Home Docs Claude Developer Platform

One capture · api

One read of Claude Developer Platformapi-20261012T230714Z

86 pages moved out of 760 read.

Pages moved 86 significant first

Pages read 760 in this capture

Captured 12 Oct 2026 23:07 UTC

Corpus hash 8c5aa1a14983 corpus-hash

What this read moved

26-50 of 86, page 2 of 4

This capture is too large to show at once. Changes 26-50 of 86 are below, significant first; the rest are on the following screens.

api/compliance/activities/list Changed · +1515 / -3 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 15

1515

1616## Query parameters

1717

18- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 516 more`

18- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 522 more`

1919

2020 Filter activities by type. See the response `data` schema for the additional fields each type returns. Cannot be combined with `exclude_activity_types[]`.

2121

from line 267

267267

268268 A new version of an artifact was published — for an artifact created in a chat this is the action that made it publicly viewable; for an artifact created outside a chat it is recorded when the artifact is saved, including saves of private artifacts, except that automatic saves made while a person keeps editing may be recorded periodically for that person rather than once per save; changes to who can access the artifact are recorded separately as claude_artifact_sharing_updated.

269269

270 - `"claude_artifact_sent_to_partner"`

271

272 A member sent an export of an artifact to a partner application ("Send to …" on the artifact; a partner is a third-party application listed in Claude's connector directory): a file exported from the artifact was made available over a temporary link for the chosen partner to fetch. One activity is recorded per send, in the artifact owner's organization with the sending member as actor, whether or not the partner then retrieved the file; the partner's own import of the file is not part of this record. The file's name and contents are not recorded.

273

270274 - `"claude_artifact_sharing_updated"`

271275

272276 An artifact's sharing settings were updated.

from line 687

683687

684688 A security scan of a skill completed and produced a verdict.

685689

690 - `"claude_survey_closed"`

691

692 An organization admin closed an in-app survey before its end date, ending the collection of responses; a survey that reaches its end date records no event.

693

694 - `"claude_survey_created"`

695

696 An organization admin launched an in-app survey to its chosen audience, opening it immediately or at a scheduled start time.

697

698 - `"claude_survey_deleted"`

699

700 An organization admin permanently deleted a closed in-app survey together with every response collected for it.

701

702 - `"claude_survey_response_submitted"`

703

704 A member submitted their response to an in-app survey run by their organization; the record omits the response content, and a retried submission can produce more than one record for the same response.

705

706 - `"claude_survey_responses_exported"`

707

708 An organization admin downloaded a survey's responses as a CSV file, one row per response with the member's email address (blank if it is no longer available, for example because they left the organization), the groups, department and cost center they were invited through, the product they answered in, the submission time, and their answers.

709

686710 - `"claude_user_role_updated"`

687711

688712 A user's role within the organization was changed, or the user was added to or removed from the organization.

from line 2174

21502174

21512175 format: date-time

21522176

2153- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 516 more`

2177- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 522 more`

21542178

21552179 Exclude activities of these types. Cannot be combined with `activity_types[]`.

21562180

from line 2426

24022426

24032427 A new version of an artifact was published — for an artifact created in a chat this is the action that made it publicly viewable; for an artifact created outside a chat it is recorded when the artifact is saved, including saves of private artifacts, except that automatic saves made while a person keeps editing may be recorded periodically for that person rather than once per save; changes to who can access the artifact are recorded separately as claude_artifact_sharing_updated.

24042428

2429 - `"claude_artifact_sent_to_partner"`

2430

2431 A member sent an export of an artifact to a partner application ("Send to …" on the artifact; a partner is a third-party application listed in Claude's connector directory): a file exported from the artifact was made available over a temporary link for the chosen partner to fetch. One activity is recorded per send, in the artifact owner's organization with the sending member as actor, whether or not the partner then retrieved the file; the partner's own import of the file is not part of this record. The file's name and contents are not recorded.

2432

24052433 - `"claude_artifact_sharing_updated"`

24062434

24072435 An artifact's sharing settings were updated.

from line 2846

28182846

28192847 A security scan of a skill completed and produced a verdict.

28202848

2849 - `"claude_survey_closed"`

2850

2851 An organization admin closed an in-app survey before its end date, ending the collection of responses; a survey that reaches its end date records no event.

2852

2853 - `"claude_survey_created"`

2854

2855 An organization admin launched an in-app survey to its chosen audience, opening it immediately or at a scheduled start time.

2856

2857 - `"claude_survey_deleted"`

2858

2859 An organization admin permanently deleted a closed in-app survey together with every response collected for it.

2860

2861 - `"claude_survey_response_submitted"`

2862

2863 A member submitted their response to an in-app survey run by their organization; the record omits the response content, and a retried submission can produce more than one record for the same response.

2864

2865 - `"claude_survey_responses_exported"`

2866

2867 An organization admin downloaded a survey's responses as a CSV file, one row per response with the member's email address (blank if it is no longer available, for example because they left the organization), the groups, department and cost center they were invited through, the product they answered in, the submission time, and their answers.

2868

28212869 - `"claude_user_role_updated"`

28222870

28232871 A user's role within the organization was changed, or the user was added to or removed from the organization.

from line 4331

42834331

42844332## Returns

42854333

4286- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 516 more`

4334- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 522 more`

42874335

42884336 List of activity records. Each element's `type` field identifies which activity it is and which additional fields are present.

42894337

from line 9547

94999547

95009548 - `SystemActor object`

95019549

9502 Automated background processing performed by Anthropic systems, acting

9503 without a user or customer credential.

9504

9505 - `type: optional "system_actor"`

9506

9507 default: system_actor

9508

9509 - `service: optional string or null`

9510

9511 Name of the automated process that performed the action, when known.

9512

9513 - `AdminAPIKeyActor object`

9514

9515 - `type: optional "admin_api_key_actor"`

9516

9517 default: admin_api_key_actor

9518

9519 - `admin_api_key_id: string`

9520

9521 - `ip_address: string`

9522

9523 - `user_agent: string`

9524

9525 - `ServiceAccountActor object`

9526

9527 - `type: optional "service_account_actor"`

9528

9529 default: service_account_actor

9530

9531 - `ip_address: string`

9532

9533 - `service_account_id: string`

9534

9535 - `user_agent: string`

9536

9537 - `ScimDirectorySyncActor object`

9538

9539 - `type: optional "scim_directory_sync_actor"`

9540

9541 default: scim_directory_sync_actor

9542

9543 - `directory_id: string`

9544

9545 - `workos_event_id: string`

9546

9547 - `idp_connection_type: optional string or null`

9548

9549 - `FederatedIdentityActor object`

9550

9551 A federated external workload authenticated via a verified OIDC token.

9552

9553 Carries the verified issuer, subject, and audience claims from the

9554 presented JWT.

9555

9556 - `type: optional "federated_identity_actor"`

9557

9558 default: federated_identity_actor

9559

9560 - `issuer: string`

9561

9562 - `subject: string`

9563

9564 - `audience: optional array of string`

9565

9566 - `ip_address: optional string or null`

9567

9568 - `user_agent: optional string or null`

9569

9570 - `FederatedActor object`

9571

9572 An external identity asserted by a trusted provider — a cloud-provider

9573 gateway or a customer-registered federation issuer — acting without an

9574 Anthropic-provisioned account or service account.

9575

9576 - `type: optional "federated_actor"`

9577

9578 default: federated_actor

9579

9580 - `provider: FederatedActorAwsProvider or FederatedActorAzureProvider or FederatedActorGcpProvider or FederatedActorOidcProvider`

9581

9582 - `FederatedActorAwsProvider object`

9583

9584 Asserting party: the AWS account the organization is bound to.

9585

9586 - `type: optional "aws"`

9587

9588 default: aws

9589

9590 - `account_id: string`

9591

9592 - `signed_principal: string`

9593

9594 The AWS-signed ARN of the IAM principal that requested the token.

9595

9596 - `FederatedActorAzureProvider object`

9597

9598 Asserting party: the Azure subscription the organization is bound to.

9599

9600 - `type: optional "azure"`

9601

9602 default: azure

9603

9604 - `subscription_id: string`

9605

9606 - `FederatedActorGcpProvider object`

9607

9608 Asserting party: the GCP project the organization is bound to.

9609

9610 - `type: optional "gcp"`

9611

9612 default: gcp

9613

9614 - `project_number: string`

9615

9616 - `FederatedActorOidcProvider object`

9617

9618 Asserting party: a customer-registered OIDC federation issuer.

9619

9620 - `type: optional "oidc"`

9621

9622 default: oidc

9623

9624 - `issuer: optional string or null`

9625

9626 The federation issuer's URL. Null when the presented credential failed verification.

9627

9628 - `ip_address: optional string or null`

9629

9630 - `subject: optional string or null`

9631

9632 The provider's verified identifier for the caller; its form depends on the provider.

9633

9634 - `user_agent: optional string or null`

9635

9636 - `AttestedDevi

9550 Au

api/messages Changed · +4 / -4 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 4411

44114411 "role": "user"

44124412 }

44134413 ],

4414 "model": "claude-opus-5",

4414 "model": "claude-opus-5-5",

44154415 "stream": false,

44164416 "system": [

44174417 {

from line 4482

44824482 "type": "model_changed"

44834483 }

44844484 },

4485 "model": "claude-opus-5",

4485 "model": "claude-opus-5-5",

44864486 "role": "assistant",

44874487 "stop_details": {

44884488 "category": "cyber",

from line 7480

74807480 "role": "user"

74817481 }

74827482 ],

7483 "model": "claude-opus-5",

7483 "model": "claude-opus-5-5",

74847484 "system": [

74857485 {

74867486 "text": "Today'\''s date is 2024-06-01.",

from line 8575

85758575

85768576 - `text: string`

85778577

8578 The key or chord to ho

8578 The key or chord

api/models Changed · +6 / -6 lines

from line 387

387387{

388388 "data": [

389389 {

390 "id": "claude-opus-5",

390 "id": "claude-opus-5-5",

391391 "capabilities": {

392392 "batch": {

393393 "supported": true

from line 461

461461 }

462462 }

463463 },

464 "created_at": "2026-07-24T00:00:00Z",

464 "created_at": "2026-09-21T00:00:00Z",

465465 "deprecated_at": "2019-12-27T18:11:19.117Z",

466 "display_name": "Claude Opus 5",

466 "display_name": "Claude Opus 5.5",

467467 "lifecycle": "active",

468468 "line": "haiku",

469469 "max_input_tokens": 0,

from line 822

822822

823823```json

824824{

825 "id": "claude-opus-5",

825 "id": "claude-opus-5-5",

826826 "capabilities": {

827827 "batch": {

828828 "supported": true

from line 896

896896 }

897897 }

898898 },

899 "created_at": "2026-07-24T00:00:00Z",

899 "created_at": "2026-09-21T00:00:00Z",

900900 "deprecated_at": "2019-12-27T18:11:19.117Z",

901 "display_name": "Claude Opus 5",

901 "display_name": "Claude Opus 5.5",

902902 "lifecycle": "active",

903903 "line": "haiku",

904904 "max_input_tokens": 0,

api/models/list Changed · +3 / -3 lines

from line 385

385385{

386386 "data": [

387387 {

388 "id": "claude-opus-5",

388 "id": "claude-opus-5-5",

389389 "capabilities": {

390390 "batch": {

391391 "supported": true

from line 459

459459 }

460460 }

461461 },

462 "created_at": "2026-07-24T00:00:00Z",

462 "created_at": "2026-09-21T00:00:00Z",

463463 "deprecated_at": "2019-12-27T18:11:19.117Z",

464 "display_name": "Claude Opus 5",

464 "display_name": "Claude Opus 5.5",

465465 "lifecycle": "active",

466466 "line": "haiku",

467467 "max_input_tokens": 0,

api/models/retrieve Changed · +3 / -3 lines

from line 347

347347

348348```json

349349{

350 "id": "claude-opus-5",

350 "id": "claude-opus-5-5",

351351 "capabilities": {

352352 "batch": {

353353 "supported": true

from line 421

421421 }

422422 }

423423 },

424 "created_at": "2026-07-24T00:00:00Z",

424 "created_at": "2026-09-21T00:00:00Z",

425425 "deprecated_at": "2019-12-27T18:11:19.117Z",

426 "display_name": "Claude Opus 5",

426 "display_name": "Claude Opus 5.5",

427427 "lifecycle": "active",

428428 "line": "haiku",

429429 "max_input_tokens": 0,

build-with-claude/context-editing Changed · +4 / -4 lines

from line 20

2020* **Thinking block clearing** - For managing thinking blocks from earlier turns, with options to preserve recent thinking for context continuity

2121* **Client-side SDK compaction** - An SDK-based alternative for summary-based context management (server-side compaction is generally preferred)

2222

24| --------------- | ------------- | ----------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

25| **Server-side** | API | Tool result clearing (`clear_tool_uses_20250919`) Thinking block clearing (`clear_thinking_20251015`) | Applied before the prompt reaches Claude. Clears specific content from conversation history. Each strategy can be configured independently. |

26| **Client-side** | SDK | Compaction | Available in [TypeScript and Ruby SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) when using [`tool_runner`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner). Generates a summary and replaces full conversation history. See [Client-side compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk). |

24| --------------- | ------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

25| **Server-side** | API | Tool result clearing (`clear_tool_uses_20250919`) Thinking block clearing (`clear_thinking_20251015`) | Applied before the prompt reaches Claude. Clears specific content from conversation history. Each strategy can be configured independently. |

2727

2828## Server-side strategies

2929

build-with-claude/mid-conversation-effort-example Changed · +4 / -4 lines

from line 1231

12311231 if (DOC_TEST_MODE) {

12321232 $workDir = sys_get_temp_dir() . '/orchestration-' . bin2hex(random_bytes(8));

12331233 if (!mkdir($workDir, 0700)) {

1234 throw new RuntimeException("could not create working directory {$workDir}");

1234 throw new \RuntimeException("could not create working directory {$workDir}");

12351235 }

12361236 file_put_contents(

12371237 $workDir . '/sample.py',

from line 1776

17761776 */

17771777 function drainMessageStream(iterable $events): array

17781778 {

1779 $stringValue = fn ($value) => $value instanceof BackedEnum ? $value->value : $value;

1779 $stringValue = fn ($value) => $value instanceof \BackedEnum ? $value->value : $value;

17801780 $blocks = [];

17811781 $jsonBuffers = [];

17821782 $stopReason = null;

from line 2701

27012701 if (is_string($raw)) {

27022702 try {

27032703 $raw = json_decode($raw, true, flags: JSON_THROW_ON_ERROR);

2704 } catch (JsonException) {

2704 } catch (\JsonException) {

27052705 $raw = str_contains($raw, "\n") ? explode("\n", $raw) : [$raw];

27062706 }

27072707 }

from line 2746

27462746 $runOne = function (string $prompt) use ($client, $model): string {

27472747 try {

27482748 return journaled($prompt, fn () => runSubagent($client, $model, $prompt));

2749 } catch (Throwable $error) {

2749 } catch (\Throwable $error) {

27502750 // Isolation boundary: one bad subagent should not end the run.

27512751 return '(subagent failed: ' . $error::class . ': ' . $error->getMessage() . ')';

27522752 }

build-with-claude/overview Changed · +5 / -5 lines

from line 20

2020

2121The Availability column in each of the following tables lists the platforms that offer a feature. A platform listed without a label offers the feature as stable, fully supported, and recommended for production use, with no beta header and with standard API [versioning](https://platform.claude.com/docs/en/api/versioning) guarantees. A label after a platform name marks one of the following classifications on that platform. Not all features pass through every stage, and a feature may enter at any stage or skip stages.

2222

23| Classification | Description |

24| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

25| **Beta** | Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced. Features may change significantly or be discontinued based on feedback. Not guaranteed for ongoing production use. Breaking changes are possible with notice, and some platform-specific limitations may apply. Most beta features on the Claude API and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) have a [beta header](https://platform.claude.com/docs/en/api/beta-headers). |

26| **Deprecated** | Feature is still functional but no longer recommended. A migration path and removal timeline are provided. |

27| **Retired** | Feature is no longer available. |

23| Classification | Description |

25| **Beta** | Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced. Features may change significantly or be discontinued based on feedback. Not guaranteed for ongoing production use. Breaking changes are possible with notice, and some platform-specific limitations may apply. Most beta features on the Claude API and [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) have a [beta header](https://platform.claude.com/docs/en/api/beta-headers). |

26| **Deprecated** | Feature is still functional but no longer recommended. A migration path and removal timeline are provided. |

27| **Retired** | Feature is no longer available. |

2828

2929**Platform labels:** Claude API (Anthropic first-party) · [Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) (AWS-operated) · [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) (Anthropic-operated on AWS) · [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) (Google-operated) · [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Anthropic-operated on Azure)

3030

build-with-claude/prompt-caching Changed · +5 / -5 lines

from line 479

479479

480480With automatic caching, the cache point moves forward automatically as conversations grow. Each new request caches everything up to the last cacheable block, and previous content is read from cache.

481481

482| Request | Content | Cache behavior |

483| --------- | ---------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |

484| Request 1 | System + User(1) + Asst(1) + **User(2)** ◀ cache | Everything written to cache |

485| Request 2 | System + User(1) + Asst(1) + User(2) + Asst(2) + **User(3)** ◀ cache | System through User(2) read from cache; Asst(2) + User(3) written to cache |

486| Request 3 | System + User(1) + Asst(1) + User(2) + Asst(2) + User(3) + Asst(3) + **User(4)** ◀ cache | System through User(3) read from cache; Asst(3) + User(4) written to cache |

482| Request | Content | Cache behavior |

483| --------- | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------- |

484| Request 1 | System + User(1) + Asst(1) + **User(2)** ◀ cache | Everything written to cache |

485| Request 2 | System + User(1) + Asst(1) + User(2) + Asst(2) + **User(3)** ◀ cache | System through User(2) read from cache; Asst(2) + User(3) written to cache |

486| Request 3 | System + User(1) + Asst(1) + User(2) + Asst(2) + User(3) + Asst(3) + **User(4)** ◀ cache | System through User(3) read from cache; Asst(3) + User(4) written to cache |

487487

488488The cache breakpoint automatically moves to the last cacheable block in each request, so you don't need to update any `cache_control` markers as the conversation grows.

489489

cli-sdks-libraries/sdks/php Changed · +4 / -2 lines

from line 72

7272Streaming requires an HTTP client that returns the response body incrementally. When Guzzle is the discovered PSR-18 client, the SDK configures it for streaming automatically. With a buffering client, the `foreach` loop yields every event at once when the response completes instead of incrementally; if you observe that symptom, install Guzzle or supply a streaming-capable PSR-18 client through the `streamingTransporter` request option:

7373

7474```php

75$client = new Anthropic\Client(

76 requestOptions: Anthropic\RequestOptions::with(streamingTransporter: $myStreamingClient),

75$client = new \Anthropic\Client(

76 requestOptions: \Anthropic\RequestOptions::with(streamingTransporter: $myStreamingClient),

7777);

7878```

7979

from line 160

160160 echo $item->id, PHP_EOL;

161161}

162162// make additional network requests to fetch items from all pages, including and after the current page

163// ...

163164foreach ($page->pagingEachItem() as $item) {

164165 echo $item->id, PHP_EOL;

166// ...

165167}

166168```

167169

manage-claude/api-and-data-retention Changed · +37 / -37 lines

from line 165

165165* **Yes (qualified):** Your prompts and Claude's outputs are not stored, but a bounded technical artifact (named in the Details column) is retained briefly for the feature to function. See [How Anthropic approaches data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#how-anthropic-approaches-data-retention) for the commitments that govern these features.

166166* **No:** The feature is not eligible. Under HIPAA readiness, the API blocks requests that include a "No" feature and returns a `400` error, unless the feature's Details column says otherwise. Under ZDR, the API does **not** block these features; using one is a choice to step outside your ZDR arrangement for that specific data, and the feature's own documented retention policy applies. Features marked "No" for ZDR are typically stateful (they store jobs, files, or container state), which is why they cannot be zero-retention.

167167

169| -------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------- | ----------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

172| [Advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool) | `/v1/messages` with `advisor` tool | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Advisor model output is returned in the API response; nothing is stored server-side after the response. |

173| [Agent skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | `/v1/skills` `/v1/messages` with `skills` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Skill data retained per standard policy. See [Agent skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview#data-retention). |

175| [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) | `/v1/messages/batches` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | 29-day retention; async storage required. See [Batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing#data-retention). |

176| [Browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | `/v1/messages` with `browser` toolset | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Client-side tool. Anthropic does not run browser actions or retain page content beyond standard API handling. Not covered under HIPAA readiness; requests that include the browser use tool are not blocked. See [Browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#data-retention). |

177| [Cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) | `/v1/messages` with `diagnostics` | <Eligible status="qualified">Yes (qualified)</Eligible> | <Eligible status="no">No</Eligible> | Your prompts and Claude's outputs are not stored. A fingerprint of cryptographic hashes and token-count estimates is retained briefly to enable comparison against the next request. See [Cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics#data-retention). |

179| [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) | `/v1/agents` `/v1/sessions` `/v1/environments` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes). |

180| [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). |

181| [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). |

182| [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-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. |

186| [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. |

187| [Files API](https://platform.claude.com/docs/en/build-with-claude/files) | `/v1/files` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Files retained until explicitly deleted or they reach their configured expiration. See [Files API](https://platform.claude.com/docs/en/build-with-claude/files#data-retention). |

189| [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector) | `/v1/messages` with `mcp_servers` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Data retained per standard policy. See [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector#data-retention). |

190| [MCP tunnels](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview) | `/v1/tunnels` | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Research preview. See [MCP tunnels security](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/security) for the data-flow boundary and subprocessor details. |

193| [Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) | `/v1/messages` with `role: "system"` messages | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Request-shape capability of the Messages API; mid-conversation system messages flow through the standard inference path and nothing is stored server-side after the response. |

195| [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) | `/v1/messages` with `code_execution` tool | <Eligible status="no">No</Eligible> | <Eligible status="no">No</Eligible> | Built on code execution containers; data retained up to 30 days. See [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling#data-retention). |

196| [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | `/v1/messages` | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Your prompts and Claude's outputs are not stored. KV cache representations and cryptographic hashes are held in memory for the cache TTL and promptly deleted after expiry. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#data-retention). |

198| [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) | `/v1/messages` | <Eligible status="qualified">Yes (qualified)</Eligible> | <Eligible>Yes</Eligible> | Your prompts and Claude's outputs are not stored. Only the JSON schema is cached, for up to 24 hours since last use. This also covers [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) (`strict: true` on tools), which uses the same grammar pipeline. PHI must not be included in JSON schema definitions; see [PHI handling guidelines](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#phi-handling-guidelines). See [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#data-retention). |

202| [Tool search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) | `/v1/messages` with `tool_search` tool | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Server-side tool executed by Anthropic; the tool definitions in the request are searched in memory per call and nothing is stored after the response. |

203| [Web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) | `/v1/messages` with `web_fetch` tool | <Eligible>Yes</Eligible> | <Eligible status="no">No</Eligible> | Fetched web content returned in the API response. [Dynamic filtering](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#dynamic-filtering) is not eligible for ZDR or HIPAA. Website publishers may retain request data (such as fetched URLs and request metadata) according to their own policies. |

204| [Web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) | `/v1/messages` with `web_search` tool | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Real-time web search results returned in the API response. [Dynamic filtering](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool#dynamic-filtering) is not eligible for ZDR or HIPAA. |

169| -------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | ------------------------------------------------------- | ----------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |