Follow Discord
Sweep 02 Oct 2026 · 18:55Z Build v2.1.288 509 read Stable v2.1.285 Latest v2.1.288 Next v2.1.288 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 29 Sep 2026
One change · api

preserved-thinking changedbuild-with-claude/preserved-thinking

Nearest release: v2.1.285, published 2 hours before 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+9added
Lines−3removed
From line 45 where the diff opens
First seen 1 Sep 2026 this site's first read of the page
Recorded edits17to this page, all time

The whole hunk

from line 45, old and new numbered
/
lines
from line 45
4545 
4646Keep sending the full history on every request, thinking blocks included, and let the API drop what the current model can't read. The API never edits your `messages` array, so the dropped blocks stay in your history. When the same history goes back to Claude Fable 5.1, its blocks are readable again, along with the earlier model's thinking. The reasoning is lost for good only if your client removes the blocks itself, for example a harness that strips thinking on a model switch or rebuilds the history from what each model used.
4747 
48![Animation: switching to Claude Opus skips Claude Fable 5.1's thinking for that turn; switching back, everything is read again](https://platform.claude.com/docs/images/preserved-thinking-model-switch.svg)
48<Frame>
49 ![Animation: switching to Claude Opus skips Claude Fable 5.1's thinking for that turn; switching back, everything is read again](https://platform.claude.com/docs/images/preserved-thinking-model-switch.svg)
50</Frame>
4951 
5052With the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers), the response lists each dropped block in a top-level `input_transformations` array with `reason: "model_binding_mismatch"`:
5153 
from line 1429
14271429 
14281430When the conversation grows too long, summarize the whole session into one user message and send only that message plus the next instruction. Nothing earlier is replayed, so there's no thinking left to fail the check, and the model reasons afresh from the summary.
14291431 
1430![Simple compaction: request 4 sends the full history with thinking on each assistant turn; request 5 sends one user message holding a summary of turns 1 to 4 plus the next instruction, so no earlier thinking is sent and nothing is checked](https://platform.claude.com/docs/images/preserved-thinking-simple-compaction.svg)
1432<Frame>
1433 ![Simple compaction: request 4 sends the full history with thinking on each assistant turn; request 5 sends one user message holding a summary of turns 1 to 4 plus the next instruction, so no earlier thinking is sent and nothing is checked](https://platform.claude.com/docs/images/preserved-thinking-simple-compaction.svg)
1434</Frame>
14311435 
14321436```json
14331437[
from line 1452
14481452 
14491453The rest of this section covers a summary you write yourself.
14501454 
1451![Keep-tail compaction: the history is replaced by a summary of turns 1 and 2 followed by turns 3 to 5 verbatim; the thinking on assistant turns 3 and 4 was produced after the original turns, not the summary, so it fails; the same request sent with prefix\_mismatch\_behavior drop\_block succeeds, the API drops those two blocks and lists them in input\_transformations](https://platform.claude.com/docs/images/preserved-thinking-keep-tail-compaction.svg)
1455<Frame>
1456 ![Keep-tail compaction: the history is replaced by a summary of turns 1 and 2 followed by turns 3 to 5 verbatim; the thinking on assistant turns 3 and 4 was produced after the original turns, not the summary, so it fails; the same request sent with prefix\_mismatch\_behavior drop\_block succeeds, the API drops those two blocks and lists them in input\_transformations](https://platform.claude.com/docs/images/preserved-thinking-keep-tail-compaction.svg)
1457</Frame>
14521458 
14531459Fix: keep the turns exactly as they are and send `prefix_mismatch_behavior: "drop_block"`. The API drops the stale thinking blocks, the model reads the kept turns' `text` and `tool_use` blocks, and the request succeeds.
14541460 
Feedback