feat(v21): Learned Policy decision outcome closed loop - #372
feat(v21): Learned Policy decision outcome closed loop#372laiqian0239-glitch wants to merge 1 commit into
Conversation
|
Warning Review limit reached
Next review available in: 28 minutes You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (6)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Superseded by the ordinary-merged V3 production-closure authority and implementation. The merged V3 authorization explicitly records PR #372 / head |
|
Audit correction to the preceding closure note: the direct supersession authority for PR #372 is the ordinary-merged V2 successor authorization |
1 participant
Work package
V21-LEARNING-POLICY-P1-DECISION-OUTCOME-CLOSED-LOOP-V1Authorized by ordinary two-parent merge
915c487784d991e5c683daa6e167950f310b9a47from #371.Failure-first topology
Exact first implementation commit:
fb1beeb0e39ad4d6263f71b4c995eb5ec663e6e2It is the direct child of the authorization merge and adds exactly the six authorized WP0 tests, with zero product/runtime/dependency implementation.
Causal RED evidence
Stage run
31796413179, job94754440534at exact Headfb1beeb0e39ad4d6263f71b4c995eb5ec663e6e2reached the product route after the base-owned failure-first/implementation-branch contracts passed.npm run test:wp0result: 402 pass / 7 fail. The seven failures are exclusively the new Learned Policy contracts:backend/services/learningPolicyDecisionContract.js;backend/services/learningOutcomeAttributionService.js;contextAwareReplyBrain.jsdoes not yet consumelearningPolicyRuntimeAdapterbefore existing frontier generation;learningDeepTrainingContracthas noprojectPolicymethod;third_party/licenses/vowpal-wabbit-BSD-3-Clause.txt;backend/services/learningPolicyRuntimeAdapter.js.All pre-existing WP0 files in the isolated runner passed; ACV2 run
31796413446and WP-A post-merge run31796413171also succeeded on the test-only Head. This is the required causal product RED, not a runner or authorization failure.Authorized GREEN boundary
Implementation remains restricted to the 22 exact paths frozen by #371. Mature Vowpal Wabbit
9.11.2at exact upstream commit122bae254a5b8bc2b774d13b33d53e6dbc2cfba7owns the contextual-bandit action head. Existing Person/Persona/canonical serialization/immutable learning ledger/Langfuse reward/Model Brain provider-routing and frontier-generation authorities remain authoritative. P1 is deterministic (actionProbability=1.0,exploration=false) and may change onlycandidateStrategyBranch.No workflow/root npm mutation, new general-purpose Yance infrastructure, live randomized exploration, local learned-policy reply generation, release/publish/promotion, or automatic scope expansion is authorized.