One read of Claude Code CLIclaude-code-20261102T220701Z
11 pages moved out of 228 read.
Pages moved
11
significant first
Pages read
228
in this capture
Captured
22:07 UTC
Corpus hash
5dd3c4bd166a
corpus-hash
What this read moved
1-11 of 11agent-sdk/typescript Changed · +10 / -2 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 48
4848
4949If your application bundles the Agent SDK together with its own dependencies, import from `@anthropic-ai/claude-agent-sdk/core` instead of the package root. The `/core` entry requires TypeScript Agent SDK v0.3.282 or later, and its types require TypeScript 5.0 or later.
5050
51The `/core` entry exports the same `query()`, `startup()`, `tool()`, `createSdkMcpServer()`, and `resolveSettings()` as the root entry, along with the functions that rename, tag, and delete sessions, `AbortError`, the runtime constants, and every type. It adds no names of its own. To keep the code your application loads small, `/core` leaves out some root exports, including `prewarm()`, the `InMemorySessionStore` class, and the helpers that list, read, fork, import, and summarize sessions. If you need one of them, use the root entry instead.
51To keep the code your application loads small, the `/core` entry leaves out some root exports:
5252
53* **Exported**: the same `query()`, `startup()`, [`prewarm()`](#prewarm), `tool()`, `createSdkMcpServer()`, and `resolveSettings()` as the root entry, along with the functions that rename, tag, and delete sessions, `AbortError`, the runtime constants, and every type. Importing the alpha `prewarm()` from `/core` requires Agent SDK v0.3.314 or later.
54* **Left out**: root exports including the `InMemorySessionStore` class and the helpers that list, read, fork, import, and summarize sessions. If you need one of them, use the root entry instead.
55
5356The root entry inlines its own copies of `zod` and `@modelcontextprotocol/sdk`. The `/core` entry imports them from your `node_modules` at the ranges the Agent SDK's `peerDependencies` declare, so a bundle that already includes them doesn't carry a second copy. Import from either the root or `/core` in a given process, not both: they are separate bundles, and loading both gives you two copies of the Agent SDK's classes and state.
5457
5558## Functions
from line 2001
19982001
19992002* A resume that Claude Code stops because it [can't return the session to its worktree](https://code.claude.com/docs/en/worktrees.md#the-session-resumes-outside-its-worktree), with `worktree_unverified` or `worktree_resume_refused`. That section says which error carries which value.
20002003* A refused [`continue`](#options) of a conversation that a background session holds, with `session_held_by_background`. For a refused [`resume`](#options) of such a conversation, Claude Code writes the result only when the variable is set.
2004* A start that Claude Code refuses because [`failIfUnavailable`](#sandboxsettings) is on and the sandbox can't start, with `sandbox_required_unavailable`.
20012005
2006The `SDKStartupFailureReason` type lists the values `startup_failure_reason` can hold:
2007
20022008```typescript theme={null}
20032009type SDKStartupFailureReason =
20042010 | "org_pin_api_key_conflict"
from line 2025
20192025 | "cli_version_too_old"
20202026 | "bypass_root"
20212027 | "org_config_required_unavailable"
2022 | "org_config_refused";
2028 | "org_config_refused"
2029 | "sandbox_required_unavailable";
20232030```
20242031
20252032Each value names one refusal:
from line 2052
20452052| `bypass_root` | Bypass permissions mode was requested while running as root |
20462053| `org_config_required_unavailable` | The session needs the organization's policies and managed settings before it can start, and they couldn't be loaded, for example because of a network failure or an Anthropic server error. Requires Agent SDK v0.3.293 or later |
20472054| `org_config_refused` | Anthropic refused to provide the organization's policies and managed settings for this sign-in, for example because the sign-in expired or was revoked, or the organization doesn't allow Claude Code for this account. Requires Agent SDK v0.3.293 or later |
2055| `sandbox_required_unavailable` | [`failIfUnavailable`](#sandboxsettings) is on and the sandbox can't start. The text in `errors` ends with `Set sandbox.failIfUnavailable=false to allow unsandboxed execution.` Requires Agent SDK v0.3.314 or later |
20482056
20492057### `SDKSystemMessage`
20502058
from line 4801
47934801
47944802**Tool name:** `ReportFindings`
47954803
4796```typescript theme={null}
4797type ReportFindingsOutput = {
4798 count: number;
4799 level?: "low" | "medium" | "high" | "xhigh" | "max";
4800 findings: Array<{
4801 file: string;
4802 line?: number;
4803 summary: string;
4804 failure_scenario: string;
4805 short_summary?: string;
4806 category?: string;
4807 verdict?: "CONFIRMED" | "PLAUSIBLE";
4808 outcome?: "fixed" | "skipped" | "no_change_needed";
4809 }>;
4810};
4811```
4812
4813Returns the number of findings reported, the `level` value Claude passed, and the findings echoed back for the result body. Requires Claude Code v2.1.196 or later. The echoed `short_summary` field requires Claude Code v2.1.212
4804``
amazon-bedrock Changed · +10 / -2 lines
from line 304
304304
305305When Claude Code starts with Amazon Bedrock configured, it verifies that the models it intends to use are accessible in your account.
306306
307If you have pinned a model version that is older than the current Claude Code default, and your account can invoke the newer version, Claude Code prompts you to update the pin. Accepting writes the new model ID to your [user settings file](https://code.claude.com/docs/en/settings.md) and restarts Claude Code. Declining is remembered until the next default version change. Pins that point to an [application inference profile ARN](#map-each-model-version-to-an-inference-profile) are skipped, since those are managed by your administrator.
307You may have pinned a model version that is older than the current Claude Code default. If your account can invoke the newer version, Claude Code prompts you to update the pin. Accepting writes the new model ID to your [user settings file](https://code.claude.com/docs/en/settings.md) and restarts Claude Code. Declining is remembered until the next default version change.
308308
309Claude Code doesn't check or prompt for these pins:
310
311* A pin in the `env` block of [managed settings](https://code.claude.com/docs/en/managed-settings.md)
312* A pin that points to an [application inference profile ARN](#map-each-model-version-to-an-inference-profile), because your administrator manages it
313
309314If you have not pinned a model and the current default is unavailable in your account, Claude Code falls back for the current session and shows a notice. It tries earlier versions of the default model first and, when the default is an Opus model and no Opus version is available, falls back to the default Sonnet model. The fallback is not persisted. Enable the newer model in your Amazon Bedrock account or [pin a version](#4-pin-model-versions) to make the choice permanent.
310315
311316When you start the session on a specific Sonnet or Opus version, for example with `--model`, `ANTHROPIC_MODEL`, or the [`model` setting](https://code.claude.com/docs/en/settings-reference#model), that version acts as the session's pinned default for the matching `sonnet` or `opus` alias. Claude Code skips the availability check for the built-in default your model replaces and starts on the model you configured, with no fallback notice.
312317
313Model aliases such as `opus` don't act as pins, and neither does a model ID Claude Code doesn't recognize, such as an application inference profile ARN.
318These don't act as pins when you start a session on them:
319
320* A model alias such as `opus`
321* A model ID Claude Code doesn't recognize, such as an application inference profile ARN
314322
315323When these checks find a model your account can't invoke, Claude Code remembers the refusal on this machine for up to a day, and launches during that time skip the remembered model without asking Amazon Bedrock again. Claude Code checks a remembered refusal of a current default model again at launch once ten minutes have passed since the last check, so a default your administrator re-enables comes back. To turn the memory off, set [`CLAUDE_CODE_SKIP_MODEL_ACCESS_MEMORY=1`](https://code.claude.com/docs/en/env-vars).
316324
errors Changed · +5 / -7 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 548
548548
549549* Check [status.claude.com](https://status.claude.com), or the provider status page named in the message, for active incidents
550550* Wait a minute, then send your message again. Your original message is still in the conversation, so for a long prompt you can type `try again` instead of pasting the whole thing.
551* If [`ANTHROPIC_BASE_URL`](https://code.claude.com/docs/en/env-vars) points at an [LLM gateway](https://code.claude.com/docs/en/llm-gateway) and every request fails this way, check whether your gateway is rejecting the tool search fields Claude Code sends by default. To check, set `ENABLE_TOOL_SEARCH=false` as [Tool search through an LLM gateway](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) describes, then try again. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
551* If [`ANTHROPIC_BASE_URL`](https://code.claude.com/docs/en/env-vars) points at an [LLM gateway](https://code.claude.com/docs/en/llm-gateway) and every request fails this way, check that your gateway and its upstream accept [tool search](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) fields. By default, Claude Code sends `defer_loading` tool fields and `tool_reference` blocks, with the `anthropic-beta` header that enables them. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
552552* If the error persists with no posted incident, run `/feedback` so Anthropic can investigate with your request details. See [Report an error](#report-an-error) if `/feedback` is unavailable in your environment.
553553
554554### API Error: Repeated 529 Overloaded errors
from line 1346
13461346* If `/status` shows only your login, run `/login` once. If the credential was revoked, a fresh login replaces it.
13471347* If the same message returns for the same login account, the account or organization is no longer active. Check the account and organization that `/status` reports, and ask your organization admin to restore access.
13481348* If [`ANTHROPIC_BASE_URL`](https://code.claude.com/docs/en/env-vars) points at an [LLM gateway](https://code.claude.com/docs/en/llm-gateway), the text after `401` is your gateway's message rather than Anthropic's, and `/login` doesn't change it. Fix the credential your gateway expects instead.
1349* If every request fails with a `401` once your gateway has the credential it expects, check whether the gateway is rejecting the tool search fields Claude Code sends by default. To check, set `ENABLE_TOOL_SEARCH=false` as [Tool search through an LLM gateway](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) describes, then try again. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
1349* If every request fails with a `401` once your gateway has the credential it expects, check that the gateway and its upstream accept [tool search](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) fields. By default, Claude Code sends `defer_loading` tool fields and `tool_reference` blocks, with the `anthropic-beta` header that enables them. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
13501350
13511351### Login expired
13521352
from line 1949
19491949* Confirm you can reach the API host from the same shell by running `curl -I https://api.anthropic.com`. On Windows PowerShell use `curl.exe -I https://api.anthropic.com` so the built-in `Invoke-WebRequest` alias is not used.
19501950* If you are behind a corporate proxy, set `HTTPS_PROXY` before launching Claude Code and see [Network configuration](https://code.claude.com/docs/en/network-config.md)
19511951* If you route through an LLM gateway or relay, set [`ANTHROPIC_BASE_URL`](https://code.claude.com/docs/en/env-vars) to its address. See [Connect Claude Code to an LLM gateway](https://code.claude.com/docs/en/llm-gateway-connect.md) for setup.
1952* If `ANTHROPIC_BASE_URL` already points at your gateway and every request ends in `Connection dropped`, check whether your gateway is rejecting the tool search fields Claude Code sends by default. To check, set `ENABLE_TOOL_SEARCH=false` as [Tool search through an LLM gateway](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) describes, then try again. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
1952* If `ANTHROPIC_BASE_URL` already points at your gateway and every request ends in `Connection dropped`, check that your gateway and its upstream accept [tool search](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) fields. By default, Claude Code sends `defer_loading` tool fields and `tool_reference` blocks, with the `anthropic-beta` header that enables them. Before v2.1.304, tool search was off behind a gateway unless you turned it on with `ENABLE_TOOL_SEARCH`.
19531953* Ensure your firewall allows the hosts listed in [Network access requirements](https://code.claude.com/docs/en/network-config.md#network-access-requirements)
19541954* Intermittent failures are [retried automatically](#automatic-retries)
19551955
from line 2484
24842484**What to do:**
24852485
24862486* If the message contains `context_management: Extra inputs are not permitted`, [update Claude Code](https://code.claude.com/docs/en/setup.md#update-claude-code) to v2.1.304 or later. After you update, Claude Code answers this rejection by sending the request once more without the field. Before v2.1.304, Claude Code didn't retry this rejection.
2487* If the message names `defer_loading` or `tool_reference`, update Claude Code or turn [tool search](https://code.claude.com/docs/en/mcp.md#tool-search-through-a-gateway) off:
2488 * [Update Claude Code](https://code.claude.com/docs/en/setup.md#update-claude-code) to v2.1.305 or later. Claude Code then answers this rejection by sending the request once more without tool search fields.
2489 * If you can't update, or the message still appears after you do, set `ENABLE_TOOL_SEARCH=false` in your shell or your [settings `env`](https://code.claude.com/docs/en/settings-reference#env). If a settings file already sets the variable, change it there, since that value [can override a shell export](https://code.claude.com/docs/en/settings-reference.md#how-env-values-interact-with-your-shell). Claude Code then loads MCP tools upfront.
2487* If the message names `defer_loading` or `tool_reference`, [update Claude Code](https://code.claude.com/docs/en/setup.md#update-claude-code) to v2.1.305 or later. Claude Code then answers this rejection by [sending the request once more](https://code.claude.com/docs/en/llm-gateway-protocol.md#retry-without-tool-search) without tool search fields.
24902488* If your gateway drops the header, configure it to forward the `anthropic-beta` header. See [feature pass-through](https://code.claude.com/docs/en/llm-gateway-protocol.md#feature-pass-through) for what gateways must forward.
24912489* As a fallback, set [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1`](https://code.claude.com/docs/en/env-vars) before launching. [Disable pre-release capabilities](https://code.claude.com/docs/en/llm-gateway-protocol.md#disable-pre-release-capabilities) covers the exact scope.
24922490
from line 2505
25072505
25082506On a [deployment where flag fetching is off](https://code.claude.com/docs/en/env-vars.md#features-that-need-feature-flag-fetching), or on a machine whose flags have never arrived, Claude Code records in the server's log which tool would be rejected but sends it anyway, so this error can still occur.
25092507
2510The error can also occur for a tool whose schema declares a JSON Schema dialect other than draft 2020-12 in `$schema`. Claude Code doesn't check those schemas against the JSON Schema meta-schema, though the top-level pro
2508The error can also occur for a tool whose schema declares a JSON Schema dialect other than draft 2020-12 in `$schema`. Claude Code doesn't check those schemas against the JSON Schema meta-schema, though the top-level property-name check still applies.
2509
2510Before v2.1.216, no deployment ran the exclusion checks.
2511
2512**What to do:**
2513
2514* If your Claude Code version is earlier than v2.1.300, run [`claude update`](https://code.claude.com/docs/en/setup#update-claude-code) in your shell. Before v2.1.300, Claude Code didn't [retry the request without the rejected tool's parameters](https://code.claude.com/docs/en/mcp.md#tools-whose-input-schema-the-api-refuses), so this error repe
google-vertex-ai Changed · +6 / -1 lines
from line 188
188188
189189When Claude Code starts with Google Cloud's Agent Platform configured, it verifies that the models it intends to use are accessible in your project.
190190
191If you have pinned a model version that is older than the current Claude Code default, and your project can invoke the newer version, Claude Code prompts you to update the pin. Accepting writes the new model ID to your [user settings file](https://code.claude.com/docs/en/settings.md) and restarts Claude Code. Declining is remembered until the next default version change.
191You may have pinned a model version that is older than the current Claude Code default. If your project can invoke the newer version, Claude Code prompts you to update the pin:
192
193* **If you accept**: Claude Code writes the new model ID to your [user settings file](https://code.claude.com/docs/en/settings.md) and restarts
194* **If you decline**: Claude Code remembers your choice until the next default version change
195
196For a pin in the `env` block of [managed settings](https://code.claude.com/docs/en/managed-settings.md), Claude Code runs no check and shows no prompt.
192197
193198If you have not pinned a model and the current default is unavailable in your project, Claude Code falls back for the current session and shows a notice. It tries earlier versions of the default model first and, when the default is an Opus model and no Opus version is available, falls back to the default Sonnet model. The fallback is not persisted. Enable the newer model in [Model Garden](https://console.cloud.google.com/vertex-ai/model-garden) or [pin a version](#5-pin-model-versions) to make the choice permanent.
194199
interactive-mode Changed · +10 / -2 lines
### Ask /btw about a subagent
from line 704
704704
705705In an attached [background session](https://code.claude.com/docs/en/agent-view.md#attach-to-a-session), `Left` detaches and returns you to agent view, even while the answer is still arriving. The side question keeps running while you're away. The next time you attach to the session, the overlay reopens with the side question, or with its answer. Before v2.1.257, `Left` didn't detach there.
706706
707`/btw` sees your full conversation but has no tools. A [subagent](https://code.claude.com/docs/en/sub-agents.md) has tools and starts from the prompt it receives, or, for a [fork](https://code.claude.com/docs/en/sub-agents.md#fork-the-current-conversation), from a copy of this conversation. Use `/btw` to ask about what Claude already knows from this session; use a subagent to go find out something new.
707`/btw` sees your full conversation, or the [subagent transcript you have open](#ask-btw-about-a-subagent), but has no tools. A [subagent](https://code.claude.com/docs/en/sub-agents.md) has tools and starts from the prompt it receives. A [fork](https://code.claude.com/docs/en/sub-agents.md#fork-the-current-conversation) starts from a copy of this conversation. Use `/btw` to ask about what Claude already knows from this session; use a subagent to go find out something new.
708708
709### Ask /btw about a subagent
710
711With a [subagent's transcript open](https://code.claude.com/docs/en/sub-agents.md#observe-and-steer-running-forks), Claude answers `/btw` from that transcript instead of the main conversation, so you can ask what the subagent did. A later `/btw` from that transcript sees only the side questions you asked from it. Requires Claude Code v2.1.314 or later.
712
713From an [agent team](https://code.claude.com/docs/en/agent-teams.md) teammate's transcript, Claude answers from the main conversation.
714
709715## Task list
710716
711717The task list is Claude's to-do checklist: items Claude created to plan multi-step work, with indicators showing what's pending, in progress, or complete. It's separate from the background-task view. To see running shells and subagents, use [`/tasks`](https://code.claude.com/docs/en/commands) instead.
from line 751
745751* **After your computer slept**: if it slept for more than about 30 minutes and the limit reset while it slept, the first line reads `Your usage limit has reset` and the second reads `Press enter to continue`. Press `Enter` to continue. After a shorter sleep, or one that ended before the reset, Claude Code continues on its own.
746752* **Early**: when you finish adding [usage credits](https://code.claude.com/docs/en/costs.md#add-usage-credits-to-your-subscription) with `/usage-credits`, sign back in after `/upgrade`, or switch models with `/model` during the wait, Claude Code checks whether usage is available again and continues right away if it is. It doesn't check after an upgrade or purchase you make in a browser on your own. Under [`opusplan`](https://code.claude.com/docs/en/model-config#opusplan-model-setting) and other model settings that run plan mode on a different model, Claude Code waits for the reset instead.
747753
748The continued task runs like any other turn. Claude Code still asks for [permissions](https://code.claude.com/docs/en/permissions.md) as usual, so the task can stop on a prompt while you're away. If it hits the limit again, Claude Code re-arms the wait on its own at most twice in a row, then stops and shows `Automatic continue stopped after repeated usage-limit hits · /rate-limit-options to try again`.
754In the continued task, Claude Code still asks for [permissions](https://code.claude.com/docs/en/permissions.md) as usual, so the task can stop on a prompt while you're away. If the task hits the limit again, the wait starts again.
755
756After three automatic continuations, automatic continue stops and the `Automatic continue stopped after repeated usage-limit hits` notification appears. Run `/rate-limit-options` to choose what to do next. When you send another prompt, or pick a wait from that menu, the count starts over. Automatic continue also stops after three continuations for a [`/goal`](https://code.claude.com/docs/en/goal) or [session-scoped scheduled task](https://code.claude.com/docs/en/scheduled-tasks.md) that runs through several reset windows.
749757
750758### Cancel the wait
751759
mcp Changed · +3 / -3 lines
from line 1822
18221822> * **You've set `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`**: see [how it affects tool search](#configure-tool-search)
18231823> * **A request failed with an error that names `defer_loading` or `tool_reference`**: see [Extra inputs are not permitted](https://code.claude.com/docs/en/errors.md#extra-inputs-are-not-permitted)
18241824
1825When `ANTHROPIC_BASE_URL` points to a gateway, tool search is on by default, so requests include `defer_loading` tool fields and `tool_reference` blocks for the gateway to forward. While tool search is on, MCP tools are [deferred](#scale-with-mcp-tool-search). To load every tool upfront instead, set `ENABLE_TOOL_SEARCH=false` in your shell or your [settings `env`](https://code.claude.com/docs/en/settings-reference#env). Before v2.1.304, tool search was off behind a gateway unless `ENABLE_TOOL_SEARCH` was `true`, `auto`, or `auto:N`.
1825When `ANTHROPIC_BASE_URL` points to a gateway, Claude Code expects the gateway to forward `defer_loading` tool fields and `tool_reference` blocks [along with the `anthropic-beta` header](https://code.claude.com/docs/en/llm-gateway-protocol#beta-header-and-body-field-pairs). Tool search is on by default behind the gateway, so MCP tools are [deferred](#scale-with-mcp-tool-search) and requests include those fields and blocks. Before v2.1.304, tool search was off behind a gateway unless `ENABLE_TOOL_SEARCH` was `true`, `auto`, or `auto:N`.
18261826
1827On v2.1.305 or later, Claude Code can [retry a request without tool search](https://code.claude.com/docs/en/llm-gateway-protocol.md#retry-without-tool-search) after a `400` or `422` whose cause it doesn't recognize. When the retry works, nothing shows on screen and you don't need to do anything: MCP tools load upfront instead. Claude Code tries tool search again later, at the cost of another rejected request. To skip those requests, set `ENABLE_TOOL_SEARCH=false`.
1827On v2.1.305 or later, Claude Code can [retry a request without tool search](https://code.claude.com/docs/en/llm-gateway-protocol.md#retry-without-tool-search) after a `400` or `422` whose cause it doesn't recognize. When the retry works, nothing shows on screen and you don't need to do anything: MCP tools load upfront instead. Claude Code tries tool search again later, at the cost of another rejected request.
18281828
18291829#### Tools that stay deferred below the `ENABLE_TOOL_SEARCH=auto` threshold
18301830
claude-tag Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
Nothing in the body moved in this read. What changed is above.
cloud-environments Changed · +1 / -0 lines
from line 331
331331| **C/C++** | GCC, Clang, cmake, ninja, conan |
332332| **Docker** | docker, dockerd, docker compose |
333333| **Databases** | PostgreSQL 16, Redis 7.0 |
334| **Browser** | Chrome for Testing at `/usr/bin/google-chrome`, with the `CHROME_PATH` environment variable set to that path |
334335| **Utilities** | git, gh, jq, yq, ripgrep, tmux, vim, nano |
335336
336337¹ Bun is installed but has known [proxy compatibility issues](#install-dependencies-with-a-sessionstart-hook) for package fetching.
llm-gateway-protocol Changed · +1 / -1 lines
from line 249
249249
250250On v2.1.305 or later, a request carrying [`defer_loading` fields and `tool_reference` blocks](https://code.claude.com/docs/en/mcp#tool-search-through-a-gateway) can arrive again without them after a `400` or `422` whose cause Claude Code doesn't recognize. After a successful retry, later requests omit them too.
251251
252The developer's requests keep working without any change on the gateway, with their MCP tools loaded upfront. Claude Code tries tool search again later, so the gateway can see another rejected request followed by its retry. To keep the fields out of every request, have developers set `ENABLE_TOOL_SEARCH=false`. For tool search itself, Claude Code expects the gateway to forward the `defer_loading` fields and `tool_reference` blocks with their `anthropic-beta` value.
252The developer's requests keep working without any change on the gateway, with their MCP tools loaded upfront. Claude Code tries tool search again later, so the gateway can see another rejected request followed by its retry. For tool search itself, Claude Code expects the gateway to forward the `defer_loading` fields and `tool_reference` blocks with their `anthropic-beta` value.
253253
254254### Disable pre-release capabilities
255255
settings-reference Changed · +1 / -2 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 2465
24652465* **Session**: you're in an interactive terminal session, in the VS Code extension's chat panel, or in the desktop app's Code tab when the session runs on your machine or over SSH
24662466* **Auto-compaction**: [`autoCompactEnabled`](#autocompactenabled) is on
24672467* **Prompt cache**: the conversation is on the [one-hour prompt cache TTL](https://code.claude.com/docs/en/prompt-caching.md#which-ttl-each-request-gets)
2468* **Feature flags**: Claude Code can [fetch feature flags from Anthropic](https://code.claude.com/docs/en/env-vars.md#features-that-need-feature-flag-fetching)
24692468* **Size**: the conversation's context has reached the token threshold, which you can [change](#change-the-idle-compaction-threshold) from its default of 200,000
24702469* **Idle time**: about an hour has passed since the last request, and your computer stays awake until then
24712470
from line 2486
24872486To turn idle compaction off or on from inside a terminal session, run `/config` and change the **Idle compaction** row. Your choice is saved to your user settings and applies right away. The row requires Claude Code v2.1.302 or later. If you run one of those versions and `/config` doesn't show the row, check for these causes:
24882487
24892488* **Another settings source sets the key**: a value in managed settings, the `--settings` flag, or a project or local settings file overrides your user settings. Change the key in that source instead
2490* **Feature flags are unavailable**: where Claude Code can't [fetch feature flags from Anthropic](https://code.claude.com/docs/en/env-vars.md#features-that-need-feature-flag-fetching), idle compaction doesn't run, so there is nothing to turn off
2489* **Feature flags are unavailable on a version before v2.1.314**: where Claude Code can't [fetch feature flags from Anthropic](https://code.claude.com/docs/en/env-vars.md#features-that-need-feature-flag-fetching), idle compaction doesn't run, so there is nothing to turn off
24912490
24922491The key requires Claude Code v2.1.290 or later. On an earlier version, which ignores this key, turn off [`autoCompactEnabled`](#autocompactenabled) to stop idle compaction.
24932492
from line 3410
34113410
34123411Once you set `commit` or `pr`, Claude Code ignores the deprecated `includeCoAuthoredBy` setting and uses its default text for whichever of the two you left unset.
34133412
3414Claude Code tells Claude that
3413Claude Code tells Claude that your own instructions about attribution, such as a CLAUDE.md or [memory](https://code.claude.com/docs/en/memory.md) rule, take pre
sub-agents Changed · +2 / -2 lines
from line 1044
10441044
10451045Consider [Skills](https://code.claude.com/docs/en/skills.md) instead when you want reusable prompts or workflows that run in the main conversation context rather than isolated subagent context.
10461046
1047For a question about something already in your conversation, use [`/btw`](https://code.claude.com/docs/en/interactive-mode#side-questions-with-%2Fbtw) instead of a subagent. It sees your full context but has no tool access, and the answer isn't added to history.
1047For a question about something already in your conversation, use [`/btw`](https://code.claude.com/docs/en/interactive-mode#side-questions-with-%2Fbtw) instead of a subagent. It has no tool access, and the answer isn't added to history.
10481048
10491049### Let subagents spawn their own subagents
10501050
from line 1238
12381238| `x` | Stop the selected fork if it's running, or dismiss its row if it's no longer running. On the main session row, or on the row of the fork whose transcript you opened with `Enter`, `x` types into the prompt instead |
12391239| `Esc` | Return focus to the prompt input |
12401240
1241With a fork's or subagent's transcript open, follow-up messages and [skills](https://code.claude.com/docs/en/skills.md) go to that agent, and built-in commands go to your main conversation, with these safeguards:
1241With a fork's or subagent's transcript open, follow-up messages and [skills](https://code.claude.com/docs/en/skills.md) go to that agent. On Claude Code v2.1.314 or later, [`/btw`](https://code.claude.com/docs/en/interactive-mode#ask-btw-about-a-subagent) answers from the open transcript. Other built-in commands go to your main conversation, with these safeguards:
12421242
12431243* `/compact`, `/clear`, and `/rewind` act on the main conversation, so Claude Code asks you to confirm before running one of them from this view.
12441244* `/model` and `/fast` set the main conversation's model and fast mode, not the viewed agent's, so they don't run from this view. A notice tells you why.