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: 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.

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.

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.

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.

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.

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.

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.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/todo.ts:9-18
Timestamp: 2026-04-28T06:51:54.812Z
Learning: In `packages/opencode/src/tool/todo.ts` (Astro-Han/pawwork), `TodoItem.status` and `TodoItem.priority` are intentionally declared as plain `Schema.String` rather than closed literal unions. This matches the upstream opencode baseline (`dev:packages/opencode/src/tool/todo.ts`). The tightening — `Schema.Literals(["pending","in_progress","completed","cancelled"])` for `status` and `Schema.Literals(["high","medium","low"])` for `priority` — is tracked as a follow-up under the harness/tool-set-v1 series (issue `#129`) to land either as part of a tool-schema tightening sweep or upstream-first. Do NOT re-flag the free-form strings for these fields in upstream-sync PRs; flag it only in a PawWork-authored PR or the dedicated sweep that touches `TodoItem` schema.

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: 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 `expect.poll(...)` for probing mock or backend state rather than transient DOM visibility

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.

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

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 : Call `project.trackSession(sessionID, directory?)` and `project.trackDirectory(directory)` for any resources created outside the fixture so teardown can clean them up

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).

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 locator assertions like `toBeVisible()`, `toHaveCount(0)`, and `toHaveAttribute(...)` for normal UI state verification

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 308
File: packages/opencode/test/server/global-session-list.test.ts:224-259
Timestamp: 2026-04-28T18:53:46.234Z
Learning: In `packages/opencode/test/server/global-session-list.test.ts` (Astro-Han/pawwork), all `it.live(...)` test bodies intentionally use `Effect.promise(async () => { ... })` rather than `Effect.gen(function* () { ... })`. This is the established local convention for the route/pagination tests in this file (e.g., "supports cursor pagination", "session route orders by creation time", "session routes omit undefined optional fields"). Do NOT flag individual `it.live` cases in this file as needing conversion to `Effect.gen`; any harness-style migration would need to cover the entire file.

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 : In terminal tests, type through the browser using `runTerminal()` and `waitTerminalReady()` instead of writing to the PTY through the SDK

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

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 : Wait on observable state with `expect(...)`, `expect.poll(...)`, or existing helpers instead of assuming work is finished after an action

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)`.

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.

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.

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.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/session/compaction.ts:169-191
Timestamp: 2026-04-28T05:36:22.128Z
Learning: In `packages/opencode/src/session/compaction.ts` (Astro-Han/pawwork), the internal helper `splitTurn` intentionally returns a raw `Effect.gen(...)` rather than being wrapped with `Effect.fnUntraced`. Converting `splitTurn` (and similar plain-Effect.gen internal helpers in this file, e.g. `turns`, `completedCompactions`, `buildPrompt`) to `Effect.fnUntraced` is a repo-wide convention sweep deferred to a dedicated follow-up PR. The same sweep covers `tool/tool.ts` and other helpers flagged in the same sync. Do NOT re-flag the absence of `Effect.fnUntraced` on `splitTurn` or other internal helpers in `compaction.ts` during upstream-sync PRs; flag it only in the dedicated convention-sweep PR.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 206
File: packages/app/e2e/prompt/prompt-footer-focus.spec.ts:131-143
Timestamp: 2026-04-24T03:51:56.211Z
Learning: In Astro-Han/pawwork E2E tests (packages/app/e2e/fixtures.ts), `project.prompt(text)` internally calls `trackSession(next.sessionID, active.directory)` after the prompt submission is observed and the active session is resolved. Tests that obtain a `sessionID` from `project.prompt()` do NOT need to call `project.trackSession(sessionID)` manually — it is already registered for teardown. Calling it again would be duplicate ownership.

Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:21.288Z
Learning: Applies to packages/opencode/**/*.ts : Use `Effect.addFinalizer` or `Effect.acquireRelease` inside the `InstanceState.make` closure for cleanup (subscriptions, process teardown, etc.)

Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:21.288Z
Learning: Applies to packages/opencode/**/*.ts : Use `Effect.gen(function* () { ... })` for Effect composition

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: 193
File: packages/app/e2e/sidebar/sidebar-leading-slot.spec.ts:5-55
Timestamp: 2026-04-23T15:25:31.118Z
Learning: In Astro-Han/pawwork E2E tests, reaching a real "running" session state requires the `project` fixture (for model bootstrap) plus `llm.wait(1)` orchestration. The bare `sdk` fixture used by `withSession` does not trigger an LLM call even with `agent: "build"` + `system` prompt set via `sdk.session.promptAsync`, so simulating running state is not lightweight in the current test infrastructure.

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: 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

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.

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 `expect.poll(...)` for probing mock or backend state rather than transient DOM visibility

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 : Call `project.trackSession(sessionID, directory?)` and `project.trackDirectory(directory)` for any resources created outside the fixture so teardown can clean them up

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 308
File: packages/opencode/test/server/global-session-list.test.ts:224-259
Timestamp: 2026-04-28T18:53:46.234Z
Learning: In `packages/opencode/test/server/global-session-list.test.ts` (Astro-Han/pawwork), all `it.live(...)` test bodies intentionally use `Effect.promise(async () => { ... })` rather than `Effect.gen(function* () { ... })`. This is the established local convention for the route/pagination tests in this file (e.g., "supports cursor pagination", "session route orders by creation time", "session routes omit undefined optional fields"). Do NOT flag individual `it.live` cases in this file as needing conversion to `Effect.gen`; any harness-style migration would need to cover the entire file.

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).

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

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/desktop-electron/src/main/index-sidecar-source.test.ts:3-11
Timestamp: 2026-04-22T08:49:47.800Z
Learning: In `packages/desktop-electron/src/main/index-sidecar-source.test.ts` (Astro-Han/pawwork), the test intentionally uses `expect(source).toContain` / `expect(source).not.toContain` string matching against the raw `index.ts` source text as a lightweight sidecar contract guard. The maintainer has explicitly chosen not to introduce an AST parser (e.g., `babel/parser` or acorn) for this purpose. Do not flag these string-based assertions as fragile or suggest converting them to AST-based matching.

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 locator assertions like `toBeVisible()`, `toHaveCount(0)`, and `toHaveAttribute(...)` for normal UI state verification

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 : Never use wall-clock waits like `page.waitForTimeout(...)` to make a test pass

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/tool/agent-list.ts:19-28
Timestamp: 2026-04-28T11:24:26.012Z
Learning: In `packages/opencode/src/tool/agent-list.ts` (Astro-Han/pawwork, PR `#287`), the `formatElapsed` function intentionally does NOT handle sub-second durations (1–999 ms) with a `<1s` branch. Sub-second elapsed times are not a real case for LLM-driven subagent dispatch because session creation alone involves multiple round trips plus a model turn. Do NOT suggest adding a `<1s` early-return to `formatElapsed` in future reviews.

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 : Wait on observable state with `expect(...)`, `expect.poll(...)`, or existing helpers instead of assuming work is finished after an action

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.

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)`.

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.

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.

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: 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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/todo.ts:9-18
Timestamp: 2026-04-28T06:51:54.812Z
Learning: In `packages/opencode/src/tool/todo.ts` (Astro-Han/pawwork), `TodoItem.status` and `TodoItem.priority` are intentionally declared as plain `Schema.String` rather than closed literal unions. This matches the upstream opencode baseline (`dev:packages/opencode/src/tool/todo.ts`). The tightening — `Schema.Literals(["pending","in_progress","completed","cancelled"])` for `status` and `Schema.Literals(["high","medium","low"])` for `priority` — is tracked as a follow-up under the harness/tool-set-v1 series (issue `#129`) to land either as part of a tool-schema tightening sweep or upstream-first. Do NOT re-flag the free-form strings for these fields in upstream-sync PRs; flag it only in a PawWork-authored PR or the dedicated sweep that touches `TodoItem` schema.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 206
File: packages/app/e2e/prompt/prompt-footer-focus.spec.ts:131-143
Timestamp: 2026-04-24T03:51:56.211Z
Learning: In Astro-Han/pawwork E2E tests (packages/app/e2e/fixtures.ts), `project.prompt(text)` internally calls `trackSession(next.sessionID, active.directory)` after the prompt submission is observed and the active session is resolved. Tests that obtain a `sessionID` from `project.prompt()` do NOT need to call `project.trackSession(sessionID)` manually — it is already registered for teardown. Calling it again would be duplicate ownership.

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 `expect.poll(...)` for probing mock or backend state rather than transient DOM visibility

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 193
File: packages/app/e2e/sidebar/sidebar-leading-slot.spec.ts:5-55
Timestamp: 2026-04-23T15:25:31.118Z
Learning: In Astro-Han/pawwork E2E tests, reaching a real "running" session state requires the `project` fixture (for model bootstrap) plus `llm.wait(1)` orchestration. The bare `sdk` fixture used by `withSession` does not trigger an LLM call even with `agent: "build"` + `system` prompt set via `sdk.session.promptAsync`, so simulating running state is not lightweight in the current test infrastructure.

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

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

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 `expect.poll(...)` for probing mock or backend state rather than transient DOM visibility

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: 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.

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 : Call `project.trackSession(sessionID, directory?)` and `project.trackDirectory(directory)` for any resources created outside the fixture so teardown can clean them up

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 308
File: packages/opencode/test/server/global-session-list.test.ts:224-259
Timestamp: 2026-04-28T18:53:46.234Z
Learning: In `packages/opencode/test/server/global-session-list.test.ts` (Astro-Han/pawwork), all `it.live(...)` test bodies intentionally use `Effect.promise(async () => { ... })` rather than `Effect.gen(function* () { ... })`. This is the established local convention for the route/pagination tests in this file (e.g., "supports cursor pagination", "session route orders by creation time", "session routes omit undefined optional fields"). Do NOT flag individual `it.live` cases in this file as needing conversion to `Effect.gen`; any harness-style migration would need to cover the entire file.

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).

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 locator assertions like `toBeVisible()`, `toHaveCount(0)`, and `toHaveAttribute(...)` for normal UI state verification

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 : Never use wall-clock waits like `page.waitForTimeout(...)` to make a test pass

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/tool/agent-list.ts:19-28
Timestamp: 2026-04-28T11:24:26.012Z
Learning: In `packages/opencode/src/tool/agent-list.ts` (Astro-Han/pawwork, PR `#287`), the `formatElapsed` function intentionally does NOT handle sub-second durations (1–999 ms) with a `<1s` branch. Sub-second elapsed times are not a real case for LLM-driven subagent dispatch because session creation alone involves multiple round trips plus a model turn. Do NOT suggest adding a `<1s` early-return to `formatElapsed` in future reviews.

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 : Wait on observable state with `expect(...)`, `expect.poll(...)`, or existing helpers instead of assuming work is finished after an action

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.

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

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.

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} : Use `it.effect(...)` when the test should run with `TestClock` and `TestConsole`. Use `it.live(...)` when the test depends on real time, filesystem mtimes, child processes, git, locks, or other live OS behavior.

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 : Import test utilities from `../fixtures` instead of `playwright/test`

Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:21.288Z
Learning: Applies to packages/opencode/**/*.ts : Prefer `DateTime.nowAsDate` over `new Date(yield* Clock.currentTimeMillis)` when you need a `Date` in Effect code

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.

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.

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.

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.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/desktop-electron/src/main/index-sidecar-source.test.ts:3-11
Timestamp: 2026-04-22T08:49:47.800Z
Learning: In `packages/desktop-electron/src/main/index-sidecar-source.test.ts` (Astro-Han/pawwork), the test intentionally uses `expect(source).toContain` / `expect(source).not.toContain` string matching against the raw `index.ts` source text as a lightweight sidecar contract guard. The maintainer has explicitly chosen not to introduce an AST parser (e.g., `babel/parser` or acorn) for this purpose. Do not flag these string-based assertions as fragile or suggest converting them to AST-based matching.

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.

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.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:172-175
Timestamp: 2026-04-28T04:56:18.533Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), the `files dies on nonexistent directory` test hardcodes `/tmp/nonexistent-dir-12345` as the missing-directory path. This is upstream-inherited behaviour adopted wholesale via the graft strategy (`project_upstream_strategy.md`). The fix — replacing the hardcoded path with a platform-neutral guaranteed-nonexistent child path derived from the `tmpdir` fixture — is intentionally deferred to a follow-up PR or upstream report, to avoid mixing bugfix + refactor intents and drifting the diff from the upstream baseline future syncs need. Do NOT re-flag the hardcoded `/tmp/nonexistent-dir-12345` path in this file as a blocking or actionable issue until the follow-up PR lands.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/agent.ts:23-27
Timestamp: 2026-04-28T04:38:11.771Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/tool/agent.ts`), the `subagent_session_id` field in the `Parameters` schema accepts any `Schema.String` rather than a branded `SessionID`. This is inherited upstream behavior (adopted in PR `#270`, an upstream-sync graft of upstream PR `#23244`). The fix — validating `subagent_session_id` as a `SessionID` brand up front so malformed/typo'd IDs fail explicitly rather than silently forking a new subagent session — is intentionally deferred to a follow-up PR or upstream report. Do NOT re-flag this as a blocking issue in PR `#270` or in future upstream-sync PRs that carry the same schema; flag it only in a PawWork-authored PR that touches `agent.ts` parameter validation.

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)`.

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.