models-bump: harden CI and bot prompt against catalog hallucinations

PR #790 (the first bot-authored models-bump PR) shipped a broken bump for
openrouter/gemini-flash: the bot pattern-matched the parallel google bump
and fabricated `openrouter/google/gemini-3.5-flash`, which exists on the
OpenRouter API but not on models.dev's openrouter section — the catalog
OpenCode actually reads. The slug failed at runtime with `Model not found`.
Two CI gaps let it through:

1. `models-live` matrix pruned every `openrouter/*` and keyed `opencode/*`
   alias as a "passthrough", smoke-testing only one canary per routing
   layer. But those aren't passthroughs — each is a distinct models.dev
   catalog entry that can drift independently of the direct-provider
   mirror. Drop the pruning; smoke every keyed alias (53 jobs, up from 25).
   Only `bedrock/byok` stays pruned (sentinel resolve).

2. `models-catalog` test (the integrity gate that asserts every resolve
   exists on models.dev) was main-only by design — to keep upstream catalog
   churn from blocking unrelated PRs. But it's exactly the test we want
   running on the bot's own catalog edits. Add `pullfrog/models-bump`
   head-ref to its trigger.

Also tighten the bot prompt in models-bump.yml: new rule 0 requires every
new `resolve` to equal `<alias-provider>/<c.modelId>` for some `c` in the
alias's own `candidates[]` in models-bump-context.json — the deterministic
preprocessor only emits candidates sourced from models.dev's mirror, so
this gates against the cross-alias pattern-matching that broke PR #790.
For `openRouterResolve` the gate is `openRouterCandidates[]` (OpenRouter
API), which is necessary but not sufficient; the `models-catalog` job is
the authoritative models.dev check.

Verified locally:
- baseline `pnpm -C action test:catalog` passes 133 tests
- simulated the PR #790 hunk (sed'd `openrouter/google/gemini-3.5-flash`
  into action/models.ts) and the catalog test fails with the right
  assertion: `model "google/gemini-3.5-flash" not found under openrouter
  on models.dev`
- `FULL=1 node action/test/matrix.ts` emits 53 aliases (was 25); every
  openrouter/* alias and every keyed opencode/* alias now smoked
This commit is contained in:
Colin McDonnell
2026-05-20 02:18:38 +00:00
committed by pullfrog[bot]
parent f3d18401ac
commit 69c7d4b8cd
5 changed files with 27 additions and 45 deletions
+2 -7
View File
@@ -194,12 +194,8 @@ function buildAliasesMatrix(input: {
changedFiles: string[];
full: boolean;
filter: string;
includePassthroughs: boolean;
}): SlugEntry[] {
const all = buildAliasMatrix({
filter: input.filter,
includePassthroughs: input.includePassthroughs,
});
const all = buildAliasMatrix({ filter: input.filter });
const coverageByProvider = new Map(providers.map((p) => [p.name, p.coverage]));
return all.filter((entry) => {
const provider = entry.slug.split("/")[0];
@@ -214,14 +210,13 @@ function buildAliasesMatrix(input: {
function main(): void {
const full = process.env.FULL === "1";
const filter = process.env.MATRIX_FILTER?.trim().toLowerCase() ?? "";
const includePassthroughs = process.env.INCLUDE_PASSTHROUGHS === "1";
const changedFiles = full ? [] : readChangedFiles();
const output: MatrixOutput = {
agents: buildAgentsMatrix({ changedFiles, full }),
agnostic: buildAgnosticMatrix({ changedFiles, full }),
flagships: buildFlagshipsMatrix({ changedFiles, full, filter }),
aliases: buildAliasesMatrix({ changedFiles, full, filter, includePassthroughs }),
aliases: buildAliasesMatrix({ changedFiles, full, filter }),
};
process.stdout.write(JSON.stringify(output));