add test-driven grinder harness v2 (#74) + failure-triage supervisor (#75)
#74 bin/bullpen-grinder: proxy-backed, tiered (floor 4B -> ceiling deepseek-local),
git-worktree workspace, local pytest, fence-optional FILE-block parser (4B fences,
deepseek does not), auto-escalates on stall. --serve <nick> = room coordinator
(runs on noether, grinds on boltzmann via sic). @py graduated off the lurker.
Proven: 4B solves add()+roman() in 1 iter; forced escalation climbs to deepseek and
its fix applies; room path bp py -> GREEN.
#75 bin/bullpen-triage: small-model failure supervisor — watches for failure replies
(timeout/rc/RED/turn-cap), classifies why + proposes a fix, surfaces to @markus for
approval. Advisory only. TRIAGE_MODEL swaps the classifier (4B default; 30b sharper).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EWpfhDgYNA21tETDP9ueBE
Markus Fritsche
b5cf3b2019