Jev 4: build bounded context and targeting questions - #256
Merged
Merged
Conversation
MaggieAppleton
added this pull request to stack #254
October 3, 2026 06:23
MaggieAppleton
changed the title
MaggieAppleton
marked this pull request as ready for review
October 3, 2026 08:09
MaggieAppleton
force-pushed
the
maggie/jev-question-context
branch
3 times, most recently
from
October 3, 2026 11:19
be7af2c to
d9e2716
Compare
MaggieAppleton
force-pushed
the
maggie/jev-question-context
branch
from
October 3, 2026 11:27
d9e2716 to
8f9e0a7
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This fourth slice of #241 builds the bounded requests that Jev will answer: triage, candidate targeting, and possible research needs. It selects relevant conversation threads, carries current linked-card choices, and keeps a candidate's context separate from later clauses in the same message.
The layer constructs requests from supplied snapshots; it does not call the provider, persist events, or start research. Policy and interpreter orchestration follow separately.
Review scope: 14 files; 870 source lines and 877 test/helper lines, above the decision-record layer.
Validation: all 24 focused tests (105 assertions), full workspace/E2E types, repository CI, and formatting pass. Tests cover bounded context, current option targeting, source isolation, and research-question admission.