936 pages for error.

migration-guide Claude Developer Platform · in the page models/fable-5-2/migration-guide …inking (`thinking: {type: "enabled", budget_tokens: N}`) return a 400 error. * **Effort:** All five [effort](https://platform.claude.com/docs/en/build-with-claude/effort) levels are supported, and the… overview Claude Developer Platform · in the page models/fable-5-2/overview …Forced tool use (`tool_choice` types `any` and `tool`) returns a 400 error. See [Thinking and tool choice](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#thinking-and-tool-c… whats-new-fable-5-2 Claude Developer Platform · in the page models/fable-5-2/whats-new-fable-5-2 …Fable 5.1 can break your code: * [Failed prefix checks return a 400 error](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#editing-earlier-turns-invalidates-thinking-blocks)… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …able Claude Haiku 5.5 includes the new model ID, settings that return errors, thinking changes, and a checklist for each starting model. --- <Note> This guide covers migrating [Messages API](https:… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …| | [Manual extended thinking returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#configure-thinking) | Break… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …dance to enable Claude Opus 5.5 includes request settings that return errors, thinking blocks in every response, and a checklist for each starting model. --- <Note> This guide covers migrating [Mes… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …ew-opus-5-5#thinking-cant-be-disabled). * [Forced tool use returns an error](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#forced-tool-use-is-not-supported). * [Thinking block… Models overview Claude Developer Platform · in the page models/overview …`supported` is `false` when the model rejects `"disabled"` with a 400 error, and `true` on a model that doesn’t support thinking. Even when `supported` is `true`, the API can still reject a `"disabled… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …he guidance to enable Claude Sonnet 5.5 includes settings that return errors, thinking changes, and a checklist for each starting model. --- This guide lists the code changes for moving to Claude Son… overview Claude Developer Platform · in the page models/sonnet-5-5/overview …thinking). * Setting `temperature`, `top_p`, or `top_k` returns a 400 error. * The minimum cacheable prompt length is 512 tokens. See [Prompt caching](https://platform.claude.com/docs/en/build-with-cl… whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …sonnet-5-5#turn-off-up-front-thinking). * [Forced tool use returns an error](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#forced-tool-use-is-not-supported). * [Thinking b… overview Claude Developer Platform · in the page models/sonnet-5/overview …ta header. * Setting `temperature`, `top_p`, or `top_k` returns a 400 error. * Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list)… overview Claude Developer Platform · in the page release-notes/overview …ck) for every account, whatever its age. Claude Fable 5.1 returns the error by default on accounts created on or after August 31, 2026 (see [When `prefix_mismatch_behavior` is unset](https://platform.… claude-fable-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-fable-5-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5-1 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-fable-5-2 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5-2 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-haiku-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-5-5 …or weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-opus-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4 …e carefully before acknowledging the user, since users sometimes make errors themselves. Claude tailors its response format to suit the conversation topic. For example, Claude avoids using markdown o… claude-opus-4-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-1 …e carefully before acknowledging the user, since users sometimes make errors themselves. Claude tailors its response format to suit the conversation topic. For example, Claude avoids using markdown o… claude-opus-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-6 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-sonnet-3-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-3-5 …providing general information about topics like weapons, drugs, sex, terrorism, abuse, profanity, and so on if that information would be available in an educational context, discussing legal but ethic… claude-sonnet-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4 …e carefully before acknowledging the user, since users sometimes make errors themselves. Claude tailors its response format to suit the conversation topic. For example, Claude avoids using markdown o… claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …'s weight and the specific product. For infants and toddlers, a small error can cause real harm. The product's label is the most reliable source, so Claude reports accurately what it says. If neither… develop-tests Claude Developer Platform · in the page test-and-evaluate/develop-tests …s. * Edge case analysis: Percentage of edge cases handled without errors. **Qualitative scales:** * Likert scales: “Rate coherence from 1 (nonsensical) to 5 (perfectly logical)” * Ex… handle-streaming-refusals Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/handle-streaming-refusals …() break except Exception as e: print(f"Error: {e}") ``` ```typescript TypeScript const client = new Anthropic(); let messages: Anthropic.MessageParam[] = [];… increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …sks. Each prompt then covers a single subtask, reducing inconsistency errors across scaled workflows. ## Keep Claude in character For role-based applications, maintaining consistent character requir… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …} } ``` If `injection_suspected` is `true`, return an error or a stripped summary in the `tool_result` block instead of the raw content, and consider surfacing the attempt to the user.… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …t it is: your messages, Claude's replies and thinking, tool activity, errors and warnings, and prompts. The labels are also searchable, so you can jump between sections of the transcript by searching… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …sage.md#telemetry-services) | Turn off Anthropic-bound usage metrics, error reports, and surveys on every device | `env` with `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` set to `1`; the linked section… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …, such as before committing to an approach, when stuck on a recurring error, or before declaring a task complete. The advisor receives the full conversation, including every tool call and result, and… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …hout that extra turn, the run ends with a `ResultMessage` of subtype `error_max_turns` and no final response. For example, `max_turns=2` in the loop above would have stopped before the edit step. You… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …age.type === "result" && message.subtype === "success" && !message.is_error) { console.log(message.result); } } ``` ```python Python theme={null} import asyncio from claude_agent_sdk import Cl… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …onal, so check that it isn't `None` before you read it. * Success and error results both carry it, though the final result of a [session crash](#recover-totals-after-a-session-crash) may carry it zero… Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …s. See [Add tool annotations](#add-tool-annotations). | | Control the error message Claude reads | Return `isError: true` to compose the message instead of surfacing the raw exception. See [Handle err… Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …d) { sessionId = message.session_id; } } } catch (error) { // A single-shot query() throws after yielding an error result. If the // failure was an error result, sessionId… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …UseFailure` | Yes | Yes | Tool execution failure | Handle or log tool errors | | `PostToolBatch` | No | Yes | A full batch of tool calls resolves, once per batch before the next model call | Inject co… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …sk hits the 20-turn limit instead, the result message's `subtype` is `error_max_turns` and the `query()` call raises an error after yielding it, so wrap the loop in a try block if the container needs… Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …transport types, tool search for large tool sets, authentication, and error handling. The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/docs/getting-started/intro) is an open standar… Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …reviewed. Unattended coding automation, like a CI job that fixes lint errors or reviews diffs, still fits the preset because the work itself is what the preset is written for. * **Different identity**… Observability with OpenTelemetry Claude Code CLI · in the page agent-sdk/observability …| | Log events | Structured records for each prompt, API request, API error, and tool result | `OTEL_LOGS_EXPORTER` | | Traces | Spans for each interaction, model request, tool call, and hook (beta) |… Plugins in the SDK Claude Code CLI · in the page agent-sdk/plugins …message.message.content); } } } runWithPlugin().catch(console.error); ``` ```python Python theme={null} #!/usr/bin/env python3 """Example demonstrating how to use plugins with the Agent SDK."… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …hon installs, running `pip install` against system Python fails with `error: externally-managed-environment`. ```bash theme={null} python3 -m venv .venv source .venv/bin/activate pip install claude-a… Quickstart Claude Code CLI · in the page agent-sdk/quickstart …``` > > If PowerShell blocks `Activate.ps1` with an execution policy error, run `Set-ExecutionPolicy -Scope Process RemoteSigned` first. > [!NOTE] > > Both the TypeScript and Python SDKs bundle a na… Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …pt injection (instructions embedded in content they process) or model error. Claude models are designed to resist this; see the [model overview](https://platform.claude.com/docs/en/about-claude/models… Persist sessions to external storage Claude Code CLI · in the page agent-sdk/session-storage …StoreEntry] | None: ... # Optional — omit or raise NotImplementedError async def list_sessions( self, project_key: str ) -> list[SessionStoreListEntry]: ... async def list_ses…