One read of Claude Developer Platformapi-20260923T183720Z
268 pages moved out of 637 read.
Pages moved
268
significant first
Pages read
637
in this capture
Captured
18:37 UTC
Corpus hash
f552f1fbd6ec
corpus-hash
What this read moved
201-225 of 268, page 9 of 11This capture is too large to show at once. Changes 201-225 of 268 are below, significant first; the rest are on the following screens.
api/beta/vaults/list Changed · +5 / -1 lines
from line 33
3333
3434 - `string`
3535
36 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
36 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
3737
3838 - `"message-batches-2024-09-24"`
3939
from line 126
126126 - `"mid-conversation-system-clear-at-2026-08-21"`
127127
128128 - `"compact-2026-09-04"`
129
130 - `"inline-tools-2026-09-15"`
131
132 - `"mcp-client-2026-09-15"`
129133
130134- `"anthropic-workspace-id": optional string`
131135
api/beta/vaults/retrieve Changed · +5 / -1 lines
from line 23
2323
2424 - `string`
2525
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
2727
2828 - `"message-batches-2024-09-24"`
2929
from line 116
116116 - `"mid-conversation-system-clear-at-2026-08-21"`
117117
118118 - `"compact-2026-09-04"`
119
120 - `"inline-tools-2026-09-15"`
121
122 - `"mcp-client-2026-09-15"`
119123
120124- `"anthropic-workspace-id": optional string`
121125
api/beta/vaults/update Changed · +5 / -1 lines
from line 23
2323
2424 - `string`
2525
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
2727
2828 - `"message-batches-2024-09-24"`
2929
from line 116
116116 - `"mid-conversation-system-clear-at-2026-08-21"`
117117
118118 - `"compact-2026-09-04"`
119
120 - `"inline-tools-2026-09-15"`
121
122 - `"mcp-client-2026-09-15"`
119123
120124- `"anthropic-workspace-id": optional string`
121125
api/claude-code/routines-fire Changed · +20 / -24 lines
from line 5
55---
66
77<Warning>
8 This is an experimental API. Request and response shapes, rate limits, and token semantics might change. Breaking changes ship behind new dated beta header versions, and the two previous header versions continue to work so that callers have time to migrate.
8 This is an experimental API. Request and response shapes, rate limits, and token semantics might change.
99</Warning>
1010
1111[Claude Code](https://code.claude.com/docs) is Anthropic's agentic coding tool. [Claude Code on the web](https://code.claude.com/docs/en/claude-code-on-the-web) runs Claude Code sessions on Anthropic-managed cloud infrastructure at claude.ai/code, and a [routine](https://code.claude.com/docs/en/routines) is a saved configuration there: a prompt, one or more repositories, and connectors, packaged so it can run unattended on a schedule, in response to GitHub events, or when called over HTTP.
from line 25
2525| SDK support | None | Available in all [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) |
2626| Billing | Claude Code subscription usage on claude.ai | Claude Platform usage |
2727| Path namespace | `/v1/claude_code/...` | `/v1/...` |
28| Stability | Experimental; requires `anthropic-beta: experimental-cc-routine-2026-04-01` | Stable or standard beta |
28| Stability | Experimental | Stable or standard beta |
2929
3030## Before you begin
3131
from line 42
4242POST https://api.anthropic.com/v1/claude_code/routines/{routine_id}/fire
4343```
4444
45Every request must include the `anthropic-beta: experimental-cc-routine-2026-04-01` header. Requests without it return `400 invalid_request_error`.
46
4745The Claude Code web UI provides the full URL alongside the token when you add an API trigger, so most integrations store both as secrets and call the endpoint directly. The following examples show a shell call and a GitHub Actions step that triggers the routine on CI failure.
4846
4947```bash cURL
from line 48
5048curl -X POST https://api.anthropic.com/v1/claude_code/routines/$ROUTINE_ID/fire \
5149 -H "Authorization: Bearer $ROUTINE_TOKEN" \
5250 -H "anthropic-version: 2023-06-01" \
53 -H "anthropic-beta: experimental-cc-routine-2026-04-01" \
5451 -H "Content-Type: application/json" \
5552 -d '{"text": "Sentry alert SEN-4521 fired in prod. Stack trace attached."}'
5653```
from line 61
6461 curl -X POST "$ROUTINE_FIRE_URL" \
6562 -H "Authorization: Bearer $ROUTINE_FIRE_TOKEN" \
6663 -H "anthropic-version: 2023-06-01" \
67 -H "anthropic-beta: experimental-cc-routine-2026-04-01" \
6864 -H "Content-Type: application/json" \
6965 -d "{\"text\": \"CI failed: $GITHUB_WORKFLOW run $GITHUB_RUN_ID on $GITHUB_REF\"}"
7066```
from line 69
7369
7470### Headers
7571
76| Name | Required | Description |
77| ------------------- | -------------------- | ---------------------------------------------------------------------------------------------------- |
78| `Authorization` | Yes | `Bearer <token>`. The per-routine token created in the Claude Code web UI, prefixed `sk-ant-oat01-`. |
79| `anthropic-beta` | Yes | Must include `experimental-cc-routine-2026-04-01`. |
80| `anthropic-version` | Yes | The [API version](https://platform.claude.com/docs/en/api/versioning), for example `2023-06-01`. |
81| `Content-Type` | When body is present | `application/json`. |
72| Name | Required | Description |
73| ------------------- | -------------------- | --------------------------------------------------------------------------------------------------------------- |
74| `Authorization` | Yes | `Bearer <token>`. The per-routine token created in the Claude Code web UI, prefixed `sk-ant-oat01-`. |
75| `anthropic-version` | Yes | The [API version](https://platform.claude.com/docs/en/api/versioning). `2023-06-01` is the only accepted value. |
76| `Content-Type` | When body is present | `application/json`. |
8277
78Older integrations that send an `anthropic-beta: experimental-cc-routine-2026-04-01` header are unaffected: the endpoint accepts requests with and without it.
79
8380### Path parameters
8481
8582| Name | Type | Description |
from line 123
126123}
127124```
128125
129| HTTP status | Error type | Cause |
130| ----------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
131| 400 | `invalid_request_error` | Missing or invalid `anthropic-beta` header, `text` exceeds 65,536 characters, or the routine is paused (see [Edit and control routines](https://code.claude.com/docs/en/routines#edit-and-control-routines)). |
132| 401 | `authentication_error` | No bearer token in the `Authorization` header, or the token does not match this routine. |
133| 403 | `permission_error` | The account or organization does not have access to this endpoint. |
134| 404 | `not_found_error` | The routine does not exist. |
135| 429 | `rate_limit_error` | The account's routine run limit or usage limit has been reached. The response includes a `Retry-After` header indicating when the window resets. |
136| 500 | `api_error` | An unexpected server error. Retry with exponential backoff; if the error persists, contact support with the request ID. |
137| 503 | `overloaded_error` | The service is temporarily overloaded. Retry after a short delay. The Claude Platform returns 529 for this error type; this endpoint returns 503. |
126| HTTP status | Error type | Cause |
127| ----------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
128| 400 | `invalid_request_error` | Missing or unsupported `anthropic-version` header, `text` exceeds 65,536 characters, or the routine is paused (see [Edit and control routines](https://code.claude.com/docs/en/routines#edit-and-control-routines)). |
129| 401 | `authentication_error` | No bearer token in the `Authorization` header, or the token does not match this routine. |
130| 403 | `permission_error` | The account or organization does not have access to this endpoint. |
131| 404 | `not_found_error` | The routine does not exist. |
132| 429 | `rate_limit_error` | An hourly fire limit for the routine or the account has been reached. The response includes a `Retry-After` header indicating when the window resets. |
133| 500 | `api_error` | An unexpected server error. Retry with exponential backoff; if the error persists, contact support with the request ID. |
134| 503 | `overloaded_error` | The service is temporarily overloaded. Retry after a short delay. The Claude Platform returns 529 for this error type; this endpoint returns 503. |
138135
139136## Authentication
140137
from line 145
148145
149146## Rate limits
150147
151Routine runs count against a per-account daily allowance that varies by plan, and the resulting sessions draw down the same Claude Code subscription usage as interactive sessions. When either limit is reached, the endpoint returns `429 rate_limit_error` with a `Retry-After` header. Organizations with extra usage enabled continue past the included allowance on metered overage.
148API fires are limited per hour: each routine accepts up to 30 fires per hour (shared across API fires, the **Run now** button in the web UI, and one-shot re-arms), and each account can make up to 100 API fires per hour across all routines. The resulting sessions draw down the same Claude Code subscription usage as interactive sessions. When a limit is reached, the endpoint returns `429 rate_limit_error` with a `Retry-After` header.
152149
153View your remaining daily runs at [claude.ai/code/routines](https://claude.ai/code/routines). To learn how routine usage interacts with subscription limits and extra usage billing, see [Usage and limits](https://code.claude.com/docs/en/routines#usage-and-limits) in the Claude Code documentation.
150To learn how routine usage interacts with subscription limits and extra usage billing, see [Usage and limits](https://code.claude.com/docs/en/routines#usage-and-limits) in the Claude Code documentation.
154151
155152## SDK support
156153
from line 156
159156## See also
160157
161158* [Automate work with routines](https://code.claude.com/docs/en/routines) in the Claude Code documentation
162* [Beta headers](https://platform.claude.com/docs/en/api/beta-headers)
163159* [Errors](https://platform.claude.com/docs/en/api/errors)
164160
api/completions Changed · +20 / -4 lines
from line 23
2323
2424 - `string`
2525
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
26 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
2727
2828 - `"message-batches-2024-09-24"`
2929
from line 117
117117
118118 - `"compact-2026-09-04"`
119119
120 - `"inline-tools-2026-09-15"`
121
122 - `"mcp-client-2026-09-15"`
123
120124- `"anthropic-workspace-id": optional string`
121125
122126 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 143
139143
140144 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
141145
142 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
146 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
143147
144148 The model that will complete your prompt.
145149
from line 153
149153
150154 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
151155
156 - `"claude-opus-5-5"`
157
158 Powerful intelligence for coding, knowledge work, and long-running agents
159
152160 - `"claude-mythos-5-1"`
153161
154162 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 335
327335
328336 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
329337
330 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
338 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
331339
332340 The model that will complete your prompt.
333341
from line 345
337345
338346 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
339347
348 - `"claude-opus-5-5"`
349
350 Powerful intelligence for coding, knowledge work, and long-running agents
351
340352 - `"claude-mythos-5-1"`
341353
342354 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 484
472484
473485 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
474486
475 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
487 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
476488
477489 The model that will complete your prompt.
478490
from line 493
481493 - `"claude-fable-5-1"`
482494
483495 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
496
497 - `"claude-opus-5-5"`
498
499 Powerful intelligence for coding, knowledge work, and long-running agents
484500
485501 - `"claude-mythos-5-1"`
486502
api/completions/create Changed · +15 / -3 lines
from line 21
2121
2222 - `string`
2323
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
2525
2626 - `"message-batches-2024-09-24"`
2727
from line 115
115115
116116 - `"compact-2026-09-04"`
117117
118 - `"inline-tools-2026-09-15"`
119
120 - `"mcp-client-2026-09-15"`
121
118122- `"anthropic-workspace-id": optional string`
119123
120124 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 141
137141
138142 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
139143
140 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
144 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
141145
142146 The model that will complete your prompt.
143147
from line 151
147151
148152 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
149153
154 - `"claude-opus-5-5"`
155
156 Powerful intelligence for coding, knowledge work, and long-running agents
157
150158 - `"claude-mythos-5-1"`
151159
152160 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 333
325333
326334 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
327335
328 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
336 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
329337
330338 The model that will complete your prompt.
331339
from line 342
334342 - `"claude-fable-5-1"`
335343
336344 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
345
346 - `"claude-opus-5-5"`
347
348 Powerful intelligence for coding, knowledge work, and long-running agents
337349
338350 - `"claude-mythos-5-1"`
339351
api/compliance Changed · +795 / -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 19
1919
2020#### Query parameters
2121
22- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 504 more`
22- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
2323
2424 Filter activities by type. See the response `data` schema for the additional fields each type returns. Cannot be combined with `exclude_activity_types[]`.
2525
from line 839
839839
840840 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
841841
842 - `"gitlab_configuration_created"`
843
844 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
845
846 - `"gitlab_configuration_deleted"`
847
848 An organization admin deleted a self-managed GitLab configuration.
849
850 - `"gitlab_configuration_updated"`
851
852 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
853
842854 - `"group_created"`
843855
844856 A group was created (RBAC admin or SCIM provisioning).
from line 2118
21062118
21072119 format: date-time
21082120
2109- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 504 more`
2121- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
21102122
21112123 Exclude activities of these types. Cannot be combined with `activity_types[]`.
21122124
from line 2938
29262938
29272939 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
29282940
2941 - `"gitlab_configuration_created"`
2942
2943 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
2944
2945 - `"gitlab_configuration_deleted"`
2946
2947 An organization admin deleted a self-managed GitLab configuration.
2948
2949 - `"gitlab_configuration_updated"`
2950
2951 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
2952
29292953 - `"group_created"`
29302954
29312955 A group was created (RBAC admin or SCIM provisioning).
from line 4209
41854209
41864210#### Returns
41874211
4188- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 504 more`
4212- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 507 more`
41894213
41904214 List of activity records. Each element's `type` field identifies which activity it is and which additional fields are present.
41914215
from line 9833
98099833
98109834 - `to_email_count: optional number or null`
98119835
9812 Number of 'to' email recipients.
9813
9814 - `CcrAgentCreated object`
9815
9816 A Claude Code agent was created.
9817
9818 - `type: optional "ccr_agent_created"`
9819
9820 default: ccr_agent_created
9821
9822 - `actor: APIActor or UserActor or UnauthenticatedUserActor or 8 more`
9823
9824 - `APIActor object`
9825
9826 - `type: optional "api_actor"`
9827
9828 default: api_actor
9829
9830 - `api_key_id: string`
9831
9832 - `ip_address: string`
9833
9834 - `user_agent: string`
9835
9836 - `UserActor object`
9837
9838 - `type: optional "user_actor"`
9839
9840 default: user_actor
9841
9842 - `email_address: string`
9843
9844 format: email
9845
9846 - `ip_address: string`
9847
9848 - `user_agent: string`
9849
9850 - `user_id: string`
9851
9852 - `UnauthenticatedUserActor object`
9853
9854 - `type: optional "unauthenticated_user_actor"`
9855
9856 default: unauthenticated_user_actor
9857
9858 - `ip_address: string`
9859
9860 - `user_agent: string`
9861
9862 - `unauthenticated_email_address: optional string or null`
9863
9864 format: email
9865
9866 - `AnthropicActor object`
9867
9868 - `typ
9836 Number of 'to' em
api/compliance/activities Changed · +7320 / -5760 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 17
1717
1818### Query parameters
1919
20- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 504 more`
20- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
2121
2222 Filter activities by type. See the response `data` schema for the additional fields each type returns. Cannot be combined with `exclude_activity_types[]`.
2323
from line 837
837837
838838 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
839839
840 - `"gitlab_configuration_created"`
841
842 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
843
844 - `"gitlab_configuration_deleted"`
845
846 An organization admin deleted a self-managed GitLab configuration.
847
848 - `"gitlab_configuration_updated"`
849
850 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
851
840852 - `"group_created"`
841853
842854 A group was created (RBAC admin or SCIM provisioning).
from line 2116
21042116
21052117 format: date-time
21062118
2107- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 504 more`
2119- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
21082120
21092121 Exclude activities of these types. Cannot be combined with `activity_types[]`.
21102122
from line 2936
29242936
29252937 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
29262938
2939 - `"gitlab_configuration_created"`
2940
2941 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
2942
2943 - `"gitlab_configuration_deleted"`
2944
2945 An organization admin deleted a self-managed GitLab configuration.
2946
2947 - `"gitlab_configuration_updated"`
2948
2949 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
2950
29272951 - `"group_created"`
29282952
29292953 A group was created (RBAC admin or SCIM provisioning).
from line 4207
41834207
41844208### Returns
41854209
4186- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 504 more`
4210- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 507 more`
41874211
41884212 List of activity records. Each element's `type` field identifies which activity it is and which additional fields are present.
41894213
from line 9833
98099833
98109834 Number of 'to' email recipients.
98119835
9812 - `CcrAgentCreated object`
9813
9814 A Claude Code agent was created.
9815
9816 - `type: optional "ccr_agent_created"`
9817
9818 default: ccr_agent_created
9819
9820 - `actor: APIActor or UserActor or UnauthenticatedUserActor or 8 more`
9821
9822 - `APIActor object`
9823
9824 - `type: optional "api_actor"`
9825
9826 default: api_actor
9827
9828 - `api_key_id: string`
9829
9830 - `ip_address: string`
9831
9832 - `user_agent: string`
9833
9834 - `UserActor object`
9835
9836 - `type: optional "user_actor"`
9837
9838 default: user_actor
9839
9840 - `email_address: string`
9841
9842 format: email
9843
9844 - `ip_address: string`
9845
9846 - `user_agent: string`
9847
9848 - `user_id: string`
9849
9850 - `UnauthenticatedUserActor object`
9851
9852 - `type: optional "unauthenticated_user_actor"`
9853
9854 default: unauthenticated_user_actor
9855
9856 - `ip_address: string`
9857
9858 - `user_agent: string`
9859
9860 - `unauthenticated_email_address: optional string or null`
9861
9862 format: email
9863
9864 - `AnthropicActor object`
9865
9866 - `type: optional "anthropic_actor"`
9867
9868
9836 - `CcrAgentCreat
api/compliance/activities/list Changed · +795 / -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 504 more`
18- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 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 835
835835
836836 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
837837
838 - `"gitlab_configuration_created"`
839
840 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
841
842 - `"gitlab_configuration_deleted"`
843
844 An organization admin deleted a self-managed GitLab configuration.
845
846 - `"gitlab_configuration_updated"`
847
848 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
849
838850 - `"group_created"`
839851
840852 A group was created (RBAC admin or SCIM provisioning).
from line 2114
21022114
21032115 format: date-time
21042116
2105- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 504 more`
2117- `exclude_activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
21062118
21072119 Exclude activities of these types. Cannot be combined with `activity_types[]`.
21082120
from line 2934
29222934
29232935 A user attempted to import a personal GitHub access token for use with Claude Code. The `result` field indicates the outcome of the import (imported, rejected, or failed).
29242936
2937 - `"gitlab_configuration_created"`
2938
2939 An organization admin created a self-managed GitLab configuration for syncing plugin marketplaces.
2940
2941 - `"gitlab_configuration_deleted"`
2942
2943 An organization admin deleted a self-managed GitLab configuration.
2944
2945 - `"gitlab_configuration_updated"`
2946
2947 An organization admin updated a self-managed GitLab configuration. Previous/new field pairs are recorded only for settings that changed in the update; secret credentials are never recorded, only whether they were replaced.
2948
29252949 - `"group_created"`
29262950
29272951 A group was created (RBAC admin or SCIM provisioning).
from line 4205
41814205
41824206## Returns
41834207
4184- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 504 more`
4208- `data: optional array of AbuseDecisionReceived or AccountDeleted or AdminAPIKeyCreated or 507 more`
41854209
41864210 List of activity records. Each element's `type` field identifies which activity it is and which additional fields are present.
41874211
from line 9831
98079831
98089832 Number of 'to' email recipients.
98099833
9810 - `CcrAgentCreated object`
9811
9812 A Claude Code agent was created.
9813
9814 - `type: optional "ccr_agent_created"`
9815
9816 default: ccr_agent_created
9817
9818 - `actor: APIActor or UserActor or UnauthenticatedUserActor or 8 more`
9819
9820 - `APIActor object`
9821
9822 - `type: optional "api_actor"`
9823
9824 default: api_actor
9825
9826 - `api_key_id: string`
9827
9828 - `ip_address: string`
9829
9830 - `user_agent: string`
9831
9832 - `UserActor object`
9833
9834 - `type: optional "user_actor"`
9835
9836 default: user_actor
9837
9838 - `email_address: string`
9839
9840 format: email
9841
9842 - `ip_address: string`
9843
9844 - `user_agent: string`
9845
9846 - `user_id: string`
9847
9848 - `UnauthenticatedUserActor object`
9849
9850 - `type: optional "unauthenticated_user_actor"`
9851
9852 default: unauthenticated_user_actor
9853
9854 - `ip_address: string`
9855
9856 - `user_agent: string`
9857
9858 - `unauthenticated_email_address: optional string or null`
9859
9860 format: email
9861
9862 - `AnthropicActor object`
9863
9864 - `type: optional "anthropic_actor"`
9865
9834 - `CcrAgentC
api/messages Changed · +46 / -10 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 1075
10751075
10761076 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10771077
1078 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
1078 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10791079
10801080 The model that will complete your prompt.
10811081
from line 1085
10851085
10861086 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
10871087
1088 - `"claude-opus-5-5"`
1089
1090 Powerful intelligence for coding, knowledge work, and long-running agents
1091
10881092 - `"claude-mythos-5-1"`
10891093
10901094 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 3870
38663870
38673871 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
38683872
3869 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
3873 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
38703874
38713875 The model that will complete your prompt.
38723876
from line 3880
38763880
38773881 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
38783882
3883 - `"claude-opus-5-5"`
3884
3885 Powerful intelligence for coding, knowledge work, and long-running agents
3886
38793887 - `"claude-mythos-5-1"`
38803888
38813889 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 5498
54905498
54915499 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54925500
5493 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
5501 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
54945502
54955503 The model that will complete your prompt.
54965504
from line 5508
55005508
55015509 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
55025510
5511 - `"claude-opus-5-5"`
5512
5513 Powerful intelligence for coding, knowledge work, and long-running agents
5514
55035515 - `"claude-mythos-5-1"`
55045516
55055517 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 8417
84058417
84068418 - `url: string`
84078419
8408 The final post-redirect URL the download was served from.
8409
8410 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8411
8412### Browser State Change Tab Opened
8413
8414- `BrowserStateChangeTabOpened object`
8415
8416 A tab this call's execution opened that remains open at its end —
8417 the creation delta of the `tabs` inventory, not an event log.
8418
8419 C
8420 The final post
api/messages/batches Changed · +25 / -5 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 1095
10951095
10961096 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10971097
1098 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
1098 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10991099
11001100 The model that will complete your prompt.
11011101
from line 1105
11051105
11061106 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
11071107
1108 - `"claude-opus-5-5"`
1109
1110 Powerful intelligence for coding, knowledge work, and long-running agents
1111
11081112 - `"claude-mythos-5-1"`
11091113
11101114 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 4676
46724676
46734677 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
46744678
4675 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
4679 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
46764680
46774681 The model that will complete your prompt.
46784682
from line 4686
46824686
46834687 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
46844688
4689 - `"claude-opus-5-5"`
4690
4691 Powerful intelligence for coding, knowledge work, and long-running agents
4692
46854693 - `"claude-mythos-5-1"`
46864694
46874695 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 6121
61136121
61146122 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
61156123
6116 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
6124 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
61176125
61186126 The model that will complete your prompt.
61196127
from line 6131
61236131
61246132 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
61256133
6134 - `"claude-opus-5-5"`
6135
6136 Powerful intelligence for coding, knowledge work, and long-running agents
6137
61266138 - `"claude-mythos-5-1"`
61276139
61286140 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 7338
73267338
73277339 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
73287340
7329 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
7341 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
73307342
73317343 The model that will complete your prompt.
73327344
from line 7348
73367348
73377349 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
73387350
7351 - `"claude-opus-5-5"`
7352
7353 Powerful intelligence for coding, knowledge work, and long-running agents
7354
73397355 - `"claude-mythos-5-1"`
73407356
73417357 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 8507
84918507
84928508 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
84938509
8494 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
8510 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
84958511
84968512 The model that will complete your prompt.
84978513
from line 8517
85018517
85028518 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
85038519
8520 - `"claude-opus-5-5"`
8521
8522 Powerful intelligence for coding, knowledge work, and long-running agents
8523
85048524 - `"claude-mythos-5-1"`
85058525
85068526 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 8749
87298749
87308750 - `server_tool_use: ServerToolUsage or null`
87318751
8732 The number of server tool requests.
8733
8734 - `web_fetch_requests: number`
8735
8736 The number of web fetch tool requests.
8737
8738 default: 0, minimum: 0
8739
8740 - `web_search_requests: number`
8741
8742 The number of web search tool requests.
8743
8744 default: 0, minimum: 0
8745
8746 - `service_tier: "standard" or "priority" or "batch" or null`
8747
8748 If the request used the priority, standard, or batch tier.
8749
8750 - `"standard"`
8751
8752 - `"priority"`
8753
8754 - `"batch"`
8755
8752 The number of server tool r
api/messages/batches/create Changed · +5 / -1 lines
from line 1093
10931093
10941094 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10951095
1096 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
1096 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10971097
10981098 The model that will complete your prompt.
10991099
from line 1102
11021102 - `"claude-fable-5-1"`
11031103
11041104 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
1105
1106 - `"claude-opus-5-5"`
1107
1108 Powerful intelligence for coding, knowledge work, and long-running agents
11051109
11061110 - `"claude-mythos-5-1"`
11071111
api/messages/batches/results Changed · +5 / -1 lines
from line 828
828828
829829 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
830830
831 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
831 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
832832
833833 The model that will complete your prompt.
834834
from line 837
837837 - `"claude-fable-5-1"`
838838
839839 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
840
841 - `"claude-opus-5-5"`
842
843 Powerful intelligence for coding, knowledge work, and long-running agents
840844
841845 - `"claude-mythos-5-1"`
842846
api/messages/count_tokens Changed · +5 / -1 lines
from line 1061
10611061
10621062 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10631063
1064 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
1064 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10651065
10661066 The model that will complete your prompt.
10671067
from line 1070
10701070 - `"claude-fable-5-1"`
10711071
10721072 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
1073
1074 - `"claude-opus-5-5"`
1075
1076 Powerful intelligence for coding, knowledge work, and long-running agents
10731077
10741078 - `"claude-mythos-5-1"`
10751079
api/messages/create Changed · +10 / -2 lines
from line 1073
10731073
10741074 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10751075
1076 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
1076 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10771077
10781078 The model that will complete your prompt.
10791079
from line 1083
10831083
10841084 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
10851085
1086 - `"claude-opus-5-5"`
1087
1088 Powerful intelligence for coding, knowledge work, and long-running agents
1089
10861090 - `"claude-mythos-5-1"`
10871091
10881092 Our most capable model for cybersecurity and biology research, available through trusted access programs
from line 3868
38643868
38653869 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
38663870
3867 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
3871 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
38683872
38693873 The model that will complete your prompt.
38703874
from line 3877
38733877 - `"claude-fable-5-1"`
38743878
38753879 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
3880
3881 - `"claude-opus-5-5"`
3882
3883 Powerful intelligence for coding, knowledge work, and long-running agents
38763884
38773885 - `"claude-mythos-5-1"`
38783886
api/models Changed · +10 / -2 lines
from line 39
3939
4040 - `string`
4141
42 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
42 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
4343
4444 - `"message-batches-2024-09-24"`
4545
from line 133
133133
134134 - `"compact-2026-09-04"`
135135
136 - `"inline-tools-2026-09-15"`
137
138 - `"mcp-client-2026-09-15"`
139
136140- `"anthropic-workspace-id": optional string`
137141
138142 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 400
396400
397401 - `string`
398402
399 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
403 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
400404
401405 - `"message-batches-2024-09-24"`
402406
from line 493
489493 - `"mid-conversation-system-clear-at-2026-08-21"`
490494
491495 - `"compact-2026-09-04"`
496
497 - `"inline-tools-2026-09-15"`
498
499 - `"mcp-client-2026-09-15"`
492500
493501- `"anthropic-workspace-id": optional string`
494502
api/models/list Changed · +5 / -1 lines
from line 37
3737
3838 - `string`
3939
40 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
40 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
4141
4242 - `"message-batches-2024-09-24"`
4343
from line 130
130130 - `"mid-conversation-system-clear-at-2026-08-21"`
131131
132132 - `"compact-2026-09-04"`
133
134 - `"inline-tools-2026-09-15"`
135
136 - `"mcp-client-2026-09-15"`
133137
134138- `"anthropic-workspace-id": optional string`
135139
api/models/retrieve Changed · +5 / -1 lines
from line 25
2525
2626 - `string`
2727
28 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
28 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more`
2929
3030 - `"message-batches-2024-09-24"`
3131
from line 118
118118 - `"mid-conversation-system-clear-at-2026-08-21"`
119119
120120 - `"compact-2026-09-04"`
121
122 - `"inline-tools-2026-09-15"`
123
124 - `"mcp-client-2026-09-15"`
121125
122126- `"anthropic-workspace-id": optional string`
123127
build-with-claude/claude-in-amazon-bedrock Changed · +13 / -11 lines
from line 332
332332
333333Model IDs in Claude in Amazon Bedrock carry an `anthropic.` provider prefix. Model capabilities and behaviors are documented on the [Models overview](https://platform.claude.com/docs/en/models/overview) page.
334334
335| Model | Model ID | Access |
336| --------------------- | ------------------------------- | --------------------------------------------------------------------------------------------------- |
337| Claude Fable 5.1 | anthropic.claude-fable-5-1 | Open |
338| Claude Fable 5 | anthropic.claude-fable-5 | Open |
339| Claude Opus 5.5 | anthropic.claude-opus-5-5 | See [Access](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#access) |
340| Claude Opus 5 | anthropic.claude-opus-5 | See [Access](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#access) |
341| Claude Opus 4.8 | anthropic.claude-opus-4-8 | Open |
342| Claude Opus 4.7 | anthropic.claude-opus-4-7 | Open |
343| Claude Sonnet 5 | `anthropic.claude-sonnet-5` | Open |
344| Claude Haiku 4.5 | anthropic.claude-haiku-4-5 | Open |
345| Claude Mythos Preview | anthropic.claude-mythos-preview | Invitation only ([Project Glasswing](https://anthropic.com/glasswing)) |
335| Model | Model ID | Access |
336| :------------------------------------------------------------------------------ | :-------------------------------- | :-------------------------------------------------------------------------------------------------- |
337| Claude Fable 5.1 | `anthropic.claude-fable-5-1` | Open |
338| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `anthropic.claude-mythos-5-1` | Invitation only |
339| Claude Fable 5 | `anthropic.claude-fable-5` | Open |
340| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | `anthropic.claude-mythos-5` | Invitation only |
341| Claude Mythos Preview ([limited availability](https://anthropic.com/glasswing)) | `anthropic.claude-mythos-preview` | Invitation only |
342| Claude Opus 5.5 | `anthropic.claude-opus-5-5` | [See Access](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#access) |
343| Claude Opus 5 | `anthropic.claude-opus-5` | [See Access](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#access) |
344| Claude Opus 4.8 | `anthropic.claude-opus-4-8` | Open |
345| Claude Opus 4.7 | `anthropic.claude-opus-4-7` | Open |
346| Claude Sonnet 5 | `anthropic.claude-sonnet-5` | Open |
347| Claude Haiku 4.5 | `anthropic.claude-haiku-4-5` | Open |
346348
347349Use Claude Code 2.1.255 or later with Claude Fable 5.1 on Amazon Bedrock, and 2.1.280 or later with Claude Opus 5.5; run `claude update` to upgrade.
348350
build-with-claude/claude-in-microsoft-foundry Changed · +16 / -14 lines
from line 675
675675
676676The following Claude models are available through Foundry:
677677
678| Model | Default deployment name | Hosted on Azure | Hosted on Anthropic |
679| :---------------- | :---------------------- | :-------------: | :-----------------: |
680| Claude Fable 5.1 | `claude-fable-5-1` | | ✓ |
681| Claude Fable 5 | `claude-fable-5` | | ✓ |
682| Claude Opus 5.5 | `claude-opus-5-5` | ✓ | ✓ |
683| Claude Opus 5 | `claude-opus-5` | ✓ | ✓ |
684| Claude Opus 4.8 | `claude-opus-4-8` | ✓ | ✓ |
685| Claude Opus 4.7 | `claude-opus-4-7` | | ✓ |
686| Claude Opus 4.6 | `claude-opus-4-6` | | ✓ |
687| Claude Opus 4.5 | `claude-opus-4-5` | | ✓ |
688| Claude Sonnet 5 | `claude-sonnet-5` | ✓ | ✓ |
689| Claude Sonnet 4.6 | `claude-sonnet-4-6` | | ✓ |
690| Claude Sonnet 4.5 | `claude-sonnet-4-5` | | ✓ |
691| Claude Haiku 4.5 | `claude-haiku-4-5` | ✓ | ✓ |
678| Model | Default deployment name | Hosted on Azure | Hosted on Anthropic |
679| :-------------------------------------------------------------------------- | :---------------------- | :-------------: | :-----------------: |
680| Claude Fable 5.1 | `claude-fable-5-1` | | ✓ |
681| Claude Mythos 5.1 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5-1` | | ✓ |
682| Claude Fable 5 | `claude-fable-5` | | ✓ |
683| Claude Mythos 5 ([limited availability](https://anthropic.com/glasswing)) | `claude-mythos-5` | | ✓ |
684| Claude Opus 5.5 | `claude-opus-5-5` | ✓ | ✓ |
685| Claude Opus 5 | `claude-opus-5` | ✓ | ✓ |
686| Claude Opus 4.8 | `claude-opus-4-8` | ✓ | ✓ |
687| Claude Opus 4.7 | `claude-opus-4-7` | | ✓ |
688| Claude Opus 4.6 | `claude-opus-4-6` | | ✓ |
689| Claude Opus 4.5 | `claude-opus-4-5` | | ✓ |
690| Claude Sonnet 5 | `claude-sonnet-5` | ✓ | ✓ |
691| Claude Sonnet 4.6 | `claude-sonnet-4-6` | | ✓ |
692| Claude Sonnet 4.5 | `claude-sonnet-4-5` | | ✓ |
693| Claude Haiku 4.5 | `claude-haiku-4-5` | ✓ | ✓ |
692694
693695By default, deployment names match the model IDs shown in the preceding table. However, you can create custom deployments with different names in the Foundry portal to manage different configurations, versions, or rate limits. Use the deployment name (not necessarily the model ID) in your API requests.
694696
build-with-claude/compaction-on-demand Changed · +19 / -23 lines
from line 62
6262 }'
6363 ```
6464
65 <MultiFileExample language="cli" label="CLI">
66 ```bash CLI
67 ant beta:messages create --beta compact-2026-09-04 < request.yaml
68 ```
65 ```bash CLI
66 ant beta:messages create --beta compact-2026-09-04 <<'YAML'
67 model: claude-opus-5-5
68 # max_tokens caps the whole call, including any thinking, so allow several thousand tokens.
69 max_tokens: 4096
70 messages:
71 - role: user
72 content: I am building a recipe app. Help me name the main entities in the data model.
73 - role: assistant
74 content: Start with Recipe, Ingredient, and Step. Add a RecipeIngredient entry that holds the quantity and unit for each ingredient in a recipe.
75 - role: user
76 content: Good. Now suggest field names for Recipe.
77 compaction:
78 type: summarize
79 YAML
80 ```
6981
70 <File filename="request.yaml">
71 ```yaml
72 model: claude-opus-5-5
73 # max_tokens caps the whole call, including any thinking, so allow several thousand tokens.
74 max_tokens: 4096
75 messages:
76 - role: user
77 content: I am building a recipe app. Help me name the main entities in the data model.
78 - role: assistant
79 content: Start with Recipe, Ingredient, and Step. Add a RecipeIngredient entry that holds the quantity and unit for each ingredient in a recipe.
80 - role: user
81 content: Good. Now suggest field names for Recipe.
82 compaction:
83 type: summarize
84 ```
85 </File>
86 </MultiFileExample>
87
8882 ```python Python
8983 from anthropic.types.beta import BetaMessageParam
9084
from line 762
768762
769763The check on `stop_reason` comes before the code looks for the block; [Handle a missing summary or an error](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#when-no-summary-comes-back) says why. The history is replaced, not appended to: the returned message replaces every message the request carried, under the rules in [Continue from the summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#continue-from-the-summary). When no summary comes back, the loop keeps its history and asks again after the next turn.
770764
771The SDK [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) in Python, TypeScript, C#, Go, and Java can send the compaction request for you. When you decide to compact, call `compact_before_next_turn()` on the runner (`compactBeforeNextTurn()` in TypeScript and Java, `CompactBeforeNextTurn()` in C# and Go). Once the current turn and its tool calls finish, the runner sends the compaction request and replaces its history with the returned message. Create the runner with the `compact-2026-09-04` beta, because the runner doesn't add it. The runner builds the request from its own parameters and leaves `context_management` out. If those parameters include `stop_sequences`, a `tool_choice` of type `any` or `tool`, or a structured-output `output_config.format`, the API rejects the request with a 400 error. [Request a summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#request-a-summary) explains why. The runner refuses to compact while its `context_management` has a compaction edit, so use one kind of compaction on a runner.
765The SDK [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) in Python, TypeScript, C#, Go, Java, PHP, and Ruby can send the compaction request for you. When you decide to compact, call `compact_before_next_turn()` on the runner (`compactBeforeNextTurn()` in TypeScript, Java, and PHP, and `CompactBeforeNextTurn()` in C# and Go). Once the current turn and its tool calls finish, the runner sends the compaction request and replaces its history with the returned message. Create the runner with the `compact-2026-09-04` beta, because the runner doesn't add it.
766
767The runner builds the compaction request from its own parameters and leaves `context_management` out. It also leaves out `stop_sequences`, a `tool_choice` of type `any` or `tool`, and a structured-output `output_config.format`, which the API rejects on a compaction request. [Request a summary](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#request-a-summary) explains why. The runner sends them again on its later requests. SDK versions before Python 1.8.0, TypeScript 0.128.0, C# 12.50.0, Go 1.75.0, and Java 2.65.0 send them on the compaction request too. On those versions, a runner that sets any of these parameters gets a 400 error. The runner sends a [task budget](https://platform.claude.com/docs/en/build-with-claude/task-budgets) unchanged. If `output_config.task_budget` sets `remaining`, the compaction request returns a 400 error, so leave `remaining` unset, as [Limits and interactions with other features](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#how-it-fits-with-the-rest-of-the-api) says. The runner refuses to compact while its `context_management` has a compaction edit, so use one kind of compaction on a runner.
772768
773769### When to compact
774770
build-with-claude/compaction-threshold Changed · +15 / -7 lines
from line 2380
23802380 ```
23812381
23822382 ```bash CLI
2383 cat > request.yaml <<'YAML'
2383 CURRENT=$(ant beta:messages count-tokens \
2384 --beta compact-2026-01-12 \
2385 --transform input_tokens \
2386 --raw-output <<'YAML'
23842387 model: claude-opus-5-5
23852388 messages:
23862389 - role: user
from line 2392
23892392 edits:
23902393 - type: compact_20260112
23912394 YAML
2395 )
23922396
2393 CURRENT=$(ant beta:messages count-tokens \
2394 --beta compact-2026-01-12 \
2395 --transform input_tokens \
2396 --raw-output < request.yaml)
2397
23982397 ORIGINAL=$(ant beta:messages count-tokens \
23992398 --beta compact-2026-01-12 \
24002399 --transform context_management.original_input_tokens \
2401 --raw-output < request.yaml)
2400 --raw-output <<'YAML'
2401 model: claude-opus-5-5
2402 messages:
2403 - role: user
2404 content: Hello, Claude
2405 context_management:
2406 edits:
2407 - type: compact_20260112
2408 YAML
2409 )
24022410
24032411 printf 'Current tokens: %s\n' "$CURRENT"
24042412 printf 'Original tokens: %s\n' "$ORIGINAL"
build-with-claude/context-editing Changed · +21 / -7 lines
from line 1829
18291829 ```
18301830
18311831 ```bash CLI
1832 cat > request.yaml <<'YAML'
1832 ORIGINAL=$(ant beta:messages count-tokens \
1833 --beta context-management-2025-06-27 \
1834 --transform context_management.original_input_tokens \
1835 --raw-output <<'YAML'
18331836 model: claude-opus-5-5
18341837 messages:
18351838 - role: user
from line 1847
18441847 type: tool_uses
18451848 value: 5
18461849 YAML
1850 )
18471851
1848 ORIGINAL=$(ant beta:messages count-tokens \
1849 --beta context-management-2025-06-27 \
1850 --transform context_management.original_input_tokens \
1851 --raw-output < request.yaml)
1852
18531852 INPUT_TOKENS=$(ant beta:messages count-tokens \
18541853 --beta context-management-2025-06-27 \
1855 --transform input_tokens --raw-output < request.yaml)
1854 --transform input_tokens --raw-output <<'YAML'
1855 model: claude-opus-5-5
1856 messages:
1857 - role: user
1858 content: Continue our conversation...
1859 context_management:
1860 edits:
1861 - type: clear_tool_uses_20250919
1862 trigger:
1863 type: input_tokens
1864 value: 30000
1865 keep:
1866 type: tool_uses
1867 value: 5
1868 YAML
1869 )
18561870
18571871 printf 'Original tokens: %s\n' "$ORIGINAL"
18581872 printf 'After clearing: %s\n' "$INPUT_TOKENS"
build-with-claude/handling-stop-reasons Changed · +33 / -2 lines
from line 897
897897
898898 <CodeGroup exclude="shell:cURL">
899899 ```bash CLI
900 RESPONSE=$(ant messages create --max-tokens 1024 --format jsonl < request.yaml)
900 RESPONSE=$(ant messages create --max-tokens 1024 --format jsonl <<'YAML'
901 model: claude-opus-5-5
902 tools:
903 - name: get_weather
904 description: Get the current weather in a given location
905 input_schema:
906 type: object
907 properties:
908 location:
909 type: string
910 required:
911 - location
912 messages:
913 - role: user
914 content: What is the weather in San Francisco?
915 YAML
916 )
901917
902918 # Check if the response was truncated mid tool use
903919 STOP_REASON=$(jq -r '.stop_reason' <<<"$RESPONSE")
from line 920
904920 LAST_TYPE=$(jq -r '.content[-1].type' <<<"$RESPONSE")
905921 if [ "$STOP_REASON" = "max_tokens" ] && [ "$LAST_TYPE" = "tool_use" ]; then
906922 # Retry with a higher max_tokens
907 ant messages create --max-tokens 4096 < request.yaml
923 ant messages create --max-tokens 4096 <<'YAML'
924 model: claude-opus-5-5
925 tools:
926 - name: get_weather
927 description: Get the current weather in a given location
928 input_schema:
929 type: object
930 properties:
931 location:
932 type: string
933 required:
934 - location
935 messages:
936 - role: user
937 content: What is the weather in San Francisco?
938 YAML
908939 fi
909940 ```
910941
build-with-claude/mid-conversation-system-messages Changed · +39 / -45 lines
from line 533
533533 }'
534534 ```
535535
536 <MultiFileExample language="cli" label="CLI">
537 ```bash CLI
538 ant beta:messages create --beta inline-tools-2026-09-15 < request.yaml
539 ```
540
541 <File filename="request.yaml">
542 ```yaml
543 model: claude-opus-5-5
544 max_tokens: 1024
545 # Keep at least one non-deferred tool in `tools`, so a tool defined
546 # later doesn't change the start of the rendered prompt.
547 tools:
548 - name: get_weather
549 description: Get the current weather for a location.
550 input_schema:
551 type: object
552 properties:
553 location:
554 type: string
555 description: City name
556 required:
557 - location
558 messages:
559 - role: user
560 content: How many orders shipped yesterday?
561 # Define db_query by value from this point onward. `tools` and the
562 # earlier messages stay exactly as sent, so the cache still hits.
563 - role: system
564 content:
565 - type: tool_addition
566 tool:
567 type: tool_definition
568 definition:
569 name: db_query
570 description: Run a read-only SQL query against the analytics database.
571 input_schema:
572 type: object
573 properties:
574 sql:
575 type: string
576 required:
577 - sql
578 ```
579 </File>
580 </MultiFileExample>
536 ```bash CLI
537 ant beta:messages create --beta inline-tools-2026-09-15 <<'YAML'
538 model: claude-opus-5-5
539 max_tokens: 1024
540 # Keep at least one non-deferred tool in `tools`, so a tool defined
541 # later doesn't change the start of the rendered prompt.
542 tools:
543 - name: get_weather
544 description: Get the current weather for a location.
545 input_schema:
546 type: object
547 properties:
548 location:
549 type: string
550 description: City name
551 required:
552 - location
553 messages:
554 - role: user
555 content: How many orders shipped yesterday?
556 # Define db_query by value from this point onward. `tools` and the
557 # earlier messages stay exactly as sent, so the cache still hits.
558 - role: system
559 content:
560 - type: tool_addition
561 tool:
562 type: tool_definition
563 definition:
564 name: db_query
565 description: Run a read-only SQL query against the analytics database.
566 input_schema:
567 type: object
568 properties:
569 sql:
570 type: string
571 required:
572 - sql
573 YAML
574 ```
581575
582576 ```python Python
583577 client = anthropic.Anthropic()