Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One capture · api

One read of Claude Developer Platform

45 pages moved out of 628 read.

api-20260914T173733Z

Pages moved 45 significant first
Pages read 628 in this capture
Captured 17:37 UTC
Corpus hash c571ba619481 corpus-hash

What this read moved

26–45 of 45

This capture is too large to show at once. Changes 26-45 of 45 are below, significant first; the rest are on the following screens.

api/beta/organization/spend_limits/retrieve Changed · +1 / -1 lines

from line 55
5555 
5656 - `"weekly"`
5757 
58 - `scope: object or object or object or 2 more`
58 - `scope: User or SeatTier or RBACGroup or 2 more`
5959 
6060 What the limit applies to. A tagged union on `type`; each variant carries the identifier for its scope.
6161 

api/beta/organization/usage_report Changed · +2 / -2 lines

from line 437
437437 
438438 List of Claude Code usage records for the requested date.
439439 
440 - `actor: object or object`
440 - `actor: UserActor or APIActor`
441441 
442442 The user or API key that performed the Claude Code actions.
443443 
from line 681
681681 
682682 List of Claude Code usage records for the requested date.
683683 
684 - `actor: object or object`
684 - `actor: UserActor or APIActor`
685685 
686686 The user or API key that performed the Claude Code actions.
687687 

api/beta/organization/usage_report/retrieve_claude_code Changed · +1 / -1 lines

from line 36
3636 
3737 List of Claude Code usage records for the requested date.
3838 
39 - `actor: object or object`
39 - `actor: UserActor or APIActor`
4040 
4141 The user or API key that performed the Claude Code actions.
4242 

api/compliance/apps/chats Changed · +1 / -1 lines

from line 548
548548 
549549 Artifact version ID e.g. 'claude_artifact_version_abc123'
550550 
551 - `content: array of object or object or object`
551 - `content: array of Text or ToolUse or ToolResult`
552552 
553553 Content blocks within the message
554554 

api/compliance/apps/chats/messages Changed · +2 / -2 lines

from line 151
151151 
152152 Artifact version ID e.g. 'claude_artifact_version_abc123'
153153 
154 - `content: array of object or object or object`
154 - `content: array of Text or ToolUse or ToolResult`
155155 
156156 Content blocks within the message
157157 
from line 515
515515 
516516 Artifact version ID e.g. 'claude_artifact_version_abc123'
517517 
518 - `content: array of object or object or object`
518 - `content: array of Text or ToolUse or ToolResult`
519519 
520520 Content blocks within the message
521521 

api/compliance/apps/chats/messages/list Changed · +1 / -1 lines

from line 149
149149 
150150 Artifact version ID e.g. 'claude_artifact_version_abc123'
151151 
152 - `content: array of object or object or object`
152 - `content: array of Text or ToolUse or ToolResult`
153153 
154154 Content blocks within the message
155155 

api/compliance/apps/projects Changed · +2 / -2 lines

from line 586
586586 
587587#### Returns
588588 
589- `data: array of object or object`
589- `data: array of ComplianceProjectFileReference or ComplianceProjectDocReference`
590590 
591591 List of attachments sorted chronologically by created_at, tie break by id
592592 
from line 740
740740 
741741#### Returns
742742 
743- `data: array of object or object or object or object`
743- `data: array of ComplianceProjectUserCollaborator or ComplianceProjectGroupCollaborator or ComplianceProjectOrganizationCollaborator or ComplianceProjectOrganizationRoleCollaborator`
744744 
745745 List of collaborators sorted chronologically by granted_at, tie break by the underlying role-assignment UUID
746746 

api/compliance/apps/projects/attachments Changed · +2 / -2 lines

from line 50
5050 
5151### Returns
5252 
53- `data: array of object or object`
53- `data: array of ComplianceProjectFileReference or ComplianceProjectDocReference`
5454 
5555 List of attachments sorted chronologically by created_at, tie break by id
5656 
from line 165
165165 
166166### Attachment List Response
167167 
168- `AttachmentListResponse = object or object`
168- `AttachmentListResponse = ComplianceProjectFileReference or ComplianceProjectDocReference`
169169 
170170 - `ComplianceProjectFileReference object`
171171 

api/compliance/apps/projects/attachments/list Changed · +1 / -1 lines

from line 48
4848 
4949## Returns
5050 
51- `data: array of object or object`
51- `data: array of ComplianceProjectFileReference or ComplianceProjectDocReference`
5252 
5353 List of attachments sorted chronologically by created_at, tie break by id
5454 

api/compliance/apps/projects/collaborators Changed · +2 / -2 lines

from line 46
4646 
4747### Returns
4848 
49- `data: array of object or object or object or object`
49- `data: array of ComplianceProjectUserCollaborator or ComplianceProjectGroupCollaborator or ComplianceProjectOrganizationCollaborator or ComplianceProjectOrganizationRoleCollaborator`
5050 
5151 List of collaborators sorted chronologically by granted_at, tie break by the underlying role-assignment UUID
5252 
from line 214
214214 
215215### Collaborator List Response
216216 
217- `CollaboratorListResponse = object or object or object or object`
217- `CollaboratorListResponse = ComplianceProjectUserCollaborator or ComplianceProjectGroupCollaborator or ComplianceProjectOrganizationCollaborator or ComplianceProjectOrganizationRoleCollaborator`
218218 
219219 - `ComplianceProjectUserCollaborator object`
220220 

api/compliance/apps/projects/collaborators/list Changed · +1 / -1 lines

from line 44
4444 
4545## Returns
4646 
47- `data: array of object or object or object or object`
47- `data: array of ComplianceProjectUserCollaborator or ComplianceProjectGroupCollaborator or ComplianceProjectOrganizationCollaborator or ComplianceProjectOrganizationRoleCollaborator`
4848 
4949 List of collaborators sorted chronologically by granted_at, tie break by the underlying role-assignment UUID
5050 

api/compliance/apps/sessions/local Changed · +2 / -2 lines

from line 443
443443 
444444 Message identifier, prefixed `clsm_`. Stable for as long as the message's turn is retained: identifiers of retained turns do not change as older turns age out of the organization's retention period. The `retention_elapsed` placeholder's identifier is distinct from every retained turn's and changes only when further turns age out.
445445 
446 - `content: array of object or object or object`
446 - `content: array of Text or ToolUse or ToolResult`
447447 
448448 Content blocks within the message, discriminated on `type` (`text` / `tool_use` / `tool_result`: the same discriminator values as the claude.ai chat-messages endpoint; the tool variants omit `integration_name` and `mcp_server_url`, and `text` carries `truncated`). Extended-thinking content is never included. The request's `system` field is never included; a presence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the message stream as a user-role context block and are included. Empty when `provenance.type` is `content_unavailable`.
449449 
from line 539
539539 
540540 The model that served this assistant turn, as reported in the `model` field of the underlying Messages API response. Null on user messages and on any assistant message whose `provenance` is set: client-asserted history and synthetic markers were not produced by a model during this session, and for unavailable content the serving model is not known.
541541 
542 - `provenance: object or object or object or null`
542 - `provenance: ContentUnavailable or ClientAsserted or SyntheticMarker or null`
543543 
544544 Where this turn's content came from, discriminated on `type`. Null (the common case) means verified content: on an assistant message, content Claude produced during this session; on a user message, content the user sent. `content_unavailable`: the turn's content cannot be returned and `content` is empty; `reason` says why. `client_asserted`: assistant content the client supplied as conversation history; `content` shows what the model received but its authorship is not verified; never on user-role messages. `synthetic_marker`: a transcript marker the endpoint generated rather than content either party sent during the session. Both `client_asserted` and `synthetic_marker` can result from normal request or client processing, not only client modification. Callers should tolerate unrecognized `type` values.
545545 

api/compliance/apps/sessions/local/messages/list Changed · +2 / -2 lines

from line 79
7979 
8080 Message identifier, prefixed `clsm_`. Stable for as long as the message's turn is retained: identifiers of retained turns do not change as older turns age out of the organization's retention period. The `retention_elapsed` placeholder's identifier is distinct from every retained turn's and changes only when further turns age out.
8181 
82 - `content: array of object or object or object`
82 - `content: array of Text or ToolUse or ToolResult`
8383 
8484 Content blocks within the message, discriminated on `type` (`text` / `tool_use` / `tool_result`: the same discriminator values as the claude.ai chat-messages endpoint; the tool variants omit `integration_name` and `mcp_server_url`, and `text` carries `truncated`). Extended-thinking content is never included. The request's `system` field is never included; a presence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the message stream as a user-role context block and are included. Empty when `provenance.type` is `content_unavailable`.
8585 
from line 175
175175 
176176 The model that served this assistant turn, as reported in the `model` field of the underlying Messages API response. Null on user messages and on any assistant message whose `provenance` is set: client-asserted history and synthetic markers were not produced by a model during this session, and for unavailable content the serving model is not known.
177177 
178 - `provenance: object or object or object or null`
178 - `provenance: ContentUnavailable or ClientAsserted or SyntheticMarker or null`
179179 
180180 Where this turn's content came from, discriminated on `type`. Null (the common case) means verified content: on an assistant message, content Claude produced during this session; on a user message, content the user sent. `content_unavailable`: the turn's content cannot be returned and `content` is empty; `reason` says why. `client_asserted`: assistant content the client supplied as conversation history; `content` shows what the model received but its authorship is not verified; never on user-role messages. `synthetic_marker`: a transcript marker the endpoint generated rather than content either party sent during the session. Both `client_asserted` and `synthetic_marker` can result from normal request or client processing, not only client modification. Callers should tolerate unrecognized `type` values.
181181 

api/compliance/apps/sessions/remote Changed · +1 / -1 lines

from line 344
344344 
345345 Unique identifier for the message, e.g. `csev_abc123`
346346 
347 - `content: array of object or object or object`
347 - `content: array of Text or ToolUse or ToolResult`
348348 
349349 Content blocks within the message
350350 

api/compliance/apps/sessions/remote/messages Changed · +2 / -2 lines

from line 90
9090 
9191 Unique identifier for the message, e.g. `csev_abc123`
9292 
93 - `content: array of object or object or object`
93 - `content: array of Text or ToolUse or ToolResult`
9494 
9595 Content blocks within the message
9696 
from line 332
332332 
333333 Unique identifier for the message, e.g. `csev_abc123`
334334 
335 - `content: array of object or object or object`
335 - `content: array of Text or ToolUse or ToolResult`
336336 
337337 Content blocks within the message
338338 

api/compliance/apps/sessions/remote/messages/list Changed · +1 / -1 lines

from line 88
8888 
8989 Unique identifier for the message, e.g. `csev_abc123`
9090 
91 - `content: array of object or object or object`
91 - `content: array of Text or ToolUse or ToolResult`
9292 
9393 Content blocks within the message
9494 

api/compliance/organizations Changed · +2 / -2 lines

from line 561
561561 
562562- `organization_id: string`
563563 
564- `settings: array of object or object or object or 3 more`
564- `settings: array of Boolean or Integer or String or 3 more`
565565 
566566 - `Boolean object`
567567 
from line 780
780780 
781781 default: data_retention
782782 
783 - `value: map[object or object]`
783 - `value: map[Fixed or Indefinite]`
784784 
785785 - `Fixed object`
786786 

api/compliance/organizations/settings/retrieve Changed · +2 / -2 lines

from line 82
8282 
8383- `organization_id: string`
8484 
85- `settings: array of object or object or object or 3 more`
85- `settings: array of Boolean or Integer or String or 3 more`
8686 
8787 - `Boolean object`
8888 
from line 301
301301 
302302 default: data_retention
303303 
304 - `value: map[object or object]`
304 - `value: map[Fixed or Indefinite]`
305305 
306306 - `Fixed object`
307307 

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

from line 357
357357 
358358For thinking content, a special `signature_delta` event is sent just before the `content_block_stop` event. This signature is used to verify the integrity of the thinking block.
359359 
360When `display: "omitted"` is set on the thinking configuration, no `thinking_delta` events are sent. The thinking block opens, receives a single `signature_delta`, and closes. With `display: "updates"` (beta), reasoning blocks stream the same way, and only the [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) that some models write between tool calls stream `thinking_delta` events. See [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
360When `display: "omitted"` is set on the thinking configuration, no thinking text is streamed. The thinking block opens, receives a `thinking_delta` with an empty `thinking` string and then a single `signature_delta`, and closes. With `display: "updates"` (beta), reasoning blocks stream the same way, and only the [progress updates](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) that some models write between tool calls stream `thinking_delta` events that carry text. See [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
361361 
362362A typical thinking delta looks like:
363363 

manage-claude/inference-hooks Changed · +1 / -1 lines

from line 31
3131 
3232Your 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.
3333 
34If 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.
34If 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 
3636Enforcement can roll out at your pace, so nobody has to be blocked on day one: shadow mode observes verdicts on live traffic without blocking anything, a rollout percentage inspects a chosen fraction of requests, and exclusions exempt members of chosen roles entirely. See [Configure Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration).
3737