Reasoning effort defaults by agent role (CL-5162) - #302
Merged
Conversation
Orchestrators stay on high; leaves default to medium so parent high selections do not multiply sol+high latency across the fleet. Explicit profile pins still win. Precedence is covered by unit tests.
The pure resolver now owns the never-emit-unsupported-effort invariant so callers that skip validateEffort cannot put a bad pin on the wire.
Profiles set role; orchestrator/leaf defaults drive reasoning effort unless the profile pins inference.reasoningEffort.
TheGreatAxios
force-pushed
the
stack/w1d-cl-5162-effort-role
branch
from
August 4, 2026 18:10
99c89fe to
d7803de
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack
Codex stack C — independent of PerfTrace; base
main.Linear
https://linear.app/abklabs/issue/CL-5162/reasoning-effort-defaults-by-agent-role
Summary
Default reasoning effort by agent role for task leaves; clamp unsupported effort pins in the role cascade.
Test evidence
Merge note
Independent of PerfTrace stack. Safe to review/merge separately.