preserved-thinking changedbuild-with-claude/preserved-thinking
Nearest release: v2.1.309, 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
36
where the diff opens
First seen
1 Sep 2026
this site's first read of the page
Recorded edits31to this page, all time
The whole hunk
from line 36, old and new numbered
/
from line 36
3636
3737Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks produced by each other and by earlier Claude models. No other 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 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.
39Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Claude Models on Google Cloud (Google managed), 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, 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.
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 Claude Models on Google Cloud (Google managed), from Claude Haiku 5.5, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On those two platforms, 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 those platforms. 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
43Claude Haiku 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, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, Claude Opus 5.5 and Claude Sonnet 5.5 read thinking blocks from Claude Haiku 5.5; no other model does. So a conversation that moves from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning, and so does one that moves from Claude Haiku 5.5 up to Claude Opus 5.5 or Claude Sonnet 5.5 on the Claude API and Google Cloud. One that moves onto Claude Haiku 5.5 from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or a Claude Fable or Claude Mythos model runs the turns after the switch without the previous model's reasoning, and so does any other move away from Claude Haiku 5.5.
43Claude Haiku 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, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read thinking blocks from Claude Haiku 5.5; no other model does. So a conversation that moves from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning, and so does one that moves from Claude Haiku 5.5 up to Claude Opus 5.5 or Claude Sonnet 5.5 on the Claude API and Claude Models on Google Cloud (Google managed). One that moves onto Claude Haiku 5.5 from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or a Claude Fable or Claude Mythos model runs the turns after the switch without the previous model's reasoning, and so does any other move away from Claude Haiku 5.5.
4444
4545* **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.
4646* **A conversation that moves from Claude Fable 5.1 to any model other than Claude Mythos 5.1 loses Claude Fable 5.1's reasoning for that request.** This occurs 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 71
7171
7272Thinking 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.
7373
74On 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.
74On the Claude API and Claude Models on Google Cloud (Google managed), 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.
7575
7676## Keeping the prefix unchanged
7777
from line 1046
10461046
10471047Each common prefix edit has a replacement that gives the model the same information and leaves earlier bytes unchanged, so later thinking stays valid. Find the edit your code makes today in the first column:
10481048
1049| Instead of | Use | Beta header |
1050| --------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
1051| Rebuilding the top-level `system` prompt | A [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions) | None |
1052| Re-rendering the context in your first user message (environment, date, memory, project instructions) on each request | Render it once and resend it unchanged. When something changes, [put the new version in the newest turn](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#changing-context) | None |
1053| Clearing or shortening old `tool_result` content, or re-encoding old images, in place | Shorten a tool result or downscale an image before the first time you send it, not after. To clear old results later, [trim context on the server](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#server-side-trimming) with `clear_tool_uses_20250919` | `context-management-2025-06-27` |
1054| Injecting a reminder and deleting it on the next request | A [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#per-turn-reminders) (`clear_at: "next_user_message"`) | `mid-conversation-system-clear-at-2026-08-21` |
1055| Adding or removing entries in `tools` | [`tool_addition` and `tool_removal` blocks](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#tool-changes) | `inline-tools-2026-09-15` (add `mcp-client-2026-09-15` when the tool comes from an MCP server connected through the MCP connector), or the older `mid-conversation-tool-changes-2026-07-01`, which works on the Claude API, Amazon Bedrock, and Google Cloud |
1056| Changing top-level `output_config.effort` (restarts the cache, doesn't affect thinking) | A [per-message `output_config`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#effort-changes) | `mid-conversation-output-config-2026-07-01` |
1057| Dropping or summarizing old turns on the client | [On-demand compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) to keep the recent turns with their thinking, other server-side [compaction or context editing](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#server-side-trimming), or [client-side compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client) that keeps no stale thinking | `compact-2026-09-04` |
1058| An image or document URL whose bytes change between requests | A [`file_id` from the Files API](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#files-by-id), or base64 | None |
1049| Instead of | Use | Beta header |
1050| --------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1051| Rebuilding the top-level `system` prompt | A [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions) | None |
1052| Re-rendering the context in your first user message (environment, date, memory, project instructions) on each request | Render it once and resend it unchanged. When something changes, [put the new version in the newest turn](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#changing-context) | None |
1053| Clearing or shortening old `tool_result` content, or re-encoding old images, in place | Shorten a tool result or downscale an image before the first time you send it, not after. To clear old results later, [trim context on the server](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#server-side-trimming) with `clear_tool_uses_20250919` | `context-management-2025-06-27` |
1054| Injecting a reminder and deleting it on the next request | A [turn-scoped system message](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#per-turn-reminders) (`clear_at: "next_user_message"`) | `mid-conversation-system-clear-at-2026-08-21` |
1055| Adding or removing entries in `tools` | [`tool_addition` and `tool_removal` blocks](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#tool-changes) | `inline-tools-2026-09-15` (add `mcp-client-2026-09-15` when the tool comes from an MCP server connected through the MCP connector), or the older `mid-conversation-tool-changes-2026-07-01`, which works on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed) |
1056| Changing top-level `output_config.effort` (restarts the cache, doesn't affect thinking) | A [per-message `output_config`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#effort-changes) | `mid-conversation-output-config-2026-07-01` |
1057| Dropping or summarizing old turns on the client | [On-demand compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand) to keep the recent turns with their thinking, other server-side [compaction or context editing](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#server-side-trimming), or [client-side compaction](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#custom-compaction-on-the-client) that keeps no stale thinking | `compact-2026-09-04` |
1058| An image or document URL whose bytes change between requests | A [`file_id` from the Files API](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#files-by-id), or base64 | None |
10591059
10601060All of these assume you [send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned). Mid-conversation system messages, turn-scoped system messages, and tool changes aren't available on every model: [Mid-conversation system messages and tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) lists the models that accept them. If your code serves several models, keep editing the top-level `system` prompt for the models that don't accept them.
10611061
from line 1161
11611161
11621162### Add or remove tools with `tool_addition` and `tool_removal`
11631163
1164Editing the `tools` array mid-session invalidates preserved thinking blocks. Leave the array as you first sent it, and change which tools the model can use by appending a `role: "system"` message that carries `tool_addition` or `tool_removal` blocks. These are [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) and need the beta header `inline-tools-2026-09-15`, which is available on the Claude API. The older `mid-conversation-tool-changes-2026-07-01` header still works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, and Google Cloud.
1164Editing the `tools` array mid-session invalidates preserved thinking blocks. Leave the array as you first sent it, and change which tools the model can use by appending a `role: "system"` message that carries `tool_addition` or `tool_removal` blocks. These are [mid-conversation tool changes](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#mid-conversation-tool-changes) and need the beta header `inline-tools-2026-09-15`, which is available on the Claude API. The older `mid-conversation-tool-changes-2026-07-01` header still works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, and Claude Models on Google Cloud (Google managed).
11651165
11661166You have two ways to use these blocks:
11671167
from line 1229
12291229
12301230### Change effort with a per-message `output_config`
12311231
1232Changing 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. Where the model and platform support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), use it 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`. On Claude Haiku 5.5, per-message effort is available on the Claude API and Google Cloud and needs adaptive thinking.
1232Changing 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. Where the model and platform support [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta), use it 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`. On Claude Haiku 5.5, per-message effort is available on the Claude API and Claude Models on Google Cloud (Google managed) and needs adaptive thinking.
12331233
12341234```json
12351235{ "role": "system", "content": [], "output_config": { "effort": "low" } }
No line in this hunk matches that.