Commit Graph

7 Commits

Author SHA1 Message Date
Paul O'Reilly
b51d192a95 MiniMax: the model is MiniMax-M3.1-Flash (out of preview)
The API now answers MiniMax-M3.1-Flash-Preview as MiniMax-M3.1-Flash, and
accepts the new name directly. Verified 2026-11-03: a live call returns
"ok" with a 1M context window. Claude Code 2.1.317 prints an
unrecognized_model warning for either name; the session still runs.

Claude-Session: https://claude.ai/code/session_01CLUCNYsiEaER1CMqw5WqfY
2026-11-03 21:15:16 +13:00
Paul O'Reilly
840d7509e1 mm scripts: default to MiniMax-M3.1-Flash-Preview with per-script effort
Flash is the default model; --m3 falls back to M3, --effort overrides.
Defaults: max (review-minimax, review-loop, mm-worktree-task), medium
(explore), low (ci-triage). ask-minimax-run applies MINIMAX_EFFORT to
Flash models when --effort is not passed. Bump stale fixture date.
2026-10-13 10:23:53 +13:00
Paul O'Reilly
7800503348 fix(review-loop-run): CR-10 — scope exits only on headings shallower-or-equal to start depth (8c865eb4-7fd1-4a8d-b51d-04d020ba41c0) 2026-09-17 00:06:00 +12:00
Paul O'Reilly
8127cd3b46 spec(review-loop-run): CR-8 label-parenthetical exception ((C1)-style) — reconciles pre-existing list-style test
Claude-Session: https://claude.ai/code/session_01G3SkMRBRWXyiGuMGs8WVas
2026-09-16 15:23:51 +12:00
Paul O'Reilly
01ae924292 spec(review-loop-run): CR-7/8/9 — annotated table cells, declaration-only prose lines, suspect derived zero (bug 5352fe72)
Claude-Session: https://claude.ai/code/session_01G3SkMRBRWXyiGuMGs8WVas
2026-09-16 14:35:03 +12:00
Paul O'Reilly
b340e2cd5c fix(review-loop-run): counts parses count-by-severity block with scope + format branches (2026-09-13 fix, 40/40 tests)
Was live via ~/sbin symlink but never committed. Baseline for bug 5352fe72.

Claude-Session: https://claude.ai/code/session_01G3SkMRBRWXyiGuMGs8WVas
2026-09-16 14:27:52 +12:00
Paul O'Reilly
636b8b2401 feat: review-loop-run — detached MiniMax review launcher for /review-loop artefacts
launch (per-kind prompt templates: verify/plan/spec/tests/code; best-practice +
gotcha reading sets; setsid nohup launcher; round N+1 feeds back round N),
status, counts (exit 4 on CRITICAL/HIGH). Spec + 29 dryrun tests.

Claude-Session: https://claude.ai/code/session_018LRh1S2bHJYhEgrMu3UJx8
2026-09-13 17:20:36 +12:00