The whole hunk
from line 1236, old and new numbered
/
lines
from line 1236
12361236
12371237 To check an existing integration:
12381238
1239 1. Capture the exact request bodies it sends over a few normal turns, including a compaction or a tool change if your product has them. For each pair of consecutive requests, compare the `system` prompt, the `tools` array, and the shared prefix of `messages`. They should be byte-identical up to the newly appended turns.
1239 1. Capture the exact request bodies it sends over a few normal turns, including a compaction or a tool change if your product has them. For each pair of consecutive requests, compare the `system` prompt, the `tools` array, and the shared prefix of `messages`. They should be byte-identical up to the newly appended turns. An expected exception is a request that swaps in a signed `compaction` block from [on-demand compaction](https://platform.claude.com/docs/en/build-with-claude/compaction#compact-on-demand-with-the-compaction-parameter): the block replaces the messages it summarizes at the front of `messages`, and everything after it should still match.
12401240 2. Run a normal multi-turn session against `claude-fable-5-1` with the `thinking-binding-controls-2026-08-01` beta header and `prefix_mismatch_behavior: "drop_block"`, and log `input_transformations` on every response. An empty array on every turn means the history is intact. An entry with `reason: "prefix_binding_mismatch"` means something before the block at `path` changed since the previous request. An entry with `reason: "model_binding_mismatch"` means the conversation switched models, which isn't a bug in your code. This works from any account, because setting the field opts the request into enforcement. In CI, set `"error"` instead so an edit fails the run.
12411241 3. Choose a production setting. Leave the default `"error"` if a prefix mismatch can only mean a bug in your code, or set `"drop_block"` to drop the affected blocks instead of failing, and monitor the 400s or the `input_transformations` entries either way.
12421242
from line 1541
15411541
154215424. **Start at `high` effort and sweep:** The [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) default is `high`, and all five levels are supported. Keep the Claude Fable 5 guidance: `high` for most work, and `medium` as a cost control worth testing. Claude Fable 5.1's gains over Claude Fable 5 are largest at `xhigh` and `max`, but those levels also add thinking time and time-to-first-response, so step up to them for the most capability-sensitive tasks and where your evals show the gain. Run a fresh sweep on your own evals rather than carrying over a setting tuned for Claude Fable 5. See [Recommended effort levels for Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-fable-5-1).
15431543
15445. **Trim context on the server, or compact in a shape that carries no stale thinking:** If your code truncates or summarizes older turns on the client, the simplest fix is to move that work to server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) or [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing). Neither counts as an edit, because the [history check](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-preserved-thinking) compares the conversation as you sent it, so nothing they remove invalidates later thinking blocks, and compaction's [`instructions` parameter](https://platform.claude.com/docs/en/build-with-claude/compaction#custom-summarization-instructions) accepts your own summarization prompt. If you keep compaction on the client, pick one of three shapes:
15445. **Trim context on the server, or compact in a shape that carries no stale thinking:** If your code truncates or summarizes older turns on the client, the simplest fix is to move that work to server-side [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) or [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing). Neither counts as an edit, because the [history check](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-preserved-thinking) compares the conversation as you sent it, so nothing they remove invalidates later thinking blocks, and compaction's [`instructions` parameter](https://platform.claude.com/docs/en/build-with-claude/compaction#custom-summarization-instructions) accepts your own summarization prompt. If you keep recent turns verbatim behind the summary, or summarize in the background while the conversation continues, use [on-demand compaction](https://platform.claude.com/docs/en/build-with-claude/compaction#compact-on-demand-with-the-compaction-parameter) (beta header `compact-2026-09-04`, on the Claude API) rather than a client-written summary. The API writes a signed summary block that you put in place of the messages it summarizes. The thinking blocks in the turns you keep can stay valid, under the conditions that section lists. If you keep compaction on the client, pick one of three shapes:
15451545
15461546 * **Simple compaction (recommended):** replace the whole history with one summary message plus the new user turn and replay nothing else. No thinking blocks are carried over, so nothing fails. Claude models are trained on long-horizon tasks with this scheme, and it performs comparably to more elaborate ones for most workloads.
15471547 * **Keep-tail compaction:** if you keep the most recent turns verbatim behind a summary, strip the `thinking` and `redacted_thinking` blocks from those turns (text and tool calls can stay), or set `prefix_mismatch_behavior: "drop_block"`. Their thinking was produced against the full history and fails behind the summary otherwise.