Documentation 2026-04-04 18:05 UTC to 2026-04-07 21:14 UTC

45 45 

46Findings include a collapsible extended reasoning section you can expand to understand why Claude flagged the issue and how it verified the problem.46Findings include a collapsible extended reasoning section you can expand to understand why Claude flagged the issue and how it verified the problem.

47 47 

48### Rate and reply to findings

49 

50Each review comment from Claude arrives with 👍 and 👎 already attached so both buttons appear in the GitHub UI for one-click rating. Click 👍 if the finding was useful or 👎 if it was wrong or noisy. Anthropic collects reaction counts after the PR merges and uses them to tune the reviewer. Reactions do not trigger a re-review or change anything on the PR.

51 

52Replying to an inline comment does not prompt Claude to respond or update the PR. To act on a finding, fix the code and push. If the PR is subscribed to push-triggered reviews, the next run resolves the thread when the issue is fixed. To request a fresh review without pushing, comment `@claude review once` as a [top-level PR comment](#manually-trigger-reviews).

53 

48### Check run output54### Check run output

49 55 

50Beyond the inline review comments, each review populates the **Claude Code Review** check run that appears alongside your CI checks. Expand its **Details** link to see a summary of every finding in one place, sorted by severity:56Beyond the inline review comments, each review populates the **Claude Code Review** check run that appears alongside your CI checks. Expand its **Details** link to see a summary of every finding in one place, sorted by severity:

39| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |39| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |

40| `ANTHROPIC_VERTEX_BASE_URL` | Override the Vertex AI endpoint URL. Use for custom Vertex endpoints or when routing through an [LLM gateway](/en/llm-gateway). See [Google Vertex AI](/en/google-vertex-ai) |40| `ANTHROPIC_VERTEX_BASE_URL` | Override the Vertex AI endpoint URL. Use for custom Vertex endpoints or when routing through an [LLM gateway](/en/llm-gateway). See [Google Vertex AI](/en/google-vertex-ai) |

41| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI. Required when using [Google Vertex AI](/en/google-vertex-ai) |41| `ANTHROPIC_VERTEX_PROJECT_ID` | GCP project ID for Vertex AI. Required when using [Google Vertex AI](/en/google-vertex-ai) |

42| `API_TIMEOUT_MS` | Timeout for API requests in milliseconds (default: 600000, or 10 minutes). Increase this when requests time out on slow networks or when routing through a proxy |42| `API_TIMEOUT_MS` | Timeout for API requests in milliseconds (default: 600000, or 10 minutes; maximum: 2147483647). Increase this when requests time out on slow networks or when routing through a proxy. Values above the maximum overflow the underlying timer and cause requests to fail immediately |

43| `AWS_BEARER_TOKEN_BEDROCK` | Bedrock API key for authentication (see [Bedrock API keys](https://aws.amazon.com/blogs/machine-learning/accelerate-ai-development-with-amazon-bedrock-api-keys/)) |43| `AWS_BEARER_TOKEN_BEDROCK` | Bedrock API key for authentication (see [Bedrock API keys](https://aws.amazon.com/blogs/machine-learning/accelerate-ai-development-with-amazon-bedrock-api-keys/)) |

44| `BASH_DEFAULT_TIMEOUT_MS` | Default timeout for long-running bash commands |44| `BASH_DEFAULT_TIMEOUT_MS` | Default timeout for long-running bash commands (default: 120000, or 2 minutes) |

45| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before they are middle-truncated |45| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before they are middle-truncated |

46| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands |46| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands (default: 600000, or 10 minutes) |

47| `CLAUDECODE` | Set to `1` in shell environments Claude Code spawns (Bash tool, tmux sessions). Not set in [hooks](/en/hooks) or [status line](/en/statusline) commands. Use to detect when a script is running inside a shell spawned by Claude Code |47| `CLAUDECODE` | Set to `1` in shell environments Claude Code spawns (Bash tool, tmux sessions). Not set in [hooks](/en/hooks) or [status line](/en/statusline) commands. Use to detect when a script is running inside a shell spawned by Claude Code |

48| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate |48| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate |

49| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |49| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |

171| `MCP_OAUTH_CALLBACK_PORT` | Fixed port for the OAuth redirect callback, as an alternative to `--callback-port` when adding an MCP server with [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials) |171| `MCP_OAUTH_CALLBACK_PORT` | Fixed port for the OAuth redirect callback, as an alternative to `--callback-port` when adding an MCP server with [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials) |

172| `MCP_REMOTE_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of remote MCP servers (HTTP/SSE) to connect in parallel during startup (default: 20) |172| `MCP_REMOTE_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of remote MCP servers (HTTP/SSE) to connect in parallel during startup (default: 20) |

173| `MCP_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of local MCP servers (stdio) to connect in parallel during startup (default: 3) |173| `MCP_SERVER_CONNECTION_BATCH_SIZE` | Maximum number of local MCP servers (stdio) to connect in parallel during startup (default: 3) |

174| `MCP_TIMEOUT` | Timeout in milliseconds for MCP server startup |174| `MCP_TIMEOUT` | Timeout in milliseconds for MCP server startup (default: 30000, or 30 seconds) |

175| `MCP_TOOL_TIMEOUT` | Timeout in milliseconds for MCP tool execution |175| `MCP_TOOL_TIMEOUT` | Timeout in milliseconds for MCP tool execution (default: 100000000, about 28 hours) |

176| `NO_PROXY` | List of domains and IPs to which requests will be directly issued, bypassing proxy |176| `NO_PROXY` | List of domains and IPs to which requests will be directly issued, bypassing proxy |

177| `OTEL_LOG_TOOL_CONTENT` | Set to `1` to include tool input and output content in OpenTelemetry span events. Disabled by default to protect sensitive data. See [Monitoring](/en/monitoring-usage) |177| `OTEL_LOG_TOOL_CONTENT` | Set to `1` to include tool input and output content in OpenTelemetry span events. Disabled by default to protect sensitive data. See [Monitoring](/en/monitoring-usage) |

178| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include MCP server names and tool details in telemetry. Disabled by default to protect PII. See [Monitoring](/en/monitoring-usage) |178| `OTEL_LOG_TOOL_DETAILS` | Set to `1` to include MCP server names and tool details in telemetry. Disabled by default to protect PII. See [Monitoring](/en/monitoring-usage) |

503 503 

504**Exit 2** means a blocking error. Claude Code ignores stdout and any JSON in it. Instead, stderr text is fed back to Claude as an error message. The effect depends on the event: `PreToolUse` blocks the tool call, `UserPromptSubmit` rejects the prompt, and so on. See [exit code 2 behavior](#exit-code-2-behavior-per-event) for the full list.504**Exit 2** means a blocking error. Claude Code ignores stdout and any JSON in it. Instead, stderr text is fed back to Claude as an error message. The effect depends on the event: `PreToolUse` blocks the tool call, `UserPromptSubmit` rejects the prompt, and so on. See [exit code 2 behavior](#exit-code-2-behavior-per-event) for the full list.

505 505 

506**Any other exit code** is a non-blocking error. stderr is shown in verbose mode (`Ctrl+O`) and execution continues.506**Any other exit code** is a non-blocking error for most hook events. stderr is shown in verbose mode (`Ctrl+O`) and execution continues.

507 507 

508For example, a hook command script that blocks dangerous Bash commands:508For example, a hook command script that blocks dangerous Bash commands:

509 509 

520exit 0 # Success: tool call proceeds520exit 0 # Success: tool call proceeds

521```521```

522 522 

523<Warning>

524 For most hook events, only exit code 2 blocks the action. Claude Code treats exit code 1 as a non-blocking error and proceeds with the action, even though 1 is the conventional Unix failure code. If your hook is meant to enforce a policy, use `exit 2`. The exception is `WorktreeCreate`, where any non-zero exit code aborts worktree creation.

525</Warning>

526 

523#### Exit code 2 behavior per event527#### Exit code 2 behavior per event

524 528 

525Exit code 2 is the way a hook signals "stop, don't do this." The effect depends on the event, because some events represent actions that can be blocked (like a tool call that hasn't happened yet) and others represent things that already happened or can't be prevented.529Exit code 2 is the way a hook signals "stop, don't do this." The effect depends on the event, because some events represent actions that can be blocked (like a tool call that hasn't happened yet) and others represent things that already happened or can't be prevented.

642* **Console users**: confirm your account has the "Claude Code" or "Developer" role assigned by your admin642* **Console users**: confirm your account has the "Claude Code" or "Developer" role assigned by your admin

643* **Behind a proxy**: corporate proxies can interfere with API requests. See [network configuration](/en/network-config) for proxy setup.643* **Behind a proxy**: corporate proxies can interfere with API requests. See [network configuration](/en/network-config) for proxy setup.

644 644 

645### Model not found or not accessible

646 

647If you see `There's an issue with the selected model (...). It may not exist or you may not have access to it`, the API rejected the configured model name.

648 

649Common causes:

650 

651* A typo in the model name passed to `--model`

652* A stale or deprecated model ID saved in your settings

653* An API key without access to that model on your current usage tier

654 

655Check where the model is set, in [priority order](/en/model-config#setting-your-model):

656 

657* The `--model` flag

658* The `ANTHROPIC_MODEL` environment variable

659* The `model` field in `.claude/settings.local.json`

660* The `model` field in your project's `.claude/settings.json`

661* The `model` field in `~/.claude/settings.json`

662 

663To clear a stale value, remove the `model` field from your settings or unset `ANTHROPIC_MODEL`, and Claude Code will fall back to the default model for your account.

664 

665To browse models available to your account, start `claude` interactively and run `/model` to open the picker. For Vertex AI deployments, see [the Vertex AI troubleshooting section](/en/google-vertex-ai#troubleshooting).

666 

645### "This organization has been disabled" with an active subscription667### "This organization has been disabled" with an active subscription

646 668 

647If you see `API Error: 400 ... "This organization has been disabled"` despite having an active Claude subscription, an `ANTHROPIC_API_KEY` environment variable is overriding your subscription. This commonly happens when an old API key from a previous employer or project is still set in your shell profile.669If you see `API Error: 400 ... "This organization has been disabled"` despite having an active Claude subscription, an `ANTHROPIC_API_KEY` environment variable is overriding your subscription. This commonly happens when an old API key from a previous employer or project is still set in your shell profile.

421 The Quick Pick confirmation is separate from `PreToolUse` hooks. An allowlist entry for `mcp__ide__executeCode` lets Claude *propose* running a cell; the Quick Pick inside VS Code is what lets it *actually* run.421 The Quick Pick confirmation is separate from `PreToolUse` hooks. An allowlist entry for `mcp__ide__executeCode` lets Claude *propose* running a cell; the Quick Pick inside VS Code is what lets it *actually* run.

422</Note>422</Note>

423 423 

424<a id="troubleshooting" />

425 

424## Fix common issues426## Fix common issues

425 427 

426### Extension won't install428### Extension won't install