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
This commit is contained in:
Paul O'Reilly
2026-11-03 21:15:16 +13:00
parent d8abe45ea5
commit b51d192a95
14 changed files with 15 additions and 15 deletions

View File

@@ -21,7 +21,7 @@ review-minimax-run --worktree <path> [--base <ref>] [--out <findings-file>] \
| `--max-diff-lines` | 6000 | Diff budget; larger diffs exit 1 with the count |
| `--max-turns` | 40 | Sub-session turn cap |
| `--timeout` | 540 | Internal timeout (keeps callers under the harness Bash 600s cap). Why: a longer run invoked synchronously from a skill is killed by the harness with no findings file. |
| `--m3` | off | Use `MiniMax-M3[1m]` instead of the default `MiniMax-M3.1-Flash-Preview` (1M window natively, always thinks). No effort is sent unless `--effort` is given. |
| `--m3` | off | Use `MiniMax-M3[1m]` instead of the default `MiniMax-M3.1-Flash` (1M window natively, always thinks). No effort is sent unless `--effort` is given. |
| `--effort <level>` | `max` | Thinking depth `low\|medium\|high\|xhigh\|max`, passed to `ask-minimax-run --effort`. Any other value exits 1. |
| `--dryrun`, `-n` | off | Print resolved config, materialised-input plan, full prompt, and the exact sub-session command line; create/invoke nothing beyond the scratch dir |