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".
89 lines
2.6 KiB
TypeScript
89 lines
2.6 KiB
TypeScript
/**
|
|
* provider catalog — the source of truth for `providers-live` (full harness
|
|
* smoke per provider) and the per-provider coverage globs that scope `models-live`
|
|
* (per-alias CLI smoke).
|
|
*
|
|
* each entry pins one standard-tier flagship slug per provider — not the
|
|
* pro/opus tier (too expensive for per-push) and not the free/experimental
|
|
* tier (too flaky). these flagships catch provider-class regressions like
|
|
* Gemini schema sanitization or OpenAI tool-call format drift that the cheap
|
|
* per-alias CLI smoke can't see.
|
|
*
|
|
* `coverage` lists the source files that, when changed, should rerun this
|
|
* provider's flagship + every alias of this provider. `action/models.ts` is
|
|
* included on every entry — touching the resolution table reruns all model
|
|
* tests (simple model; matches the per-PR-precision answer from planning).
|
|
*
|
|
* adding a new provider:
|
|
* 1. add an entry here with the flagship slug, agent harness, coverage globs
|
|
* 2. add a row to wiki/models-catalog.md "To add a provider"
|
|
* 3. CI picks it up automatically — no workflow change
|
|
*/
|
|
|
|
export type ProviderEntry = {
|
|
name: string;
|
|
/** flagship slug for `providers-live` full-harness smoke. */
|
|
flagship: string;
|
|
/** harness used by the runtime for this provider's models. */
|
|
agent: "claude" | "opencode";
|
|
/** repo-relative globs that invalidate this provider's matrix entries. */
|
|
coverage: string[];
|
|
};
|
|
|
|
const SHARED_OPENCODE_COVERAGE = [
|
|
"action/models.ts",
|
|
"action/agents/opencode.ts",
|
|
"action/agents/opencodePlugin.ts",
|
|
];
|
|
|
|
export const providers: ProviderEntry[] = [
|
|
{
|
|
name: "anthropic",
|
|
flagship: "anthropic/claude-sonnet",
|
|
agent: "claude",
|
|
coverage: ["action/models.ts", "action/agents/claude.ts"],
|
|
},
|
|
{
|
|
name: "openai",
|
|
flagship: "openai/gpt",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
{
|
|
name: "google",
|
|
flagship: "google/gemini-pro",
|
|
agent: "opencode",
|
|
coverage: [...SHARED_OPENCODE_COVERAGE, "action/mcp/geminiSanitizer.ts"],
|
|
},
|
|
{
|
|
name: "xai",
|
|
flagship: "xai/grok",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
{
|
|
name: "deepseek",
|
|
flagship: "deepseek/deepseek-pro",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
{
|
|
name: "moonshotai",
|
|
flagship: "moonshotai/kimi-k2",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
{
|
|
name: "opencode",
|
|
flagship: "opencode/big-pickle",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
{
|
|
name: "openrouter",
|
|
flagship: "openrouter/claude-sonnet",
|
|
agent: "opencode",
|
|
coverage: SHARED_OPENCODE_COVERAGE,
|
|
},
|
|
];
|