Jev 5: admit bounded conversation events with source attribution - #257
Merged
Merged
Conversation
MaggieAppleton
added this pull request to stack #254
October 3, 2026 06:28
MaggieAppleton
marked this pull request as ready for review
October 3, 2026 08:09
MaggieAppleton
force-pushed
the
maggie/jev-policy
branch
2 times, most recently
from
October 3, 2026 11:12
9e5c0b4 to
95ef791
Compare
MaggieAppleton
force-pushed
the
maggie/jev-policy
branch
2 times, most recently
from
October 3, 2026 11:27
cef186d to
934f660
Compare
MaggieAppleton
force-pushed
the
maggie/jev-policy
branch
from
October 3, 2026 11:36
934f660 to
5d4a076
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This fifth slice of #241 applies deterministic admission rules to classified conversation excerpts. It plans thread events for questions, choices, stances, withdrawal, and reopening, while preserving exact source attribution and returning review outcomes for unsupported or ambiguous candidates. Explicit option lists are admitted together or held for review.
Policy validates against a working snapshot and returns events plus diagnostics. It does not persist events, change the document, or perform human Save. Interpreter orchestration follows in the next layer.
Review scope: 106 files; 2,443 source lines and 7,461 test/helper lines, above the question-context layer. Tests exercise accepted and rejected transitions, source boundaries, capacity, and candidate interaction; artificial callback-failure cases have been removed.
Validation: 360 focused tests pass (1,890 assertions), along with full workspace/E2E types, formatting, and repository checks.
Independent review caught partial extraction of a four-option list; the included regression now requires a review outcome when only one or two candidates are supplied for a complete three- or four-option list.