feat(ai-209): add model rollback and safe rollout controls for appeal automation#3
Open
khaadish wants to merge 4 commits into
Open
feat(ai-209): add model rollback and safe rollout controls for appeal automation#3khaadish wants to merge 4 commits into
khaadish wants to merge 4 commits into
Conversation
- ScoreCalibrationService decouples raw model confidence from policy thresholds - CalibrationPolicy exposes approveThreshold, rejectThreshold, humanReviewThreshold, biasCorrectionFactor - needsHumanReview=true whenever confidence < humanReviewThreshold (explicit review boundary) - appliedPolicy + rawScore preserved in every output for audit/replay - Corresponding types exported from @devconsole/api-contracts - Spec covers approve/escalate/reject bands, bias correction, clamping, and traceability Closes Ibinola#423
… automation - ModelRolloutService supports pinned / canary / full rollout modes - rollback() restores previous RolloutConfig instantly (single-level undo) - resolveModel() is deterministic per requestId for consistent canary bucketing - setRollout / rollback emit structured log events for operator audit - RolloutConfig/RolloutResolution/ModelRolloutState types in @devconsole/api-contracts - Spec covers all three modes, determinism, rollback, and no-op safety Closes Ibinola#426
…ation feat(ai-206): add policy-aware score calibration for AI appeal outputs
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Introduces guarded rollout modes (pinned → canary → full) so AI behaviour can be promoted incrementally and rolled back instantly if fairness or quality metrics drift.
Changes
ModelRolloutService— in-process rollout controller inappeal-decisionsmodulepinned(stable only),canary(% split),full(all traffic)rollback()restores previousRolloutConfigin one callrollout_config_updated/rollout_rolled_backlog eventsRolloutConfig,RolloutResolution,ModelRolloutStatetypes in@devconsole/api-contractsdocs/ai-209-rollout-controls.mdAcceptance Criteria
setRollout,resolveModel) and outputs (RolloutResolution.reason,ModelRolloutState) — no hidden routingcanaryPercentand mode are measurable and tunable at runtimerollback()with preserved previous config for operator overrideCloses Ibinola#426