mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-08 00:02:20 +03:00
d628105503
All 10 diagnostics in this file are the `strictNullChecks: false` narrowing limitation: a boolean-literal discriminant narrows the positive branch but leaves the negative one as the full union, so `if (!resolved.ok)` and the code after `if (outcome.success)` could not see `status`/`error`. Three unions, all module-private and untouched by any test, so per the rule recorded on #8499 these are retagged rather than fixed with predicates — predicates are for exported unions whose shape callers depend on: resolveDesignerWebRequest ok: true|false -> state: "resolved"|"invalid" DesignerWebStepResult done + success -> state: "pending"|"ready"|"failed" The step union collapsed two booleans into one discriminant; `done`/`success` encoded three states across two flags, which is also why the pending arm had no `success` property for `outcome.success` to read. Also narrowed runDesignerWebPollLoop's declared return from `DesignerWebStepResult | {…504…}` to a new DesignerWebOutcome (ready | failed). The loop returns a step only after confirming it is terminal, and otherwise synthesizes a 504 — it can never return a pending step, and the old signature claiming it could is what made `.success` unreadable on the union at all. 280 -> 270, zero new, on a line-number-agnostic diff of the full tsc error set. Tests: unlike the previous slices this rewrote real control flow (three conditionals), so the existing suite is doing actual work here — microsoft-designer-web-6672.test.ts drives the handler end-to-end through 400, 401, immediate-ready, poll-then-ready, non-OK upstream and 504-timeout, i.e. every arm but one. The "empty" arm (unrecognized 200 body -> terminal 502) was tested only at the parser level, never through the handler, so the 502 itself was unasserted. Added designer-web-empty-response-502.test.ts (2 tests) pinning that it is terminal (exactly one fetch, no polling) and distinct from the 504 deadline path. Both suites pass against the parent commit too — the tests are black-box through the exported handler, so they are agnostic to the discriminant rename and prove the retag is behavior-preserving. 61/61 across the 3 suites. Co-authored-by: backryun <busan011@ormbiz.co.kr>