6d25adfd1a
* 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
99 lines
3.1 KiB
TypeScript
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);
|