Colin McDonnell
1f4c3031be
* ci: filter test matrices by per-test coverage globs to cut LLM spend every test in `crossagent/`, `agnostic/`, and every provider entry now declares a `coverage: string[]` of repo-relative globs. the new `changes` job runs `paths-filter` for a docs-only short-circuit, then pipes the changed-file list into `action/test/matrix.ts`, which intersects each entry's coverage against the diff and emits filtered `agents`, `agnostic`, `flagships`, and `aliases` matrices. main pushes and `workflow_dispatch` set `FULL=1` to run everything as a stale-glob safety net. retires `changed-agents.sh` and the `MODE=flagships` branch in `list-aliases.ts` in favor of one consistent model. * ci(matrix): switch test discovery to dep-free static parsing the GHA `changes` job has no `node_modules` installed. the previous dynamic-import path pulled the test files transitively through `utils.ts` -> `agents/index.ts` -> `@actions/core`, which exploded with ERR_MODULE_NOT_FOUND. parse the test files via regex instead so matrix.ts stays zero-dep — the chain (matrix -> coverage / providers / list-aliases / models) imports only node builtins and relative TS files. * ci(matrix): address PR #730 review feedback - drop dangling `action/mcp/toolFiltering.ts` glob from `nobash`, `restricted`, `tokenExfil` (file doesn't exist; `.test.ts` does, but the runtime tooling lives in `mcp/shell.ts` and `agents/{claude,opencode}.ts`, both already covered). - drop unused `coverageForProvider` export and its `byName` map from `providers.ts` (matrix.ts builds its own lookup inline). - derive the active agent list from `agents/index.ts` via the same dep-free regex tactic as `parseTestFile` instead of hardcoding `["claude", "opencode"]` — adding a new harness file now wires it into the dynamic matrix automatically. - treat `coverage: []` as `coverage: undefined` in `shouldRun` so an accidentally-empty array doesn't silently skip CI on every PR. - add `action/utils/activity.ts` and `action/mcp/selectMode.ts` to the `timeout` test's coverage — the activity-timeout enforcement path was the original reason the test exists. - ungate the `root` job (lint/format/typecheck/vitest). it's a required status check on `main`, so gating it on `code == 'true'` would make docs-only PRs unmergeable (skipped jobs don't satisfy required-check rules). the real LLM savings come from skipping the four matrices, not from skipping `root`. - harden the four matrix-job `if:` guards from `outputs.matrix && ...` to `outputs.matrix != '' && ...` — explicit > implicit short-circuit. - document `expandBraces`'s flat-only support so a future author isn't surprised by `{a,{b,c}}` not expanding. - fix awkward sentence in `wiki/action-tests.md` "CI Cost Filtering".
49 lines
1.7 KiB
TypeScript
49 lines
1.7 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import type { AgentResult, TestRunnerOptions, ValidationCheck } from "../utils.ts";
|
|
import { defineFixture, getAgentOutput } from "../utils.ts";
|
|
|
|
const skillName = "pullfrog-skill-check";
|
|
const token = randomUUID();
|
|
|
|
const fixture = defineFixture(
|
|
{
|
|
prompt: `Do not modify any files.
|
|
|
|
Use the skill tool to load ${skillName}.
|
|
Then call set_output with exactly this token and nothing else: ${token}`,
|
|
shell: "restricted",
|
|
push: "disabled",
|
|
timeout: "4m",
|
|
},
|
|
{ localOnly: true }
|
|
);
|
|
|
|
const repoSetup = `mkdir -p .claude/skills/${skillName} .opencode/skills/${skillName} && printf '%s\\n' '---' 'name: ${skillName}' 'description: local skill test token source' '---' '' 'token: ${token}' > .claude/skills/${skillName}/SKILL.md && cp .claude/skills/${skillName}/SKILL.md .opencode/skills/${skillName}/SKILL.md`;
|
|
|
|
function validator(result: AgentResult): ValidationCheck[] {
|
|
const setOutputCalled = result.structuredOutput !== null;
|
|
const tokenMatches = result.structuredOutput === token;
|
|
|
|
const agentOutput = getAgentOutput(result);
|
|
const skillInvoked = /skill\(\{[^)]*"name":"pullfrog-skill-check"/.test(agentOutput);
|
|
|
|
return [
|
|
{ name: "set_output", passed: setOutputCalled },
|
|
{ name: "token_matches", passed: tokenMatches },
|
|
{ name: "skill_invoked", passed: skillInvoked },
|
|
];
|
|
}
|
|
|
|
export const test: TestRunnerOptions = {
|
|
name: "skill-invoke-opencode",
|
|
fixture,
|
|
validator,
|
|
agents: ["opencode"],
|
|
repoSetup,
|
|
env: {
|
|
PULLFROG_DISABLE_SECURITY_INSTRUCTIONS: "1",
|
|
PULLFROG_MODEL: "anthropic/claude-sonnet-4-6",
|
|
},
|
|
coverage: ["action/agents/opencode.ts", "action/agents/opencodePlugin.ts"],
|
|
};
|