One read of Claude Developer Platformapi-20261104T020710Z
159 pages moved out of 847 read.
Pages moved
159
significant first
Pages read
847
in this capture
Captured
02:07 UTC
Corpus hash
61cf340e1136
corpus-hash
What this read moved
151-159 of 159, page 7 of 7This capture is too large to show at once. Changes 151-159 of 159 are below, significant first; the rest are on the following screens.
managed-agents/self-hosted-sandboxes-security Changed · +2 / -2 lines
from line 30
3030 - claude-sonnet-4-5-20250929
3131---
3232
33Anthropic secures the control plane across all environments: session and work queue integrity, multitenant isolation, and agent-context minimization. When you self-host sandboxes, the following responsibilities fall to you.
33In every environment, Anthropic secures the parts it runs: session and work queue integrity, multitenant isolation, and agent-context minimization. When you self-host sandboxes, the following responsibilities fall to you.
3434
3535## What you own
3636
from line 47
4747## What Anthropic cannot do for you
4848
4949* **Know that your key leaked.** Anthropic can detect anomalous usage patterns, but cannot know your key was compromised. If you suspect `ANTHROPIC_ENVIRONMENT_KEY` leaked, revoke it and generate a replacement immediately. Revocation is validated on every request, so it takes effect on the worker’s next call.
50* **Verify your worker build.** Anthropic does not inspect your sandbox image or runtime. A supply-chain compromise in your image is not detectable from the control plane.
50* **Verify your worker build.** Anthropic does not inspect your sandbox image or runtime. A supply-chain compromise in your image is not detectable from Anthropic’s side.
5151* **Isolate tools inside your sandbox.** Anthropic’s security boundary stops at the sandbox. How you isolate individual tool executions from each other inside that boundary is entirely your responsibility.
5252* **Enforce data retention in your environment.** Once session content reaches your worker, it is outside Anthropic’s data lifecycle controls.
5353
managed-agents/self-hosted-sandboxes-workers Changed · +1 / -1 lines
from line 831
831831 ```bash cURL
832832 curl -sS --fail-with-body https://api.anthropic.com/v1/sessions \
833833 -H "x-api-key: $ANTHROPIC_API_KEY" \
834 -H "anthropic-version: 2023-06-01" \
834 -H "anthropic-version: 2026-10-21" \
835835 -H "anthropic-beta: managed-agents-2026-04-01" \
836836 -H "content-type: application/json" \
837837 -d '{
managed-agents/session-observability Changed · +1 / -1 lines
from line 122
122122
123123Session usage counts toward your organization’s totals on the [Usage](https://platform.claude.com/usage) page (`platform.claude.com/usage`) and the [Cost](https://platform.claude.com/cost) page (`platform.claude.com/cost`) in the Claude Console. To see token usage by agent, set **Group by** to **Agent** on the **Usage** page.
124124
125Session usage also appears in the [usage report](https://platform.claude.com/docs/en/api/beta/organization/usage_report/retrieve_messages) from the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api). To see which account it’s reported under, group the report by one of these fields:
125To see session usage by agent or by session, use the [Usage and Cost Analytics API](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api) and group by `agent_id` or `session_id`. Session usage also appears in the [usage report](https://platform.claude.com/docs/en/api/beta/organization/usage_report/retrieve_messages) from the legacy [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api). To see which account it’s reported under, group that report by one of these fields:
126126
127127* **`account_id`:** The member who started the session. This covers sessions started in the Console or with a [personal key](https://platform.claude.com/docs/en/manage-claude/authentication#key-types) scoped to a single workspace.
128128* **`service_account_id`:** An Anthropic-managed service account (`svac_...`). This covers sessions started with a workspace key or by a [deployment](https://platform.claude.com/docs/en/managed-agents/scheduled-deployments). For this usage, `api_key_id` and `account_id` are `null`.
managed-agents/tools Changed · +2 / -2 lines
from line 67
6767 ```bash cURL
6868 curl -fsSL https://api.anthropic.com/v1/agents \
6969 -H "x-api-key: $ANTHROPIC_API_KEY" \
70 -H "anthropic-version: 2023-06-01" \
70 -H "anthropic-version: 2026-10-21" \
7171 -H "anthropic-beta: managed-agents-2026-04-01" \
7272 -H "content-type: application/json" \
7373 -d '{
from line 275
275275 ```bash cURL
276276 curl -fsSL https://api.anthropic.com/v1/agents \
277277 -H "x-api-key: $ANTHROPIC_API_KEY" \
278 -H "anthropic-version: 2023-06-01" \
278 -H "anthropic-version: 2026-10-21" \
279279 -H "anthropic-beta: managed-agents-2026-04-01" \
280280 -H "content-type: application/json" \
281281 -d '{
managed-agents/tools-web-restrictions Changed · +1 / -1 lines
from line 59
5959 ```bash cURL
6060 curl -fsSL https://api.anthropic.com/v1/agents \
6161 -H "x-api-key: $ANTHROPIC_API_KEY" \
62 -H "anthropic-version: 2023-06-01" \
62 -H "anthropic-version: 2026-10-21" \
6363 -H "anthropic-beta: managed-agents-2026-04-01" \
6464 -H "content-type: application/json" \
6565 -d '{
models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines
from line 95
9595 # Effort-only system message: the new level takes effect from the next user turn.
9696 curl https://api.anthropic.com/v1/messages \
9797 -H "x-api-key: $ANTHROPIC_API_KEY" \
98 -H "anthropic-version: 2023-06-01" \
98 -H "anthropic-version: 2026-10-21" \
9999 -H "anthropic-beta: mid-conversation-output-config-2026-07-01" \
100100 -H "content-type: application/json" \
101101 -d '{
models/haiku-5-5/migration-guide Changed · +2 / -2 lines
from line 38
3838### Claude Haiku 3.5 or earlier
3939
40401. Replace the Claude Haiku 3.5 or Claude Haiku 3 model ID with the Claude Haiku 5.5 ID for your platform. See [Migrating to Claude Haiku 5.5 from Claude Haiku 3.5 and earlier Haiku models](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#migrating-from-haiku-35).
412. If you use the legacy `code_execution_20250522` tool, move to `code_execution_20250825` or later.
412. If you use the `code_execution_20250522` tool, move to `code_execution_20250825` or later.
42423. If you use the text editor tool, move to `text_editor_20250728`.
43434. Handle the `refusal` and `model_context_window_exceeded` stop reasons.
44445. If your code matches tool call string parameters exactly, allow for trailing newlines.
from line 149
149149From either model, first apply every preceding section, then these changes:
150150
151151* **Model ID:** Replace `claude-3-5-haiku-20241022`, its alias `claude-3-5-haiku-latest`, or `claude-3-haiku-20240307` with `claude-haiku-5-5`. On Claude Models on Google Cloud (Google managed), replace `claude-3-5-haiku@20241022` with `claude-haiku-5-5`. On Amazon Bedrock, use the Claude Haiku 5.5 ID from [Use the Claude Haiku 5.5 model ID](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#use-the-claude-haiku-5-5-model-id).
152* **Code execution:** Claude Haiku 5.5 accepts `code_execution_20250825` and later versions. If you use the legacy Python-only `code_execution_20250522`, move to one of them. See [Upgrade to latest tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version).
152* **Code execution:** Claude Haiku 5.5 accepts `code_execution_20250825` and later versions. If you use the Python-only `code_execution_20250522`, move to one of them. See [Upgrade to latest tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#upgrade-to-latest-tool-version).
153153* **Text editor:** If you use the text editor tool, move to `text_editor_20250728` (tool name `str_replace_based_edit_tool`), which has no `undo_edit` command. See [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool).
154154* **Stop reasons:** Handle `refusal` and `model_context_window_exceeded`. See [Handling stop reasons](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons).
155155* **Trailing newlines:** Claude 4.5 and later models keep trailing newlines in tool call string parameters. If your code matches those strings exactly, allow for them.
release-notes/overview Changed · +1 / -1 lines
from line 84
8484* We’ve lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See [Prompt caching pricing](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching).
8585* We’ve launched **Claude Haiku 5.5** (`claude-haiku-5-5`), our most capable model tuned for high-volume and latency-sensitive work. It has a [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), 128k max output tokens, and [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort). It’s available on the Claude API, [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude on Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What’s new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5).
8686* Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (`budget_tokens`), the sampling parameters `temperature`, `top_p`, and `top_k`, and assistant message prefill can each return a 400 error. `computer_20250124` also returns a 400 error: use the `computer_toolset_20260801` toolset on the Claude API and Google Cloud, or `computer_20251124` on Amazon Bedrock. A request that sends thinking blocks back after a change to `system`, `tools`, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with `thinking` blocks, and their text is omitted unless you set `thinking.display` to `"summarized"`. The same text also counts as more tokens. See the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide) for each change. For model-specific prompting patterns, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).
87* The Python and TypeScript SDKs now include classes, in beta, for the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool). You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).
87* Python SDK 1.12.0 and TypeScript SDK 0.132.0 add classes, in beta, for the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool). You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback. See [Browser and computer use with the SDK toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-sdk).
8888* Claude Max, Ultra, and Team plans now include monthly API credits. To learn how to claim them, see [API credits for Max, Ultra, and Team plans](https://platform.claude.com/docs/en/about-claude/api-credits-for-subscribers).
8989* In Claude Managed Agents, a cloud environment with `limited` networking now also applies its `allowed_hosts` to the `web_search` and `web_fetch` tools. A `web_fetch` call for a URL on a host that `allowed_hosts` does not match returns a `url_not_allowed` error result to the agent. `web_search` omits results from such hosts. When `allowed_hosts` lists no hosts, neither tool returns a page or a search result. `allow_package_managers` and `allow_mcp_servers` add no hosts for these tools. To let the tools reach a host, add it to `allowed_hosts`, which also opens it to the sandbox. `unrestricted` networking and self-hosted environments do not limit these tools. See [Environment networking](https://platform.claude.com/docs/en/managed-agents/environments#networking).
9090* With `limited` networking, creating a session fails with a 400 error when an enabled web tool’s `allowed_domains` has an entry not within `allowed_hosts`. So does a session update that adds such an entry. An `allowed_hosts` entry matches one exact host unless it starts with `*.`, so `docs.example.com` is not within `["example.com"]`. To fix the error, add the host to `allowed_hosts` or remove the entry from `allowed_domains`. See [Restrict web search and web fetch domains](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions).
test-and-evaluate/strengthen-guardrails/reduce-latency Changed · +1 / -1 lines
from line 36
3636 # For time-sensitive applications, use Claude Haiku 5.5 at low effort
3737 curl https://api.anthropic.com/v1/messages \
3838 -H "x-api-key: $ANTHROPIC_API_KEY" \
39 -H "anthropic-version: 2023-06-01" \
39 -H "anthropic-version: 2026-10-21" \
4040 -H "content-type: application/json" \
4141 -d '{
4242 "model": "claude-haiku-5-5",