Files
model-router/README.md
T
adminandClaude Opus 5.5 d5c762b339 Fix #5: rerun reported files alone, and on base, before judging
The full suite run can time out files that pass alone (an overloaded
shared host, a suite-wide deadline in the runner): MAINT-28 T307 was
judged on 30 TIMEOUTs, T325 on a file that passes alone in 230 s.

- With testFileCommand set, every file the full run reports as TIMEOUT
  or FAIL (testIssuePattern, default ^(TIMEOUT|FAIL)\s+(\S+); lines are
  read as the run streams) is rerun alone in the clone,
  testRerunJobs at a time, testFileTimeoutSec each, at most
  testRerunMax files.
- A file that still fails or times out alone runs again on the base,
  in a git worktree next to the clone (<clone>-verifier-base), which is
  removed and pruned afterwards. Without a worktree, base stays "not
  run".
- The verifier gets a table (file, full run, alone on head, on base,
  meaning) and is told: passes alone does not count; fails on base too
  is not caused by the change; name every file it counts.
- Only file names of letters, digits and _ . - / reach the shell; no
  ".." parts, no leading "-".
- 12 new tests; each of the 23 new rules was also broken on purpose and
  caught.

Version 0.4.9.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MdqPWvuDpbpRvDEdURoAwo
2026-11-14 00:09:18 +00:00

4.7 KiB

model-router

A Claude Code plugin that picks a model for every subagent, checks dev work on a second model before it reaches a PR, and estimates what that saved compared with running everything on Opus.

What it does

Step Behaviour
Route Dev agents run on Sonnet when the brief decides the approach (Expected / acceptance criteria), on Opus when the design is still open. Review and test agents keep the model they are given (Opus when none).
Rerun reported files With testFileCommand set, every file the full run reports as TIMEOUT or FAIL is rerun alone in the clone. A file that still fails or times out alone runs again on the base branch, in a worktree next to the clone (<clone>-verifier-base, removed afterwards). The verifier gets a table: a file that passes alone does not count, one that also fails on base is not caused by the change.
Later instructions Every message sent to a dev agent after its brief (a SendMessage, or the message that resumes it) reaches the verifier as part of the task, so scope added later is judged as in scope. A resumed agent keeps its task number, routing and failure count.
Verify When a dev agent below Opus finishes a round, the router diffs its clone against the merge base, runs the test command in that clone, and has Opus judge the change.
Hand-back line Every dev hand-back gets one line at once: [model-router] Tn verifying on Opus... (a verdict follows), or [model-router] Tn no verification: dev ran on Opus. Go straight to review. Only the real hand-back counts: an interim stop while the dev waits on its own background work (e.g. a long test suite) posts nothing and starts no verifier. Decided by the model the run actually used, not only the routing choice; a difference is shown as (routed to X, ran on Y).
On FAIL 1st: resume the same agent with the issues. 2nd: a new agent one model up, in the same clone. After that: handed back to the manager.
Not verified A test timeout, a test command that cannot run, a missing clone or merge base, or a verdict that cannot be read even after asking once more: reported as NOT VERIFIED, never as a FAIL.
Savings /router savings prices every run on the model it ran on and compares it with the same tokens on Opus 5.5.

Briefs

Every dev, review and test brief carries one line:

Clone: /home/homelab/projects/goodwe/clones/<TICKET>-dev/

Add (Role: dev|review|test) when the path does not end in the role. Tickets with extra parts (OPT-11-P4) are fine. Name the base branch (Base branch: release/1.0).

Install

/plugin marketplace add <this repo's git URL>
/plugin install model-router@model-router

Or for development: claude --plugin-dir /path/to/model-router.

Settings (/config)

Setting Default Notes
testCommand empty Run in the agent's clone; output goes to the verifier
testTimeoutSec 1800 Wrapped in GNU timeout --verbose; a timeout is NOT VERIFIED
testFileCommand empty Runs one file, {file} replaced by a reported file name; only names of letters, digits, _ . - / are run
testFileTimeoutSec 900 Limit per rerun file
testRerunJobs 6 Reruns at a time
testRerunMax 40 Most files rerun per round
testIssuePattern ^(TIMEOUT|FAIL)\s+(\S+) Group 1 the kind, group 2 the file
defaultBaseBranch release/1.0 After the PR lookup and the brief's own base branch
prBaseCommand empty Optional command that prints the PR's base branch
maxRewrites 2 Failed verdicts before handing back
safetyPatterns control loop, rs485, ... Marks tasks as critical in the log
respectExplicitModel false Keep a named model on agents without a role
allowFable false Rewrite on Fable after Opus fails
prices empty JSON price overrides, USD per MTok

Commands

  • /router: recent decisions, verdicts and savings
  • /router savings [Tn]: the full savings table, or one task
  • /router clear: reset log, records and costs

Tests

claude plugin validate .
claude plugin test .

92 tests. Every routing, verification, cost and timeout rule was also checked by breaking it on purpose (66 mutations in v0.4.4, plus 13 for the verdict reader in v0.4.5 12 for the hand-back line in v0.4.6 10 for interim stops in v0.4.7 14 for resumes, later instructions and rewrites in v0.4.8 and 23 for file reruns in v0.4.9; all caught by a test).

Known limits

  • Savings are an upper bound: Opus may need fewer tokens than the cheaper model did.
  • timeout stops the docker client, not the container: name the container and remove it in a trap in the test command.
  • An Opus rewrite is not verified; the PR review covers it.