Jev 4: build bounded context and targeting questions #256
- MA
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.

MaggieAppletonadded-to-stacklast month on GitHub
MaggieAppletonrenamed Add bounded question context and targeting builders to Jev 4: build bounded context and targeting questionslast month on GitHub
MaggieAppletonreferenced this in Jev conversation-to-document workflow #241last month on GitHub
MaggieAppletonready-for-reviewlast month on GitHub
MaggieAppletonhead-ref-force-pushed 35ecd2fde097last month on GitHub
MaggieAppletonhead-ref-force-pushed be7af2cad339last month on GitHub
MaggieAppletonhead-ref-force-pushed d9e2716fee31last month on GitHub
MaggieAppletonautomatic-base-change-succeededlast month on GitHub
MaggieAppletonhead-ref-force-pushed 8f9e0a75f915last month on GitHub
MaggieAppletonmerged a5a94cc7d76blast month on GitHub
MaggieAppletonhead-ref-deletedlast month on GitHub