matching (its trailing segment varies between `ref:...`, `environment:...`, and `pull_request` events); the history entry shows reason `match_subject_prefix`.

314A successful exchange returns an `access_token` beginning with `sk-ant-oat01-` and an `expires_in` value in seconds. A denied exchange returns an opaque `401` `authentication_error` with the fixed message `Authentication failed`, whichever check failed; in most cases the deny reason is recorded on the attempt's entry in the [authentication history page](https://platform.claude.com/settings/workload-identity-federation?tab=history) in the Claude Console, and [Troubleshoot a failed exchange](https://platform.claude.com/docs/en/manage-claude/wif-reference#troubleshoot-a-failed-exchange) walks the checks in order. The most common GitHub Actions-side cause is the `sub` claim format not matching (its trailing segment varies among `ref:...`, `environment:...`, and `pull_request` events); the history entry shows reason `match_subject_prefix`.

315315 

316316## Restrict which workflows can authenticate

317317 

manage-claude/wif-providers/spiffe Changed · +1 / -1 lines

from line 475

475475* **Pin to one workload:** Set `subject_prefix` to the full SPIFFE ID with no trailing `*`.

476476* **Always set an audience:** Require `audience` on the rule and configure spiffe-helper (or the Workload API call) with the same value so SVIDs minted for other relying parties are rejected.

477477* **Scope by path segment:** Use `spiffe://prod.example.com/ns/inference/*` to grant every workload registered under a namespace, and create a separate rule and Anthropic service account for each namespace rather than widening one rule.

478* **One issuer for each trust domain:** Each SPIRE trust domain has its own signing keys and OIDC Discovery Provider. Register each as a separate federation issuer and bind rules to the issuer that owns the SPIFFE IDs they match.

478* **Register one issuer for each trust domain:** Each SPIRE trust domain has its own signing keys and OIDC Discovery Provider. Register each as a separate federation issuer and bind rules to the issuer that owns the SPIFFE IDs they match.

479479 

480480## Next steps

481481 

manage-claude/workload-identity-federation Changed · +1 / -1 lines

from line 371

371371 

372372Because the SDK re-reads `ANTHROPIC_IDENTITY_TOKEN_FILE` on every exchange, it transparently picks up rotated projected tokens (Kubernetes service-account tokens, for example, rotate well before their `exp`).

373373 

374By default, identity tokens that carry a `jti` claim are single-use: each exchange must present a JWT that has not been exchanged before, and re-presenting one fails with the reason `jti_reused` on the [authentication history page](https://platform.claude.com/settings/workload-identity-federation?tab=history) in the Claude Console. If your workload fetches its own tokens from your identity provider, mint a fresh JWT for each exchange instead of reusing a cached one (retry loops are the common culprit). The same applies to a token read from `ANTHROPIC_IDENTITY_TOKEN_FILE`: the SDK re-reads the file on every exchange, so the file must hold a new token before each refresh. A refresh that re-reads an unrotated token, or a restarted process that re-presents a token it already exchanged, is rejected the same way. Rotating the token well within the minted token's lifetime keeps the file ahead of the refresh schedule; if your token source cannot rotate that often, you can disable `check_jti` for that issuer as a last resort (this removes replay protection for every rule on the issuer). See [JWT verification](https://platform.claude.com/docs/en/manage-claude/wif-reference#jwt-verification) for details.

374By default, identity tokens that carry a `jti` claim are single-use: each exchange must present a JWT that has not been exchanged before, and re-presenting one fails with the reason `jti_reused` on the [authentication history page](https://platform.claude.com/settings/workload-identity-federation?tab=history) in the Claude Console. If your workload fetches its own tokens from your identity provider, mint a fresh JWT for each exchange instead of reusing a cached one (retry loops are the usual cause of reuse). The same applies to a token read from `ANTHROPIC_IDENTITY_TOKEN_FILE`: the SDK re-reads the file on every exchange, so the file must hold a new token before each refresh. A refresh that re-reads an unrotated token, or a restarted process that re-presents a token it already exchanged, is rejected the same way. Rotating the token well within the minted token's lifetime keeps the file ahead of the refresh schedule; if your token source cannot rotate that often, you can disable `check_jti` for that issuer as a last resort (this removes replay protection for every rule on the issuer). See [JWT verification](https://platform.claude.com/docs/en/manage-claude/wif-reference#jwt-verification) for details.

375375 

376376## Identity providers

377377 

managed-agents/dreams Changed · +1 / -1 lines

from line 154

154154 

155155The response is the full `dream` resource with `status: "pending"`:

156156 

157```json

157```text

158158{

159159 "type": "dream",

160160 "id": "drm_01AbCDefGhIjKlMnOpQrStUv",

managed-agents/files Changed · +1 / -1 lines

from line 558

558558 

559559## Listing and downloading session files

560560 

561Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Files the agent writes to `/mnt/session/outputs/` appear in the list shortly after the agent finishes writing them, sometimes a few seconds after the session goes idle. If an output file you expect is missing, list again after a short delay; once it appears in the list, its upload has finished.

561Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Files the agent writes to `/mnt/session/outputs/` appear in the list shortly after the agent finishes writing them, sometimes a few seconds after the session goes idle. If an output file you expect is missing, list again after a short delay; once it appears in the list, its upload is complete.

562562 

563563Filtering by `scope_id` (java: `scopeId`; php: `scopeID`; csharp, go: `ScopeID`) requires the `managed-agents-2026-04-01` beta header, so the list examples call `GET /v1/files` (python, typescript, ruby: `client.beta.files.list()`; go, csharp: `client.Beta.Files.List()`; java: `client.beta().files().list()`; php: `$client->beta->files->list()`; cli: `ant beta:files list`) and pass that header explicitly.

564564 

managed-agents/quickstart Changed · +1 / -1 lines

from line 33

3333 

3434## Prerequisites

3535 

36* A [Claude Console account](https://platform.claude.com)

36* A [Claude Console account](https://platform.claude.com/)

3737* An [API key](https://platform.claude.com/settings/keys) from the Console

3838 

3939## Install the CLI

managed-agents/scheduled-deployments Changed · +2 / -2 lines

from line 224

224224 

225225The response includes a deployment object with a populated `schedule.upcoming_runs_at` with the next upcoming fire times, to confirm your schedule was set correctly.

226226 

227```json

227```text wrap

228228{

229229 "id": "depl_01xyz",

230230 "status": "active",

from line 578

578578 

579579A failed run includes an `error` with a `type` describing why session creation was rejected (for example, `environment_archived_error`, `agent_archived_error`, or `session_rate_limited_error`). See the [List Deployment Runs](https://platform.claude.com/docs/en/api/beta/deployment_runs/list) reference for all filter parameters and the response schema.

580580 

581```json

581```text

582582{

583583 "type": "deployment_run",

584584 "id": "drun_01abc124",

managed-agents/self-hosted-sandboxes-workers Changed · +1 / -1 lines

from line 157

157157 

158158<Steps>

159159 <Step title="Subscribe to session webhooks">

160 In the [Console](https://platform.claude.com/settings/workspaces/default/webhooks), define a webhook endpoint that listens for `session.status_run_started` events. See [Webhooks](https://platform.claude.com/docs/en/managed-agents/webhooks) for details.

160 In the [Claude Console](https://platform.claude.com/settings/workspaces/default/webhooks), define a webhook endpoint that listens for `session.status_run_started` events. See [Webhooks](https://platform.claude.com/docs/en/managed-agents/webhooks) for details.

161161 </Step>

162162 

163163 <Step title="Export the webhook signing key">

managed-agents/session-observability Changed · +2 / -2 lines

from line 38

3838 

3939The session object includes a `usage` field with the session's cumulative usage: token counts, server tool use, active time, and the tracked list cost. Fetch the session after it goes idle to read the latest totals.

4040 

41```json

41```text wrap

4242{

4343 "id": "sesn_01...",

4444 "status": "idle",

from line 79

7979 

8080### Per-thread usage

8181 

82Each [session thread](https://platform.claude.com/docs/en/managed-agents/session-threads)'s own `usage` carries `list_cost` and `active_seconds` too. Per-thread figures are rounded independently and exclude the session's running-time cost, so they don't sum exactly to the session's `list_cost`. The session figure is the authoritative one.

82Each [session thread](https://platform.claude.com/docs/en/managed-agents/session-threads)'s own `usage` (csharp, go: `Usage`) carries `list_cost` (java, php: `listCost`; csharp, go: `ListCost`) and `active_seconds` (java, php: `activeSeconds`; csharp, go: `ActiveSeconds`) too. Per-thread figures are rounded independently and exclude the session's running-time cost, so they don't sum exactly to the session's `list_cost` (java, php: `listCost`; csharp, go: `ListCost`). The session figure is the authoritative one.

8383 

8484### Read usage from the stream

8585 

managed-agents/session-operations Changed · +1 / -1 lines

from line 538

538538 

539539## Deleting a session

540540 

541Delete a session to permanently remove its record, events, and associated sandbox. A `running` session cannot be deleted; to delete one, send a [`user.interrupt` event](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#interrupt-the-agent) by itself and wait for the session to become `idle`. If a [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#while-a-run-is-open) is open, deleting might return a 400 error, even when the session is `idle`, or it might succeed. After a delete that succeeds, no `workflow_run` event reports the end of the session's runs. Before you delete, send a `user.message` that [asks the agent to stop its runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs#interrupt-a-session-with-runs-open), or wait until each run has ended. Then delete the session once it's `idle`.

541Deleting a session is permanent. It deletes the session's record, events, and associated sandbox. A `running` session cannot be deleted; to delete one, send a [`user.interrupt` event](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#interrupt-the-agent) by itself and wait for the session to become `idle`. If a [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#while-a-run-is-open) is open, deleting might return a 400 error, even when the session is `idle`, or it might succeed. After a delete that succeeds, no `workflow_run` event reports the end of the session's runs. Before you delete, send a `user.message` that [asks the agent to stop its runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs#interrupt-a-session-with-runs-open), or wait until each run has ended. Then delete the session once it's `idle`.

542542 

543543Memory stores, vaults, skills, environments, and agents are independent resources and are not affected by session deletion. Files you uploaded through the Files API are also unaffected, but files the session itself produced are scoped to it and are permanently deleted along with its filesystem. Download anything you need to keep before deleting the session. An output file written at the end of the last turn can take a few seconds after the session goes idle to appear in the [session's file list](https://platform.claude.com/docs/en/managed-agents/files#listing-and-downloading-session-files), so check that the files you expect are listed first.

544544 

managed-agents/session-threads Changed · +1 / -1 lines

from line 653

653653 

654654If a subagent needs something from your client, such as [permission](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tool-confirmation) to run a tool call or the [result of a custom tool](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#handling-custom-tool-calls), the event is cross-posted to the **primary thread** with `session_thread_id` identifying the originating session thread. A tool call needs your permission under `always_ask`, or under [`auto`](https://platform.claude.com/docs/en/managed-agents/permission-policies#let-the-server-evaluate-each-call-with-auto) when the server reaches no determination.

655655 

656```json

656```text wrap

657657{

658658 "type": "session.thread_status_idle",

659659 "id": "sevt_01ABC...",

managed-agents/skills Changed · +1 / -1 lines

from line 385

385385 

386386## Load skills from a GitHub repository

387387 

388Skills can also live in your code base. When a session mounts a repository through the [`github_repository` resource](https://platform.claude.com/docs/en/managed-agents/github), the repository's root `.claude/skills` directory is scanned at session start, and each skill found there becomes available to the agent. No upload and no entry in the agent's `skills` (csharp, go: `Skills`) array are required. The agent sees each discovered skill's name, description, and path in the sandbox, and reads the skill's `SKILL.md` when a task matches, including any scripts and resources the skill ships. Discovery relies on the agent's `read` tool from the [agent toolset](https://platform.claude.com/docs/en/managed-agents/tools), which is enabled by default; an agent with `read` disabled doesn't load repository skills.

388Skills can also live in your code base. When a session mounts a repository through the [`github_repository` resource](https://platform.claude.com/docs/en/managed-agents/github), the repository's root `.claude/skills` directory is scanned at session start, and each skill found there becomes available to the agent. No upload and no entry in the agent's `skills` (csharp, go: `Skills`) array are required. The agent receives each discovered skill's name, description, and path in the sandbox, and reads the skill's `SKILL.md` when a task matches, including any scripts and resources the skill ships. Discovery relies on the agent's `read` tool from the [agent toolset](https://platform.claude.com/docs/en/managed-agents/tools), which is enabled by default; an agent with `read` disabled doesn't load repository skills.

389389 

390390<Warning>

391391 Repository skills are agent instructions, so a mounted repository is part of your agent's trust boundary. Anyone who can commit to the repository (a merged external pull request, a compromised dependency, a contributor) can add or change a skill, the platform loads it at session start without a review step, and session tools such as `bash` and `web_fetch` give those instructions real reach. Mount only repositories you trust, and review `.claude/skills` before mounting a repository that accepts outside contributions.

managed-agents/tools Changed · +1 / -1 lines

from line 481

481481 

482482A custom tool's name can't start with `mcp__` or `ant__`, or match the name of a built-in agent tool. A request that breaks this rule returns a 400 error. An agent that already has a custom tool whose name starts with `ant__` accepts an update only if the update sends `tools` (csharp, go: `Tools`) without that name, so rename or remove the tool in your next update. A new session is refused with a 400 error if such a tool is on its agent (after any [overrides](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session)), on an agent in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list of `subagents` (csharp, go: `Subagents`), or on an agent in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgents`) list of `workflows` (csharp, go: `Workflows`). Sessions that already exist aren't affected.

483483 

484The agent calls its custom tools during a session. To receive the calls and return results, see [Session event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#handling-custom-tool-calls).

484The agent calls its custom tools during a session. To receive the calls and return results, see [Answer tool calls that pause the session](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#handling-custom-tool-calls).

485485 

486486For sessions that run in a self-hosted sandbox, the environment worker can [serve custom tools from the sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-custom-tools). These can include tools that wrap an MCP server inside your network.

487487 

managed-agents/webhooks Changed · +1 / -1 lines

from line 427

427427 

428428* **Subscription scope:** An event is delivered only to endpoints subscribed to its type at the moment it's emitted. An event emitted while no endpoint is subscribed to its type is never delivered, and subscribing later doesn't backfill it, so subscribe to an event type before you need it.

429429 

430* **Ordering is not guaranteed.** Events aren't delivered in the order they occurred: `session.status_idled` might arrive before `session.outcome_evaluation_ended` even if the outcome was produced first, and a `.deleted` event can arrive before the `.archived` event for the same resource. Drive your state from the resource you fetch, not from the order events arrive in.

430* **Ordering:** Events aren't guaranteed to be delivered in the order they occurred: `session.status_idled` might arrive before `session.outcome_evaluation_ended` even if the outcome was produced first, and a `.deleted` event can arrive before the `.archived` event for the same resource. Drive your state from the resource you fetch, not from the order events arrive in.

431431 

432432* **Retries:** For each endpoint and event, Anthropic makes up to three delivery attempts (a response that triggers auto-disable, described later in this section, is never retried) with jittered exponential backoff between 5 and 120 seconds. Every attempt delivers the same `event.id`. After the last attempt fails, the event is dropped: it isn't queued for later delivery and there's no signal that it was lost. Webhooks aren't a durable log, so if you need to observe every transition, reconcile by listing or fetching the resource through the API.

433433 

models/fable-5-1/migration-guide Changed · +1 / -1 lines

from line 40

4040 

4141## Migrating to Claude Fable 5.1 from Claude Fable 5

4242 

43Migration is mostly drop-in. The API surface, limits, per-token pricing, tokenizer, always-on adaptive thinking, refusal handling, and `stop_details` categories all match Claude Fable 5. What changes: forced tool choice returns a 400 error; only Claude Fable 5.1 and Claude Mythos 5.1 read Claude Fable 5.1's thinking blocks, and only in the conversation that produced them; cache reads cost less; the advisor tool (beta) accepts fewer advisors; and agent-loop behavior differs in three ways. The same changes apply to [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-mythos-5-to-claude-mythos-5-1), except the conversation check on thinking blocks, which Claude Mythos 5.1 doesn't run.

43Migration is mostly drop-in. The API surface, limits, per-token pricing, tokenizer, always-on adaptive thinking, refusal handling, and `stop_details` categories all match Claude Fable 5. What changes: forced tool choice returns a 400 error; only Claude Fable 5.1 and Claude Mythos 5.1 read Claude Fable 5.1's thinking blocks, and only in the conversation that produced them; cache reads cost less; the advisor tool (beta) accepts fewer advisors; and agent-loop behavior differs in three ways. The same changes apply to the [Claude Mythos 5.1 migration](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claude-mythos-5-to-claude-mythos-5-1), except the conversation check on thinking blocks, which Claude Mythos 5.1 doesn't run.

4444 

4545### Update your model name

4646 

models/fable-5-1/overview Changed · +1 / -1 lines

from line 18

1818 

1919Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, and slide work. For most workloads, start with Claude Opus 5.5 (see [Choosing a model](https://platform.claude.com/docs/en/about-claude/models/choosing-a-model)). Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5.5 at higher effort still don't meet your requirements. Claude Mythos 5.1 offers the same capabilities only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

2020 

21If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported), [only Claude Fable 5.1 and Claude Mythos 5.1 can read Claude Fable 5.1's thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them), [editing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks), and [some advisor tool pairings are not supported](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#advisor-tool-pairings). Five are additive: [per-message effort](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta) (beta), [turn-scoped system messages](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta) (beta), [readable progress updates between tool calls](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#progress-updates-between-tool-calls-beta) (`display: "updates"`, beta), a [lower cache read price](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#pricing), and [content provenance](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#content-provenance).

21If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported), only Claude Fable 5.1 and Claude Mythos 5.1 can [read Claude Fable 5.1's thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them), [editing earlier turns invalidates thinking blocks](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks), and [some advisor tool pairings are not supported](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#advisor-tool-pairings). Five are additive: [mid-conversation effort changes](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta) (beta), [turn-scoped system messages](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta) (beta), [readable progress updates between tool calls](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#progress-updates-between-tool-calls-beta) (`display: "updates"`, beta), a [lower cache read price](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#pricing), and [content provenance](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#content-provenance).

2222 

2323[What's new in Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1)

2424 

models/opus-5-5/whats-new-opus-5-5 Changed · +2 / -2 lines

from line 80

8080 

8181* **The default effort is `medium`.** A request that omits `effort` runs at `medium`; on Claude Opus 5 it ran at `high`. Set `effort` explicitly and re-run your sweep; see [Calibrate effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort).

8282* **More thinking per turn at a given effort level.** At the same [effort](https://platform.claude.com/docs/en/build-with-claude/effort) setting the model tends to think more per turn than Claude Opus 5, most of all at `xhigh` and `max`. Re-run your effort sweep rather than carrying a setting over, and leave room in `max_tokens` for the thinking. See [Calibrate effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort).

83* **Text between tool calls comes back in thinking blocks.** The short notes the model writes between tool calls arrive as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) rather than `text` blocks, so at the default `display: "omitted"` an application that streams them to its users goes quiet between tool calls, with no error. The [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls) has the fix for receiving them, and [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates) covers how to ask for more of them.

84* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its internal reasoning in the response text might be declined with the `reasoning_extraction` category. See [Refusals and fallback](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).

83* **Text between tool calls comes back in thinking blocks.** The short notes the model writes between tool calls arrive as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) rather than `text` blocks, so at the default `display: "omitted"` an application that streams them to its users goes quiet between tool calls, with no error. The migration guide explains [how to receive text between tool calls](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls), and [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates) covers how to ask for more of them.

84* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its internal reasoning in the response text might be declined with the `reasoning_extraction` category. See [Refusals and fallback in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).

8585* **Sharper reading of charts, diagrams, and screenshots.** The model reads values off dense charts and layout-dependent visuals much more precisely without tools, so prompt-side vision workarounds built for earlier models might no longer be needed; image tools still add accuracy on the densest inputs. See [Tools for complex visual inputs](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#tools-for-complex-visual-inputs).

8686 

8787If your Claude Opus 5 integration ran with thinking disabled, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled) alongside the breaking change [Thinking can't be disabled](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled). For the capability gains in agentic coding and code review, knowledge work, communication, visual inputs, and computer use, see [Capabilities relevant to prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#capability-improvements).

models/overview Changed · +1 / -1 lines

from line 84

8484Current Claude models excel in:

8585 

8686* **Performance:** Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) for general and model-specific prompting guidance.

87* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide the model toward the desired output length. Refer to the [prompt engineering guides](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering) for details.

87* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide the model toward the output length you want. Refer to the [prompt engineering guides](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering) for details.

8888* **Output quality:** When migrating from a previous model generation, you might notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see the [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide).

8989 

9090## Get started with Claude

release-notes/system-prompts/claude-fable-5 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Fable 5 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-fable-5

4description: See updates to the core system prompt for Claude Fable 5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Fable 5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## June 9, 2026

release-notes/system-prompts/claude-fable-5-1 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Fable 5.1 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-fable-5-1

4description: See updates to the core system prompt for Claude Fable 5.1 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Fable 5.1 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## September 1, 2026

release-notes/system-prompts/claude-haiku-3 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Haiku 3 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-3

4description: See updates to the core system prompt for Claude Haiku 3 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Haiku 3 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## July 12, 2024

release-notes/system-prompts/claude-haiku-3-5 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Haiku 3.5 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-3-5

4description: See updates to the core system prompt for Claude Haiku 3.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Haiku 3.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## October 22, 2024

release-notes/system-prompts/claude-haiku-4-5 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Haiku 4.5 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-4-5

4description: See updates to the core system prompt for Claude Haiku 4.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Haiku 4.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77Changes between the following dated versions are marked with `**` around the changed text.

release-notes/system-prompts/claude-haiku-5-5 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Haiku 5.5 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-haiku-5-5

4description: See updates to the core system prompt for Claude Haiku 5.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Haiku 5.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## October 7, 2026

release-notes/system-prompts/claude-opus-3 Changed · +1 / -1 lines

from line 1

11---

22title: Claude Opus 3 system prompts

33url: https://platform.claude.com/docs/en/release-notes/system-prompts/claude-opus-3

4description: See updates to the core system prompt for Claude Opus 3 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic.com/android).

4description: See updates to the core system prompt for Claude Opus 3 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthropic.com/android).

55---

66 

77## July 12, 2024