feat(check): parse vapi-checks.yml check configuration

[scott-lowe-vapi]

Value

V.A.L.U.E. tier: project — PR 4 of 10 for inline simulation PR checks (TEST-141); this PR adds a config parser with no caller yet.

• Problem: a customer needs one place to say which agents to test, with which suites, in which org, and how strictly. promotion.yml can't hold it: promotionConfigParse requires a pipeline of two or more orgs, and most customers have one.
• Who it affects: gitops users setting up PR checks, single-org and CI-org alike. The PR check (PRs 5–8) and the promotion gate (PR 10) both read this file, so the gate runs the same tests as the PR check.
• What changes:
  • src/check-config.ts parses a root vapi-checks.yml into typed check definitions:
    • org, plus an optional runOrg and baseUrl;
    • targets (assistants/<id> or squads/<id>, nested IDs allowed);
    • suites and/or simulations;
    • bindings (promotion's shape, via promotionBindingsParse);
    • extra paths;
    • run settings with repo-wide defaults: transport chat, 1 iteration, 20 min, toolMocks: strict, stripWebhooks: true.
  • vapi-checks.example.yml is the commented starting point: a single-org check, plus a commented CI-org check.
  • Every key is validated, and unknown keys fail, so a typo can't silently run fewer tests. A mode: key fails with a message explaining that checks always build from the branch, since a "run what's deployed" mode was deliberately left out.

Evidence of value

Check	Result
Valid configs	Minimal check (defaults applied, runOrg = org, credentials bind / phones omit); default and per-check overrides; a CI-org check with EU baseUrl and bindings
Rejections	31 invalid shapes, each asserted against its exact message naming the field (table in tests/check-config.test.ts)
Shipped example	Parses as-is, and the commented CI-org check parses once uncommented, so the docs can't drift from the parser
npm test	398 → 404 passing; npm run build clean

Testing plan

• tests/check-config.test.ts covers:
  • parse results for valid configs;
  • one table row per rejection: version, empty or unknown keys at each level, mode, slugs, target shape, extension and .. in IDs, duplicates, missing suites/simulations, each setting's range, baseUrl, paths, bindings;
  • the example file;
  • checksConfigLoad, which returns null when no vapi-checks.yml exists (checks are opt-in).
• Not tested: nothing uses the config yet. Resolving targets and suites against real files is PR 5, and the baseUrl fallback order (.env.<runOrg>, $VAPI_BASE_URL, api.vapi.ai) is applied at run time in PR 7.

Stacked on #59.

Refs TEST-141

🤖 Generated with Claude Code

[scott-lowe-vapi]

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

• feat(promotion): gate promotion out of an org on a passing check #66
• feat(check): add the opt-in Vapi checks PR workflow and user docs #64
• feat(check): run checks live and report Vapi Evals statuses #63
• feat(check): fail closed on tools and servers in inline check payloads #62
• feat(check): build inline simulation-run payloads and add a dry-run CLI #61
• feat(check): parse vapi-checks.yml check configuration #60 👈 (View in Graphite)
• refactor: move resource parsing and org connection helpers into config-free modules #59
• fix(sim): report failed, canceled and incomplete runs instead of a false pass #58
• ci: type-check tests/ and send a User-Agent on sim API requests #57
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.