fix: support per-question skip in question dock#353
Merged
Conversation
Contributor
📝 WalkthroughWalkthroughPer-question skip added: UI gains a "skip current" action and per-tab draft/unset state; backend no longer treats empty per-question answers as hard rejection and serializes skipped answers as "Skipped by user"; tests added for skip flows and CI workflow expectations updated. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor User as "User"
participant UI as "Session Question Dock (UI)"
participant QC as "Question Service (Opencode)"
participant Sync as "Global Sync / Event Reducer"
User->>UI: Click "Skip question"
UI->>UI: mark current tab as skipped (answers[current]=[])
UI->>UI: advance focus to next unsettled tab
UI->>QC: call Question.reply (includes skipped tab -> `[]`)
QC->>QC: treat empty per-question answer as skipped, continue processing
QC->>Sync: publish `question.replied` with skipped info
Sync->>UI: clear pending question, update composer state
UI->>User: dock closes / prompt becomes available
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Review rate limit: 9/10 reviews remaining, refill in 6 minutes. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/app/src/pages/session/composer/session-question-dock.tsx`:
- Around line 405-419: The current forward-only search should be replaced with a
wrap-around search that finds any unsettled question other than the current tab;
change the logic that computes nextUnsettled (currently using
questions().findIndex((_, i) => i > store.tab && !settled(i))) to scan indexes
starting at store.tab+1, wrapping to 0 and continuing until all tabs checked
(using total() and modulo arithmetic), and return the first index where
!settled(i); if found call setStore("tab", idx) and focus(pickFocus(idx)); if
none found keep the current behavior and call focus(pickFocus(store.tab)). Keep
using the existing helpers settled(i), questions(), total(), setStore("tab",
...), focus(...) and pickFocus(...) when updating/focusing.
🪄 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: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 1eebb816-8235-4579-a7bf-128f7a253089
📒 Files selected for processing (10)
packages/app/e2e/session/session-composer-dock.spec.tspackages/app/src/i18n/en.tspackages/app/src/i18n/zh.tspackages/app/src/pages/session/composer/session-question-dock.tsxpackages/opencode/src/question/index.tspackages/opencode/src/tool/question.tspackages/opencode/test/question/question.test.tspackages/ui/src/components/message-part.tsxpackages/ui/src/i18n/en.tspackages/ui/src/i18n/zh.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (11)
- GitHub Check: unit-windows-opencode-session
- GitHub Check: unit-windows-desktop
- GitHub Check: unit-windows-app
- GitHub Check: unit-windows-opencode-config-project
- GitHub Check: unit-windows-opencode-server-tools
- GitHub Check: unit-desktop
- GitHub Check: unit-opencode
- GitHub Check: typecheck
- GitHub Check: analyze-js-ts
- GitHub Check: e2e-artifacts
- GitHub Check: smoke-macos-arm64
🧰 Additional context used
📓 Path-based instructions (4)
packages/app/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (packages/app/AGENTS.md)
Always prefer
createStoreover multiplecreateSignalcalls in SolidJS
Files:
packages/app/src/i18n/en.tspackages/app/src/i18n/zh.tspackages/app/e2e/session/session-composer-dock.spec.tspackages/app/src/pages/session/composer/session-question-dock.tsx
packages/opencode/**/*.ts
📄 CodeRabbit inference engine (packages/opencode/AGENTS.md)
packages/opencode/**/*.ts: UseEffect.gen(function* () { ... })for Effect composition
UseEffect.fn("Domain.method")for named/traced effects andEffect.fnUntracedfor internal helpers; these accept pipeable operators as extra arguments to avoid unnecessary outer.pipe()wrappers
UseEffect.callbackfor callback-based APIs
PreferDateTime.nowAsDateovernew Date(yield* Clock.currentTimeMillis)when you need aDatein Effect code
UseSchema.Classfor multi-field data in Effect schemas
Use branded schemas (Schema.brand) for single-value types in Effect
UseSchema.TaggedErrorClassfor typed errors in Effect schemas
UseSchema.Defectinstead ofunknownfor defect-like causes in Effect code
InEffect.gen/Effect.fn, preferyield* new MyError(...)overyield* Effect.fail(new MyError(...))for direct early-failure branches
UsemakeRuntimefromsrc/effect/run-service.tsfor all services; it returns{ runPromise, runFork, runCallback }backed by a sharedmemoMapthat deduplicates layers
UseInstanceStatefromsrc/effect/instance-state.tsfor per-directory or per-project state that needs per-instance cleanup; do work directly in theInstanceState.makeclosure whereScopedCachehandles run-once semantics
UseEffect.addFinalizerorEffect.acquireReleaseinside theInstanceState.makeclosure for cleanup (subscriptions, process teardown, etc.)
UseEffect.forkScopedinside theInstanceState.makeclosure for background stream consumers — the fiber is interrupted when the instance is disposed
PreferFileSystem.FileSysteminstead of rawfs/promisesfor effectful file I/O in Effect services
PreferChildProcessSpawner.ChildProcessSpawnerwithChildProcess.make(...)instead of custom process wrappers in Effect services
PreferHttpClient.HttpClientinstead of rawfetchin Effect services
PreferPath.Path,Config,Clock, andDateTimeservices when those concerns are already inside Effect code
For backgroun...
Files:
packages/opencode/src/tool/question.tspackages/opencode/src/question/index.tspackages/opencode/test/question/question.test.ts
packages/app/e2e/**/*.spec.ts
📄 CodeRabbit inference engine (packages/app/e2e/AGENTS.md)
packages/app/e2e/**/*.spec.ts: Import test utilities from../fixturesinstead of@playwright/test
Test files should be named with the patternfeature-name.spec.ts
Use lowercase, descriptive test names (e.g., 'sidebar can be toggled')
Use camelCase for variable names in tests
Use SCREAMING_SNAKE_CASE for constants in tests
Use fixture-managed cleanup withwithSession(sdk, title, callback)for temporary sessions instead of callingsdk.session.delete(...)directly
Prefer theprojectfixture for tests that need a dedicated project with LLM mocking
Usedata-component,data-action, or semantic roles for selectors instead of CSS class names or IDs
UsemodKeyfrom utils for cross-platform keyboard shortcuts (Meta on Mac, Control on Linux/Windows)
In terminal tests, type through the browser usingrunTerminal()andwaitTerminalReady()instead of writing to the PTY through the SDK
Never use wall-clock waits likepage.waitForTimeout(...)to make a test pass
Wait on observable state withexpect(...),expect.poll(...), or existing helpers instead of assuming work is finished after an action
Use locator assertions liketoBeVisible(),toHaveCount(0), andtoHaveAttribute(...)for normal UI state verification
Useexpect.poll(...)for probing mock or backend state rather than transient DOM visibility
Prefer fluent helpers and drivers when they make intent obvious and reduce locator-heavy noise in tests
Use direct locators when the interaction is simple and a helper would not add clarity
When validating routing, assert against canonical or resolved workspace slugs using shared helpers from../actionsto account for Windows canonicalization
Test one feature per test file
Callproject.trackSession(sessionID, directory?)andproject.trackDirectory(directory)for any resources created outside the fixture so teardown can clean them up
Files:
packages/app/e2e/session/session-composer-dock.spec.ts
packages/opencode/test/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (packages/opencode/test/AGENTS.md)
packages/opencode/test/**/*.test.{ts,tsx}: Use thetmpdirfunction fromfixture/fixture.tsto create temporary directories for tests with automatic cleanup. Useawait usingsyntax to ensure automatic cleanup when the variable goes out of scope.
When using thetmpdirfunction with git repository support, pass thegit: trueoption to initialize a git repo with a root commit.
Use theconfigoption intmpdirto write anopencode.jsonconfig file during test setup by passing a partial Config.Info object.
Use theinitoption intmpdirto define custom setup functions that can return extra data accessible viatmp.extra, and use thedisposeoption for custom cleanup logic.
UsetestEffect(...)fromtest/lib/effect.tsfor tests that exercise Effect services or Effect-based workflows.
Useit.effect(...)when the test should run withTestClockandTestConsole. Useit.live(...)when the test depends on real time, filesystem mtimes, child processes, git, locks, or other live OS behavior.
Prefer Effect-aware helpers fromfixture/fixture.tsover building manual runtimes in tests: usetmpdirScoped()for scoped temp directories,provideInstance(dir)(effect)for low-level binding without directory creation,provideTmpdirInstance(...)for single temp instance binding, orprovideTmpdirServer(...)for tests that also need the test LLM server.
Defineconst it = testEffect(...)near the top of the test file and keep the test body insideEffect.gen(function* () { ... }). Yield services directly withyield* MyService.Serviceoryield* MyTool.
Avoid customManagedRuntime,attach(...), or ad hocrun(...)wrappers in Effect tests whentestEffect(...)already provides the runtime.
When a test needs instance-local state, preferprovideTmpdirInstance(...)orprovideInstance(...)over manualInstance.provide(...)inside Promise-style tests.
Files:
packages/opencode/test/question/question.test.ts
🧠 Learnings (33)
📓 Common learnings
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/question.ts:6-16
Timestamp: 2026-04-28T06:47:20.342Z
Learning: In Astro-Han/pawwork, `packages/opencode/src/tool/question.ts` is a permanent PawWork carve-out: `Question.Prompt` (defined in `packages/opencode/src/question/index.ts`) remains a Zod schema, NOT an Effect Schema. The `ts-expect-error` boundary in `tool/registry.ts` marks the Zod ↔ Effect Schema seam. The dropped `packages/opencode/test/tool/question.test.ts` covered the old Zod-mixed surface. Schema-bound regression tests for this tool are intentionally deferred until `question/index.ts` migrates to Effect Schema in its own dedicated PR. Do NOT request restoring question tool tests in upstream-sync PRs; flag it only in the PR that migrates `question/index.ts` to Effect Schema.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:36.505Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/question/index.ts`), `Question.Option.description` is intentionally **required** (`z.string()`, not `.optional()`). This matches the upstream opencode contract and all current callers (e.g. `PlanExitTool`) always supply a description. The defensive `<Show when={props.description}>` rendering in `session-question-dock.tsx` is a standard guard, not a signal that the field is intended to be optional. Do NOT suggest making `Option.description` optional without a dedicated follow-up that covers schema + tool description + dock copy + tests.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/patch/index.ts:337-346
Timestamp: 2026-04-28T04:38:05.946Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/patch/index.ts`), the BOM-transition surfacing gap — where `Bom.split` strips BOM before building `unified_diff`/`new_content` but `Bom.join` later re-attaches BOM on disk write, meaning BOM changes are not reflected in the diff payload — is intentionally deferred. PR `#270` is an upstream-sync graft; fixing the issue here would mix refactor + bugfix intents and drift the diff from the upstream baseline needed for clean future grafts. A dedicated follow-up PR (or upstream report) will address this. Do NOT re-flag the missing BOM-change surfacing in `ApplyPatchFileUpdate`/`ApplyPatchFileChange` as a blocking issue in PR `#270` or in future sync PRs that carry the same upstream baseline.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/lsp.ts:23-32
Timestamp: 2026-04-28T07:28:14.317Z
Learning: In `packages/opencode/src/tool/lsp.ts` (Astro-Han/pawwork, PR `#270`), the `Parameters` schema requires `line` and `character` for all operations, including `workspaceSymbol` and `documentSymbol` which never use coordinates. This matches the upstream `dev:packages/opencode/src/tool/lsp.ts:23-32` baseline exactly — both fields are declared as required `Schema.Number` with `>= 1` checks. The fix (per-operation schema split, or making `line`/`character` optional with handler-side presence validation for operations that need them like `goToDefinition`/`findReferences`) is deferred to a follow-up PR or upstream report to avoid mixing refactor + bug-fix intents and drifting the diff from the upstream baseline. Do NOT re-flag the required coordinates on `workspaceSymbol`/`documentSymbol` in upstream-sync PRs; flag it only in a PawWork-authored PR that directly touches `lsp.ts` parameter validation.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:58.329Z
Learning: In Astro-Han/pawwork `packages/app/src/components/prompt-input.tsx`, after the composer unification in PR `#208` (fixed in commit 5d810aa):
- `SendButton.disabled` does NOT gate on `store.mode !== "normal"`. Shell mode has a fully visible, clickable orange submit button that calls `handleSubmit` directly (same path as the Enter key in `handleKeyDown`). Do NOT suggest re-adding the mode gate.
- `SendButton` does NOT use the `buttons()` spring opacity animation (`style={buttons()}`). It is always fully visible regardless of mode.
- `WorkspaceChip` is gated on `props.homeMode && store.mode === "normal"` so it hides in shell mode (preventing it from appearing isolated/bright while neighboring controls fade).
- The left-side chip group (`aria-hidden={store.mode !== "normal"}`) covers attach/model/variant/workspace controls only; `SendButton` remains in a separate right-side sibling div.
📚 Learning: 2026-04-30T10:41:33.826Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 342
File: packages/desktop-electron/src/main/ipc.ts:342-344
Timestamp: 2026-04-30T10:41:33.826Z
Learning: In Astro-Han/pawwork, the `export-session` IPC handler in `packages/desktop-electron/src/main/ipc.ts` accepts an optional localized `title` argument for `dialog.showSaveDialog`, keeping `"Export session"` as an English fallback. The localized title is plumbed from the renderer through `platform.exportSession` → `window.api.exportSession` → preload (`preload/types.ts`, `preload/index.ts`, `renderer/index.tsx`) → main, mirroring the same shape as the `save-file-picker` handler. Both renderer callsites (`layout.tsx` and `message-timeline.tsx`) pass `language.t("session.export.action.export")`. Do NOT flag the hard-coded fallback as unlocalized — the renderer is responsible for supplying the localized title.
Applied to files:
packages/app/src/i18n/en.tspackages/app/src/i18n/zh.ts
📚 Learning: 2026-04-23T07:23:23.849Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 180
File: packages/app/src/components/session/session-new-view.tsx:13-18
Timestamp: 2026-04-23T07:23:23.849Z
Learning: In pawwork (Astro-Han/pawwork), prefer using `createStore` instead of multiple `createSignal` calls only when the signals represent **coupled** object state that is updated together (i.e., there is at least one shared batch-update site where the state is changed in the same transaction). If the state fields are **independent** and are mutated by separate handlers (e.g., one handler updates only `selectedSkill` while another updates only `mode`), keep them as individual `createSignal` calls—using `createStore` for truly independent fields adds boilerplate without behavioral benefit.
Applied to files:
packages/app/src/i18n/en.tspackages/app/src/i18n/zh.tspackages/app/e2e/session/session-composer-dock.spec.tspackages/app/src/pages/session/composer/session-question-dock.tsx
📚 Learning: 2026-04-23T15:10:21.635Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 191
File: packages/app/src/components/session/pawwork-skill-meta.ts:38-39
Timestamp: 2026-04-23T15:10:21.635Z
Learning: This repo configures Tailwind v4 with `--color-*: initial`, which effectively breaks standard Tailwind palette utilities (e.g., `text-violet-500` can resolve to no CSS variable and render as a no-op/black). For brand/accent colors that are not backed by semantic design tokens, use inline styles with the exact hex value (e.g., `style={{ color: '#8B5FBF' }}` / `homeIconStyle: { color: '#8B5FBF' }`) and add a short comment explaining that Tailwind palette utilities won’t work due to the `--color-*: initial` setup. Do not suggest replacing these inline hex colors with Tailwind palette classes anywhere in this repo.
Applied to files:
packages/app/src/i18n/en.tspackages/app/src/i18n/zh.tspackages/app/src/pages/session/composer/session-question-dock.tsx
📚 Learning: 2026-04-28T03:01:37.478Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 282
File: packages/ui/src/i18n/zh.ts:109-109
Timestamp: 2026-04-28T03:01:37.478Z
Learning: In Astro-Han/pawwork PR `#282` (`packages/ui/src/i18n/zh.ts`), the translation for `ui.tool.questions` is intentionally `提出问题` (verb-object structure), NOT `向你提问` (prepositional-phrase structure). The choice was made after a UI smoke run to keep consistent verb-object phrasing across all zh tool-card labels (`执行命令`, `列出目录`, `查找文件`, `搜索文本`, `读取文件`, `读取网页`, `批量修改`, `查看待办`). Do NOT flag `提出问题` as incorrect for this key.
Applied to files:
packages/ui/src/i18n/en.tspackages/ui/src/i18n/zh.tspackages/app/src/i18n/zh.tspackages/ui/src/components/message-part.tsx
📚 Learning: 2026-04-24T17:08:46.780Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:46.780Z
Learning: In Astro-Han/pawwork PR `#224`, the first-occurrence `PawWork 爪印` branding rule originally specified in issue `#196` was superseded by an updated Chinese-branding spec. On all zh UI surfaces in `packages/app/src/i18n/zh.ts` (e.g., `dialog.model.unpaid.freeModels.title`, `session.new.subtitle`, `sidebar.gettingStarted.line1`), the correct and intentional target is fully localized `爪印` branding — no `PawWork` prefix. Do NOT flag these strings as missing the first-occurrence `PawWork 爪印` rule in future reviews.
Applied to files:
packages/ui/src/i18n/zh.tspackages/app/src/i18n/zh.ts
📚 Learning: 2026-04-29T04:23:45.886Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 320
File: packages/ui/src/i18n/zh.ts:0-0
Timestamp: 2026-04-29T04:23:45.886Z
Learning: In Astro-Han/pawwork `packages/ui/src/i18n/zh.ts`, the canonical zh translations for message-part context counters (commit fa6771a35, PR `#320`) are:
- `ui.messagePart.context.read.one/.other` → `读取 {{count}} 个文件`
- `ui.messagePart.context.search.one/.other` → `搜索 {{count}} 处匹配` (`处` is the correct measure word for grep-style file:line hits, chosen for verb+count+量词+名词 symmetry with the other two labels)
- `ui.messagePart.context.list.one/.other` → `列出 {{count}} 个目录`
Do NOT suggest `搜索 {{count}} 次` or `浏览 {{count}} 处` for these keys in future reviews.
Applied to files:
packages/ui/src/i18n/zh.tspackages/app/src/i18n/zh.ts
📚 Learning: 2026-04-26T15:35:36.505Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:36.505Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/question/index.ts`), `Question.Option.description` is intentionally **required** (`z.string()`, not `.optional()`). This matches the upstream opencode contract and all current callers (e.g. `PlanExitTool`) always supply a description. The defensive `<Show when={props.description}>` rendering in `session-question-dock.tsx` is a standard guard, not a signal that the field is intended to be optional. Do NOT suggest making `Option.description` optional without a dedicated follow-up that covers schema + tool description + dock copy + tests.
Applied to files:
packages/opencode/src/tool/question.tspackages/opencode/src/question/index.tspackages/ui/src/components/message-part.tsxpackages/app/e2e/session/session-composer-dock.spec.tspackages/opencode/test/question/question.test.tspackages/app/src/pages/session/composer/session-question-dock.tsx
📚 Learning: 2026-04-28T06:47:20.342Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/question.ts:6-16
Timestamp: 2026-04-28T06:47:20.342Z
Learning: In Astro-Han/pawwork, `packages/opencode/src/tool/question.ts` is a permanent PawWork carve-out: `Question.Prompt` (defined in `packages/opencode/src/question/index.ts`) remains a Zod schema, NOT an Effect Schema. The `ts-expect-error` boundary in `tool/registry.ts` marks the Zod ↔ Effect Schema seam. The dropped `packages/opencode/test/tool/question.test.ts` covered the old Zod-mixed surface. Schema-bound regression tests for this tool are intentionally deferred until `question/index.ts` migrates to Effect Schema in its own dedicated PR. Do NOT request restoring question tool tests in upstream-sync PRs; flag it only in the PR that migrates `question/index.ts` to Effect Schema.
Applied to files:
packages/opencode/src/tool/question.tspackages/opencode/src/question/index.tspackages/ui/src/components/message-part.tsxpackages/app/e2e/session/session-composer-dock.spec.tspackages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-27T08:58:00.665Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/prompt.ts:531-538
Timestamp: 2026-04-27T08:58:00.665Z
Learning: When using Effect (e.g., `yield*` with `Effect`-style generator yielding), only use `yield* new SomeErrorClass(...)` if `SomeErrorClass` extends `Schema.TaggedErrorClass` (i.e., it implements Effect’s Yieldable interface). For plain `Error` subclasses (like `BlockedLoopError` / `LoopStopError`) or inline `new Error(...)` values, they are not yieldable and must be wrapped as `yield* Effect.fail(new PlainError(...))`. Do not recommend changing `yield* Effect.fail(new SomePlainError(...))` to `yield* new SomePlainError(...)` unless the error class extends `Schema.TaggedErrorClass`.
Applied to files:
packages/opencode/src/tool/question.tspackages/opencode/src/question/index.ts
📚 Learning: 2026-04-28T12:49:09.792Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/session/subagent-run.ts:445-445
Timestamp: 2026-04-28T12:49:09.792Z
Learning: In this repo’s `packages/opencode/src` module files, the canonical module-as-namespace pattern is load-bearing: at the bottom of each module file, add a self-reexport in the form `export * as <ModuleName> from "./<module-file>"` (e.g., in `subagent-run.ts`: `export * as SubagentRun from "./subagent-run"`). Consumers must import the namespace via a named binding (e.g., `import { SubagentRun } from ".../subagent-run"`) and then access members as `SubagentRun.Service`, `SubagentRun.defaultLayer`, `SubagentRun.AgentListFilter`, etc. During code review, do NOT flag these self-reexports as dead code or redundant; removing or altering them will break the consumer named binding.
Applied to files:
packages/opencode/src/tool/question.tspackages/opencode/src/question/index.ts
📚 Learning: 2026-04-22T05:32:29.012Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 98
File: packages/desktop-electron/src/main/menu-labels.ts:1-2
Timestamp: 2026-04-22T05:32:29.012Z
Learning: In Astro-Han/pawwork, the app i18n layer (`packages/app/src/i18n/`) only contains `en.ts` and `zh.ts`, and `normalizeLocale` (in `packages/app/src/context/language.tsx`) only returns `"en"` or `"zh"`. The desktop `MenuLocale = "en" | "zh"` union in `packages/desktop-electron/src/main/menu-labels.ts` is intentionally limited to these two locales and is not a broader restriction — do not flag it as overly restrictive or suggest adding other locales.
Applied to files:
packages/app/src/i18n/zh.ts
📚 Learning: 2026-04-27T12:59:49.844Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/test/session/prompt-effect.test.ts:0-0
Timestamp: 2026-04-27T12:59:49.844Z
Learning: In `packages/opencode/test/session/prompt-effect.test.ts` and `packages/opencode/src/session/diagnostics.ts` (PR `#264`), the recovery reminder copy differs between signature kinds: the input-repeat variant says "repeated the same tool input 3 times" (uses a literal count), while the target-repeat variant says "failed against the same target multiple times" (uses "multiple times" with no count). Assertions that check for injected reminder text in LLM inputs must accept both phrasings when a scenario produces both `input:` and `target:` signatures (e.g., `read` tool with a `filePath` parameter). Do NOT narrow the assertion to only the input-variant phrasing.
Applied to files:
packages/opencode/src/question/index.tspackages/ui/src/components/message-part.tsxpackages/app/e2e/session/session-composer-dock.spec.tspackages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-26T16:34:57.130Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:57.130Z
Learning: In Astro-Han/pawwork (`packages/ui/src/components/message-part.tsx`), the `taskId` createMemo and `childSessionId` createMemo both intentionally read only from `partMetadata().sessionId` (populated post-execution), not from `input.task_id` / `input.subagent_session_id`. This has always been the case — the original code never read the input field either. Adding an `input.subagent_session_id` fallback would be a new capability, not a bug fix. Do NOT flag the absence of this fallback as a regression in PR `#247` or future PRs unless there is a concrete case where metadata is not populated.
Applied to files:
packages/ui/src/components/message-part.tsx
📚 Learning: 2026-04-28T11:24:35.312Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/test/session/subagent-lifecycle-integration.test.ts:41-47
Timestamp: 2026-04-28T11:24:35.312Z
Learning: In `packages/opencode/test/session/subagent-lifecycle-integration.test.ts` (Astro-Han/pawwork, PR `#287`), the test suite intentionally uses a manual `run` helper (`Effect.runPromise(program.pipe(Effect.provide(Layer.mergeAll(SubagentRun.defaultLayer, Session.defaultLayer)), Effect.orDie))`) and raw `bun:test` test cases rather than the `testEffect(...)` harness. All 27 lifecycle tests pass with this pattern. Migration to `testEffect` + `it.live(...)` is deferred to a dedicated test-harness sweep PR to avoid fixture drift before merge. Do NOT re-flag the manual `Effect.runPromise` runner in this file as needing harness migration until that sweep PR lands.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.tspackages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-29T13:27:28.494Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 329
File: packages/app/src/pages/session/session-view-controller.test.ts:5-45
Timestamp: 2026-04-29T13:27:28.494Z
Learning: In Astro-Han/pawwork (`packages/app/src/pages/session/session-view-controller.test.ts` and related Solid + Bun test files), the Bun + Solid test environment does NOT reliably exercise `createMemo((current) => ...)` signal recomputation the way a browser runtime does. Adding signal-driven transition tests (e.g., using `createSignal` + `createRoot` to flip reactive inputs) is misleading in this environment because the reactive invalidation/recomputation path is not faithfully replicated. The correct strategy is: cover pure transition logic with plain unit tests (e.g., `nextSessionViewState`), and cover the browser reactive path with E2E tests (e.g., session-switch E2E spec). Do NOT re-flag the absence of signal-driven `createSessionViewController` tests in this environment as a gap.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.tspackages/app/src/pages/session/composer/session-question-dock.tsx
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Test one feature per test file
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-29T13:27:25.687Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 329
File: packages/app/e2e/session/session-scroll-position.spec.ts:171-230
Timestamp: 2026-04-29T13:27:25.687Z
Learning: In `packages/app/e2e/session/session-scroll-position.spec.ts`, the `describe()` formatter is intentionally duplicated in `installPageErrorProbe` (inside `page.addInitScript`, runs in browser context) and `collectPageErrors` (runs in Node.js/Playwright context). These are separate execution contexts — `addInitScript` serializes its closure to a string for injection — so extracting a shared helper would add cross-context indirection. Do NOT flag this duplication as a maintenance issue.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T03:51:54.050Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 206
File: packages/app/e2e/prompt/prompt-footer-focus.spec.ts:131-143
Timestamp: 2026-04-24T03:51:54.050Z
Learning: In Astro-Han/pawwork E2E tests under packages/app/e2e, do not manually call `project.trackSession(sessionID)` when you obtain a `sessionID` via `project.prompt(text)`. The `project.prompt()` implementation already registers `trackSession(next.sessionID, active.directory)` automatically after the prompt submission is observed and the active session is resolved, so calling `project.trackSession(sessionID)` again will create duplicate session ownership/teardown handling.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Prefer fluent helpers and drivers when they make intent obvious and reduce locator-heavy noise in tests
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-28T04:56:21.338Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/tool/tool-define.test.ts:2-9
Timestamp: 2026-04-28T04:56:21.338Z
Learning: In `packages/opencode/test/tool/tool-define.test.ts` (Astro-Han/pawwork, PR `#270`), the test suite intentionally uses a `ManagedRuntime.make(Layer.mergeAll(Truncate.defaultLayer, Agent.defaultLayer))` wrapper and raw `bun:test` `test(...)` cases rather than the `testEffect(...)` harness. This code was adopted wholesale from upstream via the graft strategy (per `project_upstream_strategy.md`). Migrating to `testEffect` is deferred to a follow-up PR so as not to mix refactor + harness-migration intents and to avoid drifting the diff from the upstream baseline needed for clean future grafts. Do NOT re-flag the `ManagedRuntime.make` usage in this file as needing harness migration until that follow-up lands.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.tspackages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-23T15:25:27.182Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 193
File: packages/app/e2e/sidebar/sidebar-leading-slot.spec.ts:5-55
Timestamp: 2026-04-23T15:25:27.182Z
Learning: In Astro-Han/pawwork E2E tests (e.g., *.spec.ts under packages/app/e2e), reaching a real "running" session state is not achievable with the bare `sdk` fixture. Use the `project` fixture (to bootstrap the model) and orchestrate the transition with `llm.wait(1)`; even if you set `agent: "build"` and a `system` prompt via `sdk.session.promptAsync`, the current test infrastructure does not trigger an actual LLM call, so it won’t simulate "running" cheaply. Review any attempt to mock/force "running" using only `sdk` as likely ineffective unless it also uses `project` + `llm.wait(1)`.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T00:02:50.599Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:50.599Z
Learning: For Astro-Han/pawwork E2E tests under packages/app/e2e/**/*.spec.ts, do not call project.trackDirectory() or project.trackSession() before project.open() has run. The project fixture throws until open() initializes internal state. Use this ordering pattern: (1) call project.trackSession(sessionID) inside the beforeGoto callback (where state is already available), (2) call project.trackDirectory(directory) and any cross-workspace tracking like project.trackSession(id, directory) immediately after project.open() returns, and (3) if you create any resources before open() that cannot yet be tracked via the fixture, ensure you clean them up explicitly in finally blocks (e.g., cleanupSession / cleanupTestProject).
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T05:48:36.205Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/e2e/app/composer-parity.spec.ts:0-0
Timestamp: 2026-04-24T05:48:36.205Z
Learning: In E2E parity tests, prefer using the existing `[data-action]` coverage when asserting UI parity. For elements whose trigger props set `data-action` (e.g., `data-action="prompt-model"` and `data-action="prompt-model-variant"` on prompt input chip triggers), you generally do not need to add separate assertions driven by `[data-component]` for parity. Avoid duplicating component-specific queries when the `[data-action]` selector sweep already includes the elements; any extra unioning of selectors should be treated as optional belt-and-suspenders rather than required.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-28T05:36:25.456Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/tool/grep.test.ts:16-22
Timestamp: 2026-04-28T05:36:25.456Z
Learning: In `packages/opencode/test/tool/grep.test.ts` (Astro-Han/pawwork, PR `#270`), the test suite intentionally uses a manual `ManagedRuntime.make(Layer.mergeAll(...))` setup and raw `bun:test` test cases rather than the `testEffect(...)` harness. The migration to `testEffect` + `it.live(...)` + `provideTmpdirInstance(...)` is a whole-file rewrite deferred to a dedicated sweep PR that will migrate all tool tests still on the manual ManagedRuntime pattern together. Do NOT re-flag the ManagedRuntime setup in this file as needing harness migration until that sweep PR lands.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-27T11:19:24.963Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/tool/websearch-auth.test.ts:0-0
Timestamp: 2026-04-27T11:19:24.963Z
Learning: In `packages/opencode/test/tool/websearch-auth.test.ts` (Astro-Han/pawwork), the tests intentionally use a small local `runWith` runner with raw `bun:test` and `Effect.runPromise` rather than the `testEffect` harness. Each test case injects a custom in-memory `Auth.Service` layer; switching to `testEffect` would be style-only churn without changing risk coverage. Do not flag these tests as needing harness migration.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-27T11:18:47.332Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/tool/mcp-exa.test.ts:1-186
Timestamp: 2026-04-27T11:18:47.332Z
Learning: In `packages/opencode/test/tool/mcp-exa.test.ts` (Astro-Han/pawwork), the tests intentionally use raw `bun:test` async cases with `Effect.runPromise(...)` and per-case `HttpClient.make(...)` fakes rather than the `testEffect(...)` harness. The maintainer has explicitly decided not to migrate, because the HttpClient fake wiring is itself the behavior under test and switching to `testEffect` would be style churn without changing risk coverage. Do not flag these tests as needing harness migration.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-27T11:18:47.596Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/agent/agent.test.ts:440-447
Timestamp: 2026-04-27T11:18:47.596Z
Learning: In `packages/opencode/test/agent/agent.test.ts` (Astro-Han/pawwork), all agent-permission tests intentionally use the manual `tmpdir()` + `Instance.provide(...)` pattern. Do not flag individual tests in this file for conversion to `provideTmpdirInstance(...)` or `provideInstance(...)`; a full harness migration would be a separate PR if the pattern ever needs to change.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-28T05:36:24.561Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:0-0
Timestamp: 2026-04-28T05:36:24.561Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), after the streaming-Service refactor of `ripgrep.ts`, there is only one code path that strips `RIPGREP_CONFIG_PATH` from the spawned environment (`delete env.RIPGREP_CONFIG_PATH` at `src/file/ripgrep.ts` line ~155). There is no longer a separate "worker" vs "direct" execution mode, so a single test titled "ignores RIPGREP_CONFIG_PATH from spawned env" (with an explanatory comment) is the correct and complete coverage. Do NOT flag the absence of a separate worker-mode RIPGREP_CONFIG_PATH test as a gap.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : When a test needs instance-local state, prefer `provideTmpdirInstance(...)` or `provideInstance(...)` over manual `Instance.provide(...)` inside Promise-style tests.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-23T08:51:00.819Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:00.819Z
Learning: For pawwork tests under packages/opencode/test/**, auth.json teardown may intentionally combine `Filesystem.write` (from `packages/opencode/src/util/filesystem.ts`) with `node:fs/promises` `unlink` for cleanup. Do not flag this as inconsistent style; it is the established/intentional pattern because `Filesystem` does not provide a `remove`/`unlink` helper.
Applied to files:
packages/opencode/test/question/question.test.ts
📚 Learning: 2026-04-24T05:39:58.329Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:58.329Z
Learning: In Astro-Han/pawwork `packages/app/src/components/prompt-input.tsx`, after the composer unification in PR `#208` (fixed in commit 5d810aa):
- `SendButton.disabled` does NOT gate on `store.mode !== "normal"`. Shell mode has a fully visible, clickable orange submit button that calls `handleSubmit` directly (same path as the Enter key in `handleKeyDown`). Do NOT suggest re-adding the mode gate.
- `SendButton` does NOT use the `buttons()` spring opacity animation (`style={buttons()}`). It is always fully visible regardless of mode.
- `WorkspaceChip` is gated on `props.homeMode && store.mode === "normal"` so it hides in shell mode (preventing it from appearing isolated/bright while neighboring controls fade).
- The left-side chip group (`aria-hidden={store.mode !== "normal"}`) covers attach/model/variant/workspace controls only; `SendButton` remains in a separate right-side sibling div.
Applied to files:
packages/app/src/pages/session/composer/session-question-dock.tsx
📚 Learning: 2026-04-23T15:26:07.250Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 193
File: packages/app/src/pages/layout/sidebar-items.tsx:102-107
Timestamp: 2026-04-23T15:26:07.250Z
Learning: In Astro-Han/pawwork (`packages/app/src/pages/layout/sidebar-items.tsx`), the `indicator()` function in `SessionRow` intentionally renders `props.leadingSlot` (the pin button) only as a fallback when no status indicator (running/permission/error/unseen) is active. When a higher-priority status wins the slot, the pin button is removed from the DOM — this is a deliberate design choice for the merged leading slot (`#150`). The keyboard unpin path is preserved via: (1) focusing the row anchor triggers `group-focus-within` which reveals the dots menu trigger, then Tab → Enter → "Unpin Session"; (2) the context menu (right-click / Shift+F10) exposes "Unpin Session". The "always render + CSS overlay" approach was considered but rejected due to z-index/pointer-events complexity; residual `...` slot behavior is tracked in `#192`. Do NOT flag the absence of the pin button from the DOM when a status is active as an accessibility regression.
Applied to files:
packages/app/src/pages/session/composer/session-question-dock.tsx
🔇 Additional comments (8)
packages/app/src/i18n/en.ts (1)
623-623: Looks good — skip-current label is correctly introduced.This key cleanly supports the new per-question skip action in the composer dock flow.
packages/ui/src/i18n/zh.ts (1)
150-150: Approved — skipped-answer zh localization is in place.The new key/value pair matches the new skipped-answer UI state.
packages/app/src/i18n/zh.ts (1)
1001-1001: LGTM — zh skip-current action label is correctly added.This keeps app-level locale parity for the new dock action.
packages/ui/src/i18n/en.ts (1)
163-163: Approved — new skipped-answer English string is correct.This provides the explicit UI wording needed for skipped question answers.
packages/opencode/src/tool/question.ts (1)
39-42: Good change — formatter now preserves explicit skip semantics.Using an empty array as “Skipped by user” matches the intended per-question skip contract.
packages/ui/src/components/message-part.tsx (1)
2297-2299: Approved — skipped answers are now rendered explicitly.This correctly surfaces per-question skip outcomes in the question answer card.
packages/opencode/src/question/index.ts (1)
293-297: Looks correct — empty per-question answers are now treated as skip, not rejection.This change is aligned with the per-question answered/skipped/pending contract and prevents premature failure on skip.
packages/app/e2e/session/session-composer-dock.spec.ts (1)
53-70: Great coverage addition for the skip-current flow.The new test exercises the exact critical path: skip one question, continue on next question, submit, and confirm dock unblocks.
Also applies to: 385-413
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces the ability to skip questions within the session composer dock, updating the UI, state management, and SDK logic to support empty answer arrays as a 'skipped' state. Key changes include new E2E tests, translation strings, and logic to navigate between unsettled questions. Feedback highlights an opportunity to improve the UX by wrapping navigation to the first unsettled question when skipping the last one and raises a concern regarding the potential for empty answers to mask invalid states that require validation.
Astro-Han
force-pushed
the
codex/fix-i352-question-dock
branch
from
70f781f to
be8f899
Compare
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/app/e2e/session/session-composer-dock.spec.ts`:
- Around line 53-70: The test constant multiQuestions should be renamed to
follow SCREAMING_SNAKE_CASE: change its declaration identifier from
multiQuestions to MULTI_QUESTIONS and update every usage/reference in this spec
(including other occurrences around the second and third blocks mentioned) to
use MULTI_QUESTIONS; ensure any imports, destructuring, or assertions that
reference multiQuestions are updated to the new name so the tests compile and
run unchanged functionally.
🪄 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: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: ec9265b3-142a-4461-a671-74c79d5ef482
📒 Files selected for processing (1)
packages/app/e2e/session/session-composer-dock.spec.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (12)
- GitHub Check: analyze-js-ts
- GitHub Check: unit-windows-desktop
- GitHub Check: unit-windows-opencode-server-tools
- GitHub Check: unit-windows-app
- GitHub Check: unit-windows-opencode-config-project
- GitHub Check: unit-windows-opencode-session
- GitHub Check: unit-opencode
- GitHub Check: unit-desktop
- GitHub Check: unit-app
- GitHub Check: typecheck
- GitHub Check: smoke-macos-arm64
- GitHub Check: e2e-artifacts
🧰 Additional context used
📓 Path-based instructions (2)
packages/app/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (packages/app/AGENTS.md)
Always prefer
createStoreover multiplecreateSignalcalls in SolidJS
Files:
packages/app/e2e/session/session-composer-dock.spec.ts
packages/app/e2e/**/*.spec.ts
📄 CodeRabbit inference engine (packages/app/e2e/AGENTS.md)
packages/app/e2e/**/*.spec.ts: Import test utilities from../fixturesinstead of@playwright/test
Test files should be named with the patternfeature-name.spec.ts
Use lowercase, descriptive test names (e.g., 'sidebar can be toggled')
Use camelCase for variable names in tests
Use SCREAMING_SNAKE_CASE for constants in tests
Use fixture-managed cleanup withwithSession(sdk, title, callback)for temporary sessions instead of callingsdk.session.delete(...)directly
Prefer theprojectfixture for tests that need a dedicated project with LLM mocking
Usedata-component,data-action, or semantic roles for selectors instead of CSS class names or IDs
UsemodKeyfrom utils for cross-platform keyboard shortcuts (Meta on Mac, Control on Linux/Windows)
In terminal tests, type through the browser usingrunTerminal()andwaitTerminalReady()instead of writing to the PTY through the SDK
Never use wall-clock waits likepage.waitForTimeout(...)to make a test pass
Wait on observable state withexpect(...),expect.poll(...), or existing helpers instead of assuming work is finished after an action
Use locator assertions liketoBeVisible(),toHaveCount(0), andtoHaveAttribute(...)for normal UI state verification
Useexpect.poll(...)for probing mock or backend state rather than transient DOM visibility
Prefer fluent helpers and drivers when they make intent obvious and reduce locator-heavy noise in tests
Use direct locators when the interaction is simple and a helper would not add clarity
When validating routing, assert against canonical or resolved workspace slugs using shared helpers from../actionsto account for Windows canonicalization
Test one feature per test file
Callproject.trackSession(sessionID, directory?)andproject.trackDirectory(directory)for any resources created outside the fixture so teardown can clean them up
Files:
packages/app/e2e/session/session-composer-dock.spec.ts
🧠 Learnings (14)
📓 Common learnings
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/question.ts:6-16
Timestamp: 2026-04-28T06:47:20.342Z
Learning: In Astro-Han/pawwork, `packages/opencode/src/tool/question.ts` is a permanent PawWork carve-out: `Question.Prompt` (defined in `packages/opencode/src/question/index.ts`) remains a Zod schema, NOT an Effect Schema. The `ts-expect-error` boundary in `tool/registry.ts` marks the Zod ↔ Effect Schema seam. The dropped `packages/opencode/test/tool/question.test.ts` covered the old Zod-mixed surface. Schema-bound regression tests for this tool are intentionally deferred until `question/index.ts` migrates to Effect Schema in its own dedicated PR. Do NOT request restoring question tool tests in upstream-sync PRs; flag it only in the PR that migrates `question/index.ts` to Effect Schema.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:36.505Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/question/index.ts`), `Question.Option.description` is intentionally **required** (`z.string()`, not `.optional()`). This matches the upstream opencode contract and all current callers (e.g. `PlanExitTool`) always supply a description. The defensive `<Show when={props.description}>` rendering in `session-question-dock.tsx` is a standard guard, not a signal that the field is intended to be optional. Do NOT suggest making `Option.description` optional without a dedicated follow-up that covers schema + tool description + dock copy + tests.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/patch/index.ts:337-346
Timestamp: 2026-04-28T04:38:05.946Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/patch/index.ts`), the BOM-transition surfacing gap — where `Bom.split` strips BOM before building `unified_diff`/`new_content` but `Bom.join` later re-attaches BOM on disk write, meaning BOM changes are not reflected in the diff payload — is intentionally deferred. PR `#270` is an upstream-sync graft; fixing the issue here would mix refactor + bugfix intents and drift the diff from the upstream baseline needed for clean future grafts. A dedicated follow-up PR (or upstream report) will address this. Do NOT re-flag the missing BOM-change surfacing in `ApplyPatchFileUpdate`/`ApplyPatchFileChange` as a blocking issue in PR `#270` or in future sync PRs that carry the same upstream baseline.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/test/session/subagent-lifecycle-integration.test.ts:41-47
Timestamp: 2026-04-28T11:24:35.312Z
Learning: In `packages/opencode/test/session/subagent-lifecycle-integration.test.ts` (Astro-Han/pawwork, PR `#287`), the test suite intentionally uses a manual `run` helper (`Effect.runPromise(program.pipe(Effect.provide(Layer.mergeAll(SubagentRun.defaultLayer, Session.defaultLayer)), Effect.orDie))`) and raw `bun:test` test cases rather than the `testEffect(...)` harness. All 27 lifecycle tests pass with this pattern. Migration to `testEffect` + `it.live(...)` is deferred to a dedicated test-harness sweep PR to avoid fixture drift before merge. Do NOT re-flag the manual `Effect.runPromise` runner in this file as needing harness migration until that sweep PR lands.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/lsp.ts:23-32
Timestamp: 2026-04-28T07:28:14.317Z
Learning: In `packages/opencode/src/tool/lsp.ts` (Astro-Han/pawwork, PR `#270`), the `Parameters` schema requires `line` and `character` for all operations, including `workspaceSymbol` and `documentSymbol` which never use coordinates. This matches the upstream `dev:packages/opencode/src/tool/lsp.ts:23-32` baseline exactly — both fields are declared as required `Schema.Number` with `>= 1` checks. The fix (per-operation schema split, or making `line`/`character` optional with handler-side presence validation for operations that need them like `goToDefinition`/`findReferences`) is deferred to a follow-up PR or upstream report to avoid mixing refactor + bug-fix intents and drifting the diff from the upstream baseline. Do NOT re-flag the required coordinates on `workspaceSymbol`/`documentSymbol` in upstream-sync PRs; flag it only in a PawWork-authored PR that directly touches `lsp.ts` parameter validation.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:58.329Z
Learning: In Astro-Han/pawwork `packages/app/src/components/prompt-input.tsx`, after the composer unification in PR `#208` (fixed in commit 5d810aa):
- `SendButton.disabled` does NOT gate on `store.mode !== "normal"`. Shell mode has a fully visible, clickable orange submit button that calls `handleSubmit` directly (same path as the Enter key in `handleKeyDown`). Do NOT suggest re-adding the mode gate.
- `SendButton` does NOT use the `buttons()` spring opacity animation (`style={buttons()}`). It is always fully visible regardless of mode.
- `WorkspaceChip` is gated on `props.homeMode && store.mode === "normal"` so it hides in shell mode (preventing it from appearing isolated/bright while neighboring controls fade).
- The left-side chip group (`aria-hidden={store.mode !== "normal"}`) covers attach/model/variant/workspace controls only; `SendButton` remains in a separate right-side sibling div.
📚 Learning: 2026-04-29T13:27:28.494Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 329
File: packages/app/src/pages/session/session-view-controller.test.ts:5-45
Timestamp: 2026-04-29T13:27:28.494Z
Learning: In Astro-Han/pawwork (`packages/app/src/pages/session/session-view-controller.test.ts` and related Solid + Bun test files), the Bun + Solid test environment does NOT reliably exercise `createMemo((current) => ...)` signal recomputation the way a browser runtime does. Adding signal-driven transition tests (e.g., using `createSignal` + `createRoot` to flip reactive inputs) is misleading in this environment because the reactive invalidation/recomputation path is not faithfully replicated. The correct strategy is: cover pure transition logic with plain unit tests (e.g., `nextSessionViewState`), and cover the browser reactive path with E2E tests (e.g., session-switch E2E spec). Do NOT re-flag the absence of signal-driven `createSessionViewController` tests in this environment as a gap.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-28T11:24:35.312Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/test/session/subagent-lifecycle-integration.test.ts:41-47
Timestamp: 2026-04-28T11:24:35.312Z
Learning: In `packages/opencode/test/session/subagent-lifecycle-integration.test.ts` (Astro-Han/pawwork, PR `#287`), the test suite intentionally uses a manual `run` helper (`Effect.runPromise(program.pipe(Effect.provide(Layer.mergeAll(SubagentRun.defaultLayer, Session.defaultLayer)), Effect.orDie))`) and raw `bun:test` test cases rather than the `testEffect(...)` harness. All 27 lifecycle tests pass with this pattern. Migration to `testEffect` + `it.live(...)` is deferred to a dedicated test-harness sweep PR to avoid fixture drift before merge. Do NOT re-flag the manual `Effect.runPromise` runner in this file as needing harness migration until that sweep PR lands.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-28T06:47:20.342Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/question.ts:6-16
Timestamp: 2026-04-28T06:47:20.342Z
Learning: In Astro-Han/pawwork, `packages/opencode/src/tool/question.ts` is a permanent PawWork carve-out: `Question.Prompt` (defined in `packages/opencode/src/question/index.ts`) remains a Zod schema, NOT an Effect Schema. The `ts-expect-error` boundary in `tool/registry.ts` marks the Zod ↔ Effect Schema seam. The dropped `packages/opencode/test/tool/question.test.ts` covered the old Zod-mixed surface. Schema-bound regression tests for this tool are intentionally deferred until `question/index.ts` migrates to Effect Schema in its own dedicated PR. Do NOT request restoring question tool tests in upstream-sync PRs; flag it only in the PR that migrates `question/index.ts` to Effect Schema.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-27T12:59:49.844Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/test/session/prompt-effect.test.ts:0-0
Timestamp: 2026-04-27T12:59:49.844Z
Learning: In `packages/opencode/test/session/prompt-effect.test.ts` and `packages/opencode/src/session/diagnostics.ts` (PR `#264`), the recovery reminder copy differs between signature kinds: the input-repeat variant says "repeated the same tool input 3 times" (uses a literal count), while the target-repeat variant says "failed against the same target multiple times" (uses "multiple times" with no count). Assertions that check for injected reminder text in LLM inputs must accept both phrasings when a scenario produces both `input:` and `target:` signatures (e.g., `read` tool with a `filePath` parameter). Do NOT narrow the assertion to only the input-variant phrasing.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T03:51:54.050Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 206
File: packages/app/e2e/prompt/prompt-footer-focus.spec.ts:131-143
Timestamp: 2026-04-24T03:51:54.050Z
Learning: In Astro-Han/pawwork E2E tests under packages/app/e2e, do not manually call `project.trackSession(sessionID)` when you obtain a `sessionID` via `project.prompt(text)`. The `project.prompt()` implementation already registers `trackSession(next.sessionID, active.directory)` automatically after the prompt submission is observed and the active session is resolved, so calling `project.trackSession(sessionID)` again will create duplicate session ownership/teardown handling.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-26T15:35:36.505Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:36.505Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/question/index.ts`), `Question.Option.description` is intentionally **required** (`z.string()`, not `.optional()`). This matches the upstream opencode contract and all current callers (e.g. `PlanExitTool`) always supply a description. The defensive `<Show when={props.description}>` rendering in `session-question-dock.tsx` is a standard guard, not a signal that the field is intended to be optional. Do NOT suggest making `Option.description` optional without a dedicated follow-up that covers schema + tool description + dock copy + tests.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-29T13:27:25.687Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 329
File: packages/app/e2e/session/session-scroll-position.spec.ts:171-230
Timestamp: 2026-04-29T13:27:25.687Z
Learning: In `packages/app/e2e/session/session-scroll-position.spec.ts`, the `describe()` formatter is intentionally duplicated in `installPageErrorProbe` (inside `page.addInitScript`, runs in browser context) and `collectPageErrors` (runs in Node.js/Playwright context). These are separate execution contexts — `addInitScript` serializes its closure to a string for injection — so extracting a shared helper would add cross-context indirection. Do NOT flag this duplication as a maintenance issue.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Test one feature per test file
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Use fixture-managed cleanup with `withSession(sdk, title, callback)` for temporary sessions instead of calling `sdk.session.delete(...)` directly
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-23T07:23:23.849Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 180
File: packages/app/src/components/session/session-new-view.tsx:13-18
Timestamp: 2026-04-23T07:23:23.849Z
Learning: In pawwork (Astro-Han/pawwork), prefer using `createStore` instead of multiple `createSignal` calls only when the signals represent **coupled** object state that is updated together (i.e., there is at least one shared batch-update site where the state is changed in the same transaction). If the state fields are **independent** and are mutated by separate handlers (e.g., one handler updates only `selectedSkill` while another updates only `mode`), keep them as individual `createSignal` calls—using `createStore` for truly independent fields adds boilerplate without behavioral benefit.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-23T15:25:27.182Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 193
File: packages/app/e2e/sidebar/sidebar-leading-slot.spec.ts:5-55
Timestamp: 2026-04-23T15:25:27.182Z
Learning: In Astro-Han/pawwork E2E tests (e.g., *.spec.ts under packages/app/e2e), reaching a real "running" session state is not achievable with the bare `sdk` fixture. Use the `project` fixture (to bootstrap the model) and orchestrate the transition with `llm.wait(1)`; even if you set `agent: "build"` and a `system` prompt via `sdk.session.promptAsync`, the current test infrastructure does not trigger an actual LLM call, so it won’t simulate "running" cheaply. Review any attempt to mock/force "running" using only `sdk` as likely ineffective unless it also uses `project` + `llm.wait(1)`.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T00:02:50.599Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:50.599Z
Learning: For Astro-Han/pawwork E2E tests under packages/app/e2e/**/*.spec.ts, do not call project.trackDirectory() or project.trackSession() before project.open() has run. The project fixture throws until open() initializes internal state. Use this ordering pattern: (1) call project.trackSession(sessionID) inside the beforeGoto callback (where state is already available), (2) call project.trackDirectory(directory) and any cross-workspace tracking like project.trackSession(id, directory) immediately after project.open() returns, and (3) if you create any resources before open() that cannot yet be tracked via the fixture, ensure you clean them up explicitly in finally blocks (e.g., cleanupSession / cleanupTestProject).
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
📚 Learning: 2026-04-24T05:48:36.205Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/e2e/app/composer-parity.spec.ts:0-0
Timestamp: 2026-04-24T05:48:36.205Z
Learning: In E2E parity tests, prefer using the existing `[data-action]` coverage when asserting UI parity. For elements whose trigger props set `data-action` (e.g., `data-action="prompt-model"` and `data-action="prompt-model-variant"` on prompt input chip triggers), you generally do not need to add separate assertions driven by `[data-component]` for parity. Avoid duplicating component-specific queries when the `[data-action]` selector sweep already includes the elements; any extra unioning of selectors should be treated as optional belt-and-suspenders rather than required.
Applied to files:
packages/app/e2e/session/session-composer-dock.spec.ts
🔇 Additional comments (1)
packages/app/e2e/session/session-composer-dock.spec.ts (1)
385-443: Skip-flow coverage is solidThese two tests validate both “skip one then submit” and “skip all then submit” paths with stable role/data-slot selectors and explicit progression assertions (
"2 of 2"). Nice coverage for the regression target.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes #352
Verification
Summary by CodeRabbit
New Features
UI / Copy
Tests