Marius CiepluchandClaude Opus 5 cde57e4293 fix(learning-harness): say why the proposer had nothing, and stop hard-coding its vendor ...

The meta-agent round journalled `no_proposal`. The real cause was an
authentication failure: `_model_config` hard-coded the anthropic provider
while the detector was talking to DeepSeek and no ANTHROPIC_API_KEY exists
here. The composition itself was fine -- MetaAgent constructed, evolve
started, budget $5 -- and the trace was thrown away.

`no_proposal` covered two different worlds: a proposer that considered the
facts and declined, and one that could not start at all. The journal now
carries the proposer's own reason, and the vendor comes from
`[harnessx] provider` instead of being assumed.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

2026-09-06 22:24:40 +02:00

..

__init__.py

feat(learning-harness): closed family taxonomy with a verifier per family

2026-09-06 09:06:09 +02:00

acceptance.py

feat(learning-harness): thinking is a measured condition, and every round

2026-09-06 15:12:09 +02:00

canaries.py

fix(learning-harness): the three defects the group 2 review found

2026-09-06 10:32:02 +02:00

candidates.py

feat(constrained-detector): the ceiling, measured offline across every slice

2026-09-06 18:44:19 +02:00

classify.py

fix(learning-harness): the three defects the group 2 review found

2026-09-06 10:32:02 +02:00

detectors.py

fix(learning-harness): the three defects the group 2 review found

2026-09-06 10:32:02 +02:00

difficulty.py

feat(learning-harness): declared twins and a fixture-difficulty check

2026-09-06 13:09:56 +02:00

endpoint.py

feat(learning-harness): thinking is a measured condition, and every round

2026-09-06 15:12:09 +02:00

families.py

docs(learning-harness): amend the taxonomy name and carry the flat-taxonomy caveat

2026-09-06 10:22:33 +02:00

journal.py

feat(learning-harness): thinking is a measured condition, and every round

2026-09-06 15:12:09 +02:00

proposer.py

fix(learning-harness): say why the proposer had nothing, and stop hard-coding its vendor

2026-09-06 22:24:40 +02:00

publish.py

fix(learning-harness): the published table lost a whole slice

2026-09-06 20:44:56 +02:00

rounds.py

fix(learning-harness): say why the proposer had nothing, and stop hard-coding its vendor

2026-09-06 22:24:40 +02:00

scoring.py

fix(learning-harness): the round-4 review findings

2026-09-06 14:03:10 +02:00

split.py

feat(learning-harness): one teacher rule across every learning path

2026-09-06 10:15:44 +02:00

verifiers.py

fix(learning-harness): the three defects the group 2 review found

2026-09-06 10:32:02 +02:00