feat: persistent audit trail of GenAI gate decisions#12
Merged
Conversation
The docs claim 'every GenAI decision is logged and auditable' — until now that was only in-memory (EngineeringResult). Add an AuditLogPort + JsonlAuditLog adapter; GenAIFeatureEngineer records every decision (accepted OR rejected, with feature name, code, score, baseline, metric, reason) durably, one JSON line per proposal. Opt-in (audit_log=...); no-op when unwired. TDD on real data; docs + 'Auditing the decisions' section added.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Increment 4 (final integrity gap). The docs claim every GenAI decision is logged and auditable — but the trail was only in-memory (
EngineeringResult). Now it can be persisted.Change
AuditLogPort+JsonlAuditLogadapter (features/audit.py).GenAIFeatureEngineergains an opt-inaudit_log=; it records every decision — accepted or rejected — with feature name, code, score, baseline, metric and reason, one JSON line per proposal. No-op when unwired (non-breaking).Tests (real data, LLM-free)
decision+score/baseline/code/dataset.Local gates green: ruff/format/pyright(0)/14 features tests + strict docs. Docs: an Auditing the decisions section added to
genai-features.md. Rebased on the post-#11 main (disjoint files).