Files
shockbot/test/smoke-models.ts
T
Colin McDonnell 6d25adfd1a Agent & model refactor (#478)
* agent & model refactor with ASKPASS git auth, UI restructure, clerk v7

Made-with: Cursor

* fix stale agent/effort refs, add tests for askpass + model resolution

- reviewCleanup.ts: payload.agent -> payload.model, remove effort
- selectMode.ts PlanEdit: remove delegation/subagent/effort references
- pullfrog.yml.ts: update env vars (drop GOOGLE_API_KEY/CURSOR_API_KEY,
  add GOOGLE_GENERATIVE_AI_API_KEY/XAI_API_KEY/MOONSHOT_API_KEY/OPENCODE_API_KEY)
- FlagsSettings/RepoInstructionsSection: remove stale effort/timeout copy
- new: gitAuthServer.test.ts (10 tests — lifecycle, token delivery, tamper detection, script gen)
- new: agent.test.ts (4 tests — default opentoad, AGENT_OVERRIDE, invalid override)
- new: models.test.ts (19 tests — parseModel, resolution, registry invariants)
- update models.dev snapshot

Made-with: Cursor

* fix changed-agents.sh to filter legacy agent files from CI matrix

legacy agent files (claude.ts, codex.ts, etc.) are @ts-nocheck and not
exported from index.ts. changed-agents.sh now reads index.ts imports to
build the active agent set and treats changes to inactive files as
non-agent changes (opentoad canary only).

Made-with: Cursor

* remove MCP file tools, old agent harnesses, and obsolete security tests

ASKPASS-based git auth makes the old MCP file tool security layer unnecessary:
- token never in subprocess env, so symlink/gitattributes/hook attacks can't exfiltrate it
- agents now use native file tools (OpenCode builtin read/edit)

deleted:
- action/mcp/file.ts (file_read, file_write, file_edit, file_delete, list_directory)
- action/mcp/index.ts (dead re-export)
- agent harnesses: claude.ts, codex.ts, cursor.ts, gemini.ts, opencode.ts
- opencode-runner.ts (inlined into opentoad.ts)
- security tests that validated MCP file tool restrictions
- commented-out three-step review flow (~300 lines)
- sanitizeSchema/wrapSchema dead code from mcp/shared.ts
- OPENCODE_MODEL_MINI/MAX env vars (effort-level model overrides removed)

updated test prompts to use generic file ops instead of MCP tool names.
restored pkg-json-scripts + requirements-txt-attack (test --ignore-scripts defense).

Made-with: Cursor

* bump actions/checkout v4 → v6 (node 24)

node 20 actions deprecated june 2, 2026.

Made-with: Cursor

* temporarily disable fail-fast on agnostic tests to debug checkout@v6

Made-with: Cursor

* re-enable fail-fast on agnostic tests

Made-with: Cursor

* fix test token mismatch: mint OIDC tokens scoped to target repo

CI tests override GITHUB_REPOSITORY to pullfrog/test-repo but inherit
the runner's GITHUB_TOKEN (scoped to pullfrog/app), causing 401s on
every run-context fetch. Clear GITHUB_TOKEN in the test subprocess so
ensureGitHubToken() mints a properly scoped token via OIDC.

Also centralizes the default GITHUB_REPOSITORY in runAgentStreaming
instead of repeating it in every test file, and fixes preview-cleanup
to remove workers from all queues (not just name-matching ones).

Made-with: Cursor

* fix ensureGitHubToken to try OIDC when app credentials are absent

ensureGitHubToken only attempted token minting when GITHUB_APP_ID and
GITHUB_PRIVATE_KEY were set. In CI, OIDC is available but app creds
aren't exposed — so the guard prevented minting entirely.

Made-with: Cursor

* dead code cleanup: remove remnants of deleted agents, file tools, effort system

remove unused @anthropic-ai/claude-agent-sdk and @openai/codex-sdk deps,
orphaned file-tool security tests, dead GEMINI_MODEL passthrough, stale
opencode-runner wiki refs, deleted test file references, and MCP file tool
docs. rename docs/effort → docs/models. fix vitest setup: move dotenv to
globalSetup (runs once before forks instead of per-file, 19s → 200ms).

Made-with: Cursor

* address review feedback: remove dead code, update stale references

- remove AGENT_OVERRIDE (only opentoad exists)
- remove shellToolName plumbing (always restricted shell)
- bump action version to 0.0.179
- remove CURSOR_API_KEY from all workflows/configs
- remove OPENCODE_MODEL_MINI/MAX from workflows/docs
- delete wiki/effort.md, rewrite docs/effort.mdx as "Models"
- rewrite wiki/modes.md: orchestrator/subagent → single agent
- simplify flag system: drop builtin flag extraction (debug, effort,
  timeout, agent), keep custom flag replacement only
- reserve all legacy flag names to prevent custom flag conflicts

Made-with: Cursor

* regenerate lockfile after removing claude-agent-sdk and codex-sdk

Made-with: Cursor

* fix import ordering, add lockfile check to pre-push hook

Made-with: Cursor

* remove dead debug payload field, stale packageExtensions

Made-with: Cursor

* merge proc-sandbox and token-exfil into a single test

proc-sandbox and token-exfil were duplicative — both tested that
SANDBOX_TEST_TOKEN couldn't be exfiltrated. consolidated into
token-exfil with shell:restricted (which actually exercises filterEnv)
and the /proc attack vector hints from proc-sandbox.

Made-with: Cursor

* fix wiki adversarial.md to match actual tokenExfil validator

Made-with: Cursor
2026-03-12 05:22:51 +00:00

99 lines
3.1 KiB
TypeScript

/**
* smoke test: runs `opencode run` with each resolved model to verify they work.
* usage: node --env-file=../../.env action/test/smoke-models.ts
*/
import { execFileSync } from "node:child_process";
import { modelAliases, type ProviderConfig, providers } from "../models.ts";
const TIMEOUT_MS = 60_000;
const PROMPT = "respond with just the word hello";
const availableKeys = new Set<string>();
for (const config of Object.values(providers) as ProviderConfig[]) {
for (const envVar of config.envVars) {
if (process.env[envVar]) availableKeys.add(envVar);
}
}
function hasKey(providerKey: string): boolean {
const config = (providers as Record<string, ProviderConfig>)[providerKey];
if (!config) return false;
if (config.envVars.length === 0) return true;
return config.envVars.some((v) => process.env[v]);
}
const results: { model: string; status: "pass" | "fail" | "skip"; detail?: string }[] = [];
const seen = new Set<string>();
for (const alias of modelAliases) {
if (seen.has(alias.resolve)) {
results.push({ model: alias.resolve, status: "skip", detail: "duplicate resolve" });
continue;
}
seen.add(alias.resolve);
if (!hasKey(alias.provider)) {
results.push({ model: alias.resolve, status: "skip", detail: `no key for ${alias.provider}` });
continue;
}
process.stdout.write(`testing ${alias.resolve} ... `);
try {
const out = execFileSync("opencode", ["run", "-m", alias.resolve, PROMPT], {
timeout: TIMEOUT_MS,
encoding: "utf-8",
stdio: ["ignore", "pipe", "pipe"],
env: { ...process.env, NO_COLOR: "1" },
});
const trimmed = out.trim().toLowerCase();
if (trimmed.includes("hello")) {
console.log("PASS");
results.push({ model: alias.resolve, status: "pass" });
} else if (trimmed.length === 0) {
console.log("FAIL (empty output)");
results.push({ model: alias.resolve, status: "fail", detail: "empty output" });
} else {
console.log("PASS (got response)");
results.push({ model: alias.resolve, status: "pass", detail: trimmed.slice(0, 80) });
}
} catch (err: any) {
if (err.killed) {
console.log(`TIMEOUT (${TIMEOUT_MS / 1000}s)`);
results.push({ model: alias.resolve, status: "fail", detail: "timeout" });
} else {
const msg =
err.stderr?.toString().trim().slice(0, 120) ||
err.message?.slice(0, 120) ||
"unknown error";
console.log(`FAIL (${msg})`);
results.push({ model: alias.resolve, status: "fail", detail: msg });
}
}
}
console.log("\n=== results ===");
const passed = results.filter((r) => r.status === "pass");
const failed = results.filter((r) => r.status === "fail");
const skipped = results.filter((r) => r.status === "skip");
console.log(`passed: ${passed.length}, failed: ${failed.length}, skipped: ${skipped.length}`);
if (failed.length > 0) {
console.log("\nfailures:");
for (const f of failed) {
console.log(` ${f.model}: ${f.detail}`);
}
}
if (skipped.length > 0) {
console.log("\nskipped:");
for (const s of skipped) {
console.log(` ${s.model}: ${s.detail}`);
}
}
process.exit(failed.length > 0 ? 1 : 0);