OpenClaw oder Claude Code: Zwei AI-Agenten für unterschiedliche Einsatzzwecke

Claude Opus 5.5 shipped on September 22, 2026 and Claude Sonnet 5.5 on September 28. If you take code that runs on Opus 5 or Sonnet 5 and change only the model string, one of these five settings will return an HTTP 400. All five are in Anthropic's official migration guides; I reproduced the first one against the live API on October 6 and pasted the exact responses below.

A static scanner that finds these in your code (file:line) is open source: claude5-migration-kit.

python scan.py path/to/your/app --target opus-5-5 python scan.py path/to/your/app --target sonnet-5-5 Enter fullscreen mode Exit fullscreen mode 1. thinking: {"type": "disabled"} returns 400 Opus 5.5 cannot turn thinking off. On Opus 5 you could send disabled at high effort or below. On Opus 5.5, both disabled and enabled + budget_tokens are rejected at every effort level:

"thinking.type.disabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior. Enter fullscreen mode Exit fullscreen mode Omit thinking (same as adaptive) and lower output_config.effort where you used to disable thinking.

Sonnet 5.5 replaces disabled with between_tools. It is the lowest thinking setting: no up-front thinking, only the short notes between tool calls.

To turn thinking off on this model, send "thinking": {"type": "between_tools"} instead of {"type": "disabled"}. The model does not think before responding. The short updates it writes between tool calls come back as thinking blocks.

Enter fullscreen mode Exit fullscreen mode # Sonnet 5 client. messages. create ( model = " claude-sonnet-5 ", max_tokens = 16000, thinking = { " type ": " disabled " }, output_config = { " effort ": " xhigh " }, messages =) # Sonnet 5.5 client. messages. create ( model = " claude-sonnet-5-5 ", max_tokens = 16000, thinking = { " type ": " between_tools " }, output_config = { " effort ": " high " }, messages =) Enter fullscreen mode Exit fullscreen mode between_tools works only at high effort or below (400 with xhigh / max ), takes no other field ( display, budget_tokens and block_binding are 400), and cannot be combined with per-message effort changes. In a request without tools it answers without thinking at all, so move multi-step reasoning tasks back to adaptive.

Both responses above are verbatim from the API ( max_tokens: 64, no charge for a 400).

{"type": "any"} and {"type": "tool", "name":...} are rejected on both models, including on the token-counting endpoint:

tool_choice: type "tool" and "any" are not supported for this model. Enter fullscreen mode Exit fullscreen mode Use tool_choice: {"type": "auto"}, mark the tool strict: true so the input matches the schema, and say in the prompt when to call it. Strict tools are capped at 20 per request and need additionalProperties: false on every object. If you only wanted JSON, use structured outputs ( output_config.format ) instead of a tool. On Amazon Bedrock, Opus 5.5 and Sonnet 5.5 have no structured outputs (strict included): send auto, name the tool in the prompt, and validate the input yourself.

Declare computer use as the computer_toolset_20260801 toolset (no beta header). Sonnet 5.5 also rejects computer_20250124 on every platform. Amazon Bedrock keeps computer_20251124. The fine-grained-tool-streaming-2025-05-14 header is a 400 next to a toolset entry; set eager_input_streaming: true on the tools that need it.

The preserved-thinking check that Fable 5.1 introduced now applies to both models: thinking blocks are bound to the model and to the conversation prefix. Editing system, tools or earlier turns and then sending the thinking blocks back is a 400 on accounts created on or after August 31, 2026 (enforced by default), or a dropped block otherwise.

With a Sonnet 5.5 executor, the advisor must be Opus 5, Opus 5.5, Sonnet 5.5, Fable 5 / 5.1 or Mythos 5 / 5.1. Opus 4.8 / 4.7 / 4.6, Sonnet 5, Sonnet 4.6 and Haiku 5.5 return 400. Advice comes back encrypted as advisor_redacted_result.

The seven things that already broke when moving from 4.x to Opus 5 / Sonnet 5 ( temperature, budget_tokens, prefill, max_tokens eaten by thinking, content on refusals, empty thinking text, the ~30% tokenizer increase) still apply.

The full guide, with per-model checklists, the prompt re-tuning table across 4.7 → 4.8 → Opus 5 → Fable 5.1 → 5.5, prompt caching and history design, and verification scripts, is a 70-page PDF: Claude 5 Migration Guide ($19). Written with AI assistance; every API behavior was checked against the live API or the official docs before publication.

Official sources: Opus 5.5 migration guide · Sonnet 5.5 migration guide