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
774 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
148 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
82 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
10,119 of the ledger's changes in api. Show every change
ReadSourcePageWhatLines
25 Sep 2026
315 pages
+42702 −44224 lines
api
api/beta/deployment_runs/list
±changed
+5−5
apichanged
api/beta/deployment_runs/list
A resolved agent reference with a concrete version.
Snapshot of the agent at fire time. Always fully resolved — deployments pin agent + version.
A timestamp in RFC 3339 format
Time this run record was persisted.
Why the run failed to create a session. The type identifies the failure; message is human-readable detail.
+5 −5 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/deployment_runs
±changed
+17−17
apichanged
api/beta/deployment_runs
A resolved agent reference with a concrete version.
Snapshot of the agent at fire time. Always fully resolved — deployments pin agent + version.
A timestamp in RFC 3339 format
Time this run record was persisted.
Why the run failed to create a session. The type identifies the failure; message is human-readable detail.
+17 −17 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/versions/list
±changed
+11−11
apichanged
api/beta/agents/versions/list
When the agent was archived. Null if not archived.
format: date-time
- `created_at: string`
+11 −11 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/versions
±changed
+11−11
apichanged
api/beta/agents/versions
When the agent was archived. Null if not archived.
format: date-time
- `created_at: string`
+11 −11 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/update
±changed
+742−733
apichanged
api/beta/agents/update
- `BetaManagedAgentsModel = "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more or string`
- `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
- `string`
- `BetaManagedAgentsModelConfigParams object`
+742 −733 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/retrieve
±changed
+11−11
apichanged
api/beta/agents/retrieve
When the agent was archived. Null if not archived.
format: date-time
- `created_at: string`
+11 −11 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/list
±changed
+11−11
apichanged
api/beta/agents/list
When the agent was archived. Null if not archived.
format: date-time
- `created_at: string`
+11 −11 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/create
±changed
+764−755
apichanged
api/beta/agents/create
- `BetaManagedAgentsModel = "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more or string`
- `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
- `string`
- `BetaManagedAgentsModelConfigParams object`
+764 −755 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents/archive
±changed
+11−11
apichanged
api/beta/agents/archive
When the agent was archived. Null if not archived.
format: date-time
- `created_at: string`
+11 −11 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta/agents
±changed
+4321−4303
apichanged
api/beta/agents
No line of the body moved in this read.
+4321 −4303 lines
Recorded here 25 Sep 2026 15:37 UTC
api
api/beta
±changed
+5515−5691
apichanged
api/beta
No line of the body moved in this read.
+5515 −5691 lines
Recorded here 25 Sep 2026 15:37 UTC
api
agents-and-tools/mcp-tunnels/reference
±changed
+1−1
apichanged
agents-and-tools/mcp-tunnels/reference
The previous Admin API surface at `/v1/organizations/tunnels` (beta header `mcp-tunnels-2026-05-19`, scope `org:manage_tunnels`) continues to work during a migration window and r
The previous Admin API surface at `/v1/organizations/tunnels` (beta header `mcp-tunnels-2026-05-19`, scope `org:manage_tunnels`) continues to work during a migration window and r
+1 −1 lines
Recorded here 25 Sep 2026 15:37 UTC
api
about-claude/use-case-guides/ticket-routing
±changed
+1−1
apichanged
about-claude/use-case-guides/ticket-routing
Many customers have found `claude-haiku-4-5-20251001` an ideal model for ticket routing, as it is the fastest and most cost-effective model in the Claude 4 family while still deliv
Many customers have found `claude-haiku-4-5-20251001` an ideal model for ticket routing, as it is the fastest and most cost-effective model in the Claude 4 family while still deliv
+1 −1 lines
Recorded here 25 Sep 2026 15:37 UTC
api
about-claude/models/choosing-a-model
±changed
+1−1
apichanged
about-claude/models/choosing-a-model
**Claude Fable 5.1** (`claude-fable-5-1`) is Anthropic's most capable widely released model. It extends Claude Fable 5 with stronger long-running agentic coding, knowledge work, an
**Claude Fable 5.1** (`claude-fable-5-1`) is Anthropic's most capable model open to all customers. It extends Claude Fable 5 with stronger long-running agentic coding, knowledge wo
+1 −1 lines
Recorded here 25 Sep 2026 15:37 UTC
api
about-claude/glossary
±changed
+1−1
apichanged
about-claude/glossary
Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. Like a USB-C port for AI applications, MCP provides a unified way to co
Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. Like a USB-C port for AI applications, MCP provides a unified way to co
+1 −1 lines
Recorded here 25 Sep 2026 15:37 UTC
24 Sep 2026
83 pages
+11972 −6344 lines
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+3−1
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
Usage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see
Usage metrics are still provided in the response, even when the response is refused.
When a refusal arrives before Claude generates any output, you are not billed for the request on the Claude API, and the usage counts in that response are informational only. Whe
+3 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
release-notes/overview
±changed
+0−4
apichanged
release-notes/overview
### September 24, 2026
* We're expanding which refusals are billed to include refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`
+0 −4 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+1−1
apichanged
models/opus-5-5/whats-new-opus-5-5
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5/migration-guide
±changed
+1−1
apichanged
models/fable-5/migration-guide
A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category
You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+1−1
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale.
You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-c
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safegua
* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fa
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
build-with-claude/refusals-and-fallback
±changed
+9−17
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
+9 −17 lines
Recorded here 24 Sep 2026 22:07 UTC
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+1−3
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
Usage metrics are still provided in the response, even when the response is refused.
When a refusal arrives before Claude generates any output, you are not billed for the request on the Claude API, and the usage counts in that response are informational only. Whe
Usage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see
+1 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
release-notes/overview
±changed
+13−0
apichanged
release-notes/overview
### September 24, 2026
* We're expanding which refusals are billed to include refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`
### September 23, 2026
+13 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+1−1
apichanged
models/opus-5-5/whats-new-opus-5-5
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/opus-5-5/migration-guide
±changed
+2−2
apichanged
models/opus-5-5/migration-guide
2. **Consider mid-conversation tool changes (beta):** Mid-conversation tool changes (beta header `mid-conversation-tool-changes-2026-07-01`) are available on the Claude API, Amazon
2. **Consider mid-conversation tool changes (beta):** Mid-conversation tool changes let you add or remove tools between turns of a conversation without invalidating [prompt cache](
5. **Migrate to output\_config.format:** If using structured outputs, update `output_format={...}` to `output_config={"format": {...}}`. The API still accepts the deprecated `outpu
5. **Migrate to output\_config.format:** If using structured outputs, update `output_format={...}` to `output_config={"format": {...}}`. The `output_format` parameter is deprecated
+2 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5/migration-guide
±changed
+1−1
apichanged
models/fable-5/migration-guide
You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed
A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+1−1
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-c
A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale.
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fa
* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safegua
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5-1/migration-guide
±changed
+1−1
apichanged
models/fable-5-1/migration-guide
2. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://p
2. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://p
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/webhooks
±changed
+1−1
apichanged
managed-agents/webhooks
Every delivery carries the `webhook-id`, `webhook-timestamp`, and `webhook-signature` headers. Use the SDK's `unwrap()` helper to verify the signature and parse the event in one st
Every delivery carries the `webhook-id`, `webhook-timestamp`, and `webhook-signature` headers. Use the SDK's `unwrap()` (csharp, go: `Unwrap()`) helper to verify the signature and
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/vaults
±changed
+1−1
apichanged
managed-agents/vaults
To diagnose why a refresh failed, call `POST /v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` (or `client.beta.vaults.credentials.mcp_oauth_validate(...)` in t
To diagnose why a refresh failed, call `POST /v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` (or `client.beta.vaults.credentials.mcp_oauth_validate(...)` (typ
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/sessions
±changed
+1−2
apichanged
managed-agents/sessions
* **Set the field to a value:** The value replaces the agent's value in full. Overrides never merge with the agent's configuration, so a `tools` override must list every tool the s
* An `effort` level inside a per-session `model` override isn't applied, and because the override replaces the agent's `model` object in full, the agent's own `effort` isn't carr
* **Set the field to a value:** The value replaces the agent's value in full. Overrides never merge with the agent's configuration, so a `tools` override must list every tool the s
+1 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/self-hosted-sandboxes
±changed
+27−27
apichanged
managed-agents/self-hosted-sandboxes
When you hand a claimed work item to `handle_item()` yourself, as this handler does, pass the work item's `secret` along as `work_secret` (`workSecret` in TypeScript, `Work
When you hand a claimed work item to `handle_item()` (typescript: `handleItem()`; go: `HandleItem()`) yourself, as this handler does, pass the work item's `secret` along as
* `.run()`: runs indefinitely, picking up sessions as they arrive.
* `.handle_item()`: handles a single claimed work item and exits. Pass the work, session, and environment identifiers explicitly, or let it read the `ANTHROPIC_*` variables that
* `memory_sync_interval` (`memorySyncIntervalMs` in TypeScript, `MemorySyncInterval` in Go) and `memory_sync_deletions` (`memorySyncDeletions`, `MemorySyncDeletions`): how often
+27 −27 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/migration
±changed
+10−10
apichanged
managed-agents/migration
| Agent SDK | Managed Agents
| --------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------
| `ClaudeAgentOptions(...)` constructed per run | `client.beta.agents.create(...)` once; the Agent is persisted and versioned server-side. See [Agent setup](https
| `async with ClaudeSDKClient(...)` or `query(...)` | `client.beta.sessions.create(...)` then send and receive [events](https://platform.claude.com/docs/en/managed-ag
| `@tool`-decorated functions dispatched automatically by the SDK | Declare as `{"type": "custom", ...}` on the Agent; your client handles `agent.custom_tool_use` events and replie
+10 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/agent-setup
±changed
+1−1
apichanged
managed-agents/agent-setup
You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. An `effort` level set inside a per-session `model` ov
You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. A `model` override replaces the agent's `model` objec
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
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
Nothing on this page matches that. Press Enter to search every page of the ledger.