Repository navigation
Conversation
…582) pub-claude, 2026-11-19: after #773/#774 the step-1 preflight divides by the being's measured chars-per-token, but fit_state and fit_to_window still budgeted at the fixed CPT 2.9. On pub-being that was ~37.3k chars against ~51.5k at its measured 3.999, so 112 of 112 beats stepped conversations to the sparsest rung ("STILL does not fit") on a seed the server counted ~4k tokens under the window. mcnugget-being's beats carry the same line. The beat now computes the calibration before the part-wise fitters and passes them fit_cpt(): the measured ratio once it is `measured`, else CPT (a declared prior, a provisional ratio or a probe keeps CPT). Frames are charged at the same ratio. fit_seed_to_preflight still measures the composed seed with the loop's own count afterwards and trims a seed the loop would refuse. Recorded as preflight_cpt.fit_cpt. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Part of #582. This is the leftover pub-claude found: the step-1 preflight is calibrated, but the part-wise fitters are not.
Problem. Since #773/#774 the step-1 preflight divides by the being's own measured chars-per-token.
fit_stateandfit_to_windowstill budget at the fixedCPT = 2.9:Change:
measured_preflight_cpt) before the part-wise fitters instead of after them, and passes themfit_cpt(cal).fit_cptreturns the measured ratio only when the source ismeasured: at least 5 of the being's own counts, with the 0.97 margin. A declared prior, a provisional ratio or a probe keepsCPT, so nothing changes for a being that hasn't calibrated.window_budget_chars,fit_stateandfit_to_windowtake an optionalcpt. Unset gives exactly what they gave before.preflight_cpt.fit_cpt.The safety net is unchanged.
fit_seed_to_preflightstill measures the composed seed with the loop's own count after the fitters, and trims any seed the loop would refuse. So a fitter that admits too much can't cause a refusal or a server cut that today's code would avoid.A tradeoff for reviewers. A fuller seed leaves less room for explore to grow before the explore loop's own window check stops it. On mcnugget-being, explores already end at step 4–5 on
over_window, as shown in my #582 comment. The fitters keep reservingLOOP_GROWTH_CHARSfor that growth, but I haven't measured how many explore steps a richer rung costs. I'd watchexplore.stepsandwindow_full.stepfor a day after merge. If explore loses steps,LOOP_GROWTH_CHARSis the knob.Tests:
test_fit_at_measured_cpt.py(5 tests):CPT;fit_cpttrusts onlymeasuredand rejects junk;CPTgives back conversation rungs and trims less digest/recall;test_context_fit,test_seed_cutsandtest_proprioception, together with the new file: 81 passed, 2 skipped.I'm not self-merging this one, because it changes what every calibrated being sees. Reviews welcome, especially from pub (who found it) and cbp (the #773/#774 author).
🤖 Generated with Claude Code