Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Home Docs Claude Code CLI
One capture · claude-code

One read of Claude Code CLI

13 pages moved out of 191 read.

claude-code-20260829T013702Z

Pages moved 13 significant first
Pages read 191 in this capture
Captured 01:37 UTC
Corpus hash 59e8bf8f7a7d corpus-hash

What this read moved

1–13 of 13

agent-sdk/modifying-system-prompts Changed · +4 / -4 lines

from line 8
88 
99A system prompt is the initial instruction set that shapes how Claude behaves throughout a conversation. The Agent SDK has three starting points for it:
1010 
11* **Minimal default**: when you don't set `systemPrompt` in TypeScript or `system_prompt` in Python, the SDK uses a minimal prompt that covers tool calling but omits Claude Code's coding guidelines, response style, and project context. This differs from `claude -p`, which uses the full Claude Code prompt by default. If you're migrating from the CLI and want matching behavior, set the `claude_code` preset.
12* **`claude_code` preset**: the full system prompt that the Claude Code CLI uses, with tool usage instructions, code style and formatting guidelines, response tone and verbosity rules, security and safety instructions, and context about the working directory and environment. Set `systemPrompt: { type: "preset", preset: "claude_code" }` in TypeScript or `system_prompt={"type": "preset", "preset": "claude_code"}` in Python, optionally with `append` to add your own instructions on the end.
11* **Minimal default**: when you don't set `systemPrompt` in TypeScript or `system_prompt` in Python, the SDK uses a minimal prompt that covers tool calling but omits the rest of the `claude_code` preset's content, including its security and safety instructions and its context about the working directory and environment. This differs from `claude -p`, which uses the Claude Code system prompt by default. If you're migrating from the CLI and want matching behavior, set the `claude_code` preset.
12* **`claude_code` preset**: the system prompt that the Claude Code CLI uses, with tool usage instructions, security and safety instructions, and context about the working directory and environment. Set `systemPrompt: { type: "preset", preset: "claude_code" }` in TypeScript or `system_prompt={"type": "preset", "preset": "claude_code"}` in Python, optionally with `append` to add your own instructions on the end.
1313* **Custom string**: a prompt you write yourself. The SDK sends only what you provide.
1414 
1515### Decide on a starting point
from line 18
1818 
1919| You're building | Use | What you get |
2020| :----------------------------------------------------------------------------------------------------------- | :--------------------------------- | :---------------------------------------------------------------------------------------------------------------------------- |
21| A CLI or IDE-like coding tool where a human watches and steers, and Claude Code's defaults are what you want | `claude_code` preset | The full Claude Code prompt: tool guidance, safety rules, terminal-friendly responses, repo-convention awareness |
21| A CLI or IDE-like coding tool where a human watches and steers, and Claude Code's defaults are what you want | `claude_code` preset | The Claude Code prompt, including tool guidance, safety rules, and environment context |
2222| The same kind of tool, plus product-specific rules like coding standards, output format, or domain context | `claude_code` preset with `append` | Everything above, with your instructions added after the preset. Nothing is removed, so this is the lowest-risk customization |
2323| An agent with a different surface, identity, or permission model, or a non-coding agent | Custom prompt string | Only what you write. You take responsibility for replacing the tool guidance and safety instructions your agent still needs |
2424| A thin tool-calling loop with no agent persona, where you supply all behavior in the user prompt | No `systemPrompt` option | The minimal default: tool-calling support and nothing else |
from line 44
4444 
4545#### Load CLAUDE.md with the SDK
4646 
47To load CLAUDE.md, set `settingSources` to include the level your CLAUDE.md lives at. The example below loads a project-level CLAUDE.md alongside the `claude_code` preset, so Claude has both the full coding-agent prompt and your project's conventions:
47To load CLAUDE.md, set `settingSources` to include the level where you keep your CLAUDE.md. The example below loads a project-level CLAUDE.md alongside the `claude_code` preset, so Claude has both the coding-agent prompt and your project's conventions:
4848 
4949<CodeGroup>
5050 ```typescript TypeScript theme={null}

agent-sdk/typescript Changed · +3 / -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 2649
26492649| ----------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
26502650| `script` | `string` | Inline workflow script. Must begin with `export const meta = { name, description }` as a literal, followed by the script body using `agent()`, `parallel()`, `pipeline()`, and `phase()`. An optional `phases` array in `meta` groups agents under named stages in the progress view |
26512651| `name` | `string` | Name of a built-in workflow or one saved in `.claude/workflows/`. Resolved to a script |
2652| `scriptPath` | `string` | Path to a workflow script file on disk. Takes precedence over `script` and `name`. Every invocation persists its script and returns the path in the result, so you can edit that file and re-invoke with the same `scriptPath` to iterate |
2652| `scriptPath` | `string` | Path to a workflow script file on disk. Takes precedence over `script` and `name`. Claude Code persists every invocation's script and returns the path in the result, so you can edit that file and re-invoke with the same `scriptPath` to iterate |
26532653| `args` | `unknown` | Input value exposed to the script as the global `args`, for parameterized named workflows such as a research question or a list of file paths. Pass arrays and objects as actual JSON values, not as a JSON-encoded string |
26542654| `resumeFromRunId` | `string` | Run ID of a prior `Workflow` invocation to resume. Completed `agent()` calls with unchanged inputs usually return cached results; the rest run live. [Resume after a pause](/docs/en/workflows#resume-after-a-pause) covers which completed calls re-run. Same session only |
26552655| `title` | `string` | Ignored; the script's `meta` block sets the title |
from line 2870
28702870 delaySeconds?: number;
28712871 reason?: string;
28722872 prompt?: string;
2873 noop?: boolean;
28732874 stop?: boolean;
28742875};
28752876```
28762877 
2877Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 seconds. The `delaySeconds`, `reason`, and `prompt` fields are required unless `stop` is true. Setting `stop: true` cancels the pending wakeup and ends the self-paced `/loop`. The `stop` field requires Claude Code v2.1.202 or later. See the [ScheduleWakeup row in the tools reference](/docs/en/tools-reference).
2878Schedules a one-shot wake-up that fires the given prompt after a delay. This tool backs the self-paced `/loop` command. The runtime clamps `delaySeconds` to between 60 and 3600 seconds. The `delaySeconds`, `reason`, `prompt`, and `noop` fields are required unless `stop` is true. `noop: true` reports a wake-up where nothing changed. Setting `stop: true` cancels the pending wakeup and ends the self-paced `/loop`. The `stop` field requires Claude Code v2.1.202 or later. See the [ScheduleWakeup row in the tools reference](/docs/en/tools-reference).
28782879 
28792880### RemoteTrigger
28802881 
from line 3740
37393740 name: string;
37403741 mimeType?: string;
37413742 description?: string;
3742 server: string;
3743}>;
3744```
3745 
3746Returns an array of available MCP resources.
3747 
3748### ReadMcpResource
3749 
3743 server: str

cross-session-messaging Changed · +2 / -4 lines

from line 64
6464 
6565The receiving Claude reads the message between tool calls during an active turn, so a running tool is never interrupted. When the receiving session is idle, Claude Code starts a new turn with the message.
6666 
67When a message that starts a new turn mentions a file as an `@` immediately followed by its path, Claude Code [attaches that file](/docs/en/common-workflows#reference-files-and-directories) as it exists on the receiving machine, resolving a relative path from the receiving session's working directory. The receiving session's [`Read` deny rules](/docs/en/permissions#read-and-edit) apply to that file, as they do to a file you mention with `@` yourself. When such a message mentions an [MCP resource](/docs/en/mcp#use-mcp-resources) with `@`, Claude Code attaches that resource from the receiving session's MCP servers. A path written without the `@` stays plain text and attaches nothing.
67A message from another session arrives as plain text. If it mentions a file or an [MCP resource](/docs/en/mcp#use-mcp-resources) with `@`, Claude sees the mention as written and Claude Code attaches nothing, whether the message starts a new turn or arrives during one. Claude can still open a mentioned path on the receiving machine with its own tools, subject to that session's permissions. Before v2.1.251, an `@` mention in a message that started a new turn attached the file or MCP resource on the receiving side.
6868 
69A message that Claude reads during an active turn arrives as plain text with nothing attached, even if it mentions files or MCP resources with `@`.
70 
7169Claude Code refuses a message in the following cases:
7270 
7371* The message is [over the size cap](#limitations). Claude Code refuses it in the sending session, before it leaves.
from line 189
191189 
192190The preview shortens only what you see. Whether or not you expand it, Claude reads the full message.
193191 
194Claude receives the message with the sender's name and a reply address, except for a [one-way cross-machine message](#message-sessions-on-other-machines), which carries no reply address. Beyond the name and reply address, the receiving Claude gets the message's text, never the sender's conversation history or files. An `@` mention in the text can still attach a file or MCP resource on the receiving side, as described under [Message delivery](#message-delivery).
192Claude receives the message with the sender's name and a reply address, except for a [one-way cross-machine message](#message-sessions-on-other-machines), which carries no reply address. Beyond the name and reply address, the receiving Claude gets the message's text, never the sender's conversation history or files. [Message delivery](#message-delivery) covers `@` mentions in the text.
195193 
196194A message that a [subagent](/docs/en/sub-agents) wrote arrives under the sending session's name, with the subagent identified in the message text. A reply to it reaches that session's main conversation, not the subagent.
197195 

errors Changed · +233 / -201 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.

The two sides of this change are more than 400 edits apart, too far apart to line up, so this is the differ's own diff of it and the words inside a line are not marked.

from line 14
1414 
1515Match the message you see to a section below.
1616 
17| Message | Section |
18| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------- |
19| `API Error: 500 Internal server error` | [Server errors](#api-error-500-internal-server-error) |
20| `API Error: Repeated 529 Overloaded errors` | [Server errors](#api-error-repeated-529-overloaded-errors) |
21| `Request timed out` | [Server errors](#request-timed-out), or [Network](#unable-to-connect-to-api) if the message mentions your internet connection |
22| `API Error: No response from API` | [Server errors](#no-response-from-api) |
23| `Server error mid-response. The response above may be incomplete.` | [Server errors](#the-response-above-may-be-incomplete) |
24| `Connection lost mid-response` / `Your computer went to sleep mid-response` / `The response stopped arriving` | [Server errors](#the-response-above-may-be-incomplete) |
25| `Connection closed mid-response` / `Response stalled mid-stream` | [Server errors](#the-response-above-may-be-incomplete) |
26| `Connection lost before a response was produced` / `Your computer went to sleep before a response was produced` / `The response stalled before a response was produced` | [Automatic retries](#automatic-retries) |
27| `Connection closed while thinking` / `Response stalled while thinking` | [Automatic retries](#automatic-retries) |
28| `Connection lost while your computer was asleep` | [Automatic retries](#automatic-retries) |
29| `<model> is temporarily unavailable, so auto mode cannot determine the safety of...` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
30| `Auto mode could not evaluate this action and is blocking it for safety` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
31| `Auto mode classifier transcript exceeded context window` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
32| `Agent aborted: auto mode classifier request refused by the safety safeguard` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
33| `Agent terminated early due to an API error` | [Server errors](#agent-terminated-early-due-to-an-api-error) |
34| `You've hit your session limit` / `You've hit your weekly limit` / `You've hit your Opus limit` / `You've hit your Sonnet limit` | [Usage limits](#youve-hit-your-session-limit) |
35| `Usage credits required for 1M context` | [Usage limits](#usage-credits-required-for-1m-context) |
36| `the prompt to confirm went unanswered — nothing was sent` | [Usage limits](#the-prompt-to-confirm-went-unanswered) |
37| `Server is temporarily limiting requests` | [Usage limits](#server-is-temporarily-limiting-requests) |
38| `Request rejected (429)` | [Usage limits](#request-rejected-429) |
39| `Credit balance is too low` | [Usage limits](#credit-balance-is-too-low) |
40| `Could not update your spend limit` | [Usage limits](#could-not-update-your-spend-limit) |
41| `spend limit reached` / `spend limit unavailable` | [Usage limits](#spend-limit-reached) |
42| `Not logged in · Please run /login` | [Authentication](#not-logged-in) |
43| `Could not resolve authentication method` | [Authentication](#could-not-resolve-authentication-method) |
44| `Invalid API key` | [Authentication](#invalid-api-key) |
45| `Your apiKeyHelper script is failing` | [Authentication](#your-apikeyhelper-script-is-failing) |
46| `Invalid auth token · Fix external auth token` | [Authentication](#invalid-request-header-value) |
47| `Invalid ANTHROPIC_CUSTOM_HEADERS · Fix the environment variable` | [Authentication](#invalid-request-header-value) |
48| `Invalid request header from the environment · Fix the environment variable` | [Authentication](#invalid-request-header-value) |
49| `This organization has been disabled` | [Authentication](#this-organization-has-been-disabled) |
50| `Your organization has disabled API key authentication` | [Authentication](#your-organization-has-disabled-api-key-authentication) |
51| `Your organization has disabled Claude subscription access` | [Authentication](#your-organization-has-disabled-claude-subscription-access) |
52| `Routines are disabled by your organization's policy` | [Authentication](#routines-are-disabled-by-your-organizations-policy) |
53| `Remote Control is only available when using Claude via api.anthropic.com` | [Authentication](#remote-control-requires-the-anthropic-api) |
54| `OAuth token refresh failed — run /login to re-authenticate` | [Authentication](#remote-control-couldnt-refresh-your-login) |
55| `JWT refresh failed: no OAuth token — run /login` | [Authentication](#remote-control-couldnt-refresh-your-login) |
56| `Claude.ai login expired` | [Authentication](#remote-control-couldnt-refresh-your-login) |
57| `Claude.ai login was rejected — run /login, then /remote-control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
58| `OAuth token unavailable — run /login to restore Remote Control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
59| `Signed out of Claude — run /login, then /remote-control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
60| `signed-in claude.ai account or organization changed on this machine` | [Authentication](#remote-control-stopped-because-the-signed-in-account-changed) |
61| `Remote Control stopped — the app running this session is now signed in to a different Claude account` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
62| `Remote Control stopped — the app running this session is signed out of Claude` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
63| `OAuth token revoked` / `OAuth token has expired` | [Authentication](#oauth-token-revoked-or-expired) |
64| `API Error: 401 Invalid authentication credentials` | [Authentication](#api-error-401-invalid-authentication-credentials) |
65| `Login expired · Please run /login` | [Authentication](#login-expired) |
66| `Failed to authenticate: OAuth session expired and could not be refreshed` | [Authentication](#login-expired) |
67| `Anthropic profile login expired · Re-authenticate your Anthropic profile` | [Authentication](#anthropic-profile-login-expired) |
68| `Anthropic profile login expired · Run /login to use your claude.ai account instead, or re-authenticate the profile` | [Authentication](#anthropic-profile-login-expired) |
69| `does not meet scope requirement user:profile` | [Authentication](#oauth-scope-requirement) |
70| `claude.ai rejected the session token` / `session token rejected` | [Authentication](#claude-ai-rejected-the-session-token) |
71| `Issuer mismatch in authorization response (RFC 9207)` | [Authentication](#issuer-mismatch-in-authorization-response) |
72| `AWS credentials expired or invalid` | [Authentication](#aws-credentials-expired-or-invalid) |
73| `AWS authentication failed` | [Authentication](#aws-authentication-failed) |
74| `AWS default-chain credential resolve timed out` | [Authentication](#aws-default-chain-credential-resolve-timed-out) |
75| `Could not load the default credentials` on Google Cloud's Agent Platform | [Automatic retries](#automatic-retries) |
76| `Unable to connect to API` | [Network](#unable-to-connect-to-api) |
77| `Connection refused —` / `Can't reach the API server —` / `No internet route —` / `Couldn't connect through your proxy` / `Connection dropped`, each ending with an error code in parentheses | [Network](#unable-to-connect-to-api) |
78| `Unable to connect to Anthropic services` during setup | [Network](#unable-to-connect-to-anthropic-services) |
79| `Socket is closed` | [Network](#socket-is-closed) |
80| `Waiting for API response · will retry in` | [Automatic retries](#automatic-retries), or [Network](#unable-to-connect-to-api) if it persists |
81| `API returned an empty or malformed response` | [Network](#api-returned-an-empty-or-malformed-response) |
82| `Streaming response ended before any complete data was received` | [Network](#streaming-response-ended-before-any-complete-data-was-received) |
83| `Bedrock streaming response has content-type "..."; expected "application/vnd.amazon.eventstream"` | [Network](#bedrock-streaming-response-has-an-unexpected-content-type) |
84| `SSL certificate verification failed` | [Network](#ssl-certificate-errors) |
85| `SSL certificate error (...)` during login or startup | [Network](#ssl-certificate-errors) |
86| `403` with `x-deny-reason: host_not_allowed` in a cloud or routine session | [Network](#host-not-allowed-in-a-cloud-session) |
87| `proxy refused the connection` | [Network](#the-proxy-refused-the-connection) |
88| `403` with `This GraphQL query is not enabled for this session` in a cloud session | [GitHub proxy](/docs/en/cloud-environments#github-proxy) |
89| `The cloud environments service returned an empty response` / `The cloud environments service returned a response in an unexpected format` | [Network](#the-cloud-environments-service-returned-an-empty-or-unexpected-response) |
90| `Couldn't reconnect to your Remote Control session` | [Network](#couldnt-reconnect-to-your-remote-control-session) |
91| `N sessions ended while this machine was offline — the environment was cleaned up on the server and can't be resumed.` | [Network](#sessions-ended-while-this-machine-was-offline) |
92| `Couldn't share the transcript.` | [Network](#couldnt-share-the-transcript) |
93| `Prompt is too long` / `Input is too long for requested model` | [Request errors](#prompt-is-too-long) |
94| `Prompt is too long · automatic compaction failed:` | [Request errors](#prompt-is-too-long) |
95| `Prompt is too long · this conversation is a single exchange` / `A single-exchange conversation cannot be compacted` | [Request errors](#prompt-is-too-long) |
96| `Context limit reached · /compact or /clear to continue` | [Request errors](#prompt-is-too-long) |
97| `Context limit reached · /clear to continue` | [Request errors](#prompt-is-too-long) |
98| `capability_rejected: prompt_too_long` on a Claude apps gateway session | [Request errors](#prompt-is-too-long) |
99| `upstream rejected the request` / `request too large for this upstream` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
100| `upstream rate limit exceeded` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
101| `all upstreams failed (N attempted)` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
102| `Context exceeds the ...-token limit by ... tokens` in `/context` output | [Request errors](#context-exceeds-the-token-limit) |
103| `Error during compaction: Conversation too long` | [Request errors](#error-during-compaction-conversation-too-long) |
104| `Request too large` | [Request errors](#request-too-large) |
105| `Request too large for the API's 32MB request limit` | [Request errors](#request-too-large) |
106| `Image was too large` | [Request errors](#image-was-too-large) |
107| `Unable to resize image` | [Request errors](#unable-to-resize-image) |
108| `PDF too large` / `PDF is password protected` | [Request errors](#pdf-errors) |
109| `Extra inputs are not permitted` | [Request errors](#extra-inputs-are-not-permitted) |
110| `API Error: 400 ... tools.N.custom.input_schema: JSON schema is invalid` | [Request errors](#tool-input-schema-is-invalid) |
111| `There's an issue with the selected model` | [Request errors](#theres-an-issue-with-the-selected-model) |
112| `Model ... is not a recognized model id` | [Request errors](#model-is-not-a-recognized-model-id) |
113| `Claude Opus is not available with the Claude Pro plan` | [Request errors](#claude-opus-is-not-available-with-the-claude-pro-plan) |
114| `Model ... is restricted by your organization's settings` | [Request errors](#model-is-restricted-by-your-organizations-settings) |
115| `thinking.type.enabled is not supported for this model` | [Request errors](#thinking-type-enabled-is-not-supported-for-this-model) |
116| `Effort '<level>' isn't available with thinking turned off on this model` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
117| `effort '<level>' is not supported when thinking is disabled` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
118| `max_tokens must be greater than thinking.budget_tokens` | [Request errors](#thinking-budget-exceeds-output-limit) |
119| `API Error: 400 due to tool use concurrency issues` | [Request errors](#tool-use-or-thinking-block-mismatch) |
120| `[Unsupported tool content removed]` | [Request errors](#unsupported-tool-content-removed) |
121| `server_tool_use.name: Input should be` on every turn of a resumed session | [Request errors](#unsupported-tool-content-removed) |
122| `<model> can't help with this. Start a new session to continue` | [Request errors](#usage-policy-refusal) |
123| `Claude Code is unable to respond to this request, which appears to violate our Usage Policy` | [Request errors](#usage-policy-refusal) |
124| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
125| `<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
126| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |
127| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
128| `Download timed out: exceeded the total deadline` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
129| `--bg and --print conflict` | [Command-line errors](#command-line-errors) |
130| `Cloud sessions cannot be created from a --restricted session` | [Command-line errors](#cloud-sessions-cannot-be-created-from-a-restricted-session) |
131| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#command-line-errors) |
132| `Error: Invalid --agents configuration:` | [Command-line errors](#invalid-agents-configuration) |
133| `Error: Settings file exceeds the 2MiB limit` | [Command-line errors](#settings-file-exceeds-the-2mib-limit) |
134| `The current directory no longer exists (it was deleted or moved)` / `Can't read the current directory` | [Command-line errors](#the-current-directory-no-longer-exists) |
135| `Error: Workspace not trusted` when starting Remote Control | [Command-line errors](#workspace-not-trusted-when-starting-remote-control) |
136| `` `<flag>` before `remote-control` is not carried over to the sessions Remote Control starts `` | [Command-line errors](#not-carried-over-to-the-sessions-remote-control-starts) |
137| `` `claude import` is not yet available in this build `` | [Command-line errors](#claude-import-is-not-yet-available-in-this-build) |
138| `Could not read Claude Code config` | [Command-line errors](#could-not-read-claude-code-config) |
139| `Could not import <server>: <reason>` | [Command-line errors](#could-not-import-a-server-from-claude-desktop) |
140| `is Anthropic-hosted and doesn't support local OAuth` | [Command-line errors](#anthropic-hosted-and-doesnt-support-local-oauth) |
141| `Server rejected the Authorization header minted by the configured headersHelper` | [Command-line errors](#server-rejected-the-authorization-header-minted-by-the-configured-headershelper) |
142| `Error: MCP tool <name> (passed via --permission-prompt-tool) not found` | [Command-line errors](#mcp-permission-prompt-tool-not-found) |
143| `Shell command failed for pattern "..."`, from `/security-review` or any skill that injects dynamic context | [Command-line errors](#security-review-fails-without-origin-head) |
144| `Shell command permission check failed for pattern "..."`, from a skill that injects dynamic context | [Command-line errors](#security-review-fails-without-origin-head) |
145| ``Skill <name> requires bash (`shell: bash` in frontmatter) but Git Bash was not found`` | [Command-line errors](#security-review-fails-without-origin-head) |
146| `Input must be provided either through stdin or as a prompt argument when using --print` | [Command-line errors](#input-must-be-provided-when-using-print) |
147| `Error: Input contained only whitespace` | [Command-line errors](#input-contained-only-whitespace) |
148| `Blank prompt — the message was only whitespace, so nothing was sent to the model.` | [Command-line errors](#input-contained-only-whitespace) |
149| `Unknown command: /<name>`, with or without a `Did you mean` suggestion | [Command-line errors](#unknown-command) |
150| `Diff is too large for ultrareview` / `PR #<N> is too large for ultrareview` | [Command-line errors](#diff-is-too-large-for-ultrareview) |
151| `Could not find merge-base with <branch>` | [Command-line errors](#could-not-find-merge-base-with-the-base-branch) |
152| `Your checkout has no branches (detached HEAD only)` | [Command-line errors](#your-checkout-has-no-branches) |
153| `Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected` | [Command-line errors](#no-github-account-is-connected-to-your-claude-account) |
154| `Your connected GitHub account can't see <owner>/<repo>` | [Command-line errors](#your-connected-github-account-cant-see-the-repository) |
155| `The GitHub App preflight failed transiently (network or service hiccup) — retry in a moment to start from GitHub instead` | [Command-line errors](#the-github-app-preflight-failed-transiently) |
156| `Failed to resume the conversation` | [Command-line errors](#failed-to-resume-the-conversation) |
157| `No conversation found with session ID: <session-id>` | [Command-line errors](#no-conversation-found-with-the-session-id) |
158| `Cannot switch renderers in this session` | [Command-line errors](#cannot-switch-renderers-in-this-session) |
159| `Cannot switch renderers while work is running in the background` | [Command-line errors](#cannot-switch-renderers-in-this-session) |
160| `Couldn't read your Zed keymap` / `Couldn't back up your Zed keymap` / `Couldn't update your Zed keymap` | [Command-line errors](#terminal-setup-left-your-zed-keymap-unchanged) |
161| `Your Zed keymap isn't a readable list of keybindings` | [Command-line errors](#terminal-setup-left-your-zed-keymap-unchanged) |
162| `Marketplace "<name>" is registered from an untrusted source` | [Plugin errors](#marketplace-is-registered-from-an-untrusted-source) |
163| `references ${user_config.*} in a shell-form command` | [Plugin errors](#plugin-command-references-user-config) |
164| `Monitor "<name>" from plugin <plugin> references ${user_config.*} in its command` | [Plugin errors](#plugin-command-references-user-config) |
165| `headersHelper for MCP server '<name>' references ${user_config.*}` | [Plugin errors](#plugin-command-references-user-config) |
166| `Plugin archive integrity check failed` | [Plugin errors](#plugin-archive-integrity-check-failed) |
167| `path escapes plugin directory` | [Plugin errors](#path-escapes-plugin-directory) |
168| `Failed to load marketplace configuration` | [Plugin errors](#failed-to-load-marketplace-configuration) |
169| `Marketplace configuration file is corrupted` | [Plugin errors](#failed-to-load-marketplace-configuration) |
170| `would be spawned with zero tools — refusing` | [Tool errors](#agent-would-be-spawned-with-zero-tools) |
171| `File is covered by a Read deny rule in your permission settings` | [Tool errors](#file-is-covered-by-a-read-deny-rule) |
172| `subagent_type is required: the general-purpose agent is not available in this session` | [Tool errors](#subagent-type-is-required) |
173| `Error: this write left the memory index at MEMORY.md at ..., over its ... read limit` | [Tool errors](#memory-index-is-over-its-read-limit) |
174| `pkill: refusing to run` | [Tool errors](#pkill-pattern-matches-the-claude-code-process) |
175| `Failed to write to <name>'s inbox — nothing was sent` | [Tool errors](#failed-to-write-to-a-teammate-inbox) |
176| `Failed to write the plan approval request to the lead's inbox — plan not submitted` | [Tool errors](#failed-to-write-to-a-teammate-inbox) |
177| `Message too large for cross-session delivery` | [Tool errors](#message-too-large-for-cross-session-delivery) |
178| `Too many messages to this session just now` | [Tool errors](#too-many-messages-to-this-session-just-now) |
179| `Refusing to send: reply target is a symlink` / `Refusing to send: cannot vet reply target` | [Tool errors](#refusing-to-send-a-cross-session-message) |
180| `Refusing to send: connected endpoint is not the expected process` / `Refusing to send: connected endpoint identity could not be read` | [Tool errors](#refusing-to-send-a-cross-session-message) |
181| `Refusing to send: connected endpoint is not owned by this user` / `Refusing to send: connected endpoint owner could not be read` | [Tool errors](#refusing-to-send-a-cross-session-message) |
182| `Refusing to send: connected endpoint is a different process with the expected pid` | [Tool errors](#refusing-to-send-a-cross-session-message) |
183| `Can't open MCP settings while no terminal is attached to this background session` | [Background session errors](#commands-refused-in-a-background-session) |
184| `Can't open MCP settings in a background session` | [Background session errors](#commands-refused-in-a-background-session) |
185| `blocked because the path is spelled in a form that cannot be safely resolved` | [Background session errors](#write-or-command-blocked-because-the-path-cannot-be-safely-resolved) |
186| `blocked because the path is network-shaped` | [Background session errors](#write-or-command-blocked-because-the-path-names-a-network-location) |
187| `This session has no saved transcript` | [Background session errors](#this-session-has-no-saved-transcript) |
188| `Can't open — this session is running in another terminal` | [Background session errors](#this-session-is-running-in-another-terminal) |
189| `This conversation is already open in another running Claude session` | [Background session errors](#this-session-is-running-in-another-terminal) |
190| `This session's saved conversation is no longer on disk` | [Background session errors](#this-sessions-saved-conversation-is-no-longer-on-disk) |
191| `kept <id> — worktree has commits that are not pushed anywhere` | [Background session errors](#worktree-has-commits-that-are-not-pushed-anywhere) |
192| `terminal host process died — press Enter to restart` / `This session's terminal host process died` | [Background session errors](#terminal-host-process-died) |
193| `Session isn't responding` / `Press enter again to restart this session — it isn't responding` | [Background session errors](#session-isnt-responding) |
194| `Session <id> was stopped while the respawn was in flight` | [Background session errors](#session-was-stopped-while-the-respawn-was-in-flight) |
195| `This session was running agent '<name>', which is no longer available` | [Background session errors](#session-agent-no-longer-available) |
196| `CLAUDE_CODE_PROCESS_WRAPPER: launcher ...` | [Background session errors](#claude_code_process_wrapper-launcher-errors) |
197| `EUNKNOWN: unknown error, uv_spawn` | [Background session errors](#eunknown-when-starting-a-background-session) |
198| `EACCES: permission denied, posix_spawn` | [Background session errors](#eacces-when-starting-a-background-session) |
199| `exited before it became reachable` | [Background session errors](#background-service-exited-before-it-became-reachable) |
200| `Claude Code process exited with code N` | [Wrapper and IDE errors](#claude-code-process-exited-with-code-n) |
201| `Could not locate the Claude CLI on PATH` | [Wrapper and IDE errors](#could-not-locate-the-claude-cli-on-path) |
202| `Restored the code, but skipped N files` | [Rewind warnings](#restored-the-code-but-skipped-files) |
203| `Transcript writes are failing (...)` | [Session saving warnings](#transcript-writes-are-failing) |
204| `Transcript saving is off — CLAUDE_CODE_SKIP_PROMPT_HISTORY is set` | [Session saving warnings](#transcript-saving-is-off-skip-prompt-history) |
205| `Transcript saving is off — inherited CLAUDE_CODE_CHILD_SESSION marker` | [Session saving warnings](#transcript-saving-is-off-child-session-marker) |
206| `Claude Code's fullscreen renderer didn't finish starting last time on this machine` / `Claude Code's fullscreen renderer has repeatedly failed to start on this machine` | [Configuration warnings](#fullscreen-failed-start-notice) |
207| `Claude Code exited after an unrecoverable interface error (...)` | [Configuration warnings](#exited-after-an-unrecoverable-interface-error) |
208| `Agent descriptions are over the 15.0k-token limit` | [Configuration warnings](#agent-descriptions-are-over-the-15000-token-limit) |
209| `Ignoring N permissions.allow entries from ... this workspace has not been trusted` | [Configuration warnings](#workspace-has-not-been-trusted) |
210| `Remote managed settings failed to load (<cause>)` | [Configuration warnings](#remote-managed-settings-failed-to-load) |
211| `"crossSessionInbound" must be one of "accept", "hold", "refuse"` | [Configuration warnings](#crosssessioninbound-must-be-one-of-accept-hold-refuse) |
212| `headersHelper not run — this workspace has no persisted trust` | [Configuration warnings](#headershelper-not-run) |
213| `... is not matched by file permission checks` | [Configuration warnings](#is-not-matched-by-file-permission-checks) |
214| `... has a wildcard before the rest of the command` | [Configuration warnings](#has-a-wildcard-before-the-rest-of-the-command) |
215| `CLAUDE_CODE_DISABLE_1M_CONTEXT is set, but the 200K limit isn't enforced` | [Configuration warnings](#the-200k-limit-isnt-enforced) |
216| `[claude-code:unrecognized_model]` | [Configuration warnings](#unrecognized-model-id-on-a-request) |
217| Responses seem lower quality than usual | [Response quality](#responses-seem-lower-quality-than-usual) |
17| Message | Section |
18| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------- |
19| `API Error: 500 Internal server error` | [Server errors](#api-error-500-internal-server-error) |
20| `API Error: Repeated 529 Overloaded errors` | [Server errors](#api-error-repeated-529-overloaded-errors) |
21| `Request timed out` | [Server errors](#request-timed-out), or [Network](#unable-to-connect-to-api) if the message mentions your internet connection |
22| `API Error: No response from API` | [Server errors](#no-response-from-api) |
23| `Server error mid-response. The response above may be incomplete.` | [Server errors](#the-response-above-may-be-incomplete) |
24| `Connection lost mid-response` / `Your computer went to sleep mid-response` / `The response stopped arriving` | [Server errors](#the-response-above-may-be-incomplete) |
25| `Connection closed mid-response` / `Response stalled mid-stream` | [Server errors](#the-response-above-may-be-incomplete) |
26| `Connection lost before a response was produced` / `Your computer went to sleep before a response was produced` / `The response stalled before a response was produced` | [Automatic retries](#automatic-retries) |
27| `Connection closed while thinking` / `Response stalled while thinking` | [Automatic retries](#automatic-retries) |
28| `Connection lost while your computer was asleep` | [Automatic retries](#automatic-retries) |
29| `<model> is temporarily unavailable, so auto mode cannot determine the safety of...` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
30| `Auto mode could not evaluate this action and is blocking it for safety` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
31| `Auto mode classifier transcript exceeded context window` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
32| `Agent aborted: auto mode classifier request refused by the safety safeguard` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
33| `Agent terminated early due to an API error` | [Server errors](#agent-terminated-early-due-to-an-api-error) |
34| `You've hit your session limit` / `You've hit your weekly limit` / `You've hit your Opus limit` / `You've hit your Sonnet limit` | [Usage limits](#youve-hit-your-session-limit) |
35| `Usage credits required for 1M context` | [Usage limits](#usage-credits-required-for-1m-context) |
36| `the prompt to confirm went unanswered — nothing was sent` | [Usage limits](#the-prompt-to-confirm-went-unanswered) |
37| `Server is temporarily limiting requests` | [Usage limits](#server-is-temporarily-limiting-requests) |
38| `Request rejected (429)` | [Usage limits](#request-rejected-429) |
39| `Credit balance is too low` | [Usage limits](#credit-balance-is-too-low) |
40| `Could not update your spend limit` | [Usage limits](#could-not-update-your-spend-limit) |
41| `spend limit reached` / `spend limit unavailable` | [Usage limits](#spend-limit-reached) |
42| `Not logged in · Please run /login` | [Authentication](#not-logged-in) |
43| `Could not resolve authentication method` | [Authentication](#could-not-resolve-authentication-method) |
44| `Invalid API key` | [Authentication](#invalid-api-key) |
45| `Your apiKeyHelper script is failing` | [Authentication](#your-apikeyhelper-script-is-failing) |
46| `Invalid auth token · Fix external auth token` | [Authentication](#invalid-request-header-value) |
47| `Invalid ANTHROPIC_CUSTOM_HEADERS · Fix the environment variable` | [Authentication](#invalid-request-header-value) |
48| `Invalid request header from the environment · Fix the environment variable` | [Authentication](#invalid-request-header-value) |
49| `This organization has been disabled` | [Authentication](#this-organization-has-been-disabled) |
50| `Your organization has disabled API key authentication` | [Authentication](#your-organization-has-disabled-api-key-authentication) |
51| `Your organization has disabled Claude subscription access` | [Authentication](#your-organization-has-disabled-claude-subscription-access) |
52| `Routines are disabled by your organization's policy` | [Authentication](#routines-are-disabled-by-your-organizations-policy) |
53| `Remote Control is only available when using Claude via api.anthropic.com` | [Authentication](#remote-control-requires-the-anthropic-api) |
54| `OAuth token refresh failed — run /login to re-authenticate` | [Authentication](#remote-control-couldnt-refresh-your-login) |
55| `JWT refresh failed: no OAuth token — run /login` | [Authentication](#remote-control-couldnt-refresh-your-login) |
56| `Claude.ai login expired` | [Authentication](#remote-control-couldnt-refresh-your-login) |
57| `Claude.ai login was rejected — run /login, then /remote-control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
58| `OAuth token unavailable — run /login to restore Remote Control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
59| `Signed out of Claude — run /login, then /remote-control` | [Authentication](#remote-control-couldnt-refresh-your-login) |
60| `signed-in claude.ai account or organization changed on this machine` | [Authentication](#remote-control-stopped-because-the-signed-in-account-changed) |
61| `Remote Control stopped — the app running this session is now signed in to a different Claude account` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
62| `Remote Control stopped — the app running this session is signed out of Claude` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
63| `OAuth token revoked` / `OAuth token has expired` | [Authentication](#oauth-token-revoked-or-expired) |
64| `API Error: 401 Invalid authentication credentials` | [Authentication](#api-error-401-invalid-authentication-credentials) |
65| `Login expired · Please run /login` | [Authentication](#login-expired) |
66| `Failed to authenticate: OAuth session expired and could not be refreshed` | [Authentication](#login-expired) |
67| `Anthropic profile login expired · Re-authenticate your Anthropic profile` | [Authentication](#anthropic-profile-login-expired) |
68| `Anthropic profile login expired · Run /login to use your claude.ai account instead, or re-authenticate the profile` | [Authentication](#anthropic-profile-login-expired) |
69| `does not meet scope requirement user:profile` | [Authentication](#oauth-scope-requirement) |
70| `claude.ai rejected the session token` / `session token rejected` | [Authentication](#claude-ai-rejected-the-session-token) |
71| `Issuer mismatch in authorization response (RFC 9207)` | [Authentication](#issuer-mismatch-in-authorization-response) |
72| `AWS credentials expired or invalid` | [Authentication](#aws-credentials-expired-or-invalid) |
73| `AWS authentication failed` | [Authentication](#aws-authentication-failed) |
74| `AWS default-chain credential resolve timed out` | [Authentication](#aws-default-chain-credential-resolve-timed-out) |
75| `Could not load the default credentials` on Google Cloud's Agent Platform | [Automatic retries](#automatic-retries) |
76| `Unable to connect to API` | [Network](#unable-to-connect-to-api) |
77| `Connection refused —` / `Can't reach the API server —` / `No internet route —` / `Couldn't connect through your proxy` / `Connection dropped`, each ending with an error code in parentheses | [Network](#unable-to-connect-to-api) |
78| `Unable to connect to Anthropic services` during setup | [Network](#unable-to-connect-to-anthropic-services) |
79| `Socket is closed` | [Network](#socket-is-closed) |
80| `Waiting for API response · will retry in` | [Automatic retries](#automatic-retries), or [Network](#unable-to-connect-to-api) if it persists |
81| `API returned an empty or malformed response` | [Network](#api-returned-an-empty-or-malformed-response) |
82| `Streaming response ended before any complete data was received` | [Network](#streaming-response-ended-before-any-complete-data-was-received) |
83| `Bedrock streaming response has content-type "..."; expected "application/vnd.amazon.eventstream"` | [Network](#bedrock-streaming-response-has-an-unexpected-content-type) |
84| `SSL certificate verification failed` | [Network](#ssl-certificate-errors) |
85| `SSL certificate error (...)` during login or startup | [Network](#ssl-certificate-errors) |
86| `403` with `x-deny-reason: host_not_allowed` in a cloud or routine session | [Network](#host-not-allowed-in-a-cloud-session) |
87| `proxy refused the connection` | [Network](#the-proxy-refused-the-connection) |
88| `403` with `This GraphQL query is not enabled for this session` in a cloud session | [GitHub proxy](/docs/en/cloud-environments#github-proxy) |
89| `The cloud environments service returned an empty response` / `The cloud environments service returned a response in an unexpected format` | [Network](#the-cloud-environments-service-returned-an-empty-or-unexpected-response) |
90| `Couldn't reconnect to your Remote Control session` | [Network](#couldnt-reconnect-to-your-remote-control-session) |
91| `N sessions ended while this machine was offline — the environment was cleaned up on the server and can't be resumed.` | [Network](#sessions-ended-while-this-machine-was-offline) |
92| `Couldn't share the transcript.` | [Network](#couldnt-share-the-transcript) |
93| `Prompt is too long` / `Input is too long for requested model` | [Request errors](#prompt-is-too-long) |
94| `Prompt is too long · automatic compaction failed:` | [Request errors](#prompt-is-too-long) |
95| `Prompt is too long · this conversation is a single exchange` / `A single-exchange conversation cannot be compacted` | [Request errors](#prompt-is-too-long) |
96| `Context limit reached · /compact or /clear to continue` | [Request errors](#prompt-is-too-long) |
97| `Context limit reached · /clear to continue` | [Request errors](#prompt-is-too-long) |
98| `capability_rejected: prompt_too_long` on a Claude apps gateway session | [Request errors](#prompt-is-too-long) |
99| `upstream rejected the request` / `request too large for this upstream` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
100| `upstream rate limit exceeded` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
101| `all upstreams failed (N attempted)` on a Claude apps gateway session | [Upstream error messages](/docs/en/claude-apps-gateway-config#upstream-error-messages) |
102| `Context exceeds the ...-token limit by ... tokens` in `/context` output | [Request errors](#context-exceeds-the-token-limit) |
103| `Error during compaction: Conversation too long` | [Request errors](#error-during-compaction-conversation-too-long) |
104| `Request too large` | [Request errors](#request-too-large) |
105| `Request too large for the API's 32MB request limit` | [Request errors](#request-too-large) |
106| `Image was too large` | [Request errors](#image-was-too-large) |
107| `Unable to resize image` | [Request errors](#unable-to-resize-image) |
108| `PDF too large` / `PDF is password protected` | [Request errors](#pdf-errors) |
109| `Extra inputs are not permitted` | [Request errors](#extra-inputs-are-not-permitted) |
110| `API Error: 400 ... tools.N.custom.input_schema: JSON schema is invalid` | [Request errors](#tool-input-schema-is-invalid) |
111| `There's an issue with the selected model` | [Request errors](#theres-an-issue-with-the-selected-model) |
112| `Model ... is not a recognized model id` | [Request errors](#model-is-not-a-recognized-model-id) |
113| `Claude Opus is not available with the Claude Pro plan` | [Request errors](#claude-opus-is-not-available-with-the-claude-pro-plan) |
114| `Model ... is restricted by your organization's settings` | [Request errors](#model-is-restricted-by-your-organizations-settings) |
115| `thinking.type.enabled is not supported for this model` | [Request errors](#thinking-type-enabled-is-not-supported-for-this-model) |
116| `Effort '<level>' isn't available with thinking turned off on this model` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
117| `effort '<level>' is not supported when thinking is disabled` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
118| `max_tokens must be greater than thinking.budget_tokens` | [Request errors](#thinking-budget-exceeds-output-limit) |
119| `API Error: 400 due to tool use concurrency issues` | [Request errors](#tool-use-or-thinking-block-mismatch) |
120| `[Unsupported tool content removed]` | [Request errors](#unsupported-tool-content-removed) |
121| `server_tool_use.name: Input should be` on every turn of a resumed session | [Request errors](#unsupported-tool-content-removed) |
122| `<model> can't help with this. Start a new session to continue` | [Request errors](#usage-policy-refusal) |
123| `Claude Code is unable to respond to this request, which appears to violate our Usage Policy` | [Request errors](#usage-policy-refusal) |
124| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
125| `<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
126| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |
127| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
128| `Download timed out: exceeded the total deadline` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
129| `--bg and --print conflict` | [Command-line errors](#command-line-errors) |
130| `Cloud sessions cannot be created from a --restricted session` | [Command-line errors](#cloud-sessions-cannot-be-created-from-a-restricted-session) |
131| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#command-line-errors) |
132| `Error: Invalid --agents configuration:` | [Command-line errors](#invalid-agents-configuration) |
133| `Error: Settings file exceeds the 2MiB limit` | [Command-line errors](#settings-file-exceeds-the-2mib-limit) |
134| `The current directory no longer exists (it was deleted or moved)` / `Can't read the current directory` | [Command-line errors](#the-current-directory-no-longer-exists) |
135| `Error: Workspace not trusted` when starting Remote Control | [Command-line errors](#workspace-not-trusted-when-starting-remote-control) |
136| `` `<flag>` before `remote-control` is not carried over to the sessions Remote Control starts `` | [Command-line errors](#not-carried-over-to-the-sessions-remote-control-starts) |
137| `` `claude import` is not yet available in this build `` | [Command-line errors](#claude-import-is-not-yet-available-in-this-build) |
138| `Could not read Claude Code config` | [Command-line errors](#could-not-read-claude-code-config) |
139| `Could not import <server>: <reason>` | [Command-line errors](#could-not-import-a-server-from-claude-desktop) |
140| `is Anthropic-hosted and doesn't support local OAuth` | [Command-line errors](#anthropic-hosted-and-doesnt-support-local-oauth) |
141| `Server rejected the Authorization header minted by the configured headersHelper` | [Command-line errors](#server-rejected-the-authorization-header-minted-by-the-configured-headershelper) |
142| `Error: MCP tool <name> (passed via --permission-prompt-tool) not found` | [Command-line errors](#mcp-permission-prompt-tool-not-found) |
143| `Shell command failed for pattern "..."`, from `/security-review` or any skill that injects dynamic context | [Command-line errors](#security-review-fails-without-origin-head) |
144| `Shell command permission check failed for pattern "..."`, from a skill that injects dynamic context | [Command-line errors](#security-review-fails-without-origin-head) |
145| ``Skill <name> requires bash (`shell: bash` in frontmatter) but Git Bash was not found`` | [Command-line errors](#security-review-fails-without-origin-head) |
146| `Input must be provided either through stdin or as a prompt argument when using --print` | [Command-line errors](#input-must-be-provided-when-using-print) |
147| `Error: Input contained only whitespace` | [Command-line errors](#input-contained-only-whitespace) |
148| `Blank prompt — the message was only whitespace, so nothing was sent to the model.` | [Command-line errors](#input-contained-only-whitespace) |
149| `Unknown command: /<name>`, with or without a `Did you mean` suggestion | [Command-line errors](#unknown-command) |
150| `Diff is too large for ultrareview` / `PR #<N> is too large for ultrareview` | [Command-line errors](#diff-is-too-large-for-ultrareview) |
151| `Could not find merge-base with <branch>` | [Command-line errors](#could-not-find-merge-base-with-the-base-branch) |
152| `Your checkout has no branches (detached HEAD only)` | [Command-line errors](#your-checkout-has-no-branches) |
153| `Ultrareview clones <owner>/<repo> in the cloud with the GitHub account connected to your Claude account, and none is connected` | [Command-line errors](#no-github-account-is-connected-to-your-claude-account) |
154| `Your connected GitHub account can't see <owner>/<repo>` | [Command-line errors](#your-connected-github-account-cant-see-the-repository) |
155| `The GitHub App preflight failed transiently (network or service hiccup) — retry in a moment to start from GitHub instead` | [Command-line errors](#the-github-app-preflight-failed-transiently) |
156| `Failed to resume the conversation` | [Command-line errors](#failed-to-resume-the-conversation) |
157| `No conversation found with session ID: <session-id>` | [Command-line errors](#no-conversation-found-with-the-session-id) |
158| `Cannot switch renderers in this session` | [Command-line errors](#cannot-switch-renderers-in-this-session) |
159| `Cannot switch renderers while work is running in the background` | [Command-line errors](#cannot-switch-renderers-in-this-session) |
160| `Couldn't read your Zed keymap` / `Couldn't back up your Zed keymap` / `Couldn't update your Zed keymap` | [Command-line errors](#terminal-setup-left-your-zed-keymap-unchanged) |
161| `Your Zed keymap isn't a readable list of keybindings` | [Command-line errors](#terminal-setup-left-your-zed-keymap-unchanged) |
162| `Marketplace "<name>" is registered from an untrusted source` | [Plugin errors](#marketplace-is-registered-from-an-untrusted-source) |
163| `references ${user_config.*} in a shell-form command` | [Plugin errors](#plugin-command-references-user-config) |
164| `Monitor "<name>" from plugin <plugin> references ${user_config.*} in its command` | [Plugin errors](#plugin-command-references-user-config) |
165| `headersHelper for MCP server '<name>' references ${user_config.*}` | [Plugin errors](#plugin-command-references-user-config) |
166| `Plugin archive integrity check failed` | [Plugin errors](#plugin-archive-integrity-check-failed) |
167| `path escapes plugin directory` | [Plugin errors](#path-escapes-plugin-directory) |
168| `Failed to load marketplace configuration` | [Plugin errors](#failed-to-load-marketplace-configuration) |
169| `Marketplace configuration file is corrupted` | [Plugin errors](#failed-to-load-marketplace-configuration) |
170| `would be spawned with zero tools — refusing` | [Tool errors](#agent-would-be-spawned-with-zero-tools) |
171| `File is covered by a Read deny rule in your permission settings` | [Tool errors](#file-is-covered-by-a-read-deny-rule) |
172| `subagent_type is required: the general-purpose agent is not available in this session` | [Tool errors](#subagent-type-is-required) |
173| `Error: this write left the memory index at MEMORY.md at ..., over its ... read limit` | [Tool errors](#memory-index-is-over-its-read-limit) |
174| `pkill: refusing to run` | [Tool errors](#pkill-pattern-matches-the-claude-code-process) |
175| `Failed to write to <name>'s inbox — nothing was sent` | [Tool errors](#failed-to-write-to-a-teammate-inbox) |
176| `Failed to write the plan approval request to the lead's inbox — plan not submitted` | [Tool errors](#failed-to-write-to-a-teammate-inbox) |
177| `Message too large for cross-session delivery` | [Tool errors](#message-too-large-for-cross-session-delivery) |
178| `Too many messages to this session just now` | [Tool errors](#too-many-messages-to-this-session-just-now) |
179| `Refusing to send: reply target is a symlink` / `Refusing to send: cannot vet reply target` | [Tool errors](#refusing-to-send-a-cross-session-message) |
180| `Refusing to send: connected endpoint is not the expected process` / `Refusing to send: connected endpoint identity could not be read` | [Tool errors](#refusing-to-send-a-cross-session-message) |
181| `Refusing to send: connected endpoint is not owned by this user` / `Refusing to send: connected endpoint owner could not be read` | [Tool errors](#refusing-to-send-a-cross-session-message) |
182| `Refusing to send: connected endpoint is a different process with the expected pid` | [Tool errors](#refusing-to-send-a-cross-session-message) |
183| `Refusing to read <path>: its symlink resolution changed after permission was checked` / `Refusing to search <path>: its symlink resolution changed after permission was checked` | [Tool errors](#refusing-after-a-symlink-changed) |
184| `Refusing to write <path>: its parent-directory symlink resolution changed after permission was checked` / `Refusing to write <path>: it is a symbolic link. Write to the link's target path instead` | [Tool errors](#refusing-after-a-symlink-changed) |
185| `Refusing to search <path>: a path one of its Read deny rules is written through changed while the search was being prepared` / `Refusing to search <path>: it could not be opened` | [Tool errors](#refusing-after-a-symlink-changed) |
186| `its permission check expired before it ran (too many concurrent file operations)` / `ripgrep was found only by name on PATH` | [Tool errors](#refusing-after-a-symlink-changed) |
187| `Can't open MCP settings while no terminal is attached to this background session` | [Background session errors](#commands-refused-in-a-background-session) |
188| `Can't open MCP settings in a background session` | [Background session errors](#commands-refused-in-a-background-session) |
189| `blocked because the path is spelled in a form that cannot be safely resolved` | [Background session errors](#write-or-command-blocked-because-the-path-cannot-be-safely-resolved) |
190| `blocked because the path is network-shaped` | [Background session errors](#write-or-command-blocked-because-the-path-names-a-network-location) |
191| `This session has no saved transcript` | [Background session errors](#this-session-has-no-saved-transcript) |
192| `Can't open — this session is running in another terminal` | [Background session errors](#this-session-is-running-in-another-terminal) |
193| `This conversation is already open in another running Claude session` | [Background session errors](#this-session-is-running-in-another-terminal) |
194| `This session's saved conversation is no longer on disk` | [Background session errors](#this-sessions-saved-conversation-is-no-longer-on-disk) |
195| `kept <id> — worktree has commits that are not pushed anywhere` | [Background session errors](#worktree-has-commits-that-are-not-pushed-anywhere) |
196| `terminal host process died — press Enter to restart` / `This session's terminal host process died` | [Background session errors](#terminal-host-process-died) |
197| `Session isn't responding` / `Press enter again to restart this session — it isn't responding` | [Background session errors](#session-isnt-responding) |
198| `Session <id> was stopped while the respawn was in flight` | [Background session errors](#session-was-stopped-while-the-respawn-was-in-flight) |
199| `This session was running agent '<name>', which is no longer available` | [Background session errors](#session-agent-no-longer-available) |
200| `CLAUDE_CODE_PROCESS_WRAPPER: launcher ...` | [Background session errors](#claude_code_process_wrapper-launcher-errors) |
201| `EUNKNOWN: unknown error, uv_spawn` | [Background session errors](#eunknown-when-starting-a-background-session) |
202| `EACCES: permission denied, posix_spawn` | [Background session errors](#eacces-when-starting-a-background-session) |
203| `exited before it became reachable` | [Background session errors](#background-service-exited-before-it-became-reachable) |
204| `Claude Code process exited with code N` | [Wrapper and IDE errors](#claude-code-process-exited-with-code-n) |
205| `Could not locate the Claude CLI on PATH` | [Wrapper and IDE errors](#could-not-locate-the-claude-cli-on-path) |
206| `Restored the code, but skipped N files` | [Rewind warnings](#restored-the-code-but-skipped-files) |
207| `Transcript writes are failing (...)` | [Session saving warnings](#transcript-writes-are-failing) |
208| `Transcript saving is off — CLAUDE_CODE_SKIP_PROMPT_HISTORY is set` | [Session saving warnings](#transcript-saving-is-off-skip-prompt-history) |
209| `Transcript saving is off — inherited CLAUDE_CODE_CHILD_SESSION marker` | [Session saving warnings](#transcript-saving-is-off-child-session-marker) |
210| `Claude Code's fullscreen renderer didn't finish starting last time on this machine` / `Claude Code's fullscreen renderer has repeatedly failed to start on this machine` | [Configuration warnings](#fullscreen-failed-start-notice) |
211| `Claude Code exited after an unrecoverable interface error (...)` | [Configuration warnings](#exited-after-an-unrecoverable-interface-error) |
212| `Agent descriptions are over the 15.0k-token limit` | [Configuration warnings](#agent-descriptions-are-over-the-15000-token-limit) |
213| `Ignoring N permissions.allow entries from ... this workspace has not been trusted` | [Configuration warnings](#workspace-has-not-been-trusted) |
214| `Remote managed settings failed to load (<cause>)` | [Configuration warnings](#remote-managed-settings-failed-to-load) |
215| `"crossSessionInbound" must be one of "accept", "hold", "refuse"` | [Configuration warnings](#crosssessioninbound-must-be-one-of-accept-hold-refuse) |
216| `headersHelper not run — this workspace has no persisted trust` | [Configuration warnings](#headershelper-not-run) |
217| `... is not matched by file permission checks` | [Configuration warnings](#is-not-matched-by-file-permission-checks) |
218| `... has a wildcard before the rest of the command` | [Configuration warnings](#has-a-wildcard-before-the-rest-of-the-command) |
219| `CLAUDE_CODE_DISABLE_1M_CONTEXT is set, but the 200K limit isn't enforced` | [Configuration warnings](#the-200k-limit-isnt-enforced) |
220| `[claude-code:unrecognized_model]` | [Configuration warnings](#unrecognized-model-id-on-a-request) |
221| Responses seem lower quality than usual | [Response quality](#responses-seem-lower-quality-than-usual) |
218222 
219223## Automatic retries
220224 
from line 2623
26192623 
26202624Before v2.1.248, Claude Code didn't check the endpoint's owning user or process start time, so the refusals that name those checks don't appear on earlier versions.
26212625 
2626<h3 id="refusing-after-a-symlink-changed">
2627 Refusing to read, write, or search a path
2628</h3>
2629 
2630Claude Code checks a file path's [permission rules](/docs/en/permissions#read-and-edit), then confirms that resolution again when the tool opens the file or starts the search. When it can't confirm that the path still leads to the location the check approved, Claude Code refuses the operation instead of following it. The refusal appears in the tool result:
2631 
2632```text theme={null}
2633Refusing to read /path/to/file: its symlink resolution changed after permission was checked. If a link in the working directory is being rewritten concurrently, stop that and retry.
2634```
2635 
2636The text after the path names the reason:
2637 
2638* `its symlink resolution changed after permission was checked`: a symlink along the path, or at a Grep or Glob search root, was replaced between the permission check and the operation
2639* `its parent-directory symlink resolution changed after permission was checked`: a directory the write path passes through no longer resolves to the approved location
2640* `it is a symbolic link. Write to the link's target path instead`: a symbolic link sits at the approved write location itself
2641* `a path one of its Read deny rules is written through changed while the search was being prepared. Retry.`: a `Read` deny rule for the search names a path that passes through a symlink, and that link changed while Claude Code was preparing the search
2642* `it could not be opened (EACCES) — it is unreadable, or is being replaced concurrently.`: the search root exists but couldn't be opened; the parenthesized code is the operating system error
2643* `its permission check expired before it ran (too many concurrent file operations). Retry.`: Claude Code evicted the approval record under many simultaneous file operations before the tool used it; retrying runs a fresh permission check
2644* `ripgrep was found only by name on PATH, and a search outside the working directory cannot apply your Read deny rules in that configuration`: Claude Code couldn't resolve the `rg` binary to an absolute path, so it refuses searches outside the working directory rather than run one your deny rules don't cover
2645 
2646**What to do:**
2647 
2648* Usually nothing: the refusal reaches Claude as the tool result, and the refused operation doesn't run
2649* If a symlink refusal repeats on one path, find what keeps rewriting a link there, such as a build tool or file watcher, or ask Claude to use the file's resolved path instead of the linked one
2650* For the ripgrep refusal, install ripgrep with your package manager so `rg` resolves to an absolute path on `PATH`, or keep searches under the working directory
2651 
2652Before v2.1.251, Claude Code re-checked a path's resolution only for file writes, so a link replaced after the permission check could redirect a read or search to a different location without a message. Of these refusals, only the parent-directory write refusal appears on earlier versions.
2653 
26222654## Background session errors
26232655 
26242656[Background sessions](/docs/en/agent-view) run without an interactive terminal of their own, so commands that need one behave differently there. These messages appear in the transcript of a background session, in the terminal that attaches to one, in the session or shell you dispatch from, or, for the [worktree-guard entries](#write-or-command-blocked-because-the-path-cannot-be-safely-resolved) below, in any session isolated in a worktree or running a worktree-isolated subagent; where a message is specific to one surface, its entry says so.
26252657 

feature-availability Changed · +8 / -5 lines

from line 32
3232 
3333* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool search](/docs/en/mcp#configure-tool-search) is off by default when `ANTHROPIC_BASE_URL` points to a non-first-party host, and isn't supported on Google Cloud's Agent Platform models earlier than the Claude 4.5 generation or on Microsoft Foundry [deployments hosted on Azure](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry#hosting-options)
3434* **Subagents**: the built-in [Explore subagent](/docs/en/sub-agents#built-in-subagents) caps its inherited model at Opus on the Claude API, and inherits the main conversation's model directly on any other provider, including Claude Platform on AWS
35* **[Commands](/docs/en/commands#all-commands)**: `/design-sync`, `/import` with its `claude import` subcommand form, and `/radio` are unavailable on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform on AWS, `/voice` requires a claude.ai account, and `/list-agents` and its alias `/peers` are available only in sessions where [cross-session messaging is enabled](/docs/en/cross-session-messaging#availability)
35* **[Commands](/docs/en/commands#all-commands)**:
36 * `/design-sync` and `/import` with its `claude import` subcommand form are unavailable on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and Claude Platform on AWS
37 * `/voice` requires a claude.ai account
38 * `/list-agents` and its alias `/peers` are available only in sessions where [cross-session messaging is enabled](/docs/en/cross-session-messaging#availability)
3639 
3740### Features that require a Claude subscription
3841 
from line 220
217220 
218221<Tabs>
219222 <Tab title="Amazon Bedrock">
220 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [web search](/docs/en/tools-reference#websearch-tool-behavior), [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync`, `/import`, and `/radio` commands](/docs/en/commands#all-commands).
223 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [web search](/docs/en/tools-reference#websearch-tool-behavior), [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync` and `/import` commands](/docs/en/commands#all-commands).
221224 
222225 **Partial support:**
223226 
from line 233
230233 </Tab>
231234 
232235 <Tab title="Claude Platform on AWS">
233 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), [GitHub Actions](/docs/en/github-actions), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync`, `/import`, and `/radio` commands](/docs/en/commands#all-commands).
236 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), [GitHub Actions](/docs/en/github-actions), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync` and `/import` commands](/docs/en/commands#all-commands).
234237 
235238 **Available where Amazon Bedrock is not:** [web search](/docs/en/tools-reference#websearch-tool-behavior).
236239 
from line 245
242245 </Tab>
243246 
244247 <Tab title="Google Cloud's Agent Platform">
245 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync`, `/import`, and `/radio` commands](/docs/en/commands#all-commands).
248 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync` and `/import` commands](/docs/en/commands#all-commands).
246249 
247250 **Partial support:**
248251 
from line 259
256259 </Tab>
257260 
258261 <Tab title="Microsoft Foundry">
259 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), [GitLab CI/CD](/docs/en/gitlab-ci-cd), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync`, `/import`, and `/radio` commands](/docs/en/commands#all-commands).
262 **Not available:** all [features that require a Claude subscription](#features-that-require-a-claude-subscription), plus [fast mode](/docs/en/fast-mode), [Advisor](/docs/en/advisor), [Channels](/docs/en/channels), [GitLab CI/CD](/docs/en/gitlab-ci-cd), the [analytics dashboard](/docs/en/analytics), [server-managed settings](/docs/en/server-managed-settings), and the [`/design-sync` and `/import` commands](/docs/en/commands#all-commands).
260263 
261264 **Partial support:**
262265 

statusline Changed · +11 / -4 lines

from line 188
188188| `thinking.enabled` | Whether extended thinking is enabled for the session |
189189| `rate_limits.five_hour.used_percentage`, `rate_limits.seven_day.used_percentage` | Percentage of the 5-hour or 7-day rate limit consumed, from 0 to 100 |
190190| `rate_limits.five_hour.resets_at`, `rate_limits.seven_day.resets_at` | Unix epoch seconds when the 5-hour or 7-day rate limit window resets |
191| `rate_limits.spend_limit.used_percentage`, `rate_limits.spend_limit.resets_at` | Behind a [Claude apps gateway](/docs/en/claude-apps-gateway-spend-limits#usage-warnings-in-claude-code), the percentage used of the spend limit that applies to you, and the Unix epoch seconds when its period resets. The percentage runs from 0 to 100, or above 100 once you exceed the limit. Requires Claude Code v2.1.251 or later |
191192| `prompt_cache` | The session's [prompt cache](/docs/en/prompt-caching) statistics for the main conversation: hit ratio, misses, and whether the cache is warm. See [prompt cache fields](#prompt-cache-fields) for every field. Absent until the main conversation's first API response. Requires Claude Code v2.1.251 or later |
192193| `session_id` | Unique session identifier |
193194| `session_name` | Session name. Uses the custom name set with the `--name` flag or `/rename` when one exists, otherwise the AI-generated session title. The [default display name](/docs/en/sessions#name-your-sessions), such as `my-app-3f`, doesn't populate this field. Absent when the session has neither a custom name nor an AI-generated title |
from line 286
285286 "seven_day": {
286287 "used_percentage": 41.2,
287288 "resets_at": 1738857600
289 },
290 "spend_limit": {
291 "used_percentage": 62.8,
292 "resets_at": 1740787200
288293 }
289294 },
290295 "vim": {
from line 324
319324 * `agent`: appears only when running with the `--agent` flag or agent settings configured
320325 * `pr`: appears only while an open PR or GitLab merge request is found for the current branch, and is removed once it merges or closes. `pr.review_state` and `pr.kind` may be independently absent
321326 * `worktree`: appears only while the session is in a [worktree session](/docs/en/worktrees). When present, `branch` and `original_branch` may also be absent for hook-based worktrees
322 * `rate_limits`: appears only for Claude.ai subscribers (Pro/Max) after the first API response in the session. Each window (`five_hour`, `seven_day`) may be independently absent, and Claude Code drops a window once its `resets_at` time passes. Use `jq -r '.rate_limits.five_hour.used_percentage // empty'` to handle absence gracefully.
327 * `rate_limits`: appears only for Claude.ai Pro and Max subscribers, or behind a Claude apps gateway that sets a spend limit for you, and only after the first API response in the session. Each window (`five_hour`, `seven_day`, `spend_limit`) may be independently absent, and Claude Code drops a window once its `resets_at` time passes. Use `jq -r '.rate_limits.five_hour.used_percentage // empty'` to handle absence gracefully.
323328 * `prompt_cache`: appears after the main conversation's first API response. See [prompt cache fields](#prompt-cache-fields)
324329 
325330 **Fields that may be `null`**:
from line 803
798803 
799804### Rate limit usage
800805 
801Display Claude.ai subscription rate limit usage in the status line. The `rate_limits` object contains `five_hour` (5-hour rolling window) and `seven_day` (weekly) windows. Each window provides `used_percentage` (0-100) and `resets_at` (Unix epoch seconds when the window resets).
806Display Claude.ai subscription rate limit usage in the status line. The `rate_limits` object contains a rolling `five_hour` window and a weekly `seven_day` window. Each window provides `used_percentage`, from 0 to 100, and `resets_at`, the Unix epoch seconds when the window resets.
802807 
803This field is only present for Claude.ai subscribers (Pro/Max) after the first API response. Each script handles the absent field gracefully:
808Behind a Claude apps gateway with spend limits, `rate_limits` carries `spend_limit` with the same two fields for the spend limit that applies to you, except that its `used_percentage` can go above 100 once you exceed the limit. Requires Claude Code v2.1.251 or later.
809 
810The `rate_limits` object is only present for Claude.ai Pro and Max subscribers, or behind a Claude apps gateway with spend limits, and only after the first API response. Each script handles the absent field gracefully:
804811 
805812<CodeGroup>
806813 ```bash Bash theme={null}

terminal-config Changed · +17 / -16 lines

from line 212
212212 
213213 Set the input box border color and the accent shown while a permission mode or indicator is active.
214214 
215 | Token | Controls |
216 | :------------- | :------------------------------------------------- |
217 | `promptBorder` | Input box border in Manual mode |
218 | `planMode` | Plan mode accent and border |
219 | `autoAccept` | Accept-edits mode accent and border |
220 | `bashBorder` | Input box border when entering a `!` shell command |
221 | `ide` | IDE connection indicator |
222 | `fastMode` | Fast mode indicator |
215 | Token | Controls |
216 | :------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
217 | `promptBorder` | Input box border in Manual mode |
218 | `planMode` | Plan mode accent and border |
219 | `autoAccept` | Accept-edits mode accent and border |
220 | `bashBorder` | Input box border when entering a `!` shell command |
221 | `ide` | IDE connection indicator |
222 | `fastMode` | Fast mode indicator |
223 | `effortUltra` | The `ultracode` tag on the input box border while [ultracode](/docs/en/model-config#adjust-effort-level) is on. Your override of this color takes effect on Claude Code v2.1.239 or later |
223224 
224225 #### Diff rendering
225226 
226227 Color added and removed code in file edits and reviews.
227228 
228 | Token | Controls |
229 | :------------------ | :------------------------------------------------- |
230 | `diffAdded` | Background of added lines |
231 | `diffRemoved` | Background of removed lines |
232 | `diffAddedDimmed` | Background of unchanged context near added lines |
233 | `diffRemovedDimmed` | Background of unchanged context near removed lines |
234 | `diffAddedWord` | Word-level highlight within an added line |
235 | `diffRemovedWord` | Word-level highlight within a removed line |
229 | Token | Controls |
230 | :------------------ | :---------------------------------------------------------------------------- |
231 | `diffAdded` | Background of added lines |
232 | `diffRemoved` | Background of removed lines |
233 | `diffAddedDimmed` | Background of added lines in the dimmed diff shown after you reject an edit |
234 | `diffRemovedDimmed` | Background of removed lines in the dimmed diff shown after you reject an edit |
235 | `diffAddedWord` | Word-level highlight within an added line |
236 | `diffRemovedWord` | Word-level highlight within a removed line |
236237 
237238 #### Fullscreen mode
238239 

workflows Changed · +8 / -0 lines

from line 319
319319 
320320Every run writes its script to a file under your session's directory in `~/.claude/projects/`. Claude receives the path when the run starts, so you can ask for it. You can open that file to read the orchestration Claude wrote, diff it against a previous run's script, or edit it and ask Claude to relaunch from the edited version.
321321 
322Claude can start a workflow from a script file only when it can already read that file without a permission prompt, such as:
323 
324* The run's own persisted script under `~/.claude/projects/`
325* A file in your working directory or an [additional directory](/docs/en/permissions#working-directories)
326* A path your [Read allow rules](/docs/en/permissions#read-and-edit) cover
327 
328Claude Code refuses a script path Claude can't read that way.
329 
322330The runtime tracks each agent's result as the run progresses, which is what makes a run [resumable](#resume-after-a-pause) within the same session.
323331 
324332### Prompt caching in a fan-out

claude-apps-gateway-spend-limits Changed · +3 / -1 lines

from line 74
7474 
7575### Usage warnings in Claude Code
7676 
77Claude Code warns a developer as they approach their cap: once utilization passes 75%, and again past 95% of their fullest cap. When the gateway blocks a request, Claude Code shows the gateway's `429` message as is, including your `admin.blocked_message`.
77Claude Code warns a developer as they approach their cap: once utilization passes 75%, and again past 95% of their most-consumed cap. When the gateway blocks a request, Claude Code shows the gateway's `429` message as is, including your `admin.blocked_message`.
7878 
7979The warning works off response headers:
8080 
from line 82
8282* With v2.1.225 or later on the developer's machine as well, Claude Code reads the headers and shows the warning.
8383 
8484The headers always describe the developer's own cap: the gateway strips the upstream provider's rate-limit headers, which describe your shared quota, and never forwards them.
85 
86With v2.1.251 or later on the developer's machine, Claude Code also reads the same headers to show a **Spend limit** bar in `/usage`, with the percentage of their cap used and when it resets, and to add a `rate_limits.spend_limit` object to the [status line](/docs/en/statusline#rate-limit-usage) input. Claude Code shows both as a percentage rather than a dollar amount, and needs nothing newer than v2.1.225 on the gateway server.
8587 
8688## Admin API reference
8789 

commands Changed · +1 / -1 lines

from line 110
110110| `/powerup` | Discover Claude Code features through quick interactive lessons with animated demos |
111111| `/pr-comments [PR]` | Removed in v2.1.91. Ask Claude directly to view pull request comments instead. On earlier versions, fetches and displays comments from a GitHub pull request; automatically detects the PR for the current branch, or pass a PR URL or number. Requires the `gh` CLI |
112112| `/privacy-settings` | View and update your privacy settings. Only available for Pro and Max plan subscribers |
113| `/radio` | Open Claude FM lo-fi radio in your browser. Prints the stream URL when no browser is available. Not available on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS |
113| `/radio` | Open Claude FM lo-fi radio in your browser. Prints the stream URL when no browser is available |
114114| `/rate-limit-options` | Show ways to keep working when a claude.ai usage limit blocks a request: wait and [continue automatically when the limit resets](/docs/en/interactive-mode#wait-for-a-usage-limit-to-reset), add [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription), or upgrade your plan. Claude Code can also open this menu on its own when you hit a limit at your own terminal. See [Turn automatic continue off](/docs/en/interactive-mode#turn-automatic-continue-off). Requires a claude.ai subscription. Doesn't appear in the command menu; type it in full. The wait-and-continue rows require Claude Code v2.1.234 or later |
115115| `/recap` | Generate a one-line summary of the current session on demand. See [Session recap](/docs/en/interactive-mode#session-recap) for the automatic recap that appears after you've been away |
116116| `/release-notes` | View the changelog in an interactive version picker. Select a specific version to see its release notes, or choose to show all versions. The notes appear in your transcript without entering the conversation Claude sees |

desktop Changed · +1 / -1 lines

from line 354
354354 
355355Through this surface, Claude sees only the sessions the desktop app runs itself: local, [SSH](#ssh-sessions), and [WSL](/docs/en/desktop-wsl) sessions in the Code tab. Claude doesn't see cloud sessions, or sessions you started from the terminal CLI or the VS Code extension, even in worktrees of the same project, so with nine terminal worktrees open and two desktop sessions, Claude answering in one of them reports the one other desktop session. Claude never lists the session you're asking from. By default it sees the 20 most recently active sessions and skips archived sessions unless you ask for them. [Cross-session messaging](/docs/en/cross-session-messaging) separately lets Claude message [your other Claude Code sessions](/docs/en/cross-session-messaging#see-which-sessions-claude-can-reach), including terminal sessions.
356356 
357When Claude messages another session through this surface, Claude Code shows it there as a card labeled with the sending session's title and a link back, so you can always tell where a message came from. If the receiving session is mid-task, Claude Code holds the message and Claude reads it once the current work finishes. Claude can't deliver to an archived session, and tells you when a message doesn't go through.
357When Claude messages another session through this surface, Claude Code shows it there as a card labeled with the sending session's title and a link back, so you can always tell where a message came from. If the receiving session is mid-task, Claude Code holds the message and Claude reads it once the current work finishes. The receiving Claude can reply, and Claude Code delivers the reply back through this surface. Claude can't deliver to an archived session, and tells you when a message doesn't go through.
358358 
359359Claude Code applies four safety behaviors across sessions:
360360 

permissions Changed · +4 / -0 lines

from line 397
397397 
398398For example, with `Read(./project/**)` allowed and `Read(~/.ssh/**)` denied, a symlink at `./project/key` pointing to `~/.ssh/id_rsa` is blocked: the target fails the allow rule and matches the deny rule.
399399 
400When a tool opens an approved file, Claude Code [confirms the path still resolves to the location the permission check approved](/docs/en/errors#refusing-after-a-symlink-changed).
401 
402Grep and Glob search the directory the `path` argument resolves to. Claude Code applies `Read` deny rules to that directory.
403 
400404### WebFetch
401405 
402406WebFetch rules use a `domain:` prefix and match against the hostname of the requested URL. Matching is case-insensitive, supports `*` wildcards, and strips a trailing `.` from both the rule and the hostname so `example.com.` and `example.com` are treated the same.

sub-agents Changed · +2 / -0 lines

from line 839
839839 
840840Background subagents run with a [smaller built-in tool set](#available-tools) than foreground subagents, except for conversation forks, and they surface every permission prompt in your main session. When you answer one of those prompts with a choice that lasts beyond that one tool call, such as a grant that lasts for the rest of the session, Claude Code applies your answer to the whole session, including your main conversation.
841841 
842A background subagent can leave a background [Bash or PowerShell command](/docs/en/tools-reference#background-commands) [running past the end of its turn](/docs/en/interactive-mode#how-backgrounding-works). When that command ends, Claude Code sends the subagent a notification.
843 
842844A background subagent's results reach Claude as a completion notification in a later turn. Claude waits for that notification before reporting the subagent's results, and if you ask about progress first, it reports that the subagent is still running. Before v2.1.211, Claude sometimes reported results for a background subagent that hadn't finished.
843845 
844846You can also steer this yourself: