What this read moved
226–239 of 239This capture is too large to show at once. Changes 226-239 of 239 are below, significant first; the rest are on the following screens.
api/skills/retrieve Changed · +4 / -0 lines
from line 21
2121
2222- `"anthropic-workspace-id": optional string`
2323
24 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
25
26 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
27
2428## Returns
2529
2630- `Skill object`
api/skills/versions/create Changed · +4 / -0 lines
from line 21
2121
2222- `"anthropic-workspace-id": optional string`
2323
24 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
25
26 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
27
2428## Body parameters (form-data)
2529
2630- `files: array of string`
api/skills/versions/delete Changed · +4 / -0 lines
from line 27
2727
2828- `"anthropic-workspace-id": optional string`
2929
30 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
31
32 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
33
3034## Returns
3135
3236- `DeletedSkillVersion object`
api/skills/versions/list Changed · +4 / -0 lines
from line 35
3535
3636- `"anthropic-workspace-id": optional string`
3737
38 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
39
40 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
41
3842## Returns
3943
4044- `data: array of SkillVersion`
api/skills/versions/retrieve Changed · +4 / -0 lines
from line 27
2727
2828- `"anthropic-workspace-id": optional string`
2929
30 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
31
32 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
33
3034## Returns
3135
3236- `SkillVersion object`
build-with-claude/claude-platform-on-aws Changed · +1 / -1 lines
from line 27
2727| **Who operates the stack** | Anthropic | AWS | AWS |
2828| **API surface** | Claude API (`/v1/{endpoint}`) | Messages API at `/anthropic/v1/messages` | Bedrock Converse / InvokeModel |
2929| **Feature availability** | Typically same-day as Claude API (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported)) | Per Amazon Bedrock release schedule | Per Amazon Bedrock release schedule |
30| **Agent Skills** | Available (beta) | Not available (requires code execution) | Not available |
30| **Agent Skills** | Available in beta (no beta header needed, same behavior as on the Claude API) | Not available (requires code execution) | Not available |
3131| **Beta features** | Pass through with `anthropic-beta` headers (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported)) | `anthropic-beta` header not supported | `anthropic-beta` header not supported |
3232| **Authentication** | AWS IAM / SigV4 or API key | AWS IAM / SigV4 | AWS IAM / SigV4 or bearer token |
3333| **Billing** | AWS Marketplace | AWS (native service) | AWS (native service) |
build-with-claude/task-budgets Changed · +1 / -1 lines
from line 284
284284}
285285```
286286
287Server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) during a turn does not reset the budget: tokens the turn consumed before the compaction still count against it. Tokens from before the turn began do not count, even when a compaction at the start of a turn summarizes them. Today, that exclusion applies only to the budget carried across a server-side compaction; earlier turns' history still counts while it remains in the context.
287Server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) during a turn does not reset the budget: tokens the turn consumed before the compaction still count against it. Tokens from before the turn began do not count, even when a compaction at the start of a turn summarizes them. Today, that exclusion applies only to the budget carried across a server-side compaction; earlier turns' history still counts while it remains in the context.
288288
289289### Worked example: budget counting across requests
290290
manage-claude/api-and-data-retention Changed · +1 / -1 lines
from line 180
180180| [Code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) | `/v1/messages` (with `code_execution` tool) | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Container data retained up to 30 days. See [Code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#data-retention). |
181181| [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) | `/v1/messages` (with `computer` toolset or tool) | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Client-side tool where screenshots and files are captured and stored in your environment, not by Anthropic. See [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#data-retention). |
182182| [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) | `/v1/messages` (with `context_management`) | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Context edits (tool use clearing and thinking clearing) are applied in real time. |
183| [Context management (compaction)](https://platform.claude.com/docs/en/build-with-claude/compaction) | `/v1/messages` (with `context_management`) | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Server-side compaction results are returned and round-tripped statelessly through the API response. |
183| [Context management (compaction)](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) | `/v1/messages` (with `context_management`) | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Server-side compaction results are returned and round-tripped statelessly through the API response. |
184184| [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) | `/v1/messages` (with `inference_geo`) | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | |
185185| [Effort](https://platform.claude.com/docs/en/build-with-claude/effort) | `/v1/messages` (with `effort`) | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | |
186186| [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) | `/v1/messages` (with `speed: "fast"`) | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Same Messages API endpoint with faster inference. ZDR applies regardless of speed setting. |
manage-claude/compliance-activity-feed Changed · +3 / -0 lines
from line 157
157157| `admin_api_key_actor` | An organization admin used an Admin API key to manage users, invites, workspaces, or API keys. | `admin_api_key_id`, `ip_address`, `user_agent` |
158158| `unauthenticated_user_actor` | An action occurred before sign-in completed, for example `sso_login_initiated`. | `unauthenticated_email_address`, `ip_address`, `user_agent` |
159159| `anthropic_actor` | Anthropic acted on the organization, for example through internal tooling. | `email_address` (always `null`; present for shape consistency with `user_actor`, because Anthropic operators are not represented by individual email) |
160| `system_actor` | Automated background processing performed by Anthropic systems, acting without a user or customer credential. | `service` (nullable; the name of the automated process that performed the action, when known) |
160161| `scim_directory_sync_actor` | An identity provider (such as Okta, Microsoft Entra ID, or JumpCloud) pushed a change through SCIM directory sync. | `workos_event_id`, `directory_id`, `idp_connection_type` (nullable; for example `OktaSCIMV2`, `AzureSCIMV2`) |
162
163A `user_actor` activity does not always mean the user took the action. Processes that Anthropic runs on a user's behalf can currently appear as `user_actor` for the affected user rather than as `system_actor`, and this attribution may change. For example, memory activities from a migration, such as `platform_memory_store_created`, `platform_memory_created`, and `platform_memory_deleted`, are attributed this way. These migration activities currently show an `ip_address` of `0.0.0.0`.
161164
162165A `claude_*_viewed` activity means a Claude app loaded content, not that a person viewed it. Types such as `claude_chat_viewed`, `claude_file_viewed`, and `claude_project_viewed` are recorded each time a Claude app loads the chat, file, or project from Anthropic's servers. Repeated loads are not deduplicated. The web, desktop, and mobile apps load content at different moments, sometimes in the background, and can display a cached copy without loading it. Counts of these activities vary by platform as a result, and they do not correspond to messages sent or screens viewed.
163166
manage-claude/inference-hooks Changed · +1 / -1 lines
from line 29
2929
3030A verdict is a small JSON object: `{"action": "allow"}` lets the request proceed, and a deny carries the user-facing reason. For the full verdict schema, see [Return a verdict](https://platform.claude.com/docs/en/manage-claude/inference-hooks-endpoint#return-a-verdict).
3131
32Your AI security server sees what the user sees: transcript text, tool calls and their results, and text extracted from attachments. It never receives raw file or image bytes, system prompts, or Anthropic-internal context. Anthropic doesn't store prompt or response content as part of Inference hooks; it records only metadata about hook activity, such as verdicts, timestamps, and request identifiers.
32Your AI security server sees what the user sees: transcript text, tool calls and their results, and text extracted from attachments. It never receives raw file or image bytes, system prompts, or Anthropic-internal context.
3333
3434If your AI security server is unreachable, returns an error, or doesn't respond within the timeout, your organization's failure handling setting decides the outcome: block the request, or allow it to proceed without inspection. Sustained failures attributable to your server trip a circuit breaker: Anthropic stops contacting it and applies your failure handling setting to every request, then resets the breaker automatically once it detects that your server is returning verdicts again; see [Circuit breaker](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration#circuit-breaker).
3535
manage-claude/spend-limits-api Changed · +1 / -1 lines
from line 367
367367
368368 See [User management](https://platform.claude.com/docs/en/manage-claude/user-management#groups) for the group endpoints.
369369
3704. When your incident system marks the incident closed, roll both changes back: restore the spend limit you recorded in step 1 (or delete the override with `DELETE /v1/organizations/spend_limits/{spend_limit_id}` if the member had none), and remove the member from the group with `DELETE /v1/organizations/rbac_groups/{group_id}/members/{user_id}`.
3704. When your incident system marks the incident closed, roll both changes back: restore the spend limit you recorded in step 1 (or delete the override with `DELETE /v1/organizations/spend_limits/{spend_limit_id}` if the member had none), and remove the member from the group with `DELETE /v1/organizations/rbac_groups/{rbac_group_id}/members/{user_id}`.
371371
372372## Frequently asked questions
373373
managed-agents/agent-setup Changed · +4 / -0 lines
from line 161
161161 tools: [{type: "agent_toolset_20260401"}]
162162 )
163163 ```
164
165 <ForLanguage tab="CLI">
166 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) creates the agent from `coding-assistant.md`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this agent instead of creating a second one.
167 </ForLanguage>
164168</CodeGroup>
165169
166170The response echoes your configuration and adds `id`, `type`, `version`, `created_at`, `updated_at`, and `archived_at` fields, and fills in `model` fields you omit, such as `effort`, with their defaults. The `version` starts at 1 and increments each time an update changes the agent.
managed-agents/environments Changed · +4 / -0 lines
from line 132
132132
133133 puts "Environment ID: #{environment.id}"
134134 ```
135
136 <ForLanguage tab="CLI">
137 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) creates the environment from `environment.yaml`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this environment instead of trying to create it again.
138 </ForLanguage>
135139</CodeGroup>
136140
137141Use a unique, descriptive `name` so you can tell environments apart.
release-notes/overview Changed · +2 / -2 lines
from line 18
1818
1919### September 14, 2026
2020
21* The Messages API can now [compact a conversation on demand](https://platform.claude.com/docs/en/build-with-claude/compaction#compact-on-demand-with-the-compaction-parameter) on the Claude API, in beta with the `compact-2026-09-04` beta header. Send the top-level `compaction` parameter, and the API returns a signed `compaction` block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid.
21* The Messages API can now [compact a conversation on demand](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) on the Claude API, in beta with the `compact-2026-09-04` beta header. Send the top-level `compaction` parameter, and the API returns a signed `compaction` block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid.
2222
2323### September 10, 2026
2424
from line 369
369369
370370* We've launched [Claude Opus 4.6](https://www.anthropic.com/news/claude-opus-4-6), our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`); manual thinking (`type: "enabled"` with `budget_tokens`) is deprecated. Opus 4.6 does not support prefilling assistant messages. Learn more in [What's new in Claude 4.6](https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-6).
371371* The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) no longer requires a beta header and now supports Claude Opus 4.6. Effort replaces `budget_tokens` for controlling thinking depth on new models.
372* We've launched the [compaction API](https://platform.claude.com/docs/en/build-with-claude/compaction) in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6.
372* We've launched the [compaction API](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6.
373373* We've introduced [data residency controls](https://platform.claude.com/docs/en/manage-claude/data-residency), allowing you to specify where model inference runs with the `inference_geo` parameter. US-only inference is available at 1.1x pricing for models released after February 1, 2026.
374374* The [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) is now available in beta for Claude Opus 4.6, in addition to Sonnet 4.5 and Sonnet 4. [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing) applies to requests exceeding 200k input tokens.
375375* [Fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming) no longer requires a beta header on any model or platform.