feat(routing): apply opt-in effort knobs and fail-close measured status - #677
Closed
cursor[bot] wants to merge 5 commits into
Closed
feat(routing): apply opt-in effort knobs and fail-close measured status#677cursor[bot] wants to merge 5 commits into
cursor[bot] wants to merge 5 commits into
Conversation
…lation Issue #568 first slice: versioned per-role reasoning_effort_profile, fail-closed parse, replayable snapshot, and true-θ RMSE ablation. Temperature is not effort. Production route/conduct defaults stay locked. Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
…onduct Same snapshot_hash on both paths when the operator passes a catalog. Default constructor still omits the key so production payloads stay put. Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
Buyer next action: pass role_effort_catalog to attach the same snapshot on route and conduct, or omit it to keep today's payload. Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
Issue #568 honesty slice: θ̂ is (1-λ)θ and RMSE uses θ̂-θ, not a rank constant. Parse/hash fail closed on missing profiles, blank versions, fractional seeds, and extra roles. The same snapshot survives run, stream_route, and batch_route. Production defaults stay locked while measurement_status is estimated. Buyer next action: python tests/test_reasoning_effort_profile.py Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
Issue #568 successor to #650: the production-default gate stays locked unless measurement_status is measured. Boolean true-θ fails closed. stream_route persists the snapshot to --state-db. The fuzz target strips true_theta before parse so ablation invariants run. An opt-in catalog sends reasoning_effort and max_tokens on ModelClient chat, stream, and batch without changing OrchestrationPolicy defaults. Buyer next action: python tests/test_reasoning_effort_profile.py Co-authored-by: Seongho Bae <seonghobae@users.noreply.github.com>
This was referenced Aug 16, 2026
seonghobae
marked this pull request as ready for review
August 16, 2026 17:06
Author
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
seonghobae
enabled auto-merge (squash)
August 16, 2026 17:06
auto-merge was automatically disabled
August 16, 2026 18:23
Pull request was closed
Contributor
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.
Buyer next action
Run
python tests/test_reasoning_effort_profile.py. Prefer this PR over #631 and #650. Keep live route/conduct defaults unchanged whileproduction_default_change_allowedis false. Do not raise temperature to stand in for reasoning effort.Why this PR
Issue #568 honesty on #650 still fail-opened the production-default gate when
measurement_statuswas omitted or junk, accepted boolean true-θ, dropped streamed snapshots on--state-dbrestart, and never reached ablation from the fuzz target.ModelClientalso still sent a singlemax_tokensand noreasoning_efforteven when the operator opted into the catalog.What landed
production_default_change_allowedstays locked unlessmeasurement_statusis the explicit valuemeasured.float().stream_routewrites the same snapshot to--state-dbasrunandbatch_route.true_thetabefore parse so ablation invariants run.role_effort_catalogsends that role'sreasoning_effortandmax_tokensonModelClientchat, stream, and batch. Omit the catalog to keep today's request body.OrchestrationPolicydefaults are unchanged.Doctoring (APA 7th)
Out of scope (do not fold in)
OrchestrationPolicydefaults.Verify