5 Commits

Author SHA1 Message Date
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
3734978d56 mm-worktree-task: --gate re-runs the test suite itself, never trusts the agent's claim
Across ~12 supervised MiniMax units, more than half reported a green suite
where a manual re-run found red (see memory/gotchas-minimax.md). Add
--gate "<command>" (with --gate-timeout, default 900s): after the detached
sub-session exits, mm-worktree-task itself re-runs the command in the
worktree against the sub-session's LAST commit, in its own reapable process
group (setsid + group kill, so a hung gate and everything it forked are
bounded and cleaned up), and appends an unambiguous PASSED/FAILED verdict —
plus an explicit MISMATCH callout when the agent's own report claimed
success — to the result file. A missing command, non-zero exit, timeout, or
dirty worktree are all failures, never a silent skip. mm-worktree-task's own
exit code is unchanged: the launch already returns before the sub-session
(and gate) run, detached.

Claude-Session: https://claude.ai/code/session_014KNyfHmHpMbdMrHZXDRkAp
2026-09-23 19:40:44 +12:00
Paul O'Reilly
cbab812917 mm-worktree-task: --base flag + set -e safe returns (uncommitted WIP)
Committing work found uncommitted in the checkout: --base lets a unit be based
on a branch other than main (used throughout the M32 cut-over session for
u6-tests and hatchmate-migration bases), and the bare 'return' statements
become 'return 0' so they cannot abort under set -e when the preceding test is
false.

Per the project agent-safety rule: untracked/uncommitted work that matters gets
committed the day it is found, so local loss cannot take it.

Claude-Session: https://claude.ai/code/session_014KNyfHmHpMbdMrHZXDRkAp
2026-09-23 19:26:52 +12:00
Paul O'Reilly
f50561ea78 feat(mm-worktree-task): run from any planner-backed repo — cp_cli dir + context resolution (--context, MM_WORKTREE_TASK_CP_*), empty-docs guard, tests + spec
cp_cli lives in agent-runtimes; previously every planner call ran 'python3 -m lib.cp_cli' from the current repo with no --context, so the script only worked inside agent-runtimes. The context now resolves from ~/.cpconfig by matching project_id to the repo directory name. Verified live from hatchmate (item + parent + documents fetched via the hatchmate context).

Claude-Session: https://claude.ai/code/session_01JgJbWzVJioVznVTFyQFEfx
2026-09-11 16:27:08 +12:00
Paul O'Reilly
9a6d7135c5 feat: add mm-worktree-task — launch MiniMax worktree implementation sub-sessions
Wraps ask-minimax-run to run a MiniMax M3 implementation sub-session in an
isolated git worktree, with the prompt assembled from a planner work item
(cp_cli item + documents + parent/siblings). Supports --dryrun, --collect,
and --upload, per the pattern used for the 2026-09-10 seven-worktree batch
(see agent-runtimes memory/gotchas-minimax.md).

Claude-Session: https://claude.ai/code/session_015nXvGNNNixJPFwZKZHNyha
2026-09-10 22:57:55 +12:00