fix(web): make Skiller launch button responsive#314
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Plus Run ID: 📒 Files selected for processing (4)
📜 Recent review details⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
🧰 Additional context used📓 Path-based instructions (8)**/*.{ts,tsx}📄 CodeRabbit inference engine (CLAUDE.md)
Files:
**/*.{ts,tsx,js,jsx}📄 CodeRabbit inference engine (AGENTS.md)
Files:
**/*.{sh,bash,py,js,ts,jsx,tsx,go,java,rb,php}📄 CodeRabbit inference engine (Custom checks)
Files:
**/*.{py,js,ts,jsx,tsx,go,java,rb,php,sh,bash,c,cpp}📄 CodeRabbit inference engine (Custom checks)
Files:
**/*.{js,ts,jsx,tsx,py,java,go,rb,php,sh,bash,yml,yaml,json,env*,toml,cfg,config,dockerfile,dockerignore}📄 CodeRabbit inference engine (Custom checks)
Files:
**/*⚙️ CodeRabbit configuration file
Files:
**/*.test.{ts,tsx}📄 CodeRabbit inference engine (CLAUDE.md)
Files:
**/*.{test,spec}.{ts,tsx}📄 CodeRabbit inference engine (AGENTS.md)
Files:
🔇 Additional comments (4)
📝 WalkthroughSummary by CodeRabbit
WalkthroughРефакторит открытие URL — добавляет prepareOpenUrl/PreparedOpenUrl, интегрирует подготовленное окно в запуск Skiller, добавляет onOpenSkiller для терминальной сессии, подключает UI и обновляет тесты с фикстурой для mock-окна браузера. ChangesИнтеграция открытия Skiller через подготовленные окна браузера
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs🚥 Pre-merge checks | ✅ 7✅ Passed checks (7 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
packages/app/tests/docker-git/actions-skiller.test.ts (1)
83-171:⚠️ Potential issue | 🟠 Major | ⚡ Quick winДобавьте регрессионный тест для popup-blocked ветки (Line 83–171).
Сейчас нет проверки инварианта: при
window.open=nullдолжен сохраняться fallback-месседж для ручного открытия и не должно быть навигации/focus/close. Это заявлено в целях PR, но не покрыто тестом.As per coding guidelines "Сверь изменения с исходным ТЗ/спекой ... флагай ... отсутствие тестов для заявленного поведения".
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@packages/app/tests/docker-git/actions-skiller.test.ts` around lines 83 - 171, Add a new it.effect test in the same file that simulates a blocked popup by making browserOpenMock.mockReturnValueOnce(null), then call openSkillerApp(context) (use makeBrowserActionContext to get context and setMessage) and assert that the fallback/manual-open message was left via setMessage, that there was no navigation to openedWindow (openedWindow.location.href remains empty) and neither openedWindow.focus nor openedWindow.close were called; reference the existing mocks openSkillerMock, browserOpenMock and the helper makeBrowserActionContext and the function openSkillerApp to locate where to add this regression test.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/app/src/web/open-url.ts`:
- Around line 32-35: Функция navigate всегда возвращает true even если навигация
не произошла; исправьте вью: перед возвратом успеха проверяйте состояние
целевого окна (используя openedWindow.closed) и оборачивайте присвоение
openedWindow.location.href/focus в try/catch, возвращая false при исключении или
если openedWindow.closed === true; при false вызывайте fallback (например
открыть URL через window.open или показать инструкцию пользователю). Обновите
логику в методе navigate и там, где он вызывается, чтобы реагировать на false и
предлагать ручное открытие.
In `@packages/app/tests/docker-git/app-terminal-session-handlers.test.ts`:
- Around line 97-141: Replace the fixed examples with fast-check property tests:
generate arbitrary host URLs and combinations of projectId (string|undefined),
projectKey (string|undefined) and terminalSessionId (string|undefined) and
assert invariants using newProjectTerminalUrl and buildHandlers; for
newProjectTerminalUrl assert the returned URL preserves the host and path ends
with /ssh/{projectKey} and only includes the t= query when terminalSessionId is
defined; for buildHandlers call expectProjectHandlers(buildHandlers({ projectId,
projectKey, terminalSessionId }), expected) where expected booleans are computed
from the inputs (apply/browser/taskManager = Boolean(projectId), skiller =
Boolean(projectKey && terminalSessionId), terminal = Boolean(projectId &&
projectKey)); use fc.string()/fc.option to produce empty/defined values and run
many examples to validate invariants.
---
Outside diff comments:
In `@packages/app/tests/docker-git/actions-skiller.test.ts`:
- Around line 83-171: Add a new it.effect test in the same file that simulates a
blocked popup by making browserOpenMock.mockReturnValueOnce(null), then call
openSkillerApp(context) (use makeBrowserActionContext to get context and
setMessage) and assert that the fallback/manual-open message was left via
setMessage, that there was no navigation to openedWindow
(openedWindow.location.href remains empty) and neither openedWindow.focus nor
openedWindow.close were called; reference the existing mocks openSkillerMock,
browserOpenMock and the helper makeBrowserActionContext and the function
openSkillerApp to locate where to add this regression test.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 275716ec-c982-4d07-91fb-68a381fd2dcc
📒 Files selected for processing (9)
packages/app/src/web/actions-skiller.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/app-terminal-session.tsxpackages/app/src/web/open-url.tspackages/app/tests/docker-git/actions-skiller.test.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/browser-open-fixture.ts
📜 Review details
🧰 Additional context used
📓 Path-based instructions (8)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Implement Functional Core, Imperative Shell (FCIS) pattern: CORE layer contains only pure functions with immutable data and mathematical operations; SHELL layer isolates all effects (IO, network, database). Strict dependency direction: SHELL → CORE (never reverse).
Never useany,unknown,eslint-disable,ts-ignore, orastype assertions (except in rigorously justified cases with documentation). Always use exhaustive union type analysis through.exhaustive()pattern matching.
All external dependencies must be wrapped through typed interfaces and injected via Effect-TS Layer pattern. Never call external services directly from CORE functions.
Use monadic composition with Effect-TS for all effects:Effect<Success, Error, Requirements>. Compose effects throughpipe()andEffect.flatMap(). Implement dependency injection via Layer pattern. Handle errors without try/catch blocks.
All functions must be pure in the CORE layer: no side effects (logging, console output, IO operations, mutations). Separate all side effects into the SHELL layer.
Use exhaustive pattern matching with Effect.Match instead of switch statements. Example:Match.value(item).pipe(Match.when(...), Match.exhaustive).
Document all functions with comprehensive TSDoc including:@pure(true/false),@effect(required services),@invariant(mathematical invariants),@precondition,@postcondition,@complexity(time and space),@throwsNever (errors must be typed in Effect).
Use functional comment markers for code clarity: CHANGE (brief description), WHY (mathematical/architectural justification), QUOTE(ТЗ) (requirement citation), REF (RTM or message ID), SOURCE (external source with quote), FORMAT THEOREM (∀x ∈ Domain: P(x) → Q(f(x))), PURITY (CORE|SHELL), EFFECT (Effect type signature), INVARIANT (mathematical invariant), COMPLEXITY (time/space).
Define all external service dependencies as Context.Tag classes with fully typed methods returning Effect types. Example: `class Da...
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx}: Forbidden constructs in CORE code:any,eslint-disable,ts-ignore,async/await, raw Promise chains (then/catch),Promise.all,try/catchfor logic control,console.*, switch statements (use Match with .exhaustive() instead)
All functions must use Effect-TS for composing effects:Effect<Success, Error, Requirements>. No direct async/await, Promise chains, or try/catch in product logic.
Functional comments must include: CHANGE, WHY, QUOTE(ТЗ) or n/a, REF, SOURCE or n/a, FORMAT THEOREM, PURITY (CORE|SHELL), EFFECT signature for SHELL functions, INVARIANT, and COMPLEXITY.
All data mutations must use immutable patterns (ReadonlyArray, readonly properties, Object.freeze); mutation in SHELL only when absolutely necessary and documented.
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.{sh,bash,py,js,ts,jsx,tsx,go,java,rb,php}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce command injection or unsafe shell/process execution with user-controlled input
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.{py,js,ts,jsx,tsx,go,java,rb,php,sh,bash,c,cpp}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce path traversal or writes outside intended project/container state directories
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.{js,ts,jsx,tsx,py,java,go,rb,php,sh,bash,yml,yaml,json,env*,toml,cfg,config,dockerfile,dockerignore}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files expose credentials, tokens, private-keys, or PII in source, generated config, logs, or CI output
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*
⚙️ CodeRabbit configuration file
**/*: Ты строгий ревьюер SPEC DRIVEN DEVELOPMENT.Перед выводами изучи README.md, другие *.md файлы, linked issues,
PR description, PR comments/discussion и релевантную кодовую базу.Сверь изменения с исходным ТЗ/спекой и обсуждением. Флагай любой уход
от спеки, недокументированное изменение поведения, отсутствие тестов
для заявленного поведения и security-риск. Если спека не видна,
попроси автора добавить ее в issue или PR description.Проверь решение с точки зрения формальной верификации: какие инварианты,
предусловия и постусловия можно доказать математически, а где доказуемость
слабая. Оцени решение с точки зрения теории игр: устойчивы ли стимулы,
нет ли выгодного обхода правил, и какое решение было бы сильнее.
Files:
packages/app/src/web/app-terminal-session-ui.tsxpackages/app/src/web/open-url.tspackages/app/src/web/app-terminal-session.tsxpackages/app/tests/docker-git/browser-open-fixture.tspackages/app/src/web/app-ready-layout.tsxpackages/app/src/web/app-terminal-session-handlers.tspackages/app/src/web/actions-skiller.tspackages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants. Example:fc.property(fc.array(messageArbitrary), (messages) => isChronologicallySorted(sortMessagesByTimestamp(messages))).
Mock external dependencies in unit tests using Effect's testing utilities. Run tests without Effect runtime for speed. Example:Effect.provide(MockService), Effect.runPromise.
Files:
packages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
**/*.{test,spec}.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Property-based tests (fast-check) must verify mathematical invariants; unit tests must use Effect test utilities without async/await.
Files:
packages/app/tests/docker-git/app-terminal-session-handlers.test.tspackages/app/tests/docker-git/actions-skiller.test.ts
🔇 Additional comments (6)
packages/app/src/web/open-url.ts (1)
1-27: LGTM!Also applies to: 29-31, 36-38
packages/app/src/web/actions-skiller.ts (1)
3-3: LGTM!Also applies to: 5-5, 17-17, 30-34, 42-53
packages/app/src/web/app-terminal-session-handlers.ts (1)
4-4: LGTM!Also applies to: 12-12, 18-18, 26-26, 122-205
packages/app/src/web/app-ready-layout.tsx (1)
204-224: LGTM!Also applies to: 236-236
packages/app/src/web/app-terminal-session-ui.tsx (1)
136-136: LGTM!packages/app/src/web/app-terminal-session.tsx (1)
144-145: LGTM!
| navigate: (url) => { | ||
| openedWindow.location.href = url | ||
| openedWindow.focus() | ||
| return true |
There was a problem hiding this comment.
navigate возвращает успех без валидации факта навигации.
На Line 35 всегда возвращается true, из-за чего можно получить ложное "Opened ..." сообщение, хотя переход не состоялся (например, вкладка уже недоступна). Лучше вернуть реальный результат и дать fallback на ручное открытие.
💡 Предлагаемое исправление
navigate: (url) => {
- openedWindow.location.href = url
- openedWindow.focus()
- return true
+ if (openedWindow.closed) {
+ return openUrl(url)
+ }
+ openedWindow.location.href = url
+ openedWindow.focus()
+ return !openedWindow.closed
}🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@packages/app/src/web/open-url.ts` around lines 32 - 35, Функция navigate
всегда возвращает true even если навигация не произошла; исправьте вью: перед
возвратом успеха проверяйте состояние целевого окна (используя
openedWindow.closed) и оборачивайте присвоение openedWindow.location.href/focus
в try/catch, возвращая false при исключении или если openedWindow.closed ===
true; при false вызывайте fallback (например открыть URL через window.open или
показать инструкцию пользователю). Обновите логику в методе navigate и там, где
он вызывается, чтобы реагировать на false и предлагать ручное открытие.
| it("builds new terminal popups as project SSH links with a terminal selector", () => { | ||
| expect( | ||
| newProjectTerminalUrl("https://docker-git.local", "octocat/hello-world", "session-1") | ||
| ).toBe("https://docker-git.local/ssh/octocat/hello-world?t=session-1") | ||
| }) | ||
|
|
||
| it("returns all four project action handlers when project context is present", () => { | ||
| const handlers = buildHandlers() | ||
| expect(typeof handlers.onApplyProject).toBe("function") | ||
| expect(typeof handlers.onOpenBrowser).toBe("function") | ||
| expect(typeof handlers.onOpenTaskManager).toBe("function") | ||
| expect(typeof handlers.onOpenTerminal).toBe("function") | ||
| it("returns all project action handlers when project context is present", () => { | ||
| expectProjectHandlers(buildHandlers(), { | ||
| apply: true, | ||
| browser: true, | ||
| skiller: true, | ||
| taskManager: true, | ||
| terminal: true | ||
| }) | ||
| }) | ||
|
|
||
| it("hides all handlers when projectId is missing", () => { | ||
| const handlers = buildHandlers({ projectId: undefined }) | ||
| expect(handlers.onApplyProject).toBeUndefined() | ||
| expect(handlers.onOpenBrowser).toBeUndefined() | ||
| expect(handlers.onOpenTaskManager).toBeUndefined() | ||
| expect(handlers.onOpenTerminal).toBeUndefined() | ||
| expectProjectHandlers(buildHandlers({ projectId: undefined }), { | ||
| apply: false, | ||
| browser: false, | ||
| skiller: false, | ||
| taskManager: false, | ||
| terminal: false | ||
| }) | ||
| }) | ||
|
|
||
| it("hides project-key dependent handlers when projectKey is missing", () => { | ||
| expectProjectHandlers(buildHandlers({ projectKey: undefined }), { | ||
| apply: true, | ||
| browser: true, | ||
| skiller: false, | ||
| taskManager: true, | ||
| terminal: false | ||
| }) | ||
| }) | ||
|
|
||
| it("hides only onOpenTerminal when projectKey is missing", () => { | ||
| const handlers = buildHandlers({ projectKey: undefined }) | ||
| expect(typeof handlers.onApplyProject).toBe("function") | ||
| expect(typeof handlers.onOpenBrowser).toBe("function") | ||
| expect(typeof handlers.onOpenTaskManager).toBe("function") | ||
| expect(handlers.onOpenTerminal).toBeUndefined() | ||
| it("hides only onOpenSkiller when terminalSessionId is missing", () => { | ||
| expectProjectHandlers(buildHandlers({ terminalSessionId: undefined }), { | ||
| apply: true, | ||
| browser: true, | ||
| skiller: false, | ||
| taskManager: true, | ||
| terminal: true | ||
| }) | ||
| }) |
There was a problem hiding this comment.
🛠️ Refactor suggestion | 🟠 Major | 🏗️ Heavy lift
Усилите инвариантные тесты через fast-check (Line 97–141).
Для newProjectTerminalUrl и матрицы useProjectActionHandlers нужны property-based тесты (генерация комбинаций projectId/projectKey/terminalSessionId и проверка инвариантов доступности handler-ов), а не только фиксированные кейсы.
As per coding guidelines "**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants" и "**/*.{test,spec}.{ts,tsx}: Property-based tests (fast-check) must verify mathematical invariants".
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@packages/app/tests/docker-git/app-terminal-session-handlers.test.ts` around
lines 97 - 141, Replace the fixed examples with fast-check property tests:
generate arbitrary host URLs and combinations of projectId (string|undefined),
projectKey (string|undefined) and terminalSessionId (string|undefined) and
assert invariants using newProjectTerminalUrl and buildHandlers; for
newProjectTerminalUrl assert the returned URL preserves the host and path ends
with /ssh/{projectKey} and only includes the t= query when terminalSessionId is
defined; for buildHandlers call expectProjectHandlers(buildHandlers({ projectId,
projectKey, terminalSessionId }), expected) where expected booleans are computed
from the inputs (apply/browser/taskManager = Boolean(projectId), skiller =
Boolean(projectKey && terminalSessionId), terminal = Boolean(projectId &&
projectKey)); use fc.string()/fc.option to produce empty/defined values and run
many examples to validate invariants.
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/app/tests/docker-git/app-ready-url.test.ts`:
- Around line 108-116: Add a new unit test that verifies parseReadyUrlNavigation
round-trips the `/select/` deep-link back into navigation state: call
parseReadyUrlNavigation("https://docker-git.local/select/octocat/hello-world",
dashboard.projects) and assert it equals { activeScreen: { tag: "ProjectPicker"
}, menu: "Select", projectNavigationArmed: false, selectedProjectId: "project-1"
}; this mirrors the existing readyUrlPath test for Select and the /browser/
parse test, and ensures parseReadyUrlNavigation correctly handles project menus
(Select is in projectMenuTags).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 22971695-a6c0-4280-bbbc-8fb7e56e59b2
📒 Files selected for processing (1)
packages/app/tests/docker-git/app-ready-url.test.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (7)
- GitHub Check: E2E (Browser command)
- GitHub Check: E2E (OpenCode)
- GitHub Check: E2E (Clone cache)
- GitHub Check: E2E (Runtime volumes + SSH)
- GitHub Check: E2E (Clone auto-open SSH)
- GitHub Check: E2E (Login context)
- GitHub Check: Lint
🧰 Additional context used
📓 Path-based instructions (8)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Implement Functional Core, Imperative Shell (FCIS) pattern: CORE layer contains only pure functions with immutable data and mathematical operations; SHELL layer isolates all effects (IO, network, database). Strict dependency direction: SHELL → CORE (never reverse).
Never useany,unknown,eslint-disable,ts-ignore, orastype assertions (except in rigorously justified cases with documentation). Always use exhaustive union type analysis through.exhaustive()pattern matching.
All external dependencies must be wrapped through typed interfaces and injected via Effect-TS Layer pattern. Never call external services directly from CORE functions.
Use monadic composition with Effect-TS for all effects:Effect<Success, Error, Requirements>. Compose effects throughpipe()andEffect.flatMap(). Implement dependency injection via Layer pattern. Handle errors without try/catch blocks.
All functions must be pure in the CORE layer: no side effects (logging, console output, IO operations, mutations). Separate all side effects into the SHELL layer.
Use exhaustive pattern matching with Effect.Match instead of switch statements. Example:Match.value(item).pipe(Match.when(...), Match.exhaustive).
Document all functions with comprehensive TSDoc including:@pure(true/false),@effect(required services),@invariant(mathematical invariants),@precondition,@postcondition,@complexity(time and space),@throwsNever (errors must be typed in Effect).
Use functional comment markers for code clarity: CHANGE (brief description), WHY (mathematical/architectural justification), QUOTE(ТЗ) (requirement citation), REF (RTM or message ID), SOURCE (external source with quote), FORMAT THEOREM (∀x ∈ Domain: P(x) → Q(f(x))), PURITY (CORE|SHELL), EFFECT (Effect type signature), INVARIANT (mathematical invariant), COMPLEXITY (time/space).
Define all external service dependencies as Context.Tag classes with fully typed methods returning Effect types. Example: `class Da...
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants. Example:fc.property(fc.array(messageArbitrary), (messages) => isChronologicallySorted(sortMessagesByTimestamp(messages))).
Mock external dependencies in unit tests using Effect's testing utilities. Run tests without Effect runtime for speed. Example:Effect.provide(MockService), Effect.runPromise.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx}: Forbidden constructs in CORE code:any,eslint-disable,ts-ignore,async/await, raw Promise chains (then/catch),Promise.all,try/catchfor logic control,console.*, switch statements (use Match with .exhaustive() instead)
All functions must use Effect-TS for composing effects:Effect<Success, Error, Requirements>. No direct async/await, Promise chains, or try/catch in product logic.
Functional comments must include: CHANGE, WHY, QUOTE(ТЗ) or n/a, REF, SOURCE or n/a, FORMAT THEOREM, PURITY (CORE|SHELL), EFFECT signature for SHELL functions, INVARIANT, and COMPLEXITY.
All data mutations must use immutable patterns (ReadonlyArray, readonly properties, Object.freeze); mutation in SHELL only when absolutely necessary and documented.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{test,spec}.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Property-based tests (fast-check) must verify mathematical invariants; unit tests must use Effect test utilities without async/await.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{sh,bash,py,js,ts,jsx,tsx,go,java,rb,php}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce command injection or unsafe shell/process execution with user-controlled input
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{py,js,ts,jsx,tsx,go,java,rb,php,sh,bash,c,cpp}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce path traversal or writes outside intended project/container state directories
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{js,ts,jsx,tsx,py,java,go,rb,php,sh,bash,yml,yaml,json,env*,toml,cfg,config,dockerfile,dockerignore}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files expose credentials, tokens, private-keys, or PII in source, generated config, logs, or CI output
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*
⚙️ CodeRabbit configuration file
**/*: Ты строгий ревьюер SPEC DRIVEN DEVELOPMENT.Перед выводами изучи README.md, другие *.md файлы, linked issues,
PR description, PR comments/discussion и релевантную кодовую базу.Сверь изменения с исходным ТЗ/спекой и обсуждением. Флагай любой уход
от спеки, недокументированное изменение поведения, отсутствие тестов
для заявленного поведения и security-риск. Если спека не видна,
попроси автора добавить ее в issue или PR description.Проверь решение с точки зрения формальной верификации: какие инварианты,
предусловия и постусловия можно доказать математически, а где доказуемость
слабая. Оцени решение с точки зрения теории игр: устойчивы ли стимулы,
нет ли выгодного обхода правил, и какое решение было бы сильнее.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/app/tests/docker-git/app-ready-url.test.ts`:
- Around line 129-138: Add a property-based test using fast-check that generates
valid navigation states and asserts the round-trip invariant: for each generated
state call readyUrlPath(state) to produce a URL, feed it into
parseReadyUrlNavigation(fullUrl, dashboard.projects), and verify the parsed
result matches the normalized key fields of the original state (e.g.,
menu/currentMenu and selectedProjectId, and activeScreen tag) or null only when
expected; implement a navigationState arbitrary that mirrors valid shapes used
by readyUrlPath (activeScreen tags, currentMenu values, selectedProjectId
optional, etc.), and use fc.assert(fc.property(...)) to run the round-trip
checks.
- Line 108: Rename the test case title to accurately reflect that it checks the
Select menu URL template (not an active SSH session); update the it(...) string
currently "renders SSH project selection as a readable Select project deep link"
to a clearer name such as "renders Select project deep link for non-terminal
sessions" or "renders Select menu project deep link (not SSH)" so the test
description matches the checked URL template in the test file and avoids
implying an active SSH/terminal session.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: a7705f8c-68c8-4f6e-9c77-8a60a5f1e26e
📒 Files selected for processing (1)
packages/app/tests/docker-git/app-ready-url.test.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (9)
- GitHub Check: E2E (Browser command)
- GitHub Check: E2E (OpenCode)
- GitHub Check: Lint
- GitHub Check: E2E (Clone cache)
- GitHub Check: E2E (Login context)
- GitHub Check: E2E (Runtime volumes + SSH)
- GitHub Check: E2E (Clone auto-open SSH)
- GitHub Check: Test
- GitHub Check: Final build (windows-latest)
🧰 Additional context used
📓 Path-based instructions (8)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Implement Functional Core, Imperative Shell (FCIS) pattern: CORE layer contains only pure functions with immutable data and mathematical operations; SHELL layer isolates all effects (IO, network, database). Strict dependency direction: SHELL → CORE (never reverse).
Never useany,unknown,eslint-disable,ts-ignore, orastype assertions (except in rigorously justified cases with documentation). Always use exhaustive union type analysis through.exhaustive()pattern matching.
All external dependencies must be wrapped through typed interfaces and injected via Effect-TS Layer pattern. Never call external services directly from CORE functions.
Use monadic composition with Effect-TS for all effects:Effect<Success, Error, Requirements>. Compose effects throughpipe()andEffect.flatMap(). Implement dependency injection via Layer pattern. Handle errors without try/catch blocks.
All functions must be pure in the CORE layer: no side effects (logging, console output, IO operations, mutations). Separate all side effects into the SHELL layer.
Use exhaustive pattern matching with Effect.Match instead of switch statements. Example:Match.value(item).pipe(Match.when(...), Match.exhaustive).
Document all functions with comprehensive TSDoc including:@pure(true/false),@effect(required services),@invariant(mathematical invariants),@precondition,@postcondition,@complexity(time and space),@throwsNever (errors must be typed in Effect).
Use functional comment markers for code clarity: CHANGE (brief description), WHY (mathematical/architectural justification), QUOTE(ТЗ) (requirement citation), REF (RTM or message ID), SOURCE (external source with quote), FORMAT THEOREM (∀x ∈ Domain: P(x) → Q(f(x))), PURITY (CORE|SHELL), EFFECT (Effect type signature), INVARIANT (mathematical invariant), COMPLEXITY (time/space).
Define all external service dependencies as Context.Tag classes with fully typed methods returning Effect types. Example: `class Da...
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants. Example:fc.property(fc.array(messageArbitrary), (messages) => isChronologicallySorted(sortMessagesByTimestamp(messages))).
Mock external dependencies in unit tests using Effect's testing utilities. Run tests without Effect runtime for speed. Example:Effect.provide(MockService), Effect.runPromise.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx}: Forbidden constructs in CORE code:any,eslint-disable,ts-ignore,async/await, raw Promise chains (then/catch),Promise.all,try/catchfor logic control,console.*, switch statements (use Match with .exhaustive() instead)
All functions must use Effect-TS for composing effects:Effect<Success, Error, Requirements>. No direct async/await, Promise chains, or try/catch in product logic.
Functional comments must include: CHANGE, WHY, QUOTE(ТЗ) or n/a, REF, SOURCE or n/a, FORMAT THEOREM, PURITY (CORE|SHELL), EFFECT signature for SHELL functions, INVARIANT, and COMPLEXITY.
All data mutations must use immutable patterns (ReadonlyArray, readonly properties, Object.freeze); mutation in SHELL only when absolutely necessary and documented.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{test,spec}.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Property-based tests (fast-check) must verify mathematical invariants; unit tests must use Effect test utilities without async/await.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{sh,bash,py,js,ts,jsx,tsx,go,java,rb,php}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce command injection or unsafe shell/process execution with user-controlled input
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{py,js,ts,jsx,tsx,go,java,rb,php,sh,bash,c,cpp}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce path traversal or writes outside intended project/container state directories
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{js,ts,jsx,tsx,py,java,go,rb,php,sh,bash,yml,yaml,json,env*,toml,cfg,config,dockerfile,dockerignore}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files expose credentials, tokens, private-keys, or PII in source, generated config, logs, or CI output
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*
⚙️ CodeRabbit configuration file
**/*: Ты строгий ревьюер SPEC DRIVEN DEVELOPMENT.Перед выводами изучи README.md, другие *.md файлы, linked issues,
PR description, PR comments/discussion и релевантную кодовую базу.Сверь изменения с исходным ТЗ/спекой и обсуждением. Флагай любой уход
от спеки, недокументированное изменение поведения, отсутствие тестов
для заявленного поведения и security-риск. Если спека не видна,
попроси автора добавить ее в issue или PR description.Проверь решение с точки зрения формальной верификации: какие инварианты,
предусловия и постусловия можно доказать математически, а где доказуемость
слабая. Оцени решение с точки зрения теории игр: устойчивы ли стимулы,
нет ли выгодного обхода правил, и какое решение было бы сильнее.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
🔇 Additional comments (1)
packages/app/tests/docker-git/app-ready-url.test.ts (1)
129-138: LGTM!
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
packages/app/tests/docker-git/app-ready-url.test.ts (1)
112-318: 🧹 Nitpick | 🔵 Trivial | 💤 Low valueОтличная реализация property-based тестирования! ✨
Код демонстрирует правильное применение fast-check для проверки математических инвариантов:
- ✅ Определены чёткие arbitraries для различных сценариев навигации
- ✅ Проверяется инвариант round-trip:
∀state: parseReadyUrlNavigation(readyUrlPath(state)) ≈ normalize(state)- ✅ Покрыты различные типы меню (project/non-project) и состояний выбора проекта
- ✅ Использовано достаточное количество запусков (75) для надёжности
Это значительно повышает уверенность в корректности навигации и обработки URL при изменении схемы роутинга. As per coding guidelines: "Implement property-based testing using fast-check for mathematical properties and invariants."
Единственная рекомендация: добавьте краткий TSDoc-комментарий с формальным определением проверяемого инварианта в формате THEOREM для будущих разработчиков:
/** * THEOREM (Round-trip invariant): * ∀state ∈ ValidNavigationState: * parseReadyUrlNavigation(readyUrlPath(state), projects) = normalize(state) * * where normalize removes fields not preserved in URL encoding * (e.g., activeTerminalSession, selectedProjectSummary) */ it("preserves ready URL round-trip invariants for valid navigation states", () => {🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@packages/app/tests/docker-git/app-ready-url.test.ts` around lines 112 - 318, Add a short TSDoc THEOREM comment immediately above the test titled "preserves ready URL round-trip invariants for valid navigation states" that formally states the round-trip invariant for readyUrlPath and parseReadyUrlNavigation (e.g., ∀state ∈ ValidNavigationState: parseReadyUrlNavigation(readyUrlPath(state), projects) = normalize(state)), and mention which fields are not preserved (activeTerminalSession, selectedProjectSummary); place the comment directly before the it(...) block so future readers can see the formal property being tested for readyUrlPath and parseReadyUrlNavigation.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/app/tests/docker-git/app-ready-url.test.ts`:
- Around line 91-110: Replace the hard-coded parsedScreenByMenu map with a
dynamic build that calls the existing production function screenForMenu for each
menu tag (use browserMenuItems to iterate over items and produce a
Record<BrowserMenuTag, BrowserScreen>), so parsedScreenByMenu is constructed
from Object.fromEntries(browserMenuItems.map(item => [item.tag,
screenForMenu(item.tag)])) and cast back to the appropriate Record type; update
any references to parsedScreenByMenu to use this new value so the test relies on
the production mapping logic rather than a duplicated static map.
- Around line 309-312: The test contains contradictory null handling: it asserts
expect(path).not.toBeNull() but then silently returns if path === null; remove
the redundant guard so the assertion fails loudly (delete the if (path === null)
{ return } block), or if null is an acceptable outcome for some generated
inputs, instead enforce that by filtering inputs with fast-check using
fc.pre(...) before calling readyUrlPath so the test only runs on inputs that
should produce non-null; locate the check around the readyUrlPath call and the
variable path to apply the change.
- Around line 52-89: The test duplicates private menu constants which risks
drifting from the source; update the test to import the canonical definitions
instead of hardcoding them: export and import browserMenuOrder from
packages/app/src/web/menu.ts (currently mirrored by menuTags) and reuse the
projectMenuTags definition (or derive via the exported isProjectMenu function
and BrowserProjectMenuTag type from packages/app/src/web/screen.ts) in the test,
and compute nonProjectMenuTags dynamically as the set difference/inversion of
browserMenuOrder vs projectMenuTags rather than a hardcoded array.
- Around line 160-162: Test contains special-case logic for "Select" that
diverges from production: change the test so activeScreen uses the same behavior
as screenForMenu by removing the Select-specific branch and always using
parsedScreenByMenu[menu] (so project menus like "Select" resolve to
projectPickerScreen), i.e., delete the conditional that returns menuScreen for
Select with null selection and let parsedScreenByMenu/activeScreen mirror
production; alternatively, if the special-case is intended, implement matching
logic in screenForMenu/isProjectMenu to return menuScreen for that scenario, but
prefer updating the test to rely on parsedScreenByMenu, projectPickerScreen,
screenForMenu and isProjectMenu to match production.
---
Outside diff comments:
In `@packages/app/tests/docker-git/app-ready-url.test.ts`:
- Around line 112-318: Add a short TSDoc THEOREM comment immediately above the
test titled "preserves ready URL round-trip invariants for valid navigation
states" that formally states the round-trip invariant for readyUrlPath and
parseReadyUrlNavigation (e.g., ∀state ∈ ValidNavigationState:
parseReadyUrlNavigation(readyUrlPath(state), projects) = normalize(state)), and
mention which fields are not preserved (activeTerminalSession,
selectedProjectSummary); place the comment directly before the it(...) block so
future readers can see the formal property being tested for readyUrlPath and
parseReadyUrlNavigation.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 8ea9d8cf-3e05-4578-b0b6-79a3421edf05
📒 Files selected for processing (1)
packages/app/tests/docker-git/app-ready-url.test.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 900000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (9)
- GitHub Check: E2E (Runtime volumes + SSH)
- GitHub Check: E2E (Clone auto-open SSH)
- GitHub Check: E2E (Browser command)
- GitHub Check: E2E (Clone cache)
- GitHub Check: Lint
- GitHub Check: Final build (windows-latest)
- GitHub Check: E2E (OpenCode)
- GitHub Check: Test
- GitHub Check: E2E (Login context)
🧰 Additional context used
📓 Path-based instructions (8)
**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.{ts,tsx}: Implement Functional Core, Imperative Shell (FCIS) pattern: CORE layer contains only pure functions with immutable data and mathematical operations; SHELL layer isolates all effects (IO, network, database). Strict dependency direction: SHELL → CORE (never reverse).
Never useany,unknown,eslint-disable,ts-ignore, orastype assertions (except in rigorously justified cases with documentation). Always use exhaustive union type analysis through.exhaustive()pattern matching.
All external dependencies must be wrapped through typed interfaces and injected via Effect-TS Layer pattern. Never call external services directly from CORE functions.
Use monadic composition with Effect-TS for all effects:Effect<Success, Error, Requirements>. Compose effects throughpipe()andEffect.flatMap(). Implement dependency injection via Layer pattern. Handle errors without try/catch blocks.
All functions must be pure in the CORE layer: no side effects (logging, console output, IO operations, mutations). Separate all side effects into the SHELL layer.
Use exhaustive pattern matching with Effect.Match instead of switch statements. Example:Match.value(item).pipe(Match.when(...), Match.exhaustive).
Document all functions with comprehensive TSDoc including:@pure(true/false),@effect(required services),@invariant(mathematical invariants),@precondition,@postcondition,@complexity(time and space),@throwsNever (errors must be typed in Effect).
Use functional comment markers for code clarity: CHANGE (brief description), WHY (mathematical/architectural justification), QUOTE(ТЗ) (requirement citation), REF (RTM or message ID), SOURCE (external source with quote), FORMAT THEOREM (∀x ∈ Domain: P(x) → Q(f(x))), PURITY (CORE|SHELL), EFFECT (Effect type signature), INVARIANT (mathematical invariant), COMPLEXITY (time/space).
Define all external service dependencies as Context.Tag classes with fully typed methods returning Effect types. Example: `class Da...
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
**/*.test.{ts,tsx}: Implement property-based testing using fast-check for mathematical properties and invariants. Example:fc.property(fc.array(messageArbitrary), (messages) => isChronologicallySorted(sortMessagesByTimestamp(messages))).
Mock external dependencies in unit tests using Effect's testing utilities. Run tests without Effect runtime for speed. Example:Effect.provide(MockService), Effect.runPromise.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{ts,tsx,js,jsx}: Forbidden constructs in CORE code:any,eslint-disable,ts-ignore,async/await, raw Promise chains (then/catch),Promise.all,try/catchfor logic control,console.*, switch statements (use Match with .exhaustive() instead)
All functions must use Effect-TS for composing effects:Effect<Success, Error, Requirements>. No direct async/await, Promise chains, or try/catch in product logic.
Functional comments must include: CHANGE, WHY, QUOTE(ТЗ) or n/a, REF, SOURCE or n/a, FORMAT THEOREM, PURITY (CORE|SHELL), EFFECT signature for SHELL functions, INVARIANT, and COMPLEXITY.
All data mutations must use immutable patterns (ReadonlyArray, readonly properties, Object.freeze); mutation in SHELL only when absolutely necessary and documented.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{test,spec}.{ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Property-based tests (fast-check) must verify mathematical invariants; unit tests must use Effect test utilities without async/await.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{sh,bash,py,js,ts,jsx,tsx,go,java,rb,php}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce command injection or unsafe shell/process execution with user-controlled input
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{py,js,ts,jsx,tsx,go,java,rb,php,sh,bash,c,cpp}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files introduce path traversal or writes outside intended project/container state directories
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*.{js,ts,jsx,tsx,py,java,go,rb,php,sh,bash,yml,yaml,json,env*,toml,cfg,config,dockerfile,dockerignore}
📄 CodeRabbit inference engine (Custom checks)
Fail if changed files expose credentials, tokens, private-keys, or PII in source, generated config, logs, or CI output
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
**/*
⚙️ CodeRabbit configuration file
**/*: Ты строгий ревьюер SPEC DRIVEN DEVELOPMENT.Перед выводами изучи README.md, другие *.md файлы, linked issues,
PR description, PR comments/discussion и релевантную кодовую базу.Сверь изменения с исходным ТЗ/спекой и обсуждением. Флагай любой уход
от спеки, недокументированное изменение поведения, отсутствие тестов
для заявленного поведения и security-риск. Если спека не видна,
попроси автора добавить ее в issue или PR description.Проверь решение с точки зрения формальной верификации: какие инварианты,
предусловия и постусловия можно доказать математически, а где доказуемость
слабая. Оцени решение с точки зрения теории игр: устойчивы ли стимулы,
нет ли выгодного обхода правил, и какое решение было бы сильнее.
Files:
packages/app/tests/docker-git/app-ready-url.test.ts
🔇 Additional comments (3)
packages/app/tests/docker-git/app-ready-url.test.ts (3)
1-19: LGTM!
272-280: LGTM!
293-302: LGTM!
1 participant
Summary
Fixes #311
Mathematical guarantees
Invariants
Preconditions
Postconditions
Complexity
Verification
bun run --cwd packages/app typecheckbun run --cwd packages/app lintbun run --cwd packages/app test -- tests/docker-git/actions-skiller.test.ts tests/docker-git/app-terminal-session-handlers.test.ts tests/docker-git/panel-terminal-skiller.test.tsgit diff --checkSOURCE: n/a