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.
This commit is contained in:
Paul O'Reilly
@@ -8,7 +8,7 @@ Triage a failing Gitea Actions run in a MiniMax M3 sub-session: fetch the run's
|
||||
|
||||
```
|
||||
ci-triage-minimax-run --repo <owner/repo> --run <N> [--job <name|id>] \
|
||||
[--out <triage-file>] [--tail N] [--max-turns N] [--timeout SECS] [--dryrun|-n]
|
||||
[--out <triage-file>] [--tail N] [--max-turns N] [--timeout SECS] [--dryrun|-n] [--m3] [--effort LEVEL]
|
||||
```
|
||||
|
||||
| Flag | Default | Description |
|
||||
@@ -20,6 +20,8 @@ ci-triage-minimax-run --repo <owner/repo> --run <N> [--job <name|id>] \
|
||||
| `--tail` | 2000 | Log lines fetched (gac `--tail`) |
|
||||
| `--max-turns` | 25 | Sub-session turn cap |
|
||||
| `--timeout` | 300 | Internal timeout (logs-only task; well under the harness Bash 600s cap) |
|
||||
| `--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. |
|
||||
| `--effort <level>` | `low` | Thinking depth `low\|medium\|high\|xhigh\|max`, passed to `ask-minimax-run --effort`. Any other value exits 1. |
|
||||
| `--dryrun`, `-n` | off | Print resolved config, the gac command, the full prompt, and the sub-session command line; invoke neither gac's log fetch nor the sub-session |
|
||||
|
||||
## Requirements
|
||||
@@ -30,7 +32,7 @@ ci-triage-minimax-run --repo <owner/repo> --run <N> [--job <name|id>] \
|
||||
- **CT-4 Redaction.** Before prompt assembly, credential-shaped content in `run-logs.ndjson` (`ghp_…|glpat-|x-access-token:|Authorization:|BEGIN … PRIVATE KEY|AKIA…` — same pattern set as review-minimax-run) is replaced in place with `[REDACTED]`. Redact-and-continue, not abort: CI logs routinely carry unmasked clone URLs and the log is the whole payload. Residual risk: best-effort patterns; novel credential formats can pass.
|
||||
- **CT-5 Envelope parse.** `failed_step`, `sliced`, and `note` are extracted from the NDJSON envelope with jq. If `failed_step` is null (cancelled/crashed run, green multi-job), the prompt states this and the output contract requires the literal `UNKNOWN` under `## Failing step` — no fabricated step names.
|
||||
- **CT-6 Prompt contract.** Fixed preamble: read-only triage of the two files in cwd; explicit error-signature patterns to search (`error:|FAILED|Traceback|exit code|denied|timeout|not found|no such|ECONN|refused`); do not suggest running tests or builds; if the log carries the truncation marker or `sliced` is partial, say so — do not improvise. Output sections, exactly: `## Failing step` / `## Error excerpt` (≤10 verbatim lines) / `## Probable cause` (1–3 sentences, non-empty) / `## Suggested next action` (one command or one edit description — advisory only) / `## Confidence`.
|
||||
- **CT-7 Invocation.** From the scratch dir: `timeout <secs> ask-minimax-run --model "MiniMax-M3[1m]" --permission-mode default --allowedTools "Read,Glob,Grep,Write" --disallowedTools "Edit,MultiEdit,NotebookEdit,Bash,WebFetch,WebSearch" --max-turns N --output-format json --add-dir <out-dir> -p`. Same rationale set as review-minimax-run RM-6; no worktree access needed.
|
||||
- **CT-7 Invocation.** From the scratch dir: `timeout <secs> ask-minimax-run --model "$MODEL" --effort "$EFFORT" --permission-mode default --allowedTools "Read,Glob,Grep,Write" --disallowedTools "Edit,MultiEdit,NotebookEdit,Bash,WebFetch,WebSearch" --max-turns N --output-format json --add-dir <out-dir> -p`. Same rationale set as review-minimax-run RM-6; no worktree access needed.
|
||||
- **CT-8 Result gate.** Triage file exists, contains `## Failing step`, and has a non-blank line under `## Probable cause`.
|
||||
- **CT-9 Retry.** On MiniMax error or gate failure: remove the out-file, retry once; never retry timeout (rc 124); then exit 2 (transport) or 3 (gate). The gac fetch is NOT retried by the script (single fetch, reused across both attempts).
|
||||
- **CT-10 Test seams.** `CI_TRIAGE_FAKE_LOGS=<file>` bypasses the gac fetch (file used as `run-logs.ndjson`; `jobs.txt` gets a placeholder); `CI_TRIAGE_FAKE_JSON=<file>` substitutes the sub-session envelope; `CI_TRIAGE_FAKE_TRIAGE=<file>` (companion, optional) plays the sub-session's Write of the triage file. Gates and retry logic still run, so exits 0/2/3 and the redaction step are assertable offline.
|
||||
|
||||
@@ -9,7 +9,7 @@ Run a broad, read-only "where does X live" codebase exploration in a MiniMax M3
|
||||
```
|
||||
explore-minimax-run --root <path> [--root <path> ...] \
|
||||
--prompt-file <question-file> --out <result-file> \
|
||||
[--breadth medium|very-thorough] [--max-turns N] [--timeout SECS]
|
||||
[--breadth medium|very-thorough] [--max-turns N] [--timeout SECS] [--m3] [--effort LEVEL]
|
||||
```
|
||||
|
||||
| Flag | Default | Description |
|
||||
@@ -20,6 +20,8 @@ explore-minimax-run --root <path> [--root <path> ...] \
|
||||
| `--breadth` | `medium` | `medium` (stop when confidently answered) or `very-thorough` (full sweep, alternate naming conventions) |
|
||||
| `--max-turns` | 40 | Sub-session turn cap |
|
||||
| `--timeout` | 540 | Internal timeout in seconds (keeps callers under the harness Bash 600s cap) |
|
||||
| `--m3` | off | Use `MiniMax-M3` instead of the default `MiniMax-M3.1-Flash-Preview` (1M window natively, always thinks). No effort is sent unless `--effort` is given. |
|
||||
| `--effort <level>` | `medium` | Thinking depth `low\|medium\|high\|xhigh\|max`, passed to `ask-minimax-run --effort`. Any other value exits 1. |
|
||||
|
||||
## Behaviour / requirements
|
||||
|
||||
|
||||
@@ -26,6 +26,8 @@ mm-worktree-task <item-uuid> [OPTIONS]
|
||||
| `--docs all\|recent\|none` | `recent` | Which item documents to bundle. `recent` = documents updated in the last 14 days; falls back to `all` if the CLI does not expose update dates. The full list of document names is always included in the prompt regardless of which are bundled. |
|
||||
| `--tools "<list>"` | — | Extra `--allowedTools` entries merged into the default allowlist (comma-separated). |
|
||||
| `--timeout <secs>` | `1800` | Max seconds the sub-session may run (`timeout <secs>` wrapper). |
|
||||
| `--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. |
|
||||
| `--effort <level>` | `max` | Thinking depth `low\|medium\|high\|xhigh\|max`, passed to `ask-minimax-run --effort`. Any other value exits 1. |
|
||||
| `--gate "<command>"` | — | Supervisor gate: after the sub-session exits, `mm-worktree-task` itself re-runs this command in the worktree against the sub-session's LAST commit and appends a `## Supervisor gate` section to the result file (see Behaviour §8). Never trust the agent's own "tests pass" claim — this re-run is the check. |
|
||||
| `--gate-timeout <secs>` | `900` | Max seconds `--gate`'s command may run before it is killed and recorded as a timed-out (failed) gate. |
|
||||
| `--context <name>` | resolved (see §0) | `cp-cli --context` used for every planner call. |
|
||||
@@ -76,7 +78,7 @@ mm-worktree-task <item-uuid> [OPTIONS]
|
||||
- If `--brief <file>` is given, its content is appended (or used standalone as the task body when no uuid was given).
|
||||
8. Launch detached (skipped under `--dryrun` and `--collect`):
|
||||
```
|
||||
cd <worktree> && setsid nohup timeout <secs> ask-minimax-run --model "MiniMax-M3[1m]" \
|
||||
cd <worktree> && setsid nohup timeout <secs> ask-minimax-run --model "$MODEL" --effort "$EFFORT" \
|
||||
--allowedTools "<default-allowlist>[,<--tools>]" --permission-mode acceptEdits \
|
||||
--add-dir <report-dir> -p "$(cat <prompt-file>)" \
|
||||
> <report-dir>/<slug>-stdout.txt 2>&1
|
||||
|
||||
@@ -9,7 +9,7 @@ Launch a detached MiniMax M3 review of a review-loop artefact (plan, spec diff,
|
||||
```
|
||||
review-loop-run launch --kind <plan|spec|tests|code|verify> --name <tag> [--round N] \
|
||||
--file <path> [--file <path> ...] [--context "<text>"] [--prev <result.md>] \
|
||||
[--tools "<extra allowedTools>"] [--timeout <secs>] [--dryrun|-n]
|
||||
[--tools "<extra allowedTools>"] [--timeout <secs>] [--m3] [--effort <level>] [--dryrun|-n]
|
||||
review-loop-run status [--name <tag>] [--round N]
|
||||
review-loop-run counts <result.md>
|
||||
review-loop-run --help
|
||||
@@ -35,6 +35,8 @@ review-loop-run --help
|
||||
| `--prev` | auto | Explicit previous-round result file (overrides the auto lookup). |
|
||||
| `--tools` | kind default | Extra `--allowedTools` entries (comma-separated). |
|
||||
| `--timeout` | 1500 | Seconds before the sub-session is killed. |
|
||||
| `--m3` | off | Use `MiniMax-M3` instead of the default `MiniMax-M3.1-Flash-Preview` (1M window natively, always thinks). No effort is sent unless `--effort` is given. |
|
||||
| `--effort <level>` | `max` | Thinking depth `low\|medium\|high\|xhigh\|max`, passed to `ask-minimax-run --effort`. Any other value exits 1. |
|
||||
| `--project` | current repo root | Repo to `cd` into before launching. |
|
||||
| `--dryrun`, `-n` | off | Print the assembled prompt and the exact launch command; write nothing; launch nothing. |
|
||||
|
||||
@@ -51,7 +53,7 @@ review-loop-run --help
|
||||
2. Validate: kind in the closed set, name matches `^[A-Za-z0-9._-]+$`, every `--file` exists, `ask-minimax-run` on PATH, MiniMax profile present.
|
||||
3. Assemble the prompt from the kind template (§Templates): header (non-interactive, write to the output file), task text, `--context`, the "Files to read" list = `--file` entries + the kind's default best-practices/gotcha files that exist + the previous-round result (rounds ≥2), the output path, constraints.
|
||||
4. Write `<dir>/<name>-r<N>-prompt.txt`.
|
||||
5. Write `<dir>/<name>-r<N>-launch.sh` (a tiny bash script that `cd`s to the repo, runs `timeout <secs> ask-minimax-run --model MiniMax-M3 --allowedTools "<list>" --permission-mode acceptEdits -p "$(cat prompt)" > stdout 2>&1`, then appends `exit=$?` to the stdout file) and starts it with `setsid nohup <launch.sh> >/dev/null 2>&1 &`.
|
||||
5. Write `<dir>/<name>-r<N>-launch.sh` (a tiny bash script that `cd`s to the repo, runs `timeout <secs> ask-minimax-run --model "$MODEL" --effort "$EFFORT" --allowedTools "<list>" --permission-mode acceptEdits -p "$(cat prompt)" > stdout 2>&1`, then appends `exit=$?` to the stdout file) and starts it with `setsid nohup <launch.sh> >/dev/null 2>&1 &`.
|
||||
6. Print the three paths and `launched`.
|
||||
|
||||
`status` scans `<dir>/*-r*-stdout.txt`; a file whose last line matches `^exit=` is `done`, else `running`; counts come from `counts`.
|
||||
|
||||
@@ -9,7 +9,7 @@ Run a first-pass code review of a git branch (typically an agent-produced worktr
|
||||
```
|
||||
review-minimax-run --worktree <path> [--base <ref>] [--out <findings-file>] \
|
||||
[--profile agent-runtimes] [--max-diff-lines N] [--max-turns N] \
|
||||
[--timeout SECS] [--dryrun|-n]
|
||||
[--timeout SECS] [--dryrun|-n] [--m3] [--effort LEVEL]
|
||||
```
|
||||
|
||||
| Flag | Default | Description |
|
||||
@@ -21,6 +21,8 @@ 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. |
|
||||
| `--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 |
|
||||
|
||||
## Requirements
|
||||
@@ -30,7 +32,7 @@ review-minimax-run --worktree <path> [--base <ref>] [--out <findings-file>] \
|
||||
- **RM-3 Redaction gate.** If `diff.patch` matches `ghp_[A-Za-z0-9]|glpat-|x-access-token:|Authorization:|BEGIN [A-Z ]*PRIVATE KEY|AKIA[0-9A-Z]{16}`, exit 1 with "diff contains credential-shaped content; review in-session". No redact-and-continue for diffs: a credential in a diff means the branch itself needs attention.
|
||||
- **RM-4 Empty/oversize diff.** Empty `diff.patch` → exit 1 "nothing to review". More than `--max-diff-lines` lines → exit 1 with the count.
|
||||
- **RM-5 Prompt contract.** Fixed preamble: first-pass reviewer, non-interactive; inputs are the three files in cwd; the worktree is readable for surrounding context only; write ONLY the findings file at the given path; never modify any other file; do not run anything, fix anything, or improvise if an input is missing/truncated — say so and stop. Checklist = unconditional core (distilled from llm-code-security §10/§12: injection, hardcoded credentials, unquoted shell vars, verify=False, weak hashing/random, missing input validation, chmod 777, curl|bash, unpinned images/deps, missing idempotency, unconditional health checks, missing locking) as explicit grep-able patterns; `--profile agent-runtimes` appends the 5 recurring MiniMax test-file bugs. Findings format: `### [BLOCKER|SHOULD-FIX|NIT] <title>` blocks with `file:line`, ≤10-line excerpt, category, `Confidence: confirmed|suspected`; clean review → literal `NO FINDINGS`.
|
||||
- **RM-6 Invocation.** From the scratch dir: `timeout <secs> ask-minimax-run --model "MiniMax-M3[1m]" --permission-mode default --allowedTools "Read,Glob,Grep,Write" --disallowedTools "Edit,MultiEdit,NotebookEdit,Bash,WebFetch,WebSearch" --max-turns N --output-format json --add-dir <worktree> --add-dir <out-dir> -p < prompt > response.json`. Why each: `[1m]` pins the 1M window (unknown model ids get 200k + early auto-compact); `Write` must be allowlisted or MiniMax exits 0 without creating the file; `default` not `acceptEdits` — new-file Write needs no edit approval and nothing else is auto-approved; deny-list beats the profile's permissive defaults.
|
||||
- **RM-6 Invocation.** From the scratch dir: `timeout <secs> ask-minimax-run --model "$MODEL" --effort "$EFFORT" --permission-mode default --allowedTools "Read,Glob,Grep,Write" --disallowedTools "Edit,MultiEdit,NotebookEdit,Bash,WebFetch,WebSearch" --max-turns N --output-format json --add-dir <worktree> --add-dir <out-dir> -p < prompt > response.json`. Why each: `$MODEL` is Flash (1M natively) by default; with `--m3`, `[1m]` pins the 1M window (unknown model ids get 200k + early auto-compact); `Write` must be allowlisted or MiniMax exits 0 without creating the file; `default` not `acceptEdits` — new-file Write needs no edit approval and nothing else is auto-approved; deny-list beats the profile's permissive defaults.
|
||||
- **RM-7 Clean-tree assertion.** After each attempt, `git -C <worktree> status --porcelain` must be empty; a dirtied tree is exit 2 (and the dirt is reported, not reverted).
|
||||
- **RM-8 Result gate.** Findings file exists AND (contains `NO FINDINGS` OR (≥1 line matching `^### \[(BLOCKER|SHOULD-FIX|NIT)\]` AND ≥1 finding cites a path that exists relative to the worktree)). A bare `:NNN` match is NOT sufficient — timestamps and counters satisfy that.
|
||||
- **RM-9 Retry.** On MiniMax error OR gate failure: remove the out-file and retry once (covers the "exit 0, file never written" failure and prevents a stale attempt-1 file passing the gate). Never retry a timeout (rc 124). Then exit 2 (transport/timeout/dirty-tree) or 3 (gate).
|
||||
|
||||
Reference in New Issue
Block a user