HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
145 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
65 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
24 Sep 2026
183 pages
+21479 −7808 lines
api
manage-claude/wif-providers/okta
±changed
+1−1
apichanged
manage-claude/wif-providers/okta
Each SDK tab shows the callable pattern: the Anthropic SDK calls your identity-token provider again whenever the Anthropic access token approaches expiry, so your Okta fetcher shou
Each SDK tab shows the callable pattern: the Anthropic SDK calls the function you passed to `identity_token_provider` (typescript, php: `identityTokenProvider`; csharp: `IdentityTo
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
manage-claude/wif-providers/github-actions
±changed
+1−1
apichanged
manage-claude/wif-providers/github-actions
Set the federation environment variables on the job and call the SDK normally. `Anthropic()` reads `ANTHROPIC_IDENTITY_TOKEN_FILE`, exchanges the JWT on the first request, and refr
Set the federation environment variables on the job and call the SDK normally. `Anthropic()` (typescript: `new Anthropic()`; csharp: `new AnthropicClient()`; go: `anthropic.NewClie
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
manage-claude/wif-providers/gcp
±changed
+1−1
apichanged
manage-claude/wif-providers/gcp
Inside your Google Cloud workload, fetch the identity token from the metadata server, exchange it at `POST /v1/oauth/token`, and use the returned bearer token to call the Claude AP
Inside your Google Cloud workload, fetch the identity token from the metadata server, exchange it at `POST /v1/oauth/token`, and use the returned bearer token to call the Claude AP
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
manage-claude/wif-providers/azure
±changed
+4−4
apichanged
manage-claude/wif-providers/azure
At runtime your workload fetches its Entra token, exchanges it at `POST /v1/oauth/token`, and uses the returned bearer token to call Claude. Each Anthropic SDK handles the exchange
At runtime your workload fetches its Entra token, exchanges it at `POST /v1/oauth/token`, and uses the returned bearer token to call Claude. Each Anthropic SDK handles the exchange
If your workload already uses the Azure Identity client library, pass its token acquisition (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) as the identity to
If your workload already uses the Azure Identity client library, pass its token acquisition (`DefaultAzureCredential` with the scope `api://<APP_ID>/.default`) to `identity_token
At runtime the pod performs the two-hop exchange: it sends the Kubernetes-projected token (the file at `AZURE_FEDERATED_TOKEN_FILE`) to Entra's token endpoint as a federated `clien
+4 −4 lines
Recorded here 24 Sep 2026 17:37 UTC
api
manage-claude/wif-providers/aws
±changed
+1−1
apichanged
manage-claude/wif-providers/aws
Call `GetWebIdentityToken` with `https://api.anthropic.com` as the audience, then pass the result to the SDK's federation credentials. The token provider is a callable, so the SDK
Call `GetWebIdentityToken` with `https://api.anthropic.com` as the audience, then pass the result to the SDK's federation credentials. Because `identity_token_provider` (typescript
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
manage-claude/inference-hooks
±changed
+14−1
apichanged
manage-claude/inference-hooks
## Continue a conversation after a denied request
Each request includes the whole conversation, so a denied message is sent again with every later message. If your AI security server evaluates the whole transcript, it denies those
The steps depend on the app:
+14 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/thinking
±changed
+2−2
apichanged
build-with-claude/thinking
To reassemble complete thinking blocks with their signatures after streaming, use your SDK's message-accumulation helper where one exists (for example, `stream.get_final_message()`
To reassemble complete thinking blocks with their signatures after streaming, use your SDK's message-accumulation helper, `stream.get_final_message()` (typescript: `stream.finalMes
The SDKs require streaming when `max_tokens` is greater than 21,333, to avoid HTTP timeouts on long-running requests. This is a client-side validation, not an API restriction. If y
The SDKs require streaming when `max_tokens` is greater than 21,333, to avoid HTTP timeouts on long-running requests. This is a client-side validation, not an API restriction. If y
+2 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/structured-outputs
±changed
+1−1
apichanged
build-with-claude/structured-outputs
**Migrating from beta?** The `output_format` parameter has moved to `output_config.format`, and beta headers are no longer required. The API continues to accept the old beta head
**Migrating from beta?** The `output_format` parameter has moved to `output_config.format`, and beta headers are no longer required. The `output_format` parameter is deprecated a
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/refusals-and-fallback
±changed
+19−11
apichanged
build-with-claude/refusals-and-fallback
| `category` | What it means
| ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------
| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.
| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/leg
+19 −11 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/prompt-caching
±changed
+1−1
apichanged
build-with-claude/prompt-caching
[Cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) (beta) has the API compare consecutive requests and report exactly where the prompt p
[Cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) has the API compare consecutive requests and report where the prompt prefix diverged,
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+21−16
apichanged
build-with-claude/mid-conversation-system-messages
[Mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) are in beta and require the
[Mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) are in beta on the same mode
The `tools` array sits even earlier in the hashed request prefix than the top-level `system` field, so editing it invalidates the [prompt cache](https://platform.claude.com/docs/en
`tool_addition` and `tool_removal` are content blocks in the `content` array of a `role: "system"` message, and they can be mixed with `text` blocks in the same message. The messag
+21 −16 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/handling-stop-reasons
±changed
+1−1
apichanged
build-with-claude/handling-stop-reasons
This stop reason is currently typed only in the SDKs' `beta` namespace, so the following examples call `client.beta.messages` and use the `Beta`-prefixed types. On Sonnet 4.5 and
This stop reason is currently typed only in the SDKs' `beta` namespace, so the following examples call `client.beta.messages` (csharp, go: `client.Beta.Messages`; java: `client.b
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/fast-mode
±changed
+3−3
apichanged
build-with-claude/fast-mode
When fast mode rate limits are exceeded, the API returns a `429` error with a `retry-after` header. The Anthropic SDKs automatically retry these requests up to 2 times by default (
When fast mode rate limits are exceeded, the API returns a `429` error with a `retry-after` header. The Anthropic SDKs automatically retry these requests up to 2 times by default (
If you'd prefer to fall back to standard speed rather than wait for fast mode capacity, catch the rate limit error and retry without `speed: "fast"`. Set `max_retries` to `0` on th
If you'd prefer to fall back to standard speed rather than wait for fast mode capacity, catch the rate limit error and retry without `speed: "fast"`. Set `max_retries` (typescript,
Because setting `max_retries` to `0` also disables retries for other transient errors (overloaded, internal server errors), the following examples reissue the original request with
+3 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/compaction-on-demand
±changed
+1−1
apichanged
build-with-claude/compaction-on-demand
The 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
The 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
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+15−15
apichanged
build-with-claude/claude-platform-on-aws
| Aspect | Claude Platform on AWS
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------
| **Who operates the stack** | Anthropic
| **API surface** | Claude API (`/v1/{endpoint}`)
| **Feature availability** | Typically same-day as Claude API (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-n
+15 −15 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+2−2
apichanged
build-with-claude/claude-on-vertex-ai
Set the `region` parameter to `"global"` when initializing the client:
Set the `region` (php: `location`) parameter to `"global"` when initializing the client:
Set the `region` parameter to a multi-region identifier: `"us"` for the United States or `"eu"` for the European Union. The SDK routes requests to the corresponding multi-region en
Set the `region` (php: `location`) parameter to a multi-region identifier: `"us"` for the United States or `"eu"` for the European Union. The SDK routes requests to the correspondi
+2 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+1−1
apichanged
build-with-claude/claude-in-amazon-bedrock
You can also use the standard `Anthropic` client: set `base_url` to `https://bedrock-mantle.{region}.api.aws/anthropic` and pass your bearer token as `api_key`. This path support
You can also use the standard `Anthropic` client: set `base_url` to `https://bedrock-mantle.{region}.api.aws/anthropic` and pass your bearer token as `api_key`. This path support
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
build-with-claude/cache-diagnostics
±changed
+16−54
apichanged
build-with-claude/cache-diagnostics
status: beta
betaHeader: cache-diagnosis-2026-04-07
status: ga
Claude API: beta
Claude API: ga
+16 −54 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/models/retrieve
±changed
+8−6
apichanged
api/models/retrieve
- `"anthropic-workspace-id": optional string`
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
+8 −6 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/models/list
±changed
+8−6
apichanged
api/models/list
- `"anthropic-workspace-id": optional string`
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
+8 −6 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/models
±changed
+16−12
apichanged
api/models
- `"anthropic-workspace-id": optional string`
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
+16 −12 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/messages/create
±changed
+78−0
apichanged
api/messages/create
- `diagnostics: optional DiagnosticsParam or null`
Request-level diagnostics. Currently carries the previous response
id for prompt-cache divergence reporting.
+78 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/messages/batches/results
±changed
+61−0
apichanged
api/messages/batches/results
- `diagnostics: Diagnostics or null`
Request-level diagnostics: why the prompt cache could not fully reuse
the prefix of the request named by `diagnostics.previous_message_id`.
+61 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/messages/batches/create
±changed
+11−0
apichanged
api/messages/batches/create
- `diagnostics: optional DiagnosticsParam or null`
Request-level diagnostics. Currently carries the previous response
id for prompt-cache divergence reporting.
+11 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/messages/batches
±changed
+255−0
apichanged
api/messages/batches
- `diagnostics: optional DiagnosticsParam or null`
Request-level diagnostics. Currently carries the previous response
id for prompt-cache divergence reporting.
+255 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/messages
±changed
+529−0
apichanged
api/messages
- `diagnostics: optional DiagnosticsParam or null`
Request-level diagnostics. Currently carries the previous response
id for prompt-cache divergence reporting.
+529 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/errors
±changed
+3−3
apichanged
api/errors
The official SDKs automatically retry transient failures (such as connection errors, rate limits, and 5xx server errors) with exponential backoff, twice by default, honoring the `r
The official SDKs automatically retry transient failures (such as connection errors, rate limits, and 5xx server errors) with exponential backoff, twice by default, honoring the `r
The official SDKs raise typed exceptions for these errors instead of returning raw JSON, and the class names and namespaces differ by language. For example, a 404 surfaces as `anth
The official SDKs raise typed exceptions for these errors instead of returning raw JSON, and the class names and namespaces differ by language. For example, a 404 surfaces as `anth
The Python and TypeScript SDKs expose the request ID as a `_request_id` property on top-level response objects. The C#, Go, Java, and PHP SDKs expose it through their raw-response
+3 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/organizations/settings/retrieve
±changed
+3−1
apichanged
api/compliance/organizations/settings/retrieve
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 58 more`
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 59 more`
- `"project_sharing_enabled"`
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/organizations/settings
±changed
+6−2
apichanged
api/compliance/organizations/settings
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 58 more`
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 59 more`
- `"project_sharing_enabled"`
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 58 more`
+6 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/organizations
±changed
+3−1
apichanged
api/compliance/organizations
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 58 more`
- `name: "access_transparency_enabled" or "ai_powered_artifacts_enabled" or "api_workbench_feedback_collection_enabled" or 59 more`
- `"project_sharing_enabled"`
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/sessions/local/messages/list
±changed
+8−1
apichanged
api/compliance/apps/sessions/local/messages/list
On a very large session, some pages are too large to read and return a
400; retrying does not help. If the request used `order=desc`, read the
session oldest first from its first page instead (omit `order` and
`page`, then follow `next_page`). Rarely, an oldest-first page returns
this 400 too; contact Anthropic support and quote the `request-id`
+8 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/sessions/local/messages
±changed
+8−1
apichanged
api/compliance/apps/sessions/local/messages
On a very large session, some pages are too large to read and return a
400; retrying does not help. If the request used `order=desc`, read the
session oldest first from its first page instead (omit `order` and
`page`, then follow `next_page`). Rarely, an oldest-first page returns
this 400 too; contact Anthropic support and quote the `request-id`
+8 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/sessions/local
±changed
+8−1
apichanged
api/compliance/apps/sessions/local
On a very large session, some pages are too large to read and return a
400; retrying does not help. If the request used `order=desc`, read the
session oldest first from its first page instead (omit `order` and
`page`, then follow `next_page`). Rarely, an oldest-first page returns
this 400 too; contact Anthropic support and quote the `request-id`
+8 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/sessions
±changed
+8−1
apichanged
api/compliance/apps/sessions
On a very large session, some pages are too large to read and return a
400; retrying does not help. If the request used `order=desc`, read the
session oldest first from its first page instead (omit `order` and
`page`, then follow `next_page`). Rarely, an oldest-first page returns
this 400 too; contact Anthropic support and quote the `request-id`
+8 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/chats/messages/list
±changed
+1−1
apichanged
api/compliance/apps/chats/messages/list
Last update timestamp
Last update timestamp. Updated when the chat receives a new message, is moved into or out of a project, or is deleted in claude.ai. Other edits, such as renaming the chat, are no
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/chats/messages
±changed
+1−1
apichanged
api/compliance/apps/chats/messages
Last update timestamp
Last update timestamp. Updated when the chat receives a new message, is moved into or out of a project, or is deleted in claude.ai. Other edits, such as renaming the chat, are no
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/chats/list
±changed
+6−1
apichanged
api/compliance/apps/chats/list
Incremental polling with `order_by=updated_at` returns a chat again
after it receives a new message, is moved into or out of a project, or
is deleted in claude.ai. A chat is not guaranteed to be returned again
after other edits, such as a rename.
+6 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps/chats
±changed
+8−3
apichanged
api/compliance/apps/chats
Incremental polling with `order_by=updated_at` returns a chat again
after it receives a new message, is moved into or out of a project, or
is deleted in claude.ai. A chat is not guaranteed to be returned again
after other edits, such as a rename.
+8 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/apps
±changed
+15−3
apichanged
api/compliance/apps
Incremental polling with `order_by=updated_at` returns a chat again
after it receives a new message, is moved into or out of a project, or
is deleted in claude.ai. A chat is not guaranteed to be returned again
after other edits, such as a rename.
+15 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/activities/list
±changed
+2527−1463
apichanged
api/compliance/activities/list
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 511 more`
- `"claude_artifact_invite_accepted"`
+2527 −1463 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance/activities
±changed
+5018−2922
apichanged
api/compliance/activities
No line of the body moved in this read.
+5018 −2922 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/compliance
±changed
+2545−1467
apichanged
api/compliance
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 507 more`
- `activity_types: optional array of "abuse_decision_received" or "account_deleted" or "admin_api_key_created" or 511 more`
- `"claude_artifact_invite_accepted"`
+2545 −1467 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/completions/create
±changed
+8−6
apichanged
api/completions/create
- `"anthropic-workspace-id": optional string`
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
+8 −6 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/completions
±changed
+8−6
apichanged
api/completions
- `"anthropic-workspace-id": optional string`
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
+8 −6 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/organization/workspaces/rate_limits/list
±changed
+41−10
apichanged
api/beta/organization/workspaces/rate_limits/list
List rate-limit overrides configured for a workspace.
Returns only the groups and limiter types that have a workspace-level
override. Groups without overrides inherit the organization limits and
are not listed; use `GET /v1/organizations/rate_limits` to see those.
+41 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/organization/workspaces/rate_limits
±changed
+106−15
apichanged
api/beta/organization/workspaces/rate_limits
List rate-limit overrides configured for a workspace.
Returns only the groups and limiter types that have a workspace-level
override. Groups without overrides inherit the organization limits and
are not listed; use `GET /v1/organizations/rate_limits` to see those.
+106 −15 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/organization/workspaces
±changed
+41−10
apichanged
api/beta/organization/workspaces
List rate-limit overrides configured for a workspace.
Returns only the groups and limiter types that have a workspace-level
override. Groups without overrides inherit the organization limits and
are not listed; use `GET /v1/organizations/rate_limits` to see those.
+41 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/organization
±changed
+41−10
apichanged
api/beta/organization
List rate-limit overrides configured for a workspace.
Returns only the groups and limiter types that have a workspace-level
override. Groups without overrides inherit the organization limits and
are not listed; use `GET /v1/organizations/rate_limits` to see those.
+41 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/messages/create
±changed
+1−1
apichanged
api/beta/messages/create
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/messages/batches/results
±changed
+1−1
apichanged
api/beta/messages/batches/results
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/messages/batches
±changed
+4−4
apichanged
api/beta/messages/batches
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
+4 −4 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/messages
±changed
+64−8
apichanged
api/beta/messages
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
### Beta Cache Miss Reason
- `BetaCacheMissReason = BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more`
+64 −8 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/memory_stores/memory_versions/retrieve
±changed
+10−10
apichanged
api/beta/memory_stores/memory_versions/retrieve
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
Identifies who performed an operation. Recorded when the operation happens and not updated afterwards, so the ID may refer to a user, service account, API key, or session that
Attribution for a write made by an agent during a session, through the mounted filesystem at `/mnt/memory/`.
An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session.
ID of the session that performed the write (a `sesn_...` value). Look up the session via [Retrieve a session](/docs/en/api/beta/sessions/retrieve) for further provenance.
+10 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/memory_stores/memory_versions/redact
±changed
+10−10
apichanged
api/beta/memory_stores/memory_versions/redact
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
Identifies who performed an operation. Recorded when the operation happens and not updated afterwards, so the ID may refer to a user, service account, API key, or session that
Attribution for a write made by an agent during a session, through the mounted filesystem at `/mnt/memory/`.
An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session.
ID of the session that performed the write (a `sesn_...` value). Look up the session via [Retrieve a session](/docs/en/api/beta/sessions/retrieve) for further provenance.
+10 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/memory_stores/memory_versions/list
±changed
+10−10
apichanged
api/beta/memory_stores/memory_versions/list
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
Identifies who performed an operation. Recorded when the operation happens and not updated afterwards, so the ID may refer to a user, service account, API key, or session that
Attribution for a write made by an agent during a session, through the mounted filesystem at `/mnt/memory/`.
An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session.
ID of the session that performed the write (a `sesn_...` value). Look up the session via [Retrieve a session](/docs/en/api/beta/sessions/retrieve) for further provenance.
+10 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/memory_stores/memory_versions
±changed
+57−57
apichanged
api/beta/memory_stores/memory_versions
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
Identifies who performed an operation. Recorded when the operation happens and not updated afterwards, so the ID may refer to a user, service account, API key, or session that
Attribution for a write made by an agent during a session, through the mounted filesystem at `/mnt/memory/`.
An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session.
ID of the session that performed the write (a `sesn_...` value). Look up the session via [Retrieve a session](/docs/en/api/beta/sessions/retrieve) for further provenance.
+57 −57 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/memory_stores
±changed
+30−30
apichanged
api/beta/memory_stores
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
Identifies who performed an operation. Recorded when the operation happens and not updated afterwards, so the ID may refer to a user, service account, API key, or session that
Attribution for a write made by an agent during a session, through the mounted filesystem at `/mnt/memory/`.
An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session.
ID of the session that performed the write (a `sesn_...` value). Look up the session via [Retrieve a session](/docs/en/api/beta/sessions/retrieve) for further provenance.
+30 −30 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/dreams/retrieve
±changed
+3−1
apichanged
api/beta/dreams/retrieve
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/dreams/create
±changed
+3−1
apichanged
api/beta/dreams/create
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/dreams/cancel
±changed
+3−1
apichanged
api/beta/dreams/cancel
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/dreams/archive
±changed
+3−1
apichanged
api/beta/dreams/archive
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.
+3 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta/dreams
±changed
+15−5
apichanged
api/beta/dreams
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints.
By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into
+15 −5 lines
Recorded here 24 Sep 2026 17:37 UTC
api
api/beta
±changed
+85−46
apichanged
api/beta
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
- `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
- `cache_miss_reason: BetaCacheMissReason or null`
Identifies who performed a write or redact operation. Captured at write time on the `memory_version` row. The API key that created a session is not recorded on agent writes; at
+85 −46 lines
Recorded here 24 Sep 2026 17:37 UTC
api
agents-and-tools/tool-use/tool-runner
±changed
+3−3
apichanged
agents-and-tools/tool-use/tool-runner
You can end the loop at any iteration with a `break` statement. The runner loops until Claude returns a message without a tool use, or until it reaches `max_iterations` if you set
You can end the loop at any iteration with a `break` statement. The runner loops until Claude returns a message without a tool use, or until it reaches `max_iterations` (csharp, ja
When you take over for an iteration, the runner does not append the assistant message or tool results from that turn. You become responsible for keeping the conversation valid: app
When you take over for an iteration, the runner does not append the assistant message or tool results from that turn. You become responsible for keeping the conversation valid: app
For long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-sid
+3 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/computer-use-tool
- On the Claude API and Google Cloud, Claude Opus 5.5 supports computer use only through the `computer_toolset_20260801` toolset and returns an error for the earlier `computer_
- On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier
Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-an
Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-an
+2 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/code-execution-tool
Code execution runs in server-side sandbox containers. Container data, including execution artifacts, uploaded files, and outputs, is retained for up to 30 days. This retention app
Code execution runs in server-side sandbox containers. Container data, including execution artifacts, uploaded files, and outputs, is retained for up to 30 days. This retention app
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
agents-and-tools/tool-use/build-a-tool-using-agent
±changed
+1−1
apichanged
agents-and-tools/tool-use/build-a-tool-using-agent
Rings 2 through 4 wrote the same loop by hand: call the API, check `stop_reason`, run tools, append results, repeat. The Tool Runner does this for you. Define each tool as a functi
Rings 2 through 4 wrote the same loop by hand: call the API, check `stop_reason`, run tools, append results, repeat. The Tool Runner does this for you. Define each tool as a functi
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
agents-and-tools/mcp-connector
±changed
+1−1
apichanged
agents-and-tools/mcp-connector
The conversion functions throw `UnsupportedMCPValueError` if an MCP value isn't supported by the Claude API (in Go, the helpers return an `UnsupportedValueError`; in Java and C#, t
The conversion functions fail with `UnsupportedMCPValueError` (go: `UnsupportedValueError`; java, csharp: `AnthropicInvalidDataException`) if an MCP value isn't supported by the Cl
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+103−2
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
* **Tradeoffs** exchange cost for intelligence: model choice, effort, output caps and task budgets, and multi-model architectures.
* **Tradeoffs** exchange cost for intelligence: model choice, effort, output caps and task budgets, an elapsed-time clock, and multi-model architectures.
| You want agent runs to finish sooner | Tell the model that time matters, and show it the elapsed time; on DRACO, HLE, and an internal physics set, runs took 33% to 69
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, and the budgets and caps it works within. S
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, the budgets and caps it works within, and w
+103 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
claude-code
settings-reference
±changed
+4−0
claude-codechanged
settings-reference
If you set this key in the [claude.ai admin console](/docs/en/server-managed-settings), claude.ai also applies it when anyone in your organization adds a marketplace from a git rep
If you set this key in the [claude.ai admin console](/docs/en/server-managed-settings), claude.ai also applies it when anyone in your organization adds a marketplace from a git rep
+4 −0 lines
Upstream edited 24 Sep 2026 17:27 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
server-managed-settings
±changed
+1−1
claude-codechanged
server-managed-settings
In a [Cowork](https://claude.com/docs/cowork/overview) session in the Claude Desktop app, Claude Code doesn't fetch server-managed settings from the claude.ai admin console, even w
In a [Cowork](https://claude.com/docs/cowork/overview) session in the Claude Desktop app, Claude Code doesn't fetch server-managed settings from the claude.ai admin console, even w
+1 −1 lines
Upstream edited 24 Sep 2026 17:27 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
plugin-marketplaces
±changed
+5−0
claude-codechanged
plugin-marketplaces
Where the two lists are enforced depends on where you set them:
* **The claude.ai admin console**: Claude Code enforces both lists in the sessions that [read server-managed settings](/docs/en/managed-settings#where-and-when-a-policy-applies). c
* **A managed settings file, OS-level policy, or other managed source**: Claude Code enforces both lists where it reads that source. claude.ai doesn't read it.
+5 −0 lines
Upstream edited 24 Sep 2026 17:27 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
The [surface coverage](/docs/en/model-config#surface-coverage) table compares Cowork with the other surfaces.
Wherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/doc
+1 −1 lines
Upstream edited 24 Sep 2026 17:27 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-docs
government/changelog
±changed
+14−0
claude-docschanged
government/changelog
<Update label="2026.09.22.1">
* Fixed members whose browser sign-in is refused, for example because their account was deactivated, seeing an "Invalid redirect uri" error instead of the page that explains why
* Changed web sign-in for tenant administrators and Primary Owners: the **Choose sign-in** page is gone, **Email me a sign-in link** is now under the form where you enter your wo
* Changed sign-in for Claude Desktop: signing in right after another app sign-in in the same browser now goes through your identity provider, and you may be asked which account t
+14 −0 lines
Upstream edited 24 Sep 2026 17:22 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
Claude Code generates each of these next-prompt suggestions with a background request that reuses the conversation's prompt cache, so the additional cost is minimal.
Claude Code generates each of these next-prompt suggestions with a short background request to the same model your session is using. The request counts toward your plan's usage lim
+1 −1 lines
Upstream edited 24 Sep 2026 17:19 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
costs
±changed
+2−0
claude-codechanged
costs
When prompt suggestions are on, Claude Code also sends a short request to the model your session is using after Claude responds, to [suggest your next prompt](/docs/en/interactive-
+2 −0 lines
Upstream edited 24 Sep 2026 17:19 UTC Recorded here 24 Sep 2026 17:37 UTC
claude-code
plugin-evals
±changed
+9−1
claude-codechanged
plugin-evals
`claude plugin eval` loads the target plugin's skills and hooks and runs its eval suite on your machine, as you. Pointing it at a plugin is the same trust decision as `claude --plu
`claude plugin eval` loads the target plugin's skills, hooks, and agents and runs its eval suite on your machine, as you. Pointing it at a plugin is the same trust decision as `cla
### "Agent type '...' not found" for one of your plugin's agents
By default each case runs both with your plugin and without it, and the runs without it are the [no-plugin baseline](#the-no-plugin-baseline). When Claude dispatches one of your pl
+9 −1 lines
Upstream edited 24 Sep 2026 17:00 UTC Recorded here 24 Sep 2026 17:07 UTC
mcp
community/interest-groups/scientific-computing
±changed
+13−13
mcpchanged
community/interest-groups/scientific-computing
| Role | Name | Organization | GitHub | Term |
| ----------- | ----------- | ------------ | -------------------------------------------- | ------- |
| Facilitator | Cory Kinney | — | [@corykinney](https://github.com/corykinney) | Initial |
| Role | Name | Organization | GitHub | Term |
| - | - | - | - | - |
+13 −13 lines
Upstream edited 24 Sep 2026 01:40 UTC Recorded here 28 Sep 2026 22:07 UTC
mcp
community/interest-groups/scientific-computing
+new page
+88−0
mcpnew page
community/interest-groups/scientific-computing
No line of the body moved in this read.
+88 −0 lines
Upstream edited 24 Sep 2026 01:40 UTC Recorded here 24 Sep 2026 02:07 UTC
claude-docs
claude-tag/concepts/settings-map
±changed
+1−1
claude-docschanged
claude-tag/concepts/settings-map
* **Workspace pairing and restrictions**: which Slack workspaces are paired, whether DMs are allowed, guest-channel behavior, who can invoke Claude, and which generation of the app
* **Workspace pairing and restrictions**: which Slack workspaces are paired, whether DMs are allowed, guest-channel behavior, which channels Claude can search, who can invoke Claud
+1 −1 lines
Upstream edited 24 Sep 2026 00:41 UTC Recorded here 24 Sep 2026 01:07 UTC
claude-docs
claude-tag/concepts/how-it-works
±changed
+1−1
claude-docschanged
claude-tag/concepts/how-it-works
Claude works in channels it has been added to, but workspace search can still find messages by keyword from public channels it's not a member of (the same search any Slack user has
Claude works in channels it has been added to, but workspace search can still find messages by keyword from public channels it's not a member of (the same search any Slack user has
+1 −1 lines
Upstream edited 24 Sep 2026 00:41 UTC Recorded here 24 Sep 2026 01:07 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+24−1
claude-docschanged
claude-tag/admins/restrict-access
### Limit which channels Claude can search
By default, workspace search covers public channels across the workspace, including ones Claude hasn't been added to. The **Channels Claude can search** setting narrows workspace s
+24 −1 lines
Upstream edited 24 Sep 2026 00:41 UTC Recorded here 24 Sep 2026 01:07 UTC
claude-docs
claude-tag/admins/healthcare
±changed
+2−2
claude-docschanged
claude-tag/admins/healthcare
* Search every public channel by keyword, including public channels it hasn't been added to. [No admin setting turns this search off](/docs/claude-tag/admins/restrict-access#contro
* Search every public channel by keyword, including public channels it hasn't been added to. [No admin setting turns this search off](/docs/claude-tag/admins/restrict-access#contro
For a healthcare organization, the rule that follows is to keep PHI out of every public channel in the connected workspace, not only the channels where Claude responds, because Cla
For a healthcare organization, the rule that follows is to keep PHI out of every public channel in the connected workspace, not only the channels where Claude responds, because Cla
+2 −2 lines
Upstream edited 24 Sep 2026 00:41 UTC Recorded here 24 Sep 2026 01:07 UTC
23 Sep 2026
333 pages
+97834 −37961 lines
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+15−3
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
# Stream request and check for refusal
# Check for refusal in the stream
if echo "$response" | grep -q '"stop_reason":"refusal"'; then
if echo "$response" | jq -R -e 'select(startswith("data: "))
| sub("^data: "; "") | fromjson
+15 −3 lines
Recorded here 23 Sep 2026 22:37 UTC
api
managed-agents/webhooks
±changed
+2−2
apichanged
managed-agents/webhooks
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI">
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI">
+2 −2 lines
Recorded here 23 Sep 2026 22:37 UTC
api
managed-agents/migration
±changed
+1−1
apichanged
managed-agents/migration
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI">
+1 −1 lines
Recorded here 23 Sep 2026 22:37 UTC
api
managed-agents/agent-setup
±changed
+1−1
apichanged
managed-agents/agent-setup
<CodeGroup>
<CodeGroup exclude="shell:CLI, python, typescript, csharp, go, java, php, ruby">
+1 −1 lines
Recorded here 23 Sep 2026 22:37 UTC
api
manage-claude/workload-identity-federation
±changed
+1−1
apichanged
manage-claude/workload-identity-federation
<CodeGroup>
<CodeGroup exclude="shell:CLI">
+1 −1 lines
Recorded here 23 Sep 2026 22:37 UTC
api
manage-claude/spend-limits-api
±changed
+1−1
apichanged
manage-claude/spend-limits-api
| `denied` | An admin declined. `spend_summary` is `null`. claude.ai hides that member's request button for 30 days from `resolved_at`; an admin can still raise the member's spen
| `denied` | An admin declined. `spend_summary` is `null`. The member can send a new request right away; only a `pending` request blocks a new one. An admin can still raise the m
+1 −1 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+31−0
apichanged
build-with-claude/thinking-tool-workflows
```bash cURL
curl https://api.anthropic.com/v1/messages \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-H "x-api-key: $ANTHROPIC_API_KEY" \
+31 −0 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/task-budgets
±changed
+1−1
apichanged
build-with-claude/task-budgets
<CodeGroup>
<CodeGroup exclude="shell:cURL">
+1 −1 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/streaming
±changed
+2−2
apichanged
build-with-claude/streaming
<CodeGroup>
<CodeGroup exclude="shell:cURL">
<CodeGroup>
<CodeGroup exclude="shell:cURL">
+2 −2 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/refusals-and-fallback
±changed
+3−3
apichanged
build-with-claude/refusals-and-fallback
<Note>
**How refusals are billed:** You are not billed for a refusal that arrives before any output. `content` is empty, and token counts appear in `usage` but are not charged. The requ
</Note>
## How refusals are billed
+3 −3 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/prompt-caching
±changed
+2−2
apichanged
build-with-claude/prompt-caching
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI, typescript, csharp, go, java, php, ruby">
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI, typescript, csharp, go, java, php, ruby">
+2 −2 lines
Recorded here 23 Sep 2026 22:37 UTC
api
build-with-claude/mid-conversation-effort-example
±changed
+8−8
apichanged
build-with-claude/mid-conversation-effort-example
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI">
<CodeGroup>
<CodeGroup exclude="shell:cURL, shell:CLI">
<CodeGroup>
+8 −8 lines
Recorded here 23 Sep 2026 22:37 UTC
api
agents-and-tools/tool-use/tool-runner
±changed
+54−42
apichanged
agents-and-tools/tool-use/tool-runner
The tool runner is in beta and available in the [Python SDK](https://github.com/anthropics/anthropic-sdk-python/blob/main/tools.md), [TypeScript SDK](https://github.com/anthropic
The tool runner is in beta and available in the [Python SDK](https://github.com/anthropics/anthropic-sdk-python/blob/main/tools.md), [TypeScript SDK](https://github.com/anthropic
Define each tool as a class implementing `Supplier<String>`. Annotate the class with `@JsonClassDescription` for the tool description, and each public field with `@JsonProperty
Define each tool as a `BetaRunnableTool` that pairs an input class with a function that runs when Claude calls the tool. Annotate the input class with `@JsonClassDescription` f
+54 −42 lines
Recorded here 23 Sep 2026 22:37 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+115−113
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
| Your situation | Do this
| ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------
| Any workload, any model | Turn on prompt caching and trim unneeded tokens; both are free
| A person waits between turns | Use the 1-hour cache duration once about 1 turn in 20 follows a pause between 5 minutes and an hour and few gaps run over an ho
| Costs are too high; quality is fine | Sweep effort down on your current model
+115 −113 lines
Recorded here 23 Sep 2026 22:37 UTC
claude-docs
claude-tag/admins/connections/custom
±changed
+2−0
claude-docschanged
claude-tag/admins/connections/custom
<Note>The **MCP Connector** type signs in to a connector from your organization's connector library. If you register a new connector from this form with **Add custom connector…**,
+2 −0 lines
Upstream edited 23 Sep 2026 21:24 UTC Recorded here 23 Sep 2026 21:37 UTC
claude-docs
claude-tag/admins/customize
±changed
+6−4
claude-docschanged
claude-tag/admins/customize
Claude Tag's model lists come from the models your organization makes available for Claude Code, set in the Claude admin console, leaving out any that Claude Tag doesn't support. A
On the Team plan, Claude Tag doesn't apply the [`availableModels` allowlist](https://code.claude.com/docs/en/model-config#restrict-model-selection) from your Claude Code [server-ma
* **Model lists in Slack.** The models Claude offers when someone asks it to switch, and the model selector for direct messages, show only allowed models. Claude declines a request
* **Configured defaults.** If your organization also enforces the policy on defaults and a workspace or channel's **Default model** isn't allowed by your organization's Claude Code
* **Where the allowlist doesn't apply**: Claude offers your organization's full Claude Tag model list, both when someone asks it to switch and in the model selector for direct mess
+6 −4 lines
Upstream edited 23 Sep 2026 21:24 UTC Recorded here 23 Sep 2026 21:37 UTC
claude-docs
claude-tag/admins/restrict-access
±changed
+1−1
claude-docschanged
claude-tag/admins/restrict-access
While a guest is present, Claude replies only to mentions and to threads it's already part of. It doesn't act on other messages in the channel on its own, even where [**Respond aut
The channel's [**Respond automatically**](/docs/claude-tag/users/when-claude-responds#turn-automatic-replies-on-or-off) setting works the same while a guest is present, and it's on
+1 −1 lines
Upstream edited 23 Sep 2026 21:21 UTC Recorded here 23 Sep 2026 21:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.