b6658ddbc1
* add workflows permission to git token and waitlist improvements - add `workflows` to `InstallationTokenPermissions` type in both action and API token routes - include `workflows: write` in the git token so agents can push workflow file changes - add `githubFollowers` field to WaitlistSignup schema with migration - add script to populate waitlist followers from GitHub API - add frog-green-square-border logo asset Co-authored-by: Cursor <cursoragent@cursor.com> * improve CI, agent logging, token permissions, and delegation guardrails - add format check and build step to root CI job - standardize agent model/effort log lines across all agents - fix GitHub App permissions types to match OpenAPI schema (workflows is write-only) - improve delegation error message to prevent subagent recursion - demote noisy OpenCode stderr to debug level - add subagent delegation rules to resolved instructions Co-authored-by: Cursor <cursoragent@cursor.com> * fix graphql partial error handling, update delegation message, add workflow_run fixtures Co-authored-by: Cursor <cursoragent@cursor.com> * remove module-level env var throws that break CI build Co-authored-by: Cursor <cursoragent@cursor.com> * fix logging bug and type hole from PR review - use batch-local notFound counter so per-batch log doesn't undercount - add workflows to WorkflowTokenPermissions so wire type matches what action sends Co-authored-by: Cursor <cursoragent@cursor.com> * lazy-init appOctokit to fix next build without env vars Co-authored-by: Cursor <cursoragent@cursor.com> * drop pnpm build from CI test workflow Co-authored-by: Cursor <cursoragent@cursor.com> * fix delegate-effort test regex to match actual log format, disable fail-fast for agnostic tests the test was matching `running \w+ with effort=auto` but the actual log line from shared.ts is `» effort: auto`. also temporarily set fail-fast: false on action-agnostic so all failures surface at once. Co-authored-by: Cursor <cursoragent@cursor.com> * disable fail-fast in action workflow too, relax ci.test.ts to match both workflow files now use fail-fast: false for agnostic tests so all matrix jobs run to completion. the ci consistency test now checks that the two workflows agree rather than requiring true. Co-authored-by: Cursor <cursoragent@cursor.com> * restore fail-fast: true now that all agnostic tests pass Co-authored-by: Cursor <cursoragent@cursor.com> * skip agent tests in CI when agent harness file didn't change adds action/test/changed-agents.sh which reads the PR diff (via dorny/paths-filter) and outputs only agents whose harness file was modified. the action-agents matrix now uses this dynamic list instead of a hardcoded array, so e.g. a PR touching only cursor.ts runs 6 jobs instead of 30. Co-authored-by: Cursor <cursoragent@cursor.com> * update ci.test.ts to validate dynamic agent matrix the test now checks that the matrix references the changes job output and that changed-agents.sh correctly discovers all agents. Co-authored-by: Cursor <cursoragent@cursor.com> * parallelize action jobs and use claude canary fallback for shared changes runs action-agents in parallel with action-agnostic after root/changes, and updates changed-agents logic so shared or non-harness action runtime changes run only claude while harness-specific edits run only those changed agents. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
54 lines
2.1 KiB
TypeScript
54 lines
2.1 KiB
TypeScript
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture, getAgentOutput, getStructuredOutput } from "../utils.ts";
|
|
|
|
/**
|
|
* delegateEffort test - validates effort selection for delegation.
|
|
*
|
|
* the orchestrator delegates to Plan mode with mini effort.
|
|
* validates that the subagent runs at mini effort (visible in agent logs
|
|
* as "effort=mini" or sonnet model selection for claude).
|
|
*/
|
|
|
|
// orchestrator runs at "auto" (opus) while delegating with "mini" (sonnet).
|
|
// this tests that the delegate tool's effort parameter actually overrides
|
|
// the model selection — if it were ignored, the subagent would also run at auto.
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `This is a simple task. Delegate to the Plan mode with MINI effort (this is a trivial task).
|
|
Pass these instructions to the subagent:
|
|
"Call set_output with the value 'EFFORT_TEST_PASSED'. Do not create plans or PRs. Just call set_output."`,
|
|
effort: "auto",
|
|
timeout: "5m",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
const output = getStructuredOutput(result);
|
|
const agentOutput = getAgentOutput(result);
|
|
|
|
const setOutputCalled = output !== null;
|
|
const correctValue = setOutputCalled && /EFFORT_TEST_PASSED/i.test(output);
|
|
|
|
// the orchestrator runs at auto (» effort: auto in its log line).
|
|
// the delegate tool should spawn the subagent at mini (» effort: mini in its log line).
|
|
// if effort override works, we should see BOTH effort values in the output.
|
|
const orchestratorEffort = /» effort:\s+auto/i.test(agentOutput);
|
|
const subagentEffort = /» effort:\s+mini/i.test(agentOutput);
|
|
|
|
return [
|
|
{ name: "set_output", passed: setOutputCalled },
|
|
{ name: "correct_value", passed: correctValue },
|
|
{ name: "orchestrator_auto", passed: orchestratorEffort },
|
|
{ name: "subagent_mini", passed: subagentEffort },
|
|
];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "delegate-effort",
|
|
fixture,
|
|
validator,
|
|
env: { GITHUB_REPOSITORY: "pullfrog/test-repo" },
|
|
tags: ["agnostic"],
|
|
};
|