50 pages for debug.

Debug your configuration Claude Code CLI · title debug-your-config Debugging Model Context Protocol · title docs/2024-11-05/tools/debugging Debugging Model Context Protocol · title docs/2025-03-26/tools/debugging Debugging Model Context Protocol · title docs/2025-06-18/tools/debugging Debugging Model Context Protocol · title docs/2025-11-25/tools/debugging Debugging Model Context Protocol · title docs/2026-07-28/tools/debugging Debugging Model Context Protocol · title docs/draft/tools/debugging customer-support-chat Claude Developer Platform · in the page about-claude/use-case-guides/customer-support-chat …arting with the "Greeting and general guidance" task. This also makes debugging your prompt easier as you can more quickly adjust individual parts of the overall prompt. ```python STATIC_GREETINGS_AN… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/best-practices …* Claude can iterate on the plan without touching originals * **Clear debugging:** Error messages point to specific problems **When to use:** Batch operations, destructive changes, complex validation… claude-api-skill Claude Developer Platform · in the page agents-and-tools/agent-skills/claude-api-skill …ic-ai/sdk` for TypeScript/JavaScript) * You ask Claude to help build, debug, or optimize something with the Claude API, an Anthropic SDK, or Managed Agents * You add, modify, or tune a Claude feature… reference Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/reference …| | `log_level` | Logging verbosity: `debug`, `info`, `warn`, or `error`.… bash-tool Claude Developer Platform · in the page agents-and-tools/tool-use/bash-tool …d-tools/tool-use/text-editor-tool"> View and modify text files to debug, fix, and improve code. </Card> <Card title="Tool use with Claude" icon="tool" href="https://platform.claude.com/docs/e… code-execution-tool Claude Developer Platform · in the page agents-and-tools/tool-use/code-execution-tool …file_type": "text", "content": "{\n \"setting\": \"value\",\n \"debug\": true\n}", "num_lines": 4, "start_line": 1, "total_lines": 4 } } ``` **Create file:** ```json Output { "… computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …</CodeGroup> </Accordion> <Accordion title="Log actions for debugging"> Keep a log of all actions for troubleshooting: <CodeGroup exclude="shell"> ```python Python impor… fine-grained-tool-streaming Claude Developer Platform · in the page agents-and-tools/tool-use/fine-grained-tool-streaming …that you received invalid JSON, and preserves the original input for debugging: ```json { "INVALID_JSON": "<the unparseable input you received>" } ``` Return the wrapper, serialized to a string,… overview Claude Developer Platform · in the page agents-and-tools/tool-use/overview …d-tools/tool-use/text-editor-tool"> View and modify text files to debug, fix, and improve code. </Card> <Card title="Computer use tool" icon="computer" href="https://platform.claude.com/docs/… Process results programmatically Claude Developer Platform · in the page agents-and-tools/tool-use/programmatic-tool-calling …ovide clear output format documentation in your tool description ### Debugging tips 1. **Log all tool calls and results** to track the flow 2. **Check the `caller` field** to confirm programmatic in… text-editor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/text-editor-tool …ic-schema text editor tool to view and modify text files, helping you debug, fix, and improve your code or other text documents. This allows Claude to directly interact with your files, providing hand… Log at info level Claude Developer Platform · in the page agents-and-tools/tool-use/tool-runner …, C#, and PHP tool runners don't include client-side compaction. ### Debugging tool execution When a tool throws an exception, the tool runner catches it and returns the error to Claude as a tool re… tool-search-tool Claude Developer Platform · in the page agents-and-tools/tool-use/tool-search-tool …l's name, description, argument names, or argument descriptions. **Debugging steps:** 1. Check tool name, description, argument names, and argument descriptions. Claude searches all of these fie… errors Claude Developer Platform · in the page api/errors …e response also includes a `request_id` field for easier tracking and debugging. For example: ```json JSON { "type": "error", "error": { "type": "not_found_error", "message": "The request… claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …Ds Foundry includes request identifiers in HTTP response headers for debugging and tracing. When contacting support, provide both the `request-id` and `apim-request-id` (Azure API Management) values… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …al analysis, spreadsheets, slides, and documents. * **Code review and debugging.** Bug-finding recall (outside the cybersecurity domains the safety classifiers cover) is noticeably higher than Claude… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …ls or premature stops after setting a budget, raise the budget before debugging other parameters. Size budgets against your actual task-length distribution rather than a fixed default; see [Choosing a… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …e with no thinking block at all; a multistep math problem or a tricky debugging task triggers deeper reasoning. The decision happens per request. The same conversation can contain turns with and with… using Claude Developer Platform · in the page cli-sdks-libraries/cli/using …mand structure, output formats, GJSON transforms, request bodies, and debugging for the ant CLI. --- This page covers the `ant` CLI's input and output mechanics that apply across every endpoint. For… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …s will not be equivalent. Only use the error messages for logging and debugging. ### Header compatibility While the OpenAI SDK automatically manages headers, here is the complete list of headers sup… middleware Claude Developer Platform · in the page cli-sdks-libraries/middleware …nc (request, next, ctx) => { // Before the request ctx.logger.debug("->", request.method, request.url); // Forward the request to the rest of the chain const response = await next(req… csharp Claude Developer Platform · in the page cli-sdks-libraries/sdks/csharp …m); } ``` ### Logging <Warning> All log messages are intended for debugging only. The format and content of log messages may change between releases. </Warning> Enable debug logging by setting an… go Claude Developer Platform · in the page cli-sdks-libraries/sdks/go …string]string{"my": "object"}), ) ``` The request option `option.WithDebugLog(nil)` may be helpful while debugging. See the [full list of request options](https://pkg.go.dev/github.com/anthropics/an… java Claude Developer Platform · in the page cli-sdks-libraries/sdks/java …g requests and report them back to Anthropic. For more information on debugging requests, see [Request ID](https://platform.claude.com/docs/en/api/errors#request-id). ## Retries The SDK automaticall… For Amazon Bedrock support Claude Developer Platform · in the page cli-sdks-libraries/sdks/python …PIConnectionError` | ## Request IDs > For more information on debugging requests, see [Request ID](https://platform.claude.com/docs/en/api/errors#request-id). All object responses in the SDK… typescript Claude Developer Platform · in the page cli-sdks-libraries/sdks/typescript …PIConnectionError` | ## Request IDs > For more information on debugging requests, see [Request ID](https://platform.claude.com/docs/en/api/errors#request-id). All object responses in the SDK… wif-reference Claude Developer Platform · in the page manage-claude/wif-reference …is to mint a fresh assertion for each exchange. If you still need to debug from the JWT itself, work through these checks in order: <Steps> <Step title="Decode the JWT"> Decode the assertion y… workload-identity-federation Claude Developer Platform · in the page manage-claude/workload-identity-federation …u. The cURL tab shows the underlying HTTP exchange for shell scripts, debugging, or languages without SDK support. ### Construct the SDK client You can construct the client with explicit credentials… workspaces Claude Developer Platform · in the page manage-claude/workspaces …}' | grep -i '^anthropic-workspace-id' ``` ```bash CLI # --debug prints the HTTP response, including the Anthropic-Workspace-Id # header, to stderr; > /dev/null hides the JSON body on std… dreams Claude Developer Platform · in the page managed-agents/dreams …"instructions": "Focus on coding-style preferences; ignore one-off debugging notes." } EOF ) dream_id=$(jq -r '.id' <<< "$dream") echo "$dream_id" # drm_01... ``` ```bash CLI drea… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …nt_id}` to a session URL to open the session at a specific event. ## Debugging tips * **Check session events:** Session errors are conveyed through the `session.error` event * **Review tool results:… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …lows): patterns for everyday tasks like code review, refactoring, and debugging * [Claude 101](https://anthropic.skilljar.com/claude-101) and [Claude Code in Action](https://anthropic.skilljar.com/cla… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …lan quality determines the outcome. Examples include large refactors, debugging sessions where an error keeps recurring, and tasks you want independently checked before Claude declares them done. It… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …e. This page explains what happens inside that loop so you can build, debug, and optimize your agents effectively. ## The loop at a glance Every agent session follows the same cycle: <img src="http… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …rized file access * **Log and audit** every tool call for compliance, debugging, or analytics * **Transform inputs and outputs** to sanitize data, inject credentials, or redirect file paths * **Requir… Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …github/github-mcp-server) to list recent issues. The example includes debug logging to verify the MCP connection and tool calls. Before running, create a [GitHub personal access token](https://github… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …ield(default_factory=dict) max_buffer_size: int | None = None debug_stderr: Any = sys.stderr # Deprecated stderr: Callable[[str], None] | None = None can_use_tool: CanUseTool | None =… Quickstart Claude Code CLI · in the page agent-sdk/quickstart …cluding system initialization and internal state, which is useful for debugging but noisy otherwise. <Note> This example uses streaming to show progress in real-time. If you don't need live output… Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …g For general skills troubleshooting, such as YAML syntax errors and debugging, see the [Claude Code skills troubleshooting section](/docs/en/skills#troubleshooting). ## Next steps The [Claude Code… Streaming Input Claude Code CLI · in the page agent-sdk/streaming-vs-single-mode …error text. In the Python SDK, a generator exception is logged at debug level and the session stalls without raising, so if a streaming session hangs with no output, enable debug logging and check… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …rrors` list on the result message to tell the two causes apart before debugging your schema. When an error occurs, the result message has a `subtype` indicating what went wrong: | Subtype… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …| | `debug` | `boolean`… Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …ates can each own a separate piece without stepping on each other * **Debugging with competing hypotheses**: teammates test different theories in parallel and converge on the answer faster * **Cross-l…