Repository navigation
test(sleep): document preference-scope evidence loss during deduplication - #331
Draft
Baixin Guo (GBX-Max1220) wants to merge 2 commits into
Draft
Baixin Guo (GBX-Max1220) wants to merge 2 commits into
Baixin Guo (GBX-Max1220) wants to merge 2 commits into
Conversation
Author
|
@microsoft-github-policy-service agree |
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Refs #154.
Adds a CPU-only, synthetic paired-session matrix covering durable preferences, one-off corrections, later reversals, and ambiguous feedback through the existing SessionDigest → mining → dedup path.
Individual records retain the scope statements. Same-intent dedup merges source session IDs but retains only the first record's context. Four strict expected-failure tests document the proposed retention contract; unrelated exceptions still fail normally.
The accompanying matrix separates evidence retention from proposed persistence policies. No production code is changed, and no model calls are made.
Validation
Command:
PYTHONPATH=. python -m pytest tests/test_preference_scope_contracts.py tests/test_sleep_skill_hint.py tests/test_env_section_survives_dedup.py -q --tb=short
Result: 31 passed, 4 xfailed, 130 subtests passed.
The new file contributes 8 passing cases and 4 strict expected failures. The full suite was not run.
Review scope
This draft demonstrates an evidence-retention gap, not an incorrect persistent update or reliable preference inference. Persistence policies remain proposals for discussion; clean-context replay and learning gains are outside this patch.
Feedback on overlap and the proposed retention contract would be appreciated before expanding the work.
AI-assisted preparation and execution; submitted by Baixin Guo (Max).