haiku.rag/tests/capabilities
Yiorgis Gozadinos 3ec72363bc
Let the record say whether a question is still being answered
Resumption was inferred from the transcript, and no shape says it. A missing
prompt is how UI adapters ask their first question as much as how pydantic-ai
resumes one, so every AG-UI host failed on its first message. Reading the tail
instead moved the error rather than fixing it: a settled structured answer ends
with an output tool's return, indistinguishable from results delivered to a
question still in progress, so following questions inherited the first one's
identity.

`CapabilityEvidenceRecord.in_progress` is now the authority. `begin_question`
sets it, `after_run` clears it unless the run is only pausing for deferred work,
and a run that raised never reaches `after_run`, which is what leaves an
interrupted question claimable. The history is consulted only to catch a host
that dropped the state of a question the model is unmistakably still owed.
2026-08-13 15:03:24 +03:00
..
conftest.py replace haiku.skills with native Pydantic AI capabilities 2026-07-24 15:26:17 +03:00
test_capabilities.py Let the record say whether a question is still being answered 2026-08-13 15:03:24 +03:00
test_citation_policy.py Let the record say whether a question is still being answered 2026-08-13 15:03:24 +03:00
test_evidence_capsule.py Require an answer to declare what grounds it, once per question 2026-08-13 13:39:42 +03:00
test_evidence_ledger.py Enforce a declaration wherever there is something to declare 2026-08-13 13:39:42 +03:00
test_evidence_wire.py Let the record say whether a question is still being answered 2026-08-13 15:03:24 +03:00