feat: add versioned memory reassessments - #181
Merged
Merged
Conversation
This was referenced Sep 6, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #157.
Memory assessments need separate retention and epistemic dimensions. They also need a recovery path after provider failure or changes to the model or recorded evidence. This change adds versioned, append-only assessment history and authorized reassessment jobs.
Reassessment, automatic capture, and effective selection default to disabled. The existing promotion policy remains unchanged. Calibration requires an exact, sufficiently sampled profile. The included synthetic dataset verifies metric calculations; it does not establish production calibration.
Validation:
make check: lint and strict type checks passed; 3,596 tests passed, 2 skipped.make compose-ci: root suite 3,564 passed, 34 skipped; SDK 56 passed; hooks 190 passed; MCP 36 passed. This run used a fresh PostgreSQL and pgvector database with the non-owner application role.See the ADR and completion report for the compatibility mapping, trigger matrix, calibration results, and rollout details.