One read of Claude Developer Platformapi-20261021T193714Z

This capture is too large to show at once. Changes 226-242 of 242 are below, significant first; the rest are on the following screens.

managed-agents/cloud-sandboxes-reference Changed · +1 / -1 lines

from line 20

2020| -------- | --------------------------- | -------------------- |

2121| Python | 3.10, 3.11, 3.12, and 3.13 | pip, uv, poetry |

2222| Node.js | 20, 21, and 22 (default) | npm, yarn, pnpm, bun |

23| Go | 1.24 (default) and 1.25 | go modules |

23| Go | 1.24 (default) and 1.25 | Go modules |

2424| Rust | Stable toolchain (rustup) | cargo |

2525| Java | OpenJDK 21 | maven, gradle |

2626| Ruby | 3.1, 3.2, and 3.3 (default) | bundler, gem |

managed-agents/github Changed · +1 / -1 lines

from line 384

384384| `mount_path` (java, php: `mountPath`; csharp, go: `MountPath`) | Optional. The directory under `/workspace` to clone the repository into. Defaults to `/workspace/<repo-name>`. |

385385| `checkout` (csharp, go: `Checkout`) | Optional. A branch (`{"type": "branch", "name": "main"}`) or commit (`{"type": "commit", "sha": "..."}`) to check out. Defaults to the repository's default branch. |

386386 

387Mounting a repository also loads any skills stored in its root `.claude/skills` directory. Skills are discovered once per session, from the repository state checked out at session start. See [Load skills from a GitHub repository](https://platform.claude.com/docs/en/managed-agents/skills#load-skills-from-a-github-repository).

387Mounting a repository also loads any skills stored in its root `.claude/skills` directory. Skills are discovered once for each session, from the repository state checked out at session start. See [Load skills from a GitHub repository](https://platform.claude.com/docs/en/managed-agents/skills#load-skills-from-a-github-repository).

388388 

389389## Token permissions

390390 

managed-agents/overview Changed · +1 / -1 lines

from line 68

6868 </Step>

6969 

7070 <Step title="Steer or interrupt">

71 Send additional user events to guide the agent mid-execution, or interrupt it to change direction.

71 Send additional user events to guide the agent while it runs, or interrupt it to change direction.

7272 </Step>

7373</Steps>

7474 

managed-agents/quickstart Changed · +1 / -1 lines

from line 951

951951 </Card>

952952 

953953 <Card title="Session event stream" icon="lightning" href="https://platform.claude.com/docs/en/managed-agents/events-and-streaming">

954 Handle events and steer the agent mid-execution

954 Handle events and steer the agent while it runs

955955 </Card>

956956 

957957 <Card title="Scheduled deployments" icon="arrows-clockwise" href="https://platform.claude.com/docs/en/managed-agents/scheduled-deployments">

managed-agents/secure-deployment-risks Changed · +1 / -1 lines

from line 16

1616 

1717Hidden instructions in content that an agent reads can steer the agent. This is called [prompt injection](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks). Claude is inherently resilient to it, but model behavior is not a security control. The settings in [Secure your Managed Agents deployment](https://platform.claude.com/docs/en/managed-agents/secure-deployment) limit the effect if an attempt succeeds.

1818 

19Claude can also take a step you did not expect while it keeps working to finish the task you gave it. For example, it might use a tool or credential it can reach to get past an obstacle. The same settings limit what such a step can reach, and an [offline reviewer](https://platform.claude.com/docs/en/managed-agents/secure-deployment-monitoring#optionally-have-an-offline-reviewer-read-every-transcript) can flag it afterward.

19Claude can also take a step you did not expect while it keeps working to complete the task you gave it. For example, it might use a tool or credential it can reach to get past an obstacle. The same settings limit what such a step can reach, and an [offline reviewer](https://platform.claude.com/docs/en/managed-agents/secure-deployment-monitoring#optionally-have-an-offline-reviewer-read-every-transcript) can flag it afterward.

2020 

2121| What can go wrong | Example | Controls |

2222| ---------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

managed-agents/self-hosted-sandboxes-memory Changed · +2 / -2 lines

from line 39

3939 

4040### Isolate sessions that share a store

4141 

42Two sessions cannot mount the same store on one host at the same time, because both need the same path. If your sessions attach the same store, run one session per filesystem. Giving each session [its own sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-workers#run-one-sandbox-per-session) satisfies this rule.

42Two sessions cannot mount the same store on one host at the same time, because both need the same path. If your sessions attach the same store, run one session for each filesystem. Giving each session [its own sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-workers#run-one-sandbox-per-session) satisfies this rule.

4343 

4444## How the worker handles memory

4545 

from line 50

50503. **Reconciles changes after tool calls,** at most once per sync interval (15 seconds by default). Memories that changed in the store are written to disk, and files the agent changed are uploaded to the store.

51514. **Runs a final sync when the session ends.** It flushes any uploads still pending for up to 30 seconds, then removes the directories it created.

5252 

53The memory store on Anthropic's side remains the source of truth. [Memory versions](https://platform.claude.com/docs/en/managed-agents/memory#audit-memory-changes), redaction, and viewing or editing memories in the Console work as they do for cloud sessions. The agent's memory reads and writes appear in the [event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming) as ordinary tool events.

53The memory store on Anthropic's side remains the source of truth. [Memory versions](https://platform.claude.com/docs/en/managed-agents/memory#audit-memory-changes), redaction, and viewing or editing memories in the Claude Console work as they do for cloud sessions. The agent's memory reads and writes appear in the [event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming) as ordinary tool events.

5454 

5555Because each worker syncs on an interval, a change written in one session becomes visible to another running session only after both have synced. That is typically well under a minute at the default interval. Sessions on cloud sandboxes see each other's changes almost immediately.

5656 

managed-agents/self-hosted-sandboxes-reference Changed · +1 / -1 lines

from line 133

133133| Option | Description |

134134| ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

135135| `drain` (go: `Drain`) | Whether to stop polling once the queue is empty rather than waiting for new work. |

136| `block_ms` (typescript: `blockMs`; go: `BlockMs`) | How long each poll waits for work to arrive before returning, in milliseconds. Must be between 1 and 999; the helper re-polls automatically. Pass `null` (python: `None`; go: `param.Null[int64]()`) for a non-blocking check. Defaults to a 999 ms long-poll. |

136| `block_ms` (typescript: `blockMs`; go: `BlockMs`) | How long each poll waits for work to arrive before returning, in milliseconds. Must be between 1 and 999; the helper re-polls automatically. Pass `null` (python: `None`; go: `param.Null[int64]()`) for a non-blocking check. Defaults to a 999ms long-poll. |

137137| `reclaim_older_than_ms` (typescript: `reclaimOlderThanMs`; go: `ReclaimOlderThanMs`) | Re-claims work items that were claimed but never acknowledged within this many milliseconds. |

138138| `auto_stop` (typescript: `autoStop`; go: `AutoStop`) | Whether to post a stop signal for each work item once your loop body finishes with it. Set it to `false` (python: `False`; go: `param.NewOpt(false)`) when whatever runs the work item posts the stop itself. `handle_item()` (typescript: `handleItem()`; go: `HandleItem()`) does, and so does a sandbox you launch that owns the stop call. |

139139 

managed-agents/self-hosted-sandboxes-security Changed · +2 / -2 lines

from line 19

1919* **Service key storage and rotation.** The environment service key (`ANTHROPIC_ENVIRONMENT_KEY`) authorizes polling your environment's work queue and submitting results back to sessions. Store it in a secrets manager, not in environment files or sandbox images. Rotate it immediately if you suspect exposure.

2020* **Isolating untrusted workloads.** The environment service key is scoped to one environment's work queue. If you run untrusted code inside your sandbox, consider provisioning a separate workspace and environment for each trust boundary. This limits each key to a single user's sessions instead of a shared pool.

2121* **Per-session credentials.** Each work item your worker claims can carry a per-session `secret` (csharp, go: `Secret`), which the worker uses in place of the environment service key. Access to [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) requires the `secret` (csharp, go: `Secret`): the memory store endpoints reject the environment key (see [Forward the work item's secret](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-workers#forward-the-work-items-secret)). Pass the `secret` (csharp, go: `Secret`) only into the sandbox that serves that session, keep it out of images and shared volumes, and never log it.

22* **Tool-execution blast radius.** Tools run inside your sandbox with whatever permissions your process has. Apply least privilege to the process user and mount only the directories your tools require.

22* **Tool permissions.** Tools run inside your sandbox with whatever permissions your process has. Apply least privilege to the process user and mount only the directories your tools require.

2323* **Log retention and session content.** Conversation content and tool outputs pass through your worker and stay in your environment. You are responsible for retaining, redacting, or deleting that data in compliance with your own policies. Anthropic has no visibility into what your worker does with session content once delivered.

24* **Memory store contents.** [Memory stores](https://platform.claude.com/docs/en/managed-agents/memory) remain hosted by Anthropic, including their version history. When a session attaches one, the worker keeps a working copy under `/mnt/memory/` in your sandbox for the session's duration and syncs changes back. The worker deletes that copy when the session ends, but a worker that exits without running its teardown leaves it behind. Cleaning up leftover copies, the permissions on that path, and isolation between sessions that share a filesystem are your responsibility.

24* **Memory store contents.** [Memory stores](https://platform.claude.com/docs/en/managed-agents/memory) remain hosted by Anthropic, including their version history. When a session attaches one, the worker keeps a working copy under `/mnt/memory/` in your sandbox for the session's duration and syncs changes back. The worker deletes that copy when the session ends, but a worker that exits without running its teardown leaves it behind. Cleanup of leftover copies, the permissions on that path, and isolation between sessions that share a filesystem are your responsibility.

2525* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write under its directory, nothing there syncs back, and the memory store endpoints reject writes to it made with the session's `secret` (csharp, go: `Secret`). Other processes in the sandbox can still change the local copy: commands the agent runs through the `bash` tool, and [custom tools](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-custom-tools) or MCP servers you serve from the sandbox, which run with the worker's permissions. Later tool calls in that session read the changed copy until that memory next changes in the store. If the agent must not be able to alter even its local view of such a store, disable the `bash` tool for that agent and give it no custom tool that writes to the sandbox's filesystem.

2626 

2727## What Anthropic cannot do for you

managed-agents/session-operations Changed · +2 / -2 lines

from line 21

2121| `idle` | Agent is waiting for input, including user messages or tool confirmations. Sessions created without `initial_events` (java, php: `initialEvents`; csharp, go: `InitialEvents`) start in `idle`. A session can be `idle` while a [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#while-a-run-is-open) is still open, so `idle` alone doesn't mean that the work is done. See [Know when the work is done](https://platform.claude.com/docs/en/managed-agents/workflow-runs#know-when-the-work-is-done). |

2222| `running` | Agent is actively executing. |

2323| `rescheduling` | Transient error occurred, retrying automatically. |

24| `terminated` | Session has ended, either because of an unrecoverable error or because it was archived. A session that finishes its work goes `idle`, not `terminated`. |

24| `terminated` | Session has ended, either because of an unrecoverable error or because it was archived. A session that completes its work goes `idle`, not `terminated`. |

2525 

2626## Updating the agent configuration

2727 

28You can update a session's `agent.tools` (csharp, go: `Agent.Tools`) and `agent.mcp_servers` (java, php: `agent.mcpServers`; csharp: `Agent.McpServers`; go: `Agent.MCPServers`), including permission policies and per-tool web settings such as [domain filters](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions#change-the-lists-mid-session), mid-session without creating a new agent version. Updates are session-local and do not propagate back to the underlying agent. Updated `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) and `blocked_domains` (java, php: `blockedDomains`; csharp, go: `BlockedDomains`) apply to the rest of the session.

28You can update a session's `agent.tools` (csharp, go: `Agent.Tools`) and `agent.mcp_servers` (java, php: `agent.mcpServers`; csharp: `Agent.McpServers`; go: `Agent.MCPServers`), including permission policies and per-tool web settings such as [domain filters](https://platform.claude.com/docs/en/managed-agents/tools-web-restrictions#change-the-lists-mid-session), mid-session without creating a new agent version. Updates are session-local and do not apply to the underlying agent. Updated `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) and `blocked_domains` (java, php: `blockedDomains`; csharp, go: `BlockedDomains`) apply to the rest of the session.

2929 

3030Only the agent's `tools` (csharp, go: `Tools`) and `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`) can change after a session is created. To run a session with `model` (csharp, go: `Model`), `system` (csharp, go: `System`; ruby: `system_`), or `skills` (csharp, go: `Skills`) values other than the agent's, use [agent configuration overrides](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session) when you create the session. The agent's model configuration, including its [`inference_geo`](https://platform.claude.com/docs/en/manage-claude/data-residency) pin, also can't change mid-session: set the pin when you save the agent, or set or clear it for a single session with a `model` (csharp, go: `Model`) override when you create it. The agent's configured `system` (csharp, go: `System`; ruby: `system_`) field is fixed for the session's lifetime. On models that support it, you can still append system-level guidance mid-session by sending a [`system.message` event](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#send-system-messages).

3131 

managed-agents/session-threads Changed · +1 / -1 lines

from line 16

1616 

1717The **session-level event stream** (`/v1/sessions/{session_id}/events/stream`) is considered the **primary thread**, containing a condensed view of all activity across all threads. You don't see the full activity from [subagents](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration#delegate-to-subagents), but you do see the start and end of their work, and blocking events such as tool permission requests.

1818 

19**Session threads** are where you drill into a specific agent's activity.

19**Session threads** are where you examine a specific agent's activity.

2020 

2121The session `status` (csharp, go: `Status`) is an aggregation of all agent activity; if at least one thread is `running`, then the overall session status is `running` as well. A [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs) that's running can keep the session `running` too, even while none of its threads is working. When no thread is working and a thread waits on your client, the session is `idle`; see [Know when the work is done](https://platform.claude.com/docs/en/managed-agents/workflow-runs#know-when-the-work-is-done).

2222 

models/haiku-5-5/overview Changed · +2 / -2 lines

from line 1

11---

22title: Claude Haiku 5.5

33url: https://platform.claude.com/docs/en/models/haiku-5-5/overview

4description: "Claude Haiku 5.5 at a glance: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

4description: "An overview of Claude Haiku 5.5: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

55---

66 

77**Latest.** Released October 7, 2026.

from line 16

1616 

1717## Overview

1818 

19Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It supports adaptive thinking with the effort parameter, a 1M token context window, and up to 128k output tokens. It uses the same newer tokenizer as Claude 4.7 and later models, so the same text counts as approximately 30% more tokens than on Claude Haiku 4.5. Its thinking blocks work only in the account that produced them, or in an account linked to it.

19Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It supports adaptive thinking with the effort parameter, a 1M token context window, and up to 128k output tokens. It uses the same newer tokenizer as Claude 4.7 and later models, so the same text counts as approximately 30 percent more tokens than on Claude Haiku 4.5. Its thinking blocks work only in the account that produced them, or in an account linked to it.

2020 

2121For code changes, see the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide). For model IDs, pricing, and limits, see the [Claude Haiku 5.5 overview](https://platform.claude.com/docs/en/models/haiku-5-5/overview). For prompting guidance, see [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).

2222 

models/mythos-5-1/overview Changed · +1 / -1 lines

from line 1

11---

22title: Claude Mythos 5.1

33url: https://platform.claude.com/docs/en/models/mythos-5-1/overview

4description: "Claude Mythos 5.1 at a glance: the same model as Claude Fable 5.1, available only to organizations verified through Anthropic's verification programs. Model IDs, specifications, pricing, and how to request access."

4description: Claude Mythos 5.1 is the same model as Claude Fable 5.1, available only to organizations verified through Anthropic's verification programs. Model IDs, specifications, pricing, and how to request access.

55---

66 

77**Verification required.** Released September 1, 2026.

models/opus-5-5/overview Changed · +2 / -2 lines

from line 1

11---

22title: Claude Opus 5.5

33url: https://platform.claude.com/docs/en/models/opus-5-5/overview

4description: "Claude Opus 5.5 at a glance: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

4description: "An overview of Claude Opus 5.5: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

55---

66 

77**Latest.** Released September 22, 2026.

from line 100

100100 </Card>

101101 

102102 <Card title="Effort" icon="sliders" href="https://platform.claude.com/docs/en/build-with-claude/effort">

103 The control for thinking depth, latency, and cost. Choose a level per workload.

103 The control for thinking depth, latency, and cost. Choose a level for each workload.

104104 </Card>

105105 

106106 <Card title="Adaptive thinking" icon="brain" href="https://platform.claude.com/docs/en/build-with-claude/thinking">

models/sonnet-5-5/overview Changed · +2 / -2 lines

from line 1

11---

22title: Claude Sonnet 5.5

33url: https://platform.claude.com/docs/en/models/sonnet-5-5/overview

4description: "Claude Sonnet 5.5 at a glance: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

4description: "An overview of Claude Sonnet 5.5: what it's for, model IDs on every platform, context window, output limits, pricing, availability, and the guides and resources for building with it."

55---

66 

77**Latest.** Released September 28, 2026.

from line 109

109109 </Card>

110110 

111111 <Card title="Effort" icon="sliders" href="https://platform.claude.com/docs/en/build-with-claude/effort">

112 The control for thinking depth, latency, and cost. Choose a level per workload.

112 The control for thinking depth, latency, and cost. Choose a level for each workload.

113113 </Card>

114114 

115115 <Card title="Adaptive thinking" icon="brain" href="https://platform.claude.com/docs/en/build-with-claude/thinking">

models/sonnet-5/overview Changed · +2 / -2 lines

from line 104

104104 </Card>

105105 

106106 <Card title="Effort" icon="sliders" href="https://platform.claude.com/docs/en/build-with-claude/effort">

107 Effort defaults to `high` on the Claude API and Claude Code. Choose a level per workload.

107 Effort defaults to `high` on the Claude API and Claude Code. Choose a level for each workload.

108108 </Card>

109109 

110110 <Card title="Context windows" icon="stack" href="https://platform.claude.com/docs/en/build-with-claude/context-windows">

111 1M tokens by default. How the window is counted and managed.

111 Holds 1M tokens by default. How the window is counted and managed.

112112 </Card>

113113</CardGroup>

114114 

release-notes/overview Changed · +2 / -0 lines

from line 18

1818* We've released new versions of the [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) and the [`ant` CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) that send API version `2026-10-21` by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and `ant` CLI 2.0.0. See [Switch to 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).

1919* The new SDK and CLI versions also have breaking changes that don't depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See [SDK and CLI changes](https://platform.claude.com/docs/en/api/migration-2026-10-21#sdk-changes).

2020 

21- We've added the `enforcement_status` and `enforcement_actions` fields to [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can see whether Anthropic has restricted or banned one of your end customers. To find the profiles that have an open restriction or ban, [list your profiles](https://platform.claude.com/docs/en/api/user_profiles/list) with the new `enforcement_status[]` filter. See [Check whether Anthropic has restricted or banned a profile](https://platform.claude.com/docs/en/manage-claude/user-profiles#check-whether-anthropic-has-restricted-or-banned-a-profile).

22 

2123### October 20, 2026

2224 

2325* [Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks) are out of beta for Claude Enterprise organizations.

resources/overview Changed · +1 / -1 lines

from line 82

8282 </Card>

8383 

8484 <Card title="Claude 3 Model Card" icon="file" href="https://www.anthropic.com/claude-3-model-card">

85 Detailed documentation of Claude 3 models including latest 3.5 addendum.

85 Detailed documentation of Claude 3 models including the latest 3.5 addendum.

8686 </Card>

8787 

8888 <Card title="Claude 2 Model Card" icon="file" href="https://www.anthropic.com/claude-2-model-card">