thinking changedbuild-with-claude/thinking
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+7added
Lines−3removed
From line
284
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits18to this page, all time
The whole hunk
from line 284, old and new numbered
/
from line 284
284284 max_tokens: 16000,
285285 thinking: {
286286 type: "adaptive",
287 # A plain hash like this one takes display:. The typed ThinkingConfigAdaptive class
288 # spells it display_ (trailing underscore) to avoid shadowing Ruby's Kernel#display.
289 # The request still sends display.
287290 display: "summarized"
288291 },
289292 messages: [
from line 514
511514 The `signature` field is identical whichever `display` value you set. Switching `display` values between turns in a conversation is supported.
512515</Note>
513516
514In the Ruby SDK, plain hashes take `display:` as the examples show. The typed `ThinkingConfigAdaptive` class names the parameter `display_` (trailing underscore, to avoid shadowing Ruby's `Kernel#display`). Either way, the wire field is still `display`.
515
516517### Summarized thinking
517518
518519When `display` is `"summarized"`, the thinking text you receive is a summary of Claude's full thinking process rather than the raw chain of thought. Summarized thinking provides the full intelligence benefits of thinking while preventing misuse. No `display` setting returns the raw chain of thought.
from line 780
779780 stream = client.messages.stream(
780781 model: "claude-opus-4-8",
781782 max_tokens: 16000,
783 # A plain hash like this one takes display:. The typed ThinkingConfigAdaptive class
784 # spells it display_ (trailing underscore) to avoid shadowing Ruby's Kernel#display.
785 # The request still sends display.
782786 thinking: { type: "adaptive", display: "summarized" },
783787 messages: [
784788 { role: "user", content: "What is the greatest common divisor of 1071 and 462?" }
from line 1221
12171221
12181222### Long requests
12191223
1220The SDKs require streaming when `max_tokens` is greater than 21,333, to avoid HTTP timeouts on long-running requests. This is a client-side validation, not an API restriction. If you don't need to process events incrementally, use `.stream()` (java: `.createStreaming()`; csharp: `.CreateStreaming()`; go: `.NewStreaming()`; php: `->createStream()`) with `.get_final_message()` (typescript: `.finalMessage()`; ruby: `.accumulated_message`; csharp: `.Aggregate()`; go: `message.Accumulate(event)`; java, php: `MessageAccumulator`) to get the complete `Message` object without assembling it from individual events yourself. See [Streaming Messages](https://platform.claude.com/docs/en/build-with-claude/streaming#get-the-final-message-without-handling-events). Expect longer response times when thinking is active, because generating thinking blocks adds processing time. For workloads that push thinking above roughly 32k tokens per request, use [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) to avoid networking issues: such requests can run long enough to hit system timeouts and open connection limits.
1224The SDK requires streaming when `max_tokens` is greater than 21,333, to avoid HTTP timeouts on long-running requests. This is a client-side validation, not an API restriction. If you don't need to process events incrementally, use `.stream()` (java: `.createStreaming()`; csharp: `.CreateStreaming()`; go: `.NewStreaming()`; php: `->createStream()`) with `.get_final_message()` (typescript: `.finalMessage()`; ruby: `.accumulated_message`; csharp: `.Aggregate()`; go: `message.Accumulate(event)`; java, php: `MessageAccumulator`) to get the complete `Message` object without assembling it from individual events yourself. See [Streaming Messages](https://platform.claude.com/docs/en/build-with-claude/streaming#get-the-final-message-without-handling-events). Expect longer response times when thinking is active, because generating thinking blocks adds processing time. For workloads that push thinking above roughly 32k tokens per request, use [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) to avoid networking issues: such requests can run long enough to hit system timeouts and open connection limits.
12211225
12221226## Next steps
12231227
No line in this hunk matches that.