fix(pi-as-claude): pass max thinking level through to pi - #433
Merged
Conversation
pi added a native max thinking level (off|minimal|low|medium|high|xhigh|max), so the wrapper's max->xhigh downgrade with a stderr note is obsolete. all effort levels now pass through to --thinking verbatim; pi validates them. docs and mock-pi tests updated accordingly. verified with ralphex 1.6.0 and pi 0.84.1.
umputun
added a commit
that referenced
this pull request
Aug 19, 2026
Two separable problems found reviewing PR #433. pi drops an unknown --thinking value with only a warning and runs at its default, which is a one-field upstream bug. Separately, nothing in the wrapper can observe the level a run actually used, because pi clamps to model capability on every version and print-mode JSON never publishes the effective level.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
pi added a native
maxthinking level (earendil-works/pi#6097 (comment)), but the pi-as-claude wrapper still downgraded ralphex'smaxeffort toxhighwith a stderr note. this removes the special case: all effort levels pass through to pi's--thinkingverbatim and pi validates them. docs and mock-pi tests updated accordingly.verified with ralphex 1.6.0 and pi 0.84.1:
--task-model="k3:max"reaches pi as--thinking max; wrapper tests 70/70, shellcheck clean.