Why: I1 WP6 - eval needs per-turn command expectations to carry the
SetSlot+Start acceptance case, and corpora must reproduce standalone
in intentctl (the guard case has been red there since before I1
because the guard spec only existed as a test builtin).
Evidence: go vet clean; go test ./... all ok; intentctl eval passes
11/11 on the v1 corpus (guard case fixed via self-declaration) and
1/1 on the new two-turn SetSlot+Start corpus.
Impact: new intent/corpus.go (CorpusCase/CorpusTurn/CommandExpect,
RunCorpusCase with chained expectations); intentctl eval consumes
turns and corpus-declared builtin_specs and domains; report.generate
spec and corpus_multiturn.json fixtures added. v1 corpus format and
conformance unchanged.
Refs: Documents proposal 2026-10-07-agent-stack-n1q1i1-plans.md I1 WP6
weichen
merged commit f57645c645 into main2026-10-07 08:22:33 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
I1 WP6：eval v2 多轮格式与语料自声明
改动
intent/corpus.go：CorpusCase（v1 单轮/v2 多轮共用，v1 自动包装单轮）+CorpusTurn（逐轮分支/top/命令期望）+CommandExpect（只断言写出的字段）+RunCorpusCase——链式预期：上一轮 Top 有必填缺失/非法槽位时下轮挂起该意图（对应产品「带槽启动后追问」），使 SetSlot+Start 组合在评测中可到达。intentctl eval消费 v2：多轮用例逐轮执行、差异定位到轮次与字段；v1 输出形态不变。builtin_specs/guard_domains/protected_domains——guard_config_query在 intentctl 下自始失败（guard spec 只存在于测试内置件，证明：HEAD~5 上同样 1/10 红）。声明后 11/11 全绿。report.generatespec 入 demo registry +corpus_multiturn.json两轮用例（turn1 Start+Clarify → turn2 SetSlot+Start）通过。验证
go vet ./...通过；go test -count=1 ./...6 包全 ok（新测：多轮语料执行、v1 包装等价、命令断言差异定位）。intentctl evalv1 11/11、v2 1/1。主任务：Dev 仓
feature/agent-stack-i1。