Colin McDonnell
4b3c5ca905
* rename agent key to opencode and add skill invocation coverage. add skill-invoke tests for claude and opencode with local play-based validation signals, update CI matrices, and include the current tracked refactors in this branch for review. Made-with: Cursor * exclude agent-specific skill-invoke tests from wrong agent in CI matrix * address review follow-up and preserve workflow run UI tweak. switch changed-agents ci coverage to exercise the opentoad implementation path while keeping the opencode expectation, and include the local workflow run client interaction updates requested on this branch. Made-with: Cursor * remove opentoad agent filename from runtime. rename the opencode harness implementation file from opentoad.ts to opencode.ts and update ci coverage input accordingly so action code no longer carries the old filename. Made-with: Cursor * ensure security prompt bypass is set on every test fixture. this keeps adversarial and permissions harnesses from being blocked by the default prompt-injection refusal path during CI security tests. Made-with: Cursor --------- Co-authored-by: pullfrog[bot] <226033991+pullfrog[bot]@users.noreply.github.com>
33 lines
1.0 KiB
TypeScript
33 lines
1.0 KiB
TypeScript
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture } from "../utils.ts";
|
|
|
|
/**
|
|
* timeout test - validates timeout enforcement works correctly.
|
|
* sets a very short timeout (5s) and gives the agent a task that takes longer.
|
|
* the run should fail with a timeout error.
|
|
*/
|
|
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `Select the Build mode via select_mode. Then select Review mode via select_mode. Then read every file in the repository recursively.
|
|
Finally call set_output with "TIMEOUT TEST COMPLETED".`,
|
|
timeout: "5s",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
// run should have failed due to timeout
|
|
const timedOut = !result.success && /timed out/i.test(result.output);
|
|
return [{ name: "timeout_triggered", passed: timedOut }];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "timeout",
|
|
fixture,
|
|
validator,
|
|
expectFailure: true,
|
|
env: { PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1" },
|
|
tags: ["agnostic"],
|
|
};
|