Marc-André Bombeck c2ab9cda11 test(coach): put the dialog scenarios to a real model nightly ...

The live evaluation now captures the tool calls a generation makes, with
their arguments, and hands them to the judge. runScenarioLive puts a
scenario to the model in the chat turn's own context (system prompt,
tool-mode and dialog addenda, DATA INVENTORY, EARLIER TABLES, transcript)
over the real tool catalogue, answers each call with a stand-in result,
and reads the reply through the turn's clarification and chip parsers.
runScenarioJudge grades each scenario a few times with the same
evaluateScenario the deterministic suite uses and reports a pass rate per
scenario; the server-only scenarios and checks are left out.

Like the existing judge it runs only with COACH_EVAL_API_KEY, from the
nightly workflow's non-blocking step, and never throws.

2026-09-27 13:07:25 +02:00

..

ISSUE_TEMPLATE

feat(integrations): remove the moodLog integration

2026-07-25 11:36:18 +02:00

workflows

test(coach): put the dialog scenarios to a real model nightly

2026-09-27 13:07:25 +02:00

dependabot.yml

chore(deps): keep PostgreSQL majors out of the update stream

2026-09-16 13:05:14 +02:00

FUNDING.yml

docs: README presentation polish + community-file gaps

2026-06-05 03:01:36 +02:00

PULL_REQUEST_TEMPLATE.md

docs: PR template targets main — the develop branch was retired

2026-07-14 10:36:25 +02:00