219| `Cloud sessions use your claude.ai login`, at the end of a policy denial that names a credential | [Command-line errors](#cloud-sessions-use-your-claude-ai-login) |219| `Cloud sessions use your claude.ai login`, at the end of a policy denial that names a credential | [Command-line errors](#cloud-sessions-use-your-claude-ai-login) |
220| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |220| `Couldn't verify your organization's policy for cloud sessions` | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |
221| `Cloud sessions aren't available:` followed by why your organization's policy couldn't be loaded | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |221| `Cloud sessions aren't available:` followed by why your organization's policy couldn't be loaded | [Command-line errors](#couldnt-verify-your-organizations-policy-for-cloud-sessions) |
222| `Cloud sessions aren't available with this Console sign-in. They need a claude.ai sign-in.` | [Unable to get organization UUID](https://code.claude.com/docs/en/claude-code-on-the-web.md#unable-to-get-organization-uuid) |
222| `Cloud sessions need a claude.ai sign-in` | [Unable to get organization UUID](https://code.claude.com/docs/en/claude-code-on-the-web.md#unable-to-get-organization-uuid) |223| `Cloud sessions need a claude.ai sign-in` | [Unable to get organization UUID](https://code.claude.com/docs/en/claude-code-on-the-web.md#unable-to-get-organization-uuid) |
223| `Nothing was stashed: "<path>" is now a folder in place of a tracked file or link` / `are now folders in place of tracked files or links` | [Command-line errors](#nothing-was-stashed-because-a-folder-replaced-a-tracked-file) |224| `Nothing was stashed: "<path>" is now a folder in place of a tracked file or link` / `are now folders in place of tracked files or links` | [Command-line errors](#nothing-was-stashed-because-a-folder-replaced-a-tracked-file) |
224| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#the-json-schema-value-is-not-a-valid-json-schema) |225| `Error: --json-schema is not a valid JSON Schema` | [Command-line errors](#the-json-schema-value-is-not-a-valid-json-schema) |
325| `File is covered by a Read deny rule in your permission settings` | [Tool errors](#file-is-covered-by-a-read-deny-rule) |326| `File is covered by a Read deny rule in your permission settings` | [Tool errors](#file-is-covered-by-a-read-deny-rule) |
326| `cannot contain null bytes (\0)` | [Tool errors](#path-cannot-contain-null-bytes) |327| `cannot contain null bytes (\0)` | [Tool errors](#path-cannot-contain-null-bytes) |
327| `Path contains null bytes` | [Tool errors](#path-cannot-contain-null-bytes) |328| `Path contains null bytes` | [Tool errors](#path-cannot-contain-null-bytes) |
329| `command contains the invisible character U+FEFF (byte order mark) or U+180E (Mongolian vowel separator), and was not run` | [Tool errors](#command-contains-an-invisible-character) |
328| `File is too large to read as an image (the limit is 128MB)` | [Tool errors](#file-is-too-large-to-read-as-an-image) |330| `File is too large to read as an image (the limit is 128MB)` | [Tool errors](#file-is-too-large-to-read-as-an-image) |
329| `Cannot read this as an image: <path> is a pipe or a device` | [Tool errors](#file-is-too-large-to-read-as-an-image) |331| `Cannot read this as an image: <path> is a pipe or a device` | [Tool errors](#file-is-too-large-to-read-as-an-image) |
330| `subagent_type is required: the general-purpose agent is not available in this session` | [Tool errors](#subagent-type-is-required) |332| `subagent_type is required: the general-purpose agent is not available in this session` | [Tool errors](#subagent-type-is-required) |
397| `Claude Code process exited with code N` | [Wrapper and IDE errors](#claude-code-process-exited-with-code-n) |399| `Claude Code process exited with code N` | [Wrapper and IDE errors](#claude-code-process-exited-with-code-n) |
398| `The connection to Claude Code ended before this message completed` | [Wrapper and IDE errors](#the-connection-to-claude-code-ended-before-this-message-completed) |400| `The connection to Claude Code ended before this message completed` | [Wrapper and IDE errors](#the-connection-to-claude-code-ended-before-this-message-completed) |
399| `Could not locate the Claude CLI on PATH` | [Wrapper and IDE errors](#could-not-locate-the-claude-cli-on-path) |401| `Could not locate the Claude CLI on PATH` | [Wrapper and IDE errors](#could-not-locate-the-claude-cli-on-path) |
402| `The Claude Code program for this computer, the <build> build, could not be found` | [Wrapper and IDE errors](#the-claude-code-program-for-this-computer-could-not-be-found) |
400| `Restored the code, but skipped N files` | [Rewind warnings and errors](#restored-the-code-but-skipped-files) |403| `Restored the code, but skipped N files` | [Rewind warnings and errors](#restored-the-code-but-skipped-files) |
401| `No files were restored: N files failed (backup missing, or the file could not be updated)` | [Rewind warnings and errors](#no-files-were-restored) |404| `No files were restored: N files failed (backup missing, or the file could not be updated)` | [Rewind warnings and errors](#no-files-were-restored) |
402| `Transcript writes are failing (...)` | [Session saving warnings](#transcript-writes-are-failing) |405| `Transcript writes are failing (...)` | [Session saving warnings](#transcript-writes-are-failing) |
485 488
486As of v2.1.198, the usual spinner tip is suppressed during retries. Once the error reason is revealed, if the failure is a 529 overload the line below the countdown also names where to check service status: `status.claude.com` on the Anthropic API, or the provider or gateway host named in the message on other configurations.489As of v2.1.198, the usual spinner tip is suppressed during retries. Once the error reason is revealed, if the failure is a 529 overload the line below the countdown also names where to check service status: `status.claude.com` on the Anthropic API, or the provider or gateway host named in the message on other configurations.
487 490
488If no data arrives on the response stream for 20 seconds while a request is still pending, the spinner shows `Waiting for API response · will retry in … · check your network` before any retry has started. The request hasn't failed yet: the countdown runs to the point where Claude Code aborts the stalled connection. After the abort, what you see depends on how far the response had got:491#### Waiting for API response
492
493The `Waiting for API response · will retry in … · check your network` banner means that Claude Code has waited at least 20 seconds without receiving any data for a request. The request hasn't failed yet: the countdown runs to the point where Claude Code aborts the stalled connection. If the abort happens:
489 494
490* Before Claude has completed a block of text or a tool call, or started one after finishing its thinking, Claude Code retries the request or ends the turn with an error. [Automatic retries](#automatic-retries) says which stalls it retries and how many times.495* Before Claude has completed a block of text or a tool call, or started one after finishing its thinking, Claude Code retries the request or ends the turn with an error. [Automatic retries](#automatic-retries) says which stalls it retries and how many times.
491* After Claude has completed a block of text or a tool call, or started one after finishing its thinking, but before Claude has finished the response, Claude Code keeps what Claude completed, continues the turn from any tool calls Claude finished, and shows [The response above may be incomplete](#the-response-above-may-be-incomplete). In a non-interactive session, and for a subagent's response in any session, Claude Code may first prompt Claude to continue the response; that entry says when it does and when you still see the notice there.496* After Claude has completed a block of text or a tool call, or started one after finishing its thinking, but before Claude has finished the response, Claude Code keeps what Claude completed, continues the turn from any tool calls Claude finished, and shows [The response above may be incomplete](#the-response-above-may-be-incomplete). In a non-interactive session, and for a subagent's response in any session, Claude Code may first prompt Claude to continue the response; that entry says when it does and when you still see the notice there.
492* After Claude finished the response, Claude Code ends the turn normally.497* After Claude finished the response, Claude Code ends the turn normally.
493 498
494The banner clears on its own once data resumes or a retry succeeds. If it reappears on every attempt, treat it as a [network issue](#unable-to-connect-to-api). Before v2.1.185, the banner appeared after 10 seconds with different wording.499The banner clears on its own once data resumes or a retry succeeds. If it reappears on every attempt, treat it as a [network issue](#unable-to-connect-to-api). If you connect through a gateway, see [The waiting banner comes and goes behind a gateway](#waiting-banner-behind-a-gateway). Before v2.1.185, the banner appeared after 10 seconds with different wording.
495
496While Claude is consulting the [advisor](https://code.claude.com/docs/en/advisor.md), the banner appears after 90 seconds without data instead of 20, because a long advisor review can send nothing for well over 20 seconds. Before v2.1.214, the 20-second threshold applied during advisor calls too, so the banner appeared during advisor reviews even when nothing was wrong.
497 500
498#### The waiting banner comes and goes behind a gateway501#### The waiting banner comes and goes behind a gateway
499 502
2495 2498
2496**What to do:**2499**What to do:**
2497 2500
2498* If your Claude Code version is earlier than v2.1.216, run `claude update`.2501* 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 repeated on every request that included the tool.
2499* Remove or [disable](https://code.claude.com/docs/en/mcp.md#disable-a-server-without-removing-it) the MCP server that declares the invalid schema. The error names the tool only by position. On v2.1.216 or later, check each server's log for a line naming a tool whose input schema would be rejected. If no log names one, disable servers one at a time.2502* Remove or [disable](https://code.claude.com/docs/en/mcp.md#disable-a-server-without-removing-it) the MCP server that declares the invalid schema. The error names the tool only by position. On v2.1.216 or later, check each server's log for a line naming a tool whose input schema would be rejected. If no log names one, disable servers one at a time.
2500* If you maintain the server, fix the tool's `input_schema`. The schema must be valid JSON Schema, and top-level property names must be 1 to 64 characters long and use only ASCII letters and digits, `_`, `.`, and `-`. See [Tools with invalid input schemas](https://code.claude.com/docs/en/mcp.md#tools-with-invalid-input-schemas).2503* If you maintain the server, fix the tool's `input_schema`. The schema must be valid JSON Schema, and top-level property names must be 1 to 64 characters long and use only ASCII letters and digits, `_`, `.`, and `-`. See [Tools with invalid input schemas](https://code.claude.com/docs/en/mcp.md#tools-with-invalid-input-schemas).
2501 2504
3589 3592
3590* `Shell command permission check failed for pattern "..."`: the command's permission check didn't allow it. [Permission checks on injected commands](https://code.claude.com/docs/en/skills.md#permission-checks-on-injected-commands) covers which results abort in each permission mode and how to pre-approve a command with `allowed-tools`3593* `Shell command permission check failed for pattern "..."`: the command's permission check didn't allow it. [Permission checks on injected commands](https://code.claude.com/docs/en/skills.md#permission-checks-on-injected-commands) covers which results abort in each permission mode and how to pre-approve a command with `allowed-tools`
3591* ``Skill <name> requires bash (`shell: bash` in frontmatter) but Git Bash was not found``: the skill's frontmatter demands bash on a machine without it. Install Git for Windows or change the frontmatter to `shell: powershell`. See [How injected commands run](https://code.claude.com/docs/en/skills.md#how-injected-commands-run)3594* ``Skill <name> requires bash (`shell: bash` in frontmatter) but Git Bash was not found``: the skill's frontmatter demands bash on a machine without it. Install Git for Windows or change the frontmatter to `shell: powershell`. See [How injected commands run](https://code.claude.com/docs/en/skills.md#how-injected-commands-run)
3592* `No shell command in <name> was run`: one of the file's `!` commands contains a raw control character other than tab or newline, so none of them runs. See [how to find and remove the character](#no-shell-command-was-run)
3593 3595
3594**What to do:**3596**What to do:**
3595 3597
3599 3601
3600### No shell command in a skill or command was run3602### No shell command in a skill or command was run
3601 3603
3602One of the `` !`<command>` `` [dynamic context commands](https://code.claude.com/docs/en/skills.md#inject-dynamic-context) in a skill or custom command file contains a raw control character other than tab or newline. Claude Code refuses the whole invocation before any of the file's commands runs.3604`No shell command in <name> was run` means a `` !`<command>` `` [dynamic context command](https://code.claude.com/docs/en/skills.md#inject-dynamic-context) in that skill or command file contains a character that the Bash or PowerShell tool refuses:
3605
3606* **Either tool**: a raw control character other than a tab or newline
3607* **PowerShell tool**: also U+FEFF or U+180E
3603 3608
3604The message names the shell tool that would have run the commands, Bash or PowerShell, and ends with the refused command. Each such character is replaced by `�` so you can see where it is:3609The message ends with the refused command, showing each refused character as `�`, as in this Bash tool example:
3605 3610
3606```text theme={null}3611```text theme={null}
3607No shell command in /my-skill was run, because the Bash tool does not accept one of them: command contains control characters that would be hidden in the approval dialog. Unprintable characters are shown as � below: remove them from the skill or command file, or from the arguments or options substituted into it.3612No shell command in /my-skill was run, because the Bash tool does not accept one of them: command contains control characters that would be hidden in the approval dialog. Unprintable characters are shown as � below: remove them from the skill or command file, or from the arguments or options substituted into it.
3610 3615
3611**What to do:**3616**What to do:**
3612 3617
3613* Find each `�` in the command quoted at the end of the message. Remove the character it stands for from the skill or command file, or from the arguments or options substituted into the file.3618* Find each `�` in the command quoted at the end of the message. Remove the character it stands for from the [skill or command file](https://code.claude.com/docs/en/skills.md#where-skills-live), or from the arguments or [options](https://code.claude.com/docs/en/plugins/manifest-reference.md#user-configuration) substituted into the file.
3614 3619
3615### Input must be provided when using `--print`3620### Input must be provided when using `--print`
3616 3621
4568 4573
4569Before v2.1.281, a null byte in a Read, Write, Edit, or NotebookEdit path ended the whole turn with an error naming `Path contains null bytes`, and the tool never ran.4574Before v2.1.281, a null byte in a Read, Write, Edit, or NotebookEdit path ended the whole turn with an error naming `Path contains null bytes`, and the tool never ran.
4570 4575
4576### Command contains an invisible character
4577
4578The [PowerShell tool](https://code.claude.com/docs/en/tools-reference.md#powershell-tool) refused to run a command that contains U+FEFF or U+180E:
4579
4580```text theme={null}
4581Error: command contains the invisible character U+FEFF (byte order mark) or U+180E (Mongolian vowel separator), and was not run. Remove the character, keep the text that needs it in a file that the command reads, or write it as $([char]0xFEFF) or $([char]0x180E) inside a double-quoted string
4582```
4583
4584**What to do:**
4585
4586* **For a command Claude wrote**: you have nothing to fix. The message tells Claude how to rewrite the command.
4587* **For a skill or command file**: the message follows `No shell command in <name> was run`. See [where to find the character and remove it](#no-shell-command-was-run).
4588
4571### File is too large to read as an image4589### File is too large to read as an image
4572 4590
4573Claude tried to read a file as an image with the [Read tool](https://code.claude.com/docs/en/tools-reference.md#read-tool-behavior), and the file is larger than 128 MB, the most Read loads from an image file. Nothing was read, and Claude receives this error as the tool result:4591Claude tried to read a file as an image with the [Read tool](https://code.claude.com/docs/en/tools-reference.md#read-tool-behavior), and the file is larger than 128 MB, the most Read loads from an image file. Nothing was read, and Claude receives this error as the tool result:
5431* Set the PATH entry as a user or system environment variable, not in your PowerShell profile. The extension doesn't run your profile, so a PATH edit that lives only there never reaches it.5449* Set the PATH entry as a user or system environment variable, not in your PowerShell profile. The extension doesn't run your profile, so a PATH edit that lives only there never reaches it.
5432* Restart VS Code after changing PATH. The extension checks the PATH that VS Code captured at startup, so a PATH change takes effect only after a restart.5450* Restart VS Code after changing PATH. The extension checks the PATH that VS Code captured at startup, so a PATH change takes effect only after a restart.
5433 5451
5452### The Claude Code program for this computer could not be found
5453
5454The [VS Code extension](https://code.claude.com/docs/en/vs-code.md) looked for the copy of Claude Code bundled inside it and found none built for your computer. The message names the build your computer needs:
5455
5456```text theme={null}
5457The Claude Code program for this computer, the Linux (linux-x64) build, could not be found.
5458```
5459
5460**What to do:**
5461
5462* If the message says which build the extension holds, you have the extension package for another platform: install the package made for the build the message names
5463* If the message doesn't say which build the extension holds, reinstall the Claude Code extension from your editor's Extensions view
5464* Or, in either case, set [`claudeCode.claudeProcessWrapper`](https://code.claude.com/docs/en/vs-code#extension-settings) to a separately installed `claude` binary
5465
5466Before v2.1.290, this appeared as `Unsupported platform: <platform>-<arch>. No compatible Claude Code binary found.`
5467
5434### The connection to Claude Code ended before this message completed5468### The connection to Claude Code ended before this message completed
5435 5469
5436The [VS Code extension](https://code.claude.com/docs/en/vs-code.md) sent your message to the `claude` process, and the connection ended without an error before the process acknowledged or finished it. The extension can't tell whether the message was processed, so it asks you to send it again:5470The [VS Code extension](https://code.claude.com/docs/en/vs-code.md) sent your message to the `claude` process, and the connection ended without an error before the process acknowledged or finished it. The extension can't tell whether the message was processed, so it asks you to send it again:
