One read of Claude Developer Platformapi-20261022T020713Z

This capture is too large to show at once. Changes 101-125 of 168 are below, significant first; the rest are on the following screens.

build-with-claude/overview Changed · +1 / -1 lines

from line 85

8585| [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | Extend Claude's capabilities with Skills. Use pre-built Skills (PowerPoint, Excel, Word, PDF) or create custom Skills with instructions and scripts. Skills use progressive disclosure to efficiently manage context. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws azureAi />†‡ |

8686| [Fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) | Stream tool use parameters without buffering/JSON validation, reducing latency for receiving large parameters. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

8787| [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) | Connect to remote [MCP](https://modelcontextprotocol.io/) servers directly from the Messages API without a separate MCP client. | Not ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta azureAiBeta /> |

88| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | Enable Claude to call your tools programmatically from within code execution containers, reducing latency and token consumption for multi-tool workflows. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws azureAi />† |

88| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | Allow Claude to call your tools programmatically from within code execution containers, reducing latency and token consumption for multi-tool workflows. | Not ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws azureAi />† |

8989| [Tool search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) | Scale to thousands of tools by dynamically discovering and loading tools on demand using regex- and BM25-based search, optimizing context usage and improving tool selection accuracy. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

9090 

9191## Context management

build-with-claude/pdf-support Changed · +2 / -2 lines

from line 349

349349 

350350The response returns Claude's analysis as text blocks in `content`, with token consumption in `usage`:

351351 

352```json Output

352```text Output

353353{

354354 "id": "msg_01Hfp8YuFjQ55VgWbpdHDehB",

355355 "type": "message",

from line 1012

10121012 * The text from each page is extracted and provided alongside each page's image.

10131013 </Step>

10141014 

1015 <Step title="Claude analyzes both the text and images to better understand the document.">

1015 <Step title="Claude analyzes both the text and images.">

10161016 * Documents are provided as a combination of text and images for analysis.

10171017 * This allows users to ask for insights on visual elements of a PDF, such as charts, diagrams, and other non-textual content.

10181018 </Step>

build-with-claude/prompt-engineering/claude-prompting-best-practices Changed · +2 / -2 lines

from line 485

485485</do_not_act_before_instructions>

486486```

487487 

488Claude Opus 4.5 and Claude Opus 4.6 are also more responsive to the system prompt than previous models. If your prompts were designed to reduce undertriggering on tools or skills, these models might now overtrigger. The fix is to soften any aggressive language. Where you might have said "CRITICAL: You MUST use this tool when...", you can use more normal prompting such as "Use this tool when...".

488Claude Opus 4.5 and Claude Opus 4.6 are also more responsive to the system prompt than previous models. If your prompts were designed to reduce undertriggering on tools or skills, these models might now overtrigger. The fix is to soften any aggressive language. Where you might have said "CRITICAL: You MUST use this tool when...," you can use more normal prompting such as "Use this tool when..." instead.

489489 

490490### Optimize parallel tool calling

491491 

from line 822

822822 

8238233. **Set up convenience tools:** Encourage Claude to create setup scripts (for example, `init.sh`) to gracefully start servers and run test suites and linters. This prevents repeated work when continuing from a fresh context window.

824824 

8254. **Starting fresh versus compacting:** When a context window is cleared, consider starting with a brand new context window rather than using compaction. Claude's latest models are extremely effective at discovering state from the local filesystem. In some cases, you might want to take advantage of this over compaction. Be prescriptive about how it should start:

8254. **Choose between starting fresh and compacting:** When a context window is cleared, consider starting with a brand new context window rather than using compaction. Claude's latest models are extremely effective at discovering state from the local filesystem. In some cases, you might want to take advantage of this over compaction. Be prescriptive about how it should start:

826826 

827827 * "Call pwd; you can only read and write files in this directory."

828828 * "Review progress.txt, tests.json, and the git logs."

build-with-claude/prompt-engineering/prompting-claude-fable-5 Changed · +1 / -1 lines

from line 171

171171 

172172* **Start at the top of your difficulty range.** Pick a task harder than what you'd assign to prior models, and have Claude Fable 5 scope it, ask clarifying questions, and carry it out.

173173* **Make self-verification explicit in long-run prompts.** Separate, fresh-context verifier subagents tend to outperform self-critique. For long-running tasks, instruct: `Establish a method for checking your own work at an interval of [X] as you build. Run this every [X interval], verifying your work with subagents against the specification.`

174* **Refactor existing prompts and skills.** Skills developed for prior models are often too prescriptive for Claude Fable 5 and can degrade output quality. Review and consider removing older instructions if default performance is better. Claude Fable 5 also does a good job of updating skills on the fly based on what it learns from the task at hand.

174* **Refactor existing prompts and skills.** Skills developed for prior models are often too prescriptive for Claude Fable 5 and can degrade output quality. Review and consider removing older instructions if default performance is better. Claude Fable 5 also does a good job of updating skills as it works, based on what it learns from the current task.

175175* **Don't instruct Claude to reproduce its reasoning in the response.** Prompts, skills, or harness instructions that tell the model to echo, transcribe, or explain its internal reasoning as response text might trigger the [`reasoning_extraction` refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) on Claude Fable 5. Server-side fallback with `fallbacks: "default"` doesn't retry requests declined with `reasoning_extraction`; that refusal is returned to you. Audit existing skills and system prompts for reflection or show-your-thinking instructions when migrating. If your application needs reasoning visibility, read the structured `thinking` blocks from [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) instead, and use a [send-to-user tool](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5#create-a-send-to-user-tool) to surface progress during long runs. You can still ask for a short explanation of the answer or a summary of the actions taken; see [Keep reasoning in thinking blocks](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#keep-reasoning-in-thinking-blocks).

176176* **Create a send-to-user tool.** For long, asynchronous agents, a client-side tool delivers messages to the user verbatim without ending the turn. See [Create a send-to-user tool](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5#create-a-send-to-user-tool).

177177 

build-with-claude/prompt-engineering/prompting-claude-opus-5 Changed · +1 / -1 lines

from line 14

1414 

1515* **Agentic coding:** Claude Opus 5 is strongest on difficult coding tasks: multifile features, larger refactors, and end-to-end feature work. It completes full tasks rather than leaving stubs or placeholders, and it performs best when given the complete task specification up front and left to run. It also performs well on easier tasks such as single-turn edits, where the difference from prior models is smaller.

1616* **Code review and bug-finding:** Claude Opus 5 reviews code with high precision and recall: it finds real bugs at a high rate per pass, and its additional findings are mostly real issues rather than false positives. Accuracy holds at lower effort settings, which supports a fast pass at review time and a more thorough pass later. If your review prompt says "only report high-severity issues" or "be conservative," the model might follow that instruction literally and report less; ask it to report everything and filter in a separate pass instead.

17* **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens and latency of higher settings. Start with the default (`high`) and adjust based on your evals: use `low` and `medium` liberally as your primary control for token cost and response time wherever quality holds, and step up to `xhigh` for demanding coding and agentic work. If you carried effort defaults over from a prior model, re-run an effort sweep on your own evals. See [Effort](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-opus-5) for the full recommendations.

17* **Efficiency at lower effort:** `low` and `medium` [effort](https://platform.claude.com/docs/en/build-with-claude/effort) produce strong quality at a fraction of the tokens and latency of higher settings. Start with the default (`high`) and adjust based on your evals: use `low` and `medium` liberally as your primary control for token cost and response time wherever quality holds, and step up to `xhigh` for demanding coding and agentic work. If you carried effort defaults over from a prior model, re-run an effort sweep on your own evals. See [recommended effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-opus-5) for the full guidance.

1818* **Vision:** Claude Opus 5 is strong on chart, document, and diagram understanding, and on UI and frontend visual replication. Re-validate any prompt-side vision workarounds you tuned for prior models; they might no longer be needed. Vision performance is strongest when the model has tools to iteratively analyze, crop, and visually verify its work, and tool use is a more cost-effective lever than thinking alone.

1919* **Long-context work:** Claude Opus 5 has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) as both the default and the maximum, and its instruction following, tool calling, and reasoning stay consistent throughout the window.

2020* **Office and document tasks:** Claude Opus 5 generates and works with complex, multisheet spreadsheets with non-trivial formulas, and it produces well-structured slide decks. Prompt it with any specific styles or templates it needs to follow.

build-with-claude/prompt-engineering/prompting-claude-opus-5-5 Changed · +2 / -2 lines

from line 78

7878 

7979Claude Opus 5.5 runs safety classifiers, including for biology, cybersecurity, and reasoning extraction.

8080 

81* **Biology:** The biology safeguards are the same as Claude Fable 5.1's and are new if you're coming from Claude Opus 5. Everyday health and educational questions are unaffected. If the biology classifier gets in the way of your organization's life sciences work, apply to the [Life Sciences Verification Program](https://www.anthropic.com/news/life-sciences-verification-program).

82* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not. If the cybersecurity classifier gets in the way of your organization's legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

81* **Biology:** The biology safeguards are the same as Claude Fable 5.1's and are new if you're coming from Claude Opus 5. Everyday health and educational questions are unaffected. If the biology classifier blocks your organization's life sciences work, apply to the [Life Sciences Verification Program](https://www.anthropic.com/news/life-sciences-verification-program).

82* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not. If the cybersecurity classifier blocks your organization's legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

8383* **Reasoning extraction:** Requests that push the model to reproduce its internal reasoning in the response text might be declined with the `reasoning_extraction` category. If your prompts ask the model to write its reasoning in the response, remove those instructions, set `display: "summarized"`, and read the summarized reasoning from the thinking blocks instead; 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). You can still ask for a short explanation of the answer or a summary of the actions taken; see [Keep reasoning in thinking blocks](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#keep-reasoning-in-thinking-blocks).

8484 

8585A classifier decline arrives as a normal response with `stop_reason: "refusal"` and a `stop_details` object naming the category. You can have the request retried automatically on a fallback model, except for `reasoning_extraction` declines, which server-side fallback returns to you instead of retrying; see [Refusals and fallback](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback).

build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 Changed · +2 / -2 lines

from line 110

110110 

111111Next, remove older instructions such as "hold all findings for the final response." If you then want updates at predictable points, for example a line on what the model is about to do before its first tool call and a short recap at the end, say so in the system prompt. The model follows instructions like this. Updates at set points help most in human-in-the-loop work.

112112 

113If long tool-calling turns still go quiet for longer than you want, your harness can prompt an update. Have it count consecutive tool-calling steps that send the user no text or progress update. After several in a row, for example five, append a one-turn reminder after the latest tool results. Send it as a [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) (beta), with text like this:

113If long tool-calling turns still go quiet for longer than you want, your harness can prompt an update. Have it count consecutive tool-calling steps that send the user no text or progress update. After several in a row, for example five, append a one-turn reminder after the latest tool results. Send it as a [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages) (beta), with text such as the following:

114114 

115115```text wrap

116116The user hasn't heard from you in a while — say in a few words what you're doing, then continue.

from line 134

134134 

135135Claude Sonnet 5.5 is trained to resist indirect prompt injection, meaning malicious instructions that arrive through tool results and other content it reads during a task. Sometimes it treats a genuine user message as a possible injection. Suppose a message the user typed mid-task reaches the model as a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) placed directly after a tool result, or inside a `tool_result` block. The model can then tell the user that the tool result contained text posing as a message from them, and ignore the message or ask the user to confirm it.

136136 

137A token countdown that your harness adds after every tool result can cause this. So can letting users send messages while the model is partway through a multistep turn, or having your harness add instructions or context after the tool results on every step. In each case, text arrives right after the tool results. With a countdown or per-step instructions, that can occur on every tool call. An occasional one-turn reminder, like the one in [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates), arrives far less often. If you see this reaction to a reminder of your own, send the reminder less often. To avoid the misread:

137A token countdown that your harness adds after every tool result can cause this. So can letting users send messages while the model is partway through a multistep turn, or having your harness add instructions or context after the tool results on every step. In each case, text arrives right after the tool results. With a countdown or per-step instructions, that can occur on every tool call. An occasional one-turn reminder, such as the one in [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#user-facing-progress-updates), arrives far less often. If you see this reaction to a reminder of your own, send the reminder less often. To avoid the misread:

138138 

139139* Never put user text inside a `tool_result` block. The model misreads that placement most often.

140140* Deliver mid-turn user input as a user turn. Append the user's words as a text block in the user message that carries the `tool_result` blocks, after the last `tool_result`.

build-with-claude/skills-guide Changed · +2 / -2 lines

from line 4522

45224522To migrate:

45234523 

452445241. **Remove the beta header.** Drop `anthropic-beta: skills-2025-10-02` from your requests. With the SDK, call `client.skills` (csharp, go: `client.Skills`; java: `client.skills()`; php: `$client->skills`) instead of `client.beta.skills` (csharp, go: `client.Beta.Skills`; java: `client.beta().skills()`; php: `$client->beta->skills`); keeping `client.beta.skills` (csharp, go: `client.Beta.Skills`; java: `client.beta().skills()`; php: `$client->beta->skills`) works only on the [SDK releases that no longer send the header](https://platform.claude.com/docs/en/build-with-claude/skills-guide#sdk-beta-namespace). Earlier releases send it from `client.beta.skills` (csharp, go: `client.Beta.Skills`; java: `client.beta().skills()`; php: `$client->beta->skills`) even when you pass no beta names.

45252. **Rename fields** in your code: `display_title` to `display_name`, `latest_version` to `latest_version_id`, and read `source.type` instead of comparing `source` to a string.

45252. **Rename fields** in your code: `display_title` to `display_name` and `latest_version` to `latest_version_id`. Read `source.type` instead of comparing `source` to a string.

452645263. **Use version IDs.** Wherever you stored an epoch-microsecond version, store the version's `id` instead, or use `latest`. Skill references in Messages requests accept a version ID, `latest`, or (for Anthropic Skills) the catalog version.

452745274. **Review delete calls.** `DELETE /v1/skills/{skill_id}` now deletes every version with the Skill. If you relied on the beta's refusal as a safeguard, add your own check.

45284528 

45294529<Warning>

4530 After migrating, deleting a Skill through `client.skills` (csharp, go: `client.Skills`; java: `client.skills()`; php: `$client->skills`) or `client.beta.skills` (csharp, go: `client.Beta.Skills`; java: `client.beta().skills()`; php: `$client->beta->skills`) removes the Skill together with all of its versions in one call.

4530 After migrating, deleting a Skill through `client.skills` (csharp, go: `client.Skills`; java: `client.skills()`; php: `$client->skills`) or `client.beta.skills` (csharp, go: `client.Beta.Skills`; java: `client.beta().skills()`; php: `$client->beta->skills`) also deletes all of its versions in one call.

45314531</Warning>

45324532 

45334533A Skill whose versions were all deleted under the beta has no current version to return: `GET /v1/skills/{skill_id}` returns a 400 error and the Skill is omitted from list responses until you upload a version to it. You can still delete it.

cli-sdks-libraries/cli/scripting Changed · +1 / -1 lines

from line 25

2525 --title "Summarization task"

2626 ```

2727 

28 ```json Output

28 ```text Output wrap

2929 {

3030 "id": "session_01JZCh78XvmxJjiXVy3oSi7K",

3131 "status": "running"

cli-sdks-libraries/cli/using Changed · +2 / -2 lines

from line 48

4848ant models retrieve --model-id claude-opus-5-5 --format yaml

4949```

5050 

51```yaml Output

51```text Output wrap

5252type: model

5353id: claude-opus-5-5

5454display_name: Claude Opus 5.5

from line 74

7474ant beta:agents list --transform "{id,name,model}" --format jsonl

7575```

7676 

77```jsonl Output

77```text Output

7878{"id": "agent_011CYm1BLqPX...", "name": "Docs CLI Test Agent", "model": "claude-opus-5-5"}

7979{"id": "agent_011CYkVwfaEt...", "name": "Coffee Making Assistant", "model": "claude-opus-5-5"}

8080{"id": "agent_011CYixHhtUP...", "name": "Coding Assistant", "model": "claude-opus-5-5"}

cli-sdks-libraries/sdks/go Changed · +2 / -2 lines

from line 26

2626 

2727## Requirements

2828 

29This library requires Go 1.24+.

29This library requires Go 1.25+.

3030 

3131## Usage

3232 

from line 716

716716 

717717#### Undocumented request parameters

718718 

719To make requests using undocumented parameters, you can use either the `option.WithQuerySet()` or the `option.WithJSONSet()` functions.

719To make requests using undocumented parameters, you can use either the `option.WithQuerySet()` or the `option.WithJSONSet()` function.

720720 

721721```go

722722params := FooNewParams{

cli-sdks-libraries/sdks/ruby Changed · +1 / -1 lines

from line 80

8080 

8181## Input schema and tool calling

8282 

83The SDK provides helper mechanisms to define structured data classes for tools and let Claude automatically run them. For detailed documentation on tool use patterns including the tool runner, see [Tool Runner (SDK)](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner).

83The SDK provides helper mechanisms to define structured data classes for tools and let Claude automatically run them. For detailed documentation on tool use patterns including the tool runner, see [Tool runner (SDK)](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner).

8484 

8585```ruby

8686anthropic = Anthropic::Client.new

manage-claude/admin-api Changed · +1 / -1 lines

from line 1704

17041704 ```

17051705</CodeGroup>

17061706 

1707```json

1707```text wrap

17081708{

17091709 "id": "12345678-1234-5678-1234-567812345678",

17101710 "type": "organization",

manage-claude/claude-code-analytics-api Changed · +1 / -1 lines

from line 147

147147 

148148The API returns data in the following format:

149149 

150```json

150```text wrap

151151{

152152 "data": [

153153 {

manage-claude/compliance-activity-feed Changed · +1 / -1 lines

from line 23

2323 -H "anthropic-version: 2023-06-01"

2424```

2525 

26```json Response

26```text Response wrap

2727{

2828 "data": [

2929 {

manage-claude/compliance-api Changed · +1 / -1 lines

from line 21

2121 

2222A successful response returns a JSON object containing `data` (an array of `Activity` records), `has_more`, `first_id`, and `last_id`:

2323 

24```json Response

24```text Response wrap

2525{

2626 "data": [

2727 {

manage-claude/compliance-api-access Changed · +1 / -1 lines

from line 129

129129* **Settings UI.** For a Compliance Access Key, open the **Keys** section in [claude.ai > Organization settings > API](https://claude.ai/admin-settings/api-access) and read the **Scopes** column for the key. Admin API keys, listed on the [Admin keys](https://platform.claude.com/settings/admin-keys) page (`platform.claude.com/settings/admin-keys`) in the Claude Console, have no selectable scopes.

130130* **Error responses.** A call that exceeds the key's scopes returns a 403 with a message in the format `Missing required scopes. Got: [<scopes the key carries>] Needed one of: [<scopes the endpoint accepts>]` (`Needed: [...]` on the delete endpoints). See [Handle Compliance API errors](https://platform.claude.com/docs/en/manage-claude/compliance-errors#403-forbidden) for the full error catalog.

131131 

132```json

132```text

133133{

134134 "error": {

135135 "type": "permission_error",

manage-claude/compliance-faq Changed · +1 / -1 lines

from line 43

4343 <Accordion title="Why does my Admin API key return 403 on chat or file endpoints?">

4444 An Admin API key's only Compliance API scope is `read:compliance_activities`, which authorizes the Activity Feed only. Every other Compliance API endpoint requires a scope that only a Compliance Access Key created in claude.ai can carry. Calling a content or directory endpoint with an Admin API key returns a 403 naming the scope that endpoint family requires: `read:compliance_user_data` for chats, files, projects, project attachments, sessions, users, and group members, and `read:compliance_org_data` for organizations, roles, groups, and effective organization settings. For example, listing chats returns the following response.

4545 

46 ```json Response

46 ```text Response

4747 {

4848 "error": {

4949 "type": "permission_error",

manage-claude/organization-webhooks Changed · +2 / -2 lines

from line 85

8585| `updated_at` | string | When the endpoint last changed. Set by Anthropic. |

8686| `signing_secret` | string | A `whsec_`-prefixed secret, created with the endpoint. Only the responses that create the endpoint or replace the secret include it, so store it securely. |

8787 

88```json

88```text wrap

8989{

9090 "id": "wep_011CZkZDf8HnUq2mTxRbVn4s",

9191 "url": "https://example.com/anthropic-webhooks",

from line 232

232232 

233233With no endpoints, the API returns an empty list:

234234 

235```json

235```text wrap

236236{

237237 "data": [],

238238 "has_more": false

manage-claude/rate-limits-api Changed · +1 / -1 lines

from line 493

493493For complete parameter details and response schemas, see the [Workspace Rate Limits API reference](https://platform.claude.com/docs/en/api/organization/workspaces/rate_limits/list).

494494 

495495<Tip>

496 To retrieve your organization's workspace IDs, use the [List Workspaces](https://platform.claude.com/docs/en/api/organization/workspaces/list) endpoint, or find them on the [Workspaces](https://platform.claude.com/settings/workspaces) page in the Claude Console. List Workspaces includes the default workspace only when you pass `include_default=true`.

496 To retrieve your organization's workspace IDs, use the [List Workspaces](https://platform.claude.com/docs/en/api/organization/workspaces/list) endpoint, or find them under [Workspaces in the Claude Console](https://platform.claude.com/settings/workspaces). List Workspaces includes the default workspace only when you pass `include_default=true`.

497497</Tip>

498498 

499499<CodeGroup>

manage-claude/spend-limits-api Changed · +2 / -2 lines

from line 372

372372 ```

373373</CodeGroup>

374374 

375```json

375```text wrap

376376{

377377 "data": [

378378 {

from line 625

625625 ```

626626</CodeGroup>

627627 

628```json

628```text wrap

629629{

630630 "type": "spend_limit",

631631 "id": "spl_01RsTuVwXyZaBcDeFgHiJk",

manage-claude/user-profiles Changed · +2 / -2 lines

from line 181

181181 

182182The response is the new profile:

183183 

184```json

184```text wrap

185185{

186186 "type": "user_profile",

187187 "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9",

from line 403

403403 

404404A profile's `enforcement_status` and `enforcement_actions` fields report the enforcement actions that Anthropic has open on the end customer. An enforcement action is a restriction or a ban. Every response that returns a profile includes both fields: create, retrieve, update, and each profile in a list. Send these requests with no `user-profiles-` value in the `anthropic-beta` header, because `user-profiles-2026-09-04` and earlier values leave the fields out. The following example shows the fields on a retrieved profile, with the other fields left out:

405405 

406```json

406```text wrap

407407{

408408 "type": "user_profile",

409409 "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9",

manage-claude/user-profiles-verification-portal Changed · +1 / -1 lines

from line 127

127127 

128128The response contains the link and the time it stops working:

129129 

130```json

130```text wrap

131131{

132132 "type": "user_profile_action_url",

133133 "url": "https://portal.anthropic.com/enroll?enrollment_token=...",

manage-claude/wif-admin-api Changed · +2 / -2 lines

from line 471

471471 

472472The create endpoint returns the new service account:

473473 

474```json

474```text wrap

475475{

476476 "id": "svac_...",

477477 "name": "inference-worker",

from line 1242

12421242 

12431243The list endpoint returns a page of rules and the cursor for the next page:

12441244 

1245```json

1245```text wrap

12461246{

12471247 "data": [{ "id": "fdrl_...", "name": "gha-deploy", "...": "..." }],

12481248 "next_page": "..."

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

from line 101

101101}

102102```

103103 

104**Federation rule:** Match on both the `sub` and `email` claims. `email` is the readable service-account address; `sub` is the service account's numeric unique ID, which Google never reuses, so pinning it protects the rule if the service account is deleted and a new one is later created with the same email. Find the unique ID with `gcloud iam service-accounts describe SA_EMAIL --format='value(uniqueId)'`.

104**Federation rule:** Match on both the `sub` and `email` claims. `email` is the readable service-account address; `sub` is the service account's numeric unique ID, which Google never reuses, so pinning it protects the rule if the service account is deleted and a new one is later created with the same email. Find the unique ID with `gcloud iam service-accounts describe [email protected] --format='value(uniqueId)'`.

105105 

106106```json

107107{