haiku.rag/tests/capabilities
Yiorgis Gozadinos fa242c1c94
Tell the analysis and RAG capabilities about the databases
A capability covering several databases received `source` on every document
and search result and never used it: asked how many documents were in each
database, the model read the titles and answered that there was one corpus
of 67,581. The instruction files enumerate what a result carries, and both
enumerations had gone stale.

The note follows what the capability opens rather than what the
configuration names, through `covers_several_databases`: an explicit
`db_path` or a lent client covering one database is instructed as before,
as is every `uri` or path deployment and every eval dataset. The analysis
note separates the three interfaces, since they differ: an
`analysis_search` result carries a `Database:` line, in-code `search` and
`list_documents` return `source`, and the mounted files carry neither.
2026-08-24 10:03:47 +03:00
..
conftest.py
test_agent_spec.py Support Pydantic AI agent specs via from_spec 2026-08-21 13:04:09 +03:00
test_borrowed_client.py Lend the caller's client to the capability 2026-08-18 14:58:18 +03:00
test_capabilities.py Tell the analysis and RAG capabilities about the databases 2026-08-24 10:03:47 +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 Ask and analyze across several databases 2026-08-24 10:03:46 +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 Ask and analyze across several databases 2026-08-24 10:03:46 +03:00