Files
shockbot/test/model-smoke.ts
T
Colin McDonnell 4cc6d95a91 ci: split per-alias resolution smoke from per-provider harness smoke (#650)
* ci: split per-alias resolution smoke from per-provider harness smoke

`models-live` previously ran the full Pullfrog harness (Docker + MCP +
agent + structured-output validation) once per alias on every PR that
touched `models.ts` or `agents/**`. That cost minutes and dollars per
alias and re-validated tool-calling for every routing wrapper.

The per-alias signal we actually need from `models.ts` changes is just
"does this alias resolve and authenticate." Tool-calling correctness is
a property of the underlying model, not the alias, and it doesn't change
when someone adds a row to the catalog. Splitting the two concerns:

- `models-live` now runs `action/test/model-smoke.ts` per alias — a
  top-level CLI invocation (`opencode run -m <resolve> "reply OK"` or
  `claude -p "reply OK" --model <bare>`) with no Docker, MCP, or
  Pullfrog harness. Validates resolution + auth in seconds at fractions
  of a cent. Lets us drop the `EXPENSIVE_RESOLVE_SUBSTRINGS` carve-out
  for `gpt-pro` since the cheap smoke covers it for free.

- `providers-live` (new) runs the full harness smoke once per provider
  against a hand-curated standard-tier model (`anthropic/claude-sonnet`,
  `openai/gpt`, `google/gemini-pro`, `xai/grok`,
  `deepseek/deepseek-pro`, `moonshotai/kimi-k2`,
  `opencode/big-pickle`, `openrouter/claude-sonnet`). Catches
  provider-class regressions like the Gemini schema sanitizer or
  OpenAI tool-call format drift. ~8 jobs, ~$0.40/push, ~4min critical
  path in parallel.

Net change per push that touches `models.ts`: ~$20 → ~$0.40.

`list-aliases.ts` now branches on `MODE` to emit either matrix; the
flagship list asserts each slug exists in `modelAliases` so renames
break CI loudly. Wiki updated to reflect the new two-tier coverage and
the operational rule for new Gemini aliases (cheap smoke covers
auth, manual harness run still needed for sanitizer compatibility on
non-flagship Gemini additions).

* fix(model-smoke): walk fallback chain; address pr review comments

- model-smoke now uses `resolveCliModel(slug)` instead of `alias.resolve`
  so deprecated aliases (those with `fallback` set, e.g.
  `opencode/mimo-v2-pro-free` → `opencode/big-pickle`) hit the
  replacement model the way production does. mimo-v2-pro-free was
  failing CI because the underlying opencode model is dead — the
  fallback chain is the whole point of marking it deprecated.

- tighten stale `agentForSlug()` reference in model-smoke.ts comment
  (function was deleted in this same PR; classification is now inline
  in `list-aliases.ts toMatrixEntry`).

- tighten `FLAGSHIPS` drift comment to call out that the assertion is
  one-way (catches slug-rename, but silently omits new providers).
  Update wiki step 4 of "To add a provider" to require adding the
  standard-tier slug to `FLAGSHIPS` for harness coverage.

* docs: scrub stale env-knob refs in models-catalog parity section

`wiki/models-catalog.md` cross-provider parity paragraph still pointed
at `INCLUDE_ALL_PASSTHROUGHS` / `INCLUDE_EXPENSIVE` and the implicit
filter→expensive-gate coupling — all removed in this PR. Aligned the
copy with Step 9 (which was already updated): `INCLUDE_PASSTHROUGHS`,
no expensive gate, `MATRIX_FILTER` applies to both aliases and
flagships modes.
2026-05-11 16:36:14 +00:00

171 lines
6.3 KiB
TypeScript

/**
* model-smoke: per-alias resolution + auth check that bypasses the Pullfrog
* harness. resolves a model alias to its concrete provider/model + agent CLI,
* invokes the CLI directly with a trivial "reply OK" prompt, and asserts the
* provider replied. validates exactly the surface that changes when models.ts
* changes — alias → resolve mapping, agent classification, env-var wiring —
* without booting Docker, MCP, or the full agent runtime.
*
* tool-calling correctness is a property of the underlying model, not the
* alias; the `providers-live` job runs the full harness smoke once per
* provider (one standard-tier model each), which is enough.
*
* usage:
* node action/test/model-smoke.ts --slug openai/gpt
* PULLFROG_MODEL=openai/gpt node action/test/model-smoke.ts
*/
import { spawn } from "node:child_process";
import { mkdtempSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { config } from "dotenv";
import { modelAliases, resolveCliModel } from "../models.ts";
import { installFromNpmTarball } from "../utils/install.ts";
import { getDevDependencyVersion } from "../utils/version.ts";
config({ path: join(import.meta.dirname, "..", ".env") });
config({ path: join(import.meta.dirname, "..", "..", ".env") });
const PROMPT = "Reply with exactly OK and nothing else.";
const MATCH = /\bOK\b/i;
const TIMEOUT_MS = 60_000;
function parseSlug(): string {
const argIdx = process.argv.indexOf("--slug");
if (argIdx >= 0 && process.argv[argIdx + 1]) return process.argv[argIdx + 1];
if (process.env.PULLFROG_MODEL) return process.env.PULLFROG_MODEL;
throw new Error("model-smoke: pass --slug <alias> or set PULLFROG_MODEL");
}
type Plan =
| { agent: "opencode"; cliPath: string; args: string[] }
| { agent: "claude"; cliPath: string; args: string[] };
async function plan(slug: string): Promise<Plan> {
const alias = modelAliases.find((a) => a.slug === slug);
if (!alias) throw new Error(`model-smoke: unknown alias "${slug}"`);
// walk the fallback chain so deprecated aliases (those with `fallback` set,
// e.g. opencode/mimo-v2-pro-free → opencode/big-pickle) hit their replacement
// instead of the dead resolve target. mirrors production via resolveCliModel.
const cliModel = resolveCliModel(slug);
if (!cliModel) throw new Error(`model-smoke: fallback chain for "${slug}" is broken or cyclic`);
// anthropic/* aliases run through claude-code in production; everything else
// (openai, google, xai, deepseek, moonshot, opencode, openrouter) runs through
// opencode. mirrors the inline classification in list-aliases.ts toMatrixEntry().
if (slug.startsWith("anthropic/")) {
const cliPath = await installFromNpmTarball({
packageName: "@anthropic-ai/claude-code",
version: getDevDependencyVersion("@anthropic-ai/claude-code"),
executablePath: "cli.js",
installDependencies: false,
});
// claude expects a bare model id (e.g. "claude-sonnet-4-6"), not "anthropic/claude-sonnet-4-6"
const bareModel = cliModel.split("/").slice(1).join("/");
return {
agent: "claude",
cliPath,
args: [cliPath, "-p", PROMPT, "--model", bareModel],
};
}
const cliPath = await installFromNpmTarball({
packageName: "opencode-ai",
version: getDevDependencyVersion("opencode-ai"),
executablePath: "bin/opencode",
installDependencies: true,
});
return {
agent: "opencode",
cliPath,
args: ["run", "--model", cliModel, PROMPT],
};
}
type SpawnResult = { ok: boolean; output: string; reason: string };
function runCli(p: Plan, env: NodeJS.ProcessEnv): Promise<SpawnResult> {
// claude's cli.js shebangs to env node, but we invoke node explicitly to
// avoid PATH-resolution surprises in CI runners; opencode is a real binary.
const command = p.agent === "claude" ? "node" : p.cliPath;
return new Promise((resolve) => {
const child = spawn(command, p.args, { env, stdio: ["ignore", "pipe", "pipe"] });
let stdout = "";
let stderr = "";
child.stdout?.on("data", (chunk: Buffer) => {
stdout += chunk.toString();
});
child.stderr?.on("data", (chunk: Buffer) => {
stderr += chunk.toString();
});
const timer = setTimeout(() => {
child.kill("SIGKILL");
}, TIMEOUT_MS);
child.on("close", (code, signal) => {
clearTimeout(timer);
const output = stdout + (stderr ? `\n---stderr---\n${stderr}` : "");
if (signal === "SIGKILL") {
resolve({ ok: false, output, reason: `timed out after ${TIMEOUT_MS / 1000}s` });
return;
}
if (code !== 0) {
resolve({ ok: false, output, reason: `exit ${code}` });
return;
}
if (!MATCH.test(stdout)) {
resolve({ ok: false, output, reason: "no OK in stdout" });
return;
}
resolve({ ok: true, output, reason: "ok" });
});
child.on("error", (err) => {
clearTimeout(timer);
resolve({ ok: false, output: stderr, reason: `spawn error: ${err.message}` });
});
});
}
async function main(): Promise<void> {
const slug = parseSlug();
const tempDir = mkdtempSync(join(tmpdir(), "model-smoke-"));
const homeDir = join(tempDir, "home");
// installFromNpmTarball reads PULLFROG_TEMP_DIR from process.env, not from
// the spawn env, so we mutate process.env up-front. HOME/XDG_CONFIG_HOME are
// redirected to keep the agent CLIs from picking up the dev user's config.
process.env.PULLFROG_TEMP_DIR = tempDir;
process.env.HOME = homeDir;
process.env.XDG_CONFIG_HOME = join(homeDir, ".config");
// opencode reads GOOGLE_GENERATIVE_AI_API_KEY for gemini; mirror the harness fallback.
if (!process.env.GOOGLE_GENERATIVE_AI_API_KEY && process.env.GEMINI_API_KEY) {
process.env.GOOGLE_GENERATIVE_AI_API_KEY = process.env.GEMINI_API_KEY;
}
console.log(`» model-smoke ${slug}`);
const p = await plan(slug);
console.log(
`» agent=${p.agent} cmd=${[p.agent === "claude" ? "node" : p.cliPath, ...p.args].join(" ")}`
);
const result = await runCli(p, process.env);
if (result.ok) {
console.log(`${slug} (${p.agent})`);
process.exit(0);
}
console.error(`${slug} (${p.agent}): ${result.reason}`);
if (result.output) console.error(result.output);
process.exit(1);
}
main().catch((err: unknown) => {
console.error(err instanceof Error ? (err.stack ?? err.message) : String(err));
process.exit(1);
});