L4 Wave2: BOED provenance honesty + stage test + challenge/bandit advisory telemetry#23
Merged
Conversation
…ed_information_gain) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…t-only) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…ion_advisory stays {})
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…obin unchanged) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
L4 Wave2 — landing directions that needed spike validation
Following Wave1 (#22), this wave handles the four directions that needed spike validation. All converged via offline measurement spikes to a uniform landing point: sidecar / telemetry / honesty fix / narrow tests — zero selector-behavior change, no invariant touched. Production net +87 lines (telemetry), the rest tests.
Four dispositions
produce_boed_signalsplan_value is a simple average(uncertainty+novelty+evidence_gap)/3, but provenance mislabeled itexpected_information_gain. Relabeled honestly asheuristic_plan_value(answer-first must not misrepresent). Not wired into ordering. Net +1.stage_fractionspolicy produces early/middle/late/final states; an empty policy falls back to middle-until-safety. (Locks the mechanism per policy, not the current state; no objective-switch added.)compile_search_pressurerecords challenge-pressure x candidate-text overlap inSearchPressure.metadata, advisory only.selection_advisorystays{},selection_advisory_featuresstill returns{}, the parent selector is untouched (real ordering would need future non-circular blind-labeled samples).OperatorArmStats+suggest_budget_allocation, aggregating by raw policy-action (not canonical operator), emitting advisory allocation toMutationPlan.metadata. Round-robin / actual mutation budget / operator allocation byte-for-byte unchanged (shadow-only; ordering revisited only after runs stabilize).Invariants
Verification
_shadow_action_rewardare an internal telemetry heuristic, advisory-only; revisit before wiring into ordering.🤖 Generated with Claude Code