preserved-thinking changedbuild-with-claude/preserved-thinking
Nearest release: v2.1.293, published an hour 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+18added
Lines−18removed
From line
9
where the diff opens
First seen
1 Sep 2026
this site's first read of the page
Recorded edits22to this page, all time
The whole hunk
from line 9, old and new numbered
/
from line 9
99* **The model can read the block.** Each model reads its own thinking blocks and those of a fixed set of other models. Claude Fable 5.1 reads blocks from Claude Opus 5 and, on the Claude API, from Claude Opus 5.5; neither Claude Opus 5 nor Claude Opus 5.5 reads blocks from Claude Fable 5.1. If the current model can't read a block, the API drops it from that request without an error. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
1010* **Nothing before the thinking block has changed.** The top-level `system` prompt, `tools`, and `messages` before the block are its prefix. If the prefix differs from what you sent when the block was produced, that block and every later thinking block are invalid, and the API rejects the request with a 400 error or drops the invalid blocks, whichever you choose. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
1111
12Claude Sonnet 5.5's thinking blocks are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where the API enforces this.
12Thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 are also tied to the account that produced them. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking) for where the API enforces this.
1313
1414The model check applies to every account. The API enforces the prefix check by default for accounts created on or after August 31, 2026, 00:00 UTC. On older accounts, it enforces the prefix check only on requests that set `thinking.block_binding.prefix_mismatch_behavior`. **Make your integration append-only regardless of your account's age**, so the same code works on every account, including newer accounts enforced by default.
1515
from line 30
3030
3131On an older account, none of these produces an error unless the request sets `prefix_mismatch_behavior`, so a run with no errors on your own key doesn't show whether your code is affected. If people run your tool with their own API keys, those on newer accounts get the 400 error before you do. To see what they see without changing how your requests behave, send the `thinking-binding-controls-2026-08-01` beta header. On an older account, each response then flags blocks that fail the check, and the model still reads them (see [Set the mismatch behavior and read `input_transformations`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#preserved-thinking-controls)).
3232
33Also check your integration if it sends Claude Sonnet 5.5 thinking blocks from one account in a request made by a different account. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
33Also check your integration if it sends Claude Sonnet 5.5 or Claude Haiku 5.5 thinking blocks from one account in a request made by a different account. See [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking).
3434
3535## Switching models mid-conversation
3636
3737Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks produced by each other and by earlier Claude models. No earlier model reads thinking blocks from Claude Fable 5.1 or Claude Mythos 5.1.
3838
39Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Google Cloud, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. So a conversation that moves from Claude Opus 5 onto Claude Opus 5.5 keeps its reasoning, and so does one that moves from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API. One that moves from Claude Fable 5.1 or Claude Mythos 5.1 to Claude Opus 5.5, or from Claude Opus 5.5 to any model other than those two, runs the turns after the switch without the previous model's reasoning. The blocks are dropped, not rejected, as described below.
39Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Google Cloud, from Claude Sonnet 5.5 and Claude Haiku 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. So a conversation that moves from Claude Opus 5 onto Claude Opus 5.5 keeps its reasoning, and so does one that moves from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API. One that moves from Claude Fable 5.1 or Claude Mythos 5.1 to Claude Opus 5.5, or from Claude Opus 5.5 to any model other than those two, runs the turns after the switch without the previous model's reasoning. The blocks are dropped, not rejected, as described later in this section.
4040
41Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, Claude Opus 5.5 reads thinking blocks from Claude Sonnet 5.5; no other model does. So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5 keeps its reasoning, and so does one that moves from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Google Cloud. One that moves onto Claude Sonnet 5.5 from Claude Opus 5, Claude Opus 5.5, or a Claude Fable or Claude Mythos model runs the turns after the switch without the previous model's reasoning. So does any other move away from Claude Sonnet 5.5, for example a [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) to Claude Sonnet 5.
41Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, and, on the Claude API and Google Cloud, from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, Claude Opus 5.5 reads thinking blocks from Claude Sonnet 5.5; no other model does. So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5 keeps its reasoning, and so does one that moves from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Google Cloud. One that moves onto Claude Sonnet 5.5 from Claude Opus 5, Claude Opus 5.5, or a Claude Fable or Claude Mythos model runs the turns after the switch without the previous model's reasoning. So does any other move away from Claude Sonnet 5.5, for example a [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) to Claude Sonnet 5.
4242
4343* **A conversation that moves to Claude Fable 5.1 from an earlier model, or from Claude Opus 5.5 on the Claude API, keeps its reasoning.** The earlier model's thinking blocks stay readable, so the model thinks as usual from the first turn after the switch.
4444* **A conversation that moves down to an earlier model loses Claude Fable 5.1's reasoning for that request.** This happens when a router sends a turn to a cheaper model, after a [classifier refusal fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback), or during a [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback). The API removes the unreadable blocks before the prompt reaches the model. They aren't billed and don't count toward `input_tokens`.
from line 67
6767
6868## Thinking blocks stay with the account that produced them
6969
70Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. The model answers without the reasoning in the dropped blocks. Blocks from earlier models aren't affected.
70Thinking blocks that Claude Sonnet 5.5 or Claude Haiku 5.5 produces work only in the account that produced them, or in an account linked to it. When another account sends one of these blocks, the API drops the block before the model sees it, and the request succeeds. The model answers without the reasoning in the dropped blocks. Blocks from earlier models aren't affected.
7171
7272On the Claude API and Google Cloud, with 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 `input_transformations` as a `thinking_dropped` entry with `reason: "organization_binding_mismatch"`. Without the header, the drop is silent.
7373
7474## Keeping the prefix unchanged
7575
76On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, a thinking block stays valid only while everything you sent before it is unchanged on later requests. The checked prefix has three parts:
76On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, a thinking block stays valid only while everything you sent before it is unchanged on later requests. The checked prefix has three parts:
7777
7878* The top-level `system` prompt
7979* The set of `tools`
from line 120
120120
121121#### Handle the error in code
122122
123This is the 400 `invalid_request_error` shown earlier in this section. Don't resend the same body: it fails the same way every time. Retry once with the beta header and `prefix_mismatch_behavior: "drop_block"`, and store that choice with the session so every later request sends it too, including after a restart. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on. If you can't send the beta header, remove every `thinking` and `redacted_thinking` block from the history once, leave them out, and continue. Then fix the edit that caused the mismatch.
123This is the 400 `invalid_request_error` shown earlier in this section. Don't resend the same body: it fails the same way every time. Retry once with the beta header and `prefix_mismatch_behavior: "drop_block"`, and store that choice with the session so every later request sends it too, including after a restart. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools` on Claude Sonnet 5.5, or `thinking: {"type": "disabled"}` on Claude Haiku 5.5, keep the history append-only, or strip the thinking blocks from the edited turn on. If you can't send the beta header, remove every `thinking` and `redacted_thinking` block from the history once, leave them out, and continue. Then fix the edit that caused the mismatch.
124124
125125### Set the mismatch behavior and read `input_transformations`
126126
from line 129
129129* A top-level `input_transformations` array on every response
130130* A `block_binding` object on the `thinking` configuration, whose one field is `prefix_mismatch_behavior`
131131
132`block_binding` is accepted alongside `thinking.type: "adaptive"` and `thinking.type: "enabled"`. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. Sending it with `between_tools` returns a 400 error. Sending it without the beta header returns a 400 error whose message ends `block_binding: Extra inputs are not permitted`. Models that don't run the prefix check accept the object and report only model-check drops, so one request body works across models. The API reference calls the prefix check the conversation check.
132`block_binding` is accepted alongside `thinking.type: "adaptive"` and `thinking.type: "enabled"`. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. Sending it with `between_tools` on Claude Sonnet 5.5, or with `thinking: {"type": "disabled"}` on Claude Haiku 5.5, returns a 400 error. Sending it without the beta header returns a 400 error whose message ends `block_binding: Extra inputs are not permitted`. Models that don't run the prefix check accept the object and report only model-check drops, so one request body works across models. The API reference calls the prefix check the conversation check.
133133
134134The following request opts into dropping rather than rejecting. On a first turn there's nothing to replay, so `input_transformations` comes back empty:
135135
from line 396
396396
397397### When the API enforces the check
398398
399The API enforces the prefix check on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 for new accounts.
399The API enforces the prefix check on Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 for new accounts.
400400
401* **Accounts created on or after August 31, 2026, 00:00 UTC:** the API checks Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 requests and applies `"error"` unless you set `"drop_block"`. The same definition of a new account applies to the Claude API and to cloud platforms.
401* **Accounts created on or after August 31, 2026, 00:00 UTC:** the API checks Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 requests and applies `"error"` unless you set `"drop_block"`. The same definition of a new account applies to the Claude API and to cloud platforms.
402402* **Older accounts:** the API enforces the check only on requests that set `prefix_mismatch_behavior`. Setting the field opts a request in, so you can see what a new account sees without creating one. On requests that leave it unset, the API still runs the check but lets failing blocks through to the model. With the beta header, the response lists each one in `input_transformations` as `thinking_mismatch_allowed`, so you can find prefix edits without changing what the model receives.
403403
404404To find out which group your account is in, take a Claude Fable 5.1 conversation that contains a thinking block, change something before that block, and send it to Claude Fable 5.1 without the beta header or the `block_binding` field. A 400 response that names the header means your account is enforced by default. A 200 response means it isn't. To confirm, send the same request again with the beta header, still without `block_binding`: the response lists every thinking block after your edit in `input_transformations` as `thinking_mismatch_allowed`.
from line 1259
12591259
12601260Store the `content` array from each response and send it back unchanged as the assistant turn: every block type, in the order received, including `thinking` blocks whose `thinking` field is empty. A serializer that drops unknown block types, drops empty fields, or reorders blocks edits the prefix for every later turn.
12611261
1262On Claude Fable 5.1, the `thinking` field is empty by default and the `signature` carries the reasoning, so a serializer that skips empty blocks removes thinking. If it removes all of them, nothing fails and the model loses its earlier reasoning on every turn. If you parse the stream yourself, keep the block even when no thinking text arrives: it opens, receives its `signature` in a `signature_delta` event, and closes. A block sent back with an empty `signature` fails.
1262On Claude Fable 5.1 and Claude Haiku 5.5, the `thinking` field is empty by default and the `signature` carries the reasoning, so a serializer that skips empty blocks removes thinking. If it removes all of them, nothing fails and the model loses its earlier reasoning on every turn. If you parse the stream yourself, keep the block even when no thinking text arrives: it opens, receives its `signature` in a `signature_delta` event, and closes. A block sent back with an empty `signature` fails.
12631263
12641264### Add instructions with a mid-conversation system message
12651265
from line 1356
13561356* **Declare every tool up front.** Put every tool the session might need in `tools` on the first request, with `defer_loading: true` on any the model shouldn't see yet. Then turn tools on and off with `tool_addition` and `tool_removal` blocks that name them.
13571357* **Start with a snapshot and add tools as you go.** Put the tools you know about in `tools` on the first request. When a new tool comes along, define it inside a `tool_addition` block instead of editing `tools`.
13581358
1359Either way, `tools` never changes, so earlier thinking stays valid and the prompt cache still hits, with the one exception noted below.
1359Either way, `tools` never changes, so earlier thinking stays valid and the prompt cache still hits, with the one exception noted later in this section.
13601360
13611361For example, to withdraw a dangerous tool after a mode switch:
13621362
from line 1417
14171417
14181418### Change effort with a per-message `output_config`
14191419
1420Changing top-level `output_config.effort` between requests doesn't invalidate thinking, because effort isn't part of the prefix. Changing top-level effort does restart the prompt cache. On Claude Fable 5.1, use [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) instead: append a `role: "system"` message with empty `content` and the new level. It needs the beta header `mid-conversation-output-config-2026-07-01`.
1420Changing top-level `output_config.effort` between requests doesn't invalidate thinking, because effort isn't part of the prefix. Changing top-level effort does restart the prompt cache. On Claude Fable 5.1 and on Claude Haiku 5.5 with adaptive thinking, use [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) instead: append a `role: "system"` message with empty `content` and the new level. It needs the beta header `mid-conversation-output-config-2026-07-01`.
14211421
14221422```json
14231423{ "role": "system", "content": [], "output_config": { "effort": "low" } }
from line 1717
17171717 </Accordion>
17181718
17191719 <Accordion title="Does changing effort or other thinking settings between requests invalidate earlier thinking?">
1720 No. `output_config.effort`, `max_tokens`, and the `thinking` configuration aren't part of the checked prefix, which covers only `system`, `tools`, and `messages`. A top-level effort change invalidates most of the prompt cache. On Claude Fable 5.1, a [per-message effort](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#effort-changes) change keeps the prompt cache and is used as the new effort level until changed again.
1720 No. `output_config.effort`, `max_tokens`, and the `thinking` configuration aren't part of the checked prefix, which covers only `system`, `tools`, and `messages`. A top-level effort change invalidates most of the prompt cache. On Claude Fable 5.1 and on Claude Haiku 5.5 with adaptive thinking, a [per-message effort](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#effort-changes) change keeps the prompt cache and is used as the new effort level until changed again.
17211721 </Accordion>
17221722
17231723 <Accordion title="My tool list changes mid-session. How do I avoid invalidating the conversation?">
from line 1739
17391739 </Accordion>
17401740
17411741 <Accordion title="A saved session now fails on every request. How do I get it working again?">
1742 The stored history has an edit in it, so replaying it can't succeed. Send that session with `prefix_mismatch_behavior: "drop_block"` from now on, or remove its `thinking` and `redacted_thinking` blocks once and continue. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on. Thinking the model produces from that point on stays valid as long as nothing before it changes again. Then find the edit so that new sessions don't hit it. See [Handle the error in code](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#handle-the-error-in-code).
1742 The stored history has an edit in it, so replaying it can't succeed. Send that session with `prefix_mismatch_behavior: "drop_block"` from now on, or remove its `thinking` and `redacted_thinking` blocks once and continue. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools` on Claude Sonnet 5.5, or `thinking: {"type": "disabled"}` on Claude Haiku 5.5, keep the history append-only, or strip the thinking blocks from the edited turn on. Thinking the model produces from that point on stays valid as long as nothing before it changes again. Then find the edit so that new sessions don't hit it. See [Handle the error in code](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#handle-the-error-in-code).
17431743 </Accordion>
17441744
17451745 <Accordion title="My harness can route a turn to a non-Claude model. Do those turns invalidate Claude's earlier thinking?">
from line 1747
17471747 </Accordion>
17481748
17491749 <Accordion title="Can I carry a conversation's reasoning into a new conversation?">
1750 Not into a different conversation. A thinking block is usable only when it follows the exact `system`, `tools`, and `messages` it was produced from. A branch that replays that history unchanged up to the fork point keeps its thinking. A conversation that starts from anything else can't use it, so start that conversation from a summary of the task state, as in [simple compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client): the goal, decisions made, files and results so far, and the next step. Claude Sonnet 5.5's thinking blocks also can't be reused from another account (see [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking)).
1750 Not into a different conversation. A thinking block is usable only when it follows the exact `system`, `tools`, and `messages` it was produced from. A branch that replays that history unchanged up to the fork point keeps its thinking. A conversation that starts from anything else can't use it, so start that conversation from a summary of the task state, as in [simple compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client): the goal, decisions made, files and results so far, and the next step. Thinking blocks from Claude Sonnet 5.5 and Claude Haiku 5.5 also can't be reused from another account (see [Thinking blocks stay with the account that produced them](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#account-bound-thinking)).
17511751 </Accordion>
17521752</AccordionGroup>
17531753
No line in this hunk matches that.