claude-api-skill changedagents-and-tools/agent-skills/claude-api-skill
Nearest release: v2.1.286, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+22added
Lines−1removed
From line
27
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits8to this page, all time
## Checking an integration for preserved thinking
The whole hunk
from line 27, old and new numbered
/
from line 27
2727* **Batch processing:** Offline batch processing at 50% cost
2828* **Prompt caching:** Prefix-stability design, breakpoint placement, and silent-invalidator audit
2929* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide))
30* **Preserved thinking migration:** Finding, measuring, and fixing the history edits that invalidate `thinking` blocks, available through the `/claude-api preserved-thinking-migration` subcommand
3031* **Current model information:** Model IDs, context window sizes, and pricing
3132* **Common pitfalls:** Detailed guidance on avoiding frequent mistakes when integrating with the API
3233
from line 121
120121* **Cloud platform detection**, preserving platform-specific model ID formats (for example, the `anthropic.` prefix on Amazon Bedrock) and skipping changes for features that are unavailable on partner-operated platforms
121122* **Breaking parameter changes**, such as removing `temperature`, `top_p`, and `top_k` for Claude Opus 4.8 and Claude Opus 4.7, and converting `thinking: {type: "enabled", budget_tokens: N}` to `thinking: {type: "adaptive"}`
122123* **Prefill replacement**, converting assistant-message prefill patterns to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) where applicable
123* **Beta header cleanup**, removing beta headers that the target model doesn't require (for example, `effort-2025-11-24`, `fine-grained-tool-streaming-2025-05-14`, `interleaved-thinking-2025-05-14`) and switching back from `client.beta.messages.create` to `client.messages.create`
124* **Beta header cleanup**, removing beta headers that the target model doesn't require (for example, `effort-2025-11-24`, `fine-grained-tool-streaming-2025-05-14`, `interleaved-thinking-2025-05-14`) and switching back from `client.beta.messages.create()` (python, typescript, ruby; go: `client.Beta.Messages.New()`; java: `client.beta().messages().create()`; csharp: `client.Beta.Messages.Create()`; php: `$client->beta->messages->create()`) to `client.messages.create()` (python, typescript, ruby; go: `client.Messages.New()`; java: `client.messages().create()`; csharp: `client.Messages.Create()`; php: `$client->messages->create()`)
124125* **Effort calibration**, recommending an `output_config.effort` starting point for the target model (for example, the default `high` on Claude Opus 5, and `xhigh` for coding and agentic use cases on Claude Opus 4.8 and Claude Opus 4.7)
125126* **Prompt-behavior tuning**, flagging length-control, tool-triggering, subagent, and instruction-following prompts that may behave differently on the target model
126127* **Silent default handling**, opting back into thinking summarization (`thinking.display: "summarized"`) when reasoning is surfaced to users on Claude Opus 4.8 and Claude Opus 4.7
from line 130
129130As it edits, the skill explains each change and its motivation inline. On completion, it produces a checklist of items that require manual verification (typically integration tests, length-control prompt tuning, and cost/rate-limit re-baselining).
130131
131132For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Migrating to Claude Opus 5.5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Migrating to Claude Sonnet 5.5 from Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#migrating-from-claude-sonnet-5), and [Migrating to Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide).
133
134## Checking an integration for preserved thinking
135
136[Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) keeps a `thinking` block valid only while the `system` prompt, `tools`, and messages before it stay unchanged. To find and fix the places where your code edits that history, open the repository that builds your requests and invoke the `preserved-thinking-migration` subcommand:
137
138```text wrap
139/claude-api preserved-thinking-migration
140```
141
142The skill works through five steps:
143
1441. **Scope:** Checks whether your integration is affected, then sends three test requests to confirm that the API reports a deliberate edit.
1452. **Find:** Captures a few of your own multi-turn sessions, diffs consecutive requests, and lists each place your code edits the prefix.
1463. **Measure:** Replays the sessions with `"drop_block"` and reports which conversations lose `thinking` blocks, at which turn, and why.
1474. **Fix:** Replaces one edit at a time with the matching pattern in [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits), and measures again after each change.
1485. **Report:** Summarizes each cause, the change made for it, and the counts before and after.
149
150If your project has an eval, the skill also compares scores and token usage with and without dropped `thinking` blocks.
151
152The test requests and replays are real Messages API requests, billed at the model's normal rates. Each replay requests only a few output tokens and sets `tool_choice` to `none`, so no tool runs. The skill states the cost and asks for your approval before it sends them.
132153
133154## Setting up a Managed Agent
134155
No line in this hunk matches that.