uloop-run-tests
/uloop-run-tests
Uruchamia testy Unity Test Runner w trybach EditMode i PlayMode, opisuje szczegółowe wyniki oraz przyczyny błędów.
- Autor
- hatayama ↗
- Repozytorium
- uLoopMCP ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 14.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 3
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 14.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Uruchamia testy Unity Test Runner w trybach EditMode i PlayMode, opisuje szczegółowe wyniki oraz przyczyny błędów.
Oryginalny opis (EN)
Run Unity Test Runner and report detailed results. Use for EditMode/PlayMode tests or failure diagnosis; for runtime behavior the tests do not exercise, use pause-point (trace) or record-video.
Jak działa
- Usage
- Parameters
- Output
Podgląd SKILL.md
--- name: uloop-run-tests toolName: run-tests description: "Run Unity Test Runner and report detailed results. Use for EditMode/PlayMode tests or failure diagnosis; for runtime behavior the tests do not exercise, use pause-point (trace) or record-video." --- # uloop run-tests Execute Unity Test Runner. When a test or suite fails or a test ends inconclusive, NUnit XML results with failure messages, stack traces, and inconclusive reasons are automatically saved. Read the XML file at `XmlPath` for detailed diagnosis. `uloop run-tests` automatically compiles pending script changes before running tests. Pass `--skip-compile` only while validating active hot-reload patches, because the compile clears those patches; otherwise let the default compile surface errors and run against current scripts. `--skip-compile` skips only the CLI-side compile: script edits saved since the last compile can still be imported during the run; such an import reloads the domain as soon as the run releases its assembly lock, discarding active patches and ending the request. While hot reload holds Auto Refresh (the state an apply leaves), a verified run kept the patches live. Check `uloop hot-reload --status` after the run instead of assuming either outcome. That compile follows the `uloop compile` rules: when Unity accepts it but has not started it after 10 seconds, uloop brings the Editor to the front once and restores the previous window afterwards; after 60 seconds it returns the compile's `COMPILE_NOT_STARTED` error instead of running tests (click inside the Unity window, then rerun). Before executing tests, `uloop run-tests` handles unsaved loaded Scene and Prefab Stage changes according to `--unsaved-changes` (default `save`): `save` writes them first, `fail` stops if any remain, and `discard` reloads disk state so tests run against saved files. Untitled scenes cannot be discarded and fail. If the chosen mode cannot proceed, it returns `Success: false`, keeps `TestCount` at `0`, lists the items in `Message`, and does not start the Unity Test Runner. Active pause points are automatically cleared (the underlying code patches are removed as well) before test execution begins. Cleared IDs are reported in the response's `ClearedPausePointIds` field. A test run can end by discarding active hot-reload changes: script edits imported during the run are compiled when the test runner releases its assembly-reload lock, and that deferred domain reload wipes the patches even though the tests themselves ran patched. The response's Warning field appears whenever changes were live when the run started and does not say whether they survived; check 'uloop hot-reload --status', then re-apply 'uloop hot-reload' or bake the edits in with 'uloop compile' before the next Play or test run. `NoTestsFound` means zero tests matched — not a test failure. Check `NoTestsFoundExplanation` and `Message` for asmdef hints. When an unfiltered run finds no tests and the project has no test assembly for the TestMode, `ProposedTestAsmdef` carries a ready-to-write `.asmdef`: save `Content` at `AssetPath`, move the test scripts under that folder, then compile and rerun. `Status: Inconclusive` means no test failed but at least one could not meet an `Assume`; `Success` is `false`, as Unity's batchmode test run also fails for it. `InconclusiveTests` names them with the assumption's message. A test that cannot run in this environment should call `Assert.Ignore` so it reports as skipped. ## Usage ```bash uloop run-tests [options] ``` ## Parameters | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `--test-mode` | string | `EditMode` | Test mode: `EditMode`, `PlayMode` | | `--filter-type` | string | `all` | Filter type: `all`, `exact`, `regex`, `assembly`, `class` | | `--filter-value` | string | - | Filter value (test name, pattern, assembly, or class name) | | `--unsaved-changes` | string | `save` | `save` writes unsaved Scene/Prefab Stage changes; `fail` stops if any remain; `discard` reloads disk state (Untitled scenes fail) | | `--skip-compile` | flag | - | Skip the CLI-side compile before running tests; use only while validating active hot-reload patches. Script edits saved since the last compile can still be imported during the run. | | `--timeout-seconds` | integer | `600` | Maximum seconds to wait for RunFinished before canceling the await (max `1500`). Increase for long suites; on timeout the Test Runner may still be running until stop handling lands | | `--respect-enter-play-mode-settings` | flag | - | PlayMode only: keep the project's Enter Play Mode settings instead of forcing Domain Reload off. A Domain Reload during the run is survived; the result is recovered after the reload. Use for projects whose libraries require a Domain Reload on Play entry. | | `--rerun-failed` | flag | - | Rerun only the tests that failed or were inconclusive in the most recent completed run of the same --test-mode (whole fixtures for a failed OneTimeSetUp/OneTimeTearDown). Cannot be combined with --filter-type or --filter-value | | `--log-stack-traces` | flag | - | Leave the project's log stack trace settings in place during the run. By default `run-tests` turns them off, because each stack trace grows the Editor's native memory and Editor.log, and only an Editor restart frees that memory. Assertion and thrown-exception failures keep their location either way. | By default PlayMode still forces Domain Reload off. With `--respect-enter-play-mode-settings`, a Domain Reload may run and the command takes longer; pause-point and hot-reload notes are omitted from a result recovered after reload. Canceling the CLI (Ctrl-C) does not stop the Unity-side run on this path. exact matches the full test name (Namespace.Class.Method). class runs every test of one class by bare or namespace-qualified name, e.g. --filter-type class --filter-value PlayerTests; the name is matched literally and whole, so PlayerTests does not run EnemyPlayerTests. regex matches a .NET regex against full test names, e.g. --filter-type regex --filter-value '^MyGame\.Tests\.' Unity log stack traces are off during a run and go back to the project's settings when it finishes, so logs from the run have none in `get-logs --include-stack-trace`. Test results do not change, except for a test that reads a log's stack trace: pass `--log-stack-traces`, or have that test set `Application.SetStackTraceLogType` itself. A failure raised only by a logged error or exception has no `File` or `Line`; `Message` then names the rerun command that keeps the project's settings, which adds them unless the project has stack traces off for that log type. A Domain Reload puts the settings back, so a `--respect-enter-play-mode-settings` run that goes through one keeps its stack traces. `--rerun-failed` reads the record that every completed run writes for its test mode, so it reruns the failures of the most recent completed run, filtered or not. A run that timed out or was cancelled leaves no record. With nothing recorded as failed it returns `Status: NothingToRerun` without running; to tell a flaky test from a real failure, run `--rerun-failed` again after a failure. ## Output Returns JSON. `Success`, `Status`, `Message`, `FailedTests` (up to 10), and `XmlPath` (set when a test or suite failed or was inconclusive) are usually enough; every field is described in `references/response-fields.md`, and the XML file in `references/xml-results.md`.
Pliki w paczce (3)
- SKILL.md 7 KB
- references/response-fields.md 4 KB
- references/xml-results.md 1 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · hatayama/uLoopMCP | 95 | MIT |
| hatayama/uLoopMCP | 95 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki db21e3101b85 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100unity-tests-write
Pisze testy Unity: EditMode, PlayMode, testy wydajności i pokrycie kodu. - 100unity-testing
Podaje zasady testów Unity: wybór EditMode lub PlayMode, konfigurację zestawu testów i sposób testowania kodu Unity. - 100unity-testing
Prowadzi testowanie w Unity Test Framework: testy EditMode i PlayMode, korutyny [UnityTest], Test Runner, mockowanie czasu i wejścia, testy wydajności oraz uruchomienia w CI. - 88unity-batchmode
Uruchamia Unity bez interfejsu: testy EditMode i PlayMode, budowanie gry przez skrypt z kodem wyjścia i sprawdzanie kompilacji, a także czyta logi. - 100uw-unity-test-runner
Generuje testy EditMode i PlayMode w NUnit mapowane ze scenariuszy Gherkin z GDD, przy pisaniu testów, walidacji funkcji i weryfikacji zachowania po zmianach. - 100testing-infrastructure
Opisuje wzorce testów w Unity: UnitySystemTestBase, narzędzia ECS, mocki, tryby EditMode i PlayMode dla systemów ECS i kontrolerów.