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 (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 : 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: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

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} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

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 : Test one feature per test file

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 `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

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: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

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 : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

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 `Path.Path`, `Config`, `Clock`, and `DateTime` services when those concerns are already inside Effect code

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

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} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

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: 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 the `tmpdir` function from `fixture/fixture.ts` to create temporary directories for tests with automatic cleanup. Use `await using` syntax to ensure automatic cleanup when the variable goes out of scope.

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.

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 (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/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : Use `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

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} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

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/opencode/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:21.288Z
Learning: Applies to packages/opencode/**/*.ts : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

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 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: 233
File: packages/desktop-electron/src/main/server.ts:60-60
Timestamp: 2026-04-25T11:52:40.349Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/index.ts`), `ensureLoopbackNoProxy()` (defined at line 551) is called inside `setupApp()` at line 263, which runs synchronously before `initialize()` (line 321) and `spawnLocalServer()` (line 395). It unconditionally upserts `127.0.0.1`, `localhost`, and `::1` into both `process.env.NO_PROXY` and `process.env.no_proxy`. This guarantees that `configureProxyDispatcher(process.env)` in `server.ts` always receives a `process.env` that already excludes loopback from proxying. Do not flag the absence of a loopback-merge inside `configureProxyDispatcher` or `normalizeProxyConfig` — the exclusion is already enforced at a higher layer before those functions are ever called.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 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 (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 : Call `project.trackSession(sessionID, directory?)` and `project.trackDirectory(directory)` for any resources created outside the fixture so teardown can clean them up

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} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:56.086Z
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: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 126
File: packages/ui/src/theme/context.tsx:11-16
Timestamp: 2026-04-22T09:32:58.310Z
Learning: In Astro-Han/pawwork (`packages/ui/src/theme/context.tsx` and related files), the renaming of localStorage theme keys from `opencode-*` to `pawwork-*` (THEME_ID, COLOR_SCHEME, THEME_CSS_LIGHT, THEME_CSS_DARK) is intentional and should NOT include a migration path from the old keys. Migrating would re-couple PawWork and OpenCode browser storage namespaces, which the PR is explicitly designed to avoid. A reset to the PawWork default theme on upgrade is acceptable by design.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 233
File: packages/desktop-electron/src/main/server.ts:60-60
Timestamp: 2026-04-25T11:52:40.349Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/index.ts`), `ensureLoopbackNoProxy()` (defined at line 551) is called inside `setupApp()` at line 263, which runs synchronously before `initialize()` (line 321) and `spawnLocalServer()` (line 395). It unconditionally upserts `127.0.0.1`, `localhost`, and `::1` into both `process.env.NO_PROXY` and `process.env.no_proxy`. This guarantees that `configureProxyDispatcher(process.env)` in `server.ts` always receives a `process.env` that already excludes loopback from proxying. Do not flag the absence of a loopback-merge inside `configureProxyDispatcher` or `normalizeProxyConfig` — the exclusion is already enforced at a higher layer before those functions are ever called.

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: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:31.757Z
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: 71
File: packages/app/src/components/session/session-status-connections.tsx:146-147
Timestamp: 2026-04-20T14:21:56.373Z
Learning: In the Astro-Han/pawwork repository (SolidJS app), `sync.data.config` is always initialized to `{}` at `packages/app/src/context/global-sync.tsx` line 71 and is never `undefined` at runtime. Non-optional property access like `sync.data.config.plugin` is intentional and consistent with the pattern used in `packages/app/src/components/status-popover-body.tsx` line 243. Do not flag `sync.data.config.plugin` as needing optional chaining.

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 the `tmpdir` function from `fixture/fixture.ts` to create temporary directories for tests with automatic cleanup. Use `await using` syntax to ensure automatic cleanup when the variable goes out of scope.

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.

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/session/export.ts:75-88
Timestamp: 2026-04-25T12:52:36.999Z
Learning: In `packages/opencode/src/session/export.ts` (Astro-Han/pawwork), the `extractReasonFromCause` function intentionally uses a lightweight cast-based inspection of the Cause `reasons` array instead of `Cause.failures()` / `Cause.defects()` utilities. This is a deliberate choice: the function is diagnostic-only (used to populate a best-effort reason string for export diagnostics), and the maintainer explicitly prefers not to add coupling to Effect's Cause API surface for this purpose. Do not flag this pattern as fragile or suggest replacing it with Cause utilities.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

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: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:04.230Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/util/filesystem.ts`), the `Filesystem` utility does NOT expose a `remove` or `unlink` helper. The established repository pattern for auth.json teardown in tests (e.g. `provider.test.ts`, `amazon-bedrock.test.ts`, `workspace-adaptor.test.ts`) is to combine `Filesystem.write` with `node:fs/promises unlink`. Do not flag this mixed usage as inconsistent — it is the correct and intentional pattern.

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 : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

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 `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

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/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:291-304
Timestamp: 2026-04-24T06:50:04.597Z
Learning: In `packages/opencode/src/provider/models.ts`, the `getWithVersion()` function intentionally uses an unbounded `while (true)` retry loop. It only retries when `catalogVersion` changes between the pre- and post-`Data()` read, which is tied to refresh races. The maintainer (Astro-Han) explicitly rejected adding a MAX_RETRIES cap because a hard failure on provider state bootstrap (due to an arbitrary retry limit) is a worse failure mode than retrying until the catalog stabilizes. The loop is expected to self-settle once concurrent writes stop.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:113-179
Timestamp: 2026-04-24T06:50:02.712Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/provider/models.ts`), `PublishModel` and `PublishProvider` intentionally duplicate fields from `Model` and `Provider` with looser optionality. The split is a deliberate behavior boundary: `PublishModel`/`PublishProvider` (with `.passthrough()`) are used for lenient publish-time validation of incoming catalogs, while `Model`/`Provider` are used for strict runtime normalization. Do not flag this duplication as a maintenance burden or suggest extracting a shared base schema — the explicit separation is intentional and tied to the models-refresh reliability path introduced in PR `#211`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

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: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

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

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: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

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 `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

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} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:56.086Z
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: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 126
File: packages/ui/src/theme/context.tsx:11-16
Timestamp: 2026-04-22T09:32:58.310Z
Learning: In Astro-Han/pawwork (`packages/ui/src/theme/context.tsx` and related files), the renaming of localStorage theme keys from `opencode-*` to `pawwork-*` (THEME_ID, COLOR_SCHEME, THEME_CSS_LIGHT, THEME_CSS_DARK) is intentional and should NOT include a migration path from the old keys. Migrating would re-couple PawWork and OpenCode browser storage namespaces, which the PR is explicitly designed to avoid. A reset to the PawWork default theme on upgrade is acceptable by design.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 233
File: packages/desktop-electron/src/main/server.ts:60-60
Timestamp: 2026-04-25T11:52:40.349Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/index.ts`), `ensureLoopbackNoProxy()` (defined at line 551) is called inside `setupApp()` at line 263, which runs synchronously before `initialize()` (line 321) and `spawnLocalServer()` (line 395). It unconditionally upserts `127.0.0.1`, `localhost`, and `::1` into both `process.env.NO_PROXY` and `process.env.no_proxy`. This guarantees that `configureProxyDispatcher(process.env)` in `server.ts` always receives a `process.env` that already excludes loopback from proxying. Do not flag the absence of a loopback-merge inside `configureProxyDispatcher` or `normalizeProxyConfig` — the exclusion is already enforced at a higher layer before those functions are ever called.

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: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:31.757Z
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: 71
File: packages/app/src/components/session/session-status-connections.tsx:146-147
Timestamp: 2026-04-20T14:21:56.373Z
Learning: In the Astro-Han/pawwork repository (SolidJS app), `sync.data.config` is always initialized to `{}` at `packages/app/src/context/global-sync.tsx` line 71 and is never `undefined` at runtime. Non-optional property access like `sync.data.config.plugin` is intentional and consistent with the pattern used in `packages/app/src/components/status-popover-body.tsx` line 243. Do not flag `sync.data.config.plugin` as needing optional chaining.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 102
File: packages/opencode/src/config/agent.ts:108-119
Timestamp: 2026-04-21T16:57:25.580Z
Learning: In `packages/opencode/src/config/agent.ts` (Astro-Han/pawwork), `ConfigPermission.Info` only accepts permission objects or the three action strings `"ask"`, `"allow"`, `"deny"`, and transforms those action strings into `{ "*": action }` before `normalize()` runs. By the time `normalize()` is reached, `configuredPermission` is always either `undefined` or a `Record<string, Rule>` — never a raw arbitrary string. The `Object.assign(permission, configuredPermission)` pattern is therefore safe. Do not flag it as corrupting string permission references.

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`.

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: 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: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:04.230Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/util/filesystem.ts`), the `Filesystem` utility does NOT expose a `remove` or `unlink` helper. The established repository pattern for auth.json teardown in tests (e.g. `provider.test.ts`, `amazon-bedrock.test.ts`, `workspace-adaptor.test.ts`) is to combine `Filesystem.write` with `node:fs/promises unlink`. Do not flag this mixed usage as inconsistent — it is the correct and intentional pattern.

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 : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 `Schema.Defect` instead of `unknown` for defect-like causes in Effect code

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: 234
File: packages/opencode/src/session/export.ts:75-88
Timestamp: 2026-04-25T12:52:36.999Z
Learning: In `packages/opencode/src/session/export.ts` (Astro-Han/pawwork), the `extractReasonFromCause` function intentionally uses a lightweight cast-based inspection of the Cause `reasons` array instead of `Cause.failures()` / `Cause.defects()` utilities. This is a deliberate choice: the function is diagnostic-only (used to populate a best-effort reason string for export diagnostics), and the maintainer explicitly prefers not to add coupling to Effect's Cause API surface for this purpose. Do not flag this pattern as fragile or suggest replacing it with Cause utilities.

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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

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 `Schema.TaggedErrorClass` for typed errors in Effect schemas

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: In `packages/opencode/src/session/prompt.ts` (and the broader Astro-Han/pawwork codebase), `yield* new ErrorClass()` is ONLY valid for classes that extend `Schema.TaggedErrorClass` (which implements Effect's Yieldable interface). Plain `Error` subclasses (e.g. `BlockedLoopError`, `LoopStopError` in prompt.ts, or inline `new Error(...)` instances) are NOT yieldable and MUST be wrapped: `yield* Effect.fail(new PlainError(...))`. Do NOT suggest replacing `yield* Effect.fail(new SomePlainError(...))` with `yield* new SomePlainError(...)` unless the class extends `Schema.TaggedErrorClass`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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 the `tmpdir` function from `fixture/fixture.ts` to create temporary directories for tests with automatic cleanup. Use `await using` syntax to ensure automatic cleanup when the variable goes out of scope.

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.

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:291-304
Timestamp: 2026-04-24T06:50:04.597Z
Learning: In `packages/opencode/src/provider/models.ts`, the `getWithVersion()` function intentionally uses an unbounded `while (true)` retry loop. It only retries when `catalogVersion` changes between the pre- and post-`Data()` read, which is tied to refresh races. The maintainer (Astro-Han) explicitly rejected adding a MAX_RETRIES cap because a hard failure on provider state bootstrap (due to an arbitrary retry limit) is a worse failure mode than retrying until the catalog stabilizes. The loop is expected to self-settle once concurrent writes stop.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:113-179
Timestamp: 2026-04-24T06:50:02.712Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/provider/models.ts`), `PublishModel` and `PublishProvider` intentionally duplicate fields from `Model` and `Provider` with looser optionality. The split is a deliberate behavior boundary: `PublishModel`/`PublishProvider` (with `.passthrough()`) are used for lenient publish-time validation of incoming catalogs, while `Model`/`Provider` are used for strict runtime normalization. Do not flag this duplication as a maintenance burden or suggest extracting a shared base schema — the explicit separation is intentional and tied to the models-refresh reliability path introduced in PR `#211`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:56.086Z
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: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 126
File: packages/ui/src/theme/context.tsx:11-16
Timestamp: 2026-04-22T09:32:58.310Z
Learning: In Astro-Han/pawwork (`packages/ui/src/theme/context.tsx` and related files), the renaming of localStorage theme keys from `opencode-*` to `pawwork-*` (THEME_ID, COLOR_SCHEME, THEME_CSS_LIGHT, THEME_CSS_DARK) is intentional and should NOT include a migration path from the old keys. Migrating would re-couple PawWork and OpenCode browser storage namespaces, which the PR is explicitly designed to avoid. A reset to the PawWork default theme on upgrade is acceptable by design.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 233
File: packages/desktop-electron/src/main/server.ts:60-60
Timestamp: 2026-04-25T11:52:40.349Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/index.ts`), `ensureLoopbackNoProxy()` (defined at line 551) is called inside `setupApp()` at line 263, which runs synchronously before `initialize()` (line 321) and `spawnLocalServer()` (line 395). It unconditionally upserts `127.0.0.1`, `localhost`, and `::1` into both `process.env.NO_PROXY` and `process.env.no_proxy`. This guarantees that `configureProxyDispatcher(process.env)` in `server.ts` always receives a `process.env` that already excludes loopback from proxying. Do not flag the absence of a loopback-merge inside `configureProxyDispatcher` or `normalizeProxyConfig` — the exclusion is already enforced at a higher layer before those functions are ever called.

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: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:31.757Z
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: 71
File: packages/app/src/components/session/session-status-connections.tsx:146-147
Timestamp: 2026-04-20T14:21:56.373Z
Learning: In the Astro-Han/pawwork repository (SolidJS app), `sync.data.config` is always initialized to `{}` at `packages/app/src/context/global-sync.tsx` line 71 and is never `undefined` at runtime. Non-optional property access like `sync.data.config.plugin` is intentional and consistent with the pattern used in `packages/app/src/components/status-popover-body.tsx` line 243. Do not flag `sync.data.config.plugin` as needing optional chaining.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 102
File: packages/opencode/src/config/agent.ts:108-119
Timestamp: 2026-04-21T16:57:25.580Z
Learning: In `packages/opencode/src/config/agent.ts` (Astro-Han/pawwork), `ConfigPermission.Info` only accepts permission objects or the three action strings `"ask"`, `"allow"`, `"deny"`, and transforms those action strings into `{ "*": action }` before `normalize()` runs. By the time `normalize()` is reached, `configuredPermission` is always either `undefined` or a `Record<string, Rule>` — never a raw arbitrary string. The `Object.assign(permission, configuredPermission)` pattern is therefore safe. Do not flag it as corrupting string permission references.

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`.

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: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

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} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

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.

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 the `tmpdir` function from `fixture/fixture.ts` to create temporary directories for tests with automatic cleanup. Use `await using` syntax to ensure automatic cleanup when the variable goes out of scope.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/session/export.ts:75-88
Timestamp: 2026-04-25T12:52:36.999Z
Learning: In `packages/opencode/src/session/export.ts` (Astro-Han/pawwork), the `extractReasonFromCause` function intentionally uses a lightweight cast-based inspection of the Cause `reasons` array instead of `Cause.failures()` / `Cause.defects()` utilities. This is a deliberate choice: the function is diagnostic-only (used to populate a best-effort reason string for export diagnostics), and the maintainer explicitly prefers not to add coupling to Effect's Cause API surface for this purpose. Do not flag this pattern as fragile or suggest replacing it with Cause utilities.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:04.230Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/util/filesystem.ts`), the `Filesystem` utility does NOT expose a `remove` or `unlink` helper. The established repository pattern for auth.json teardown in tests (e.g. `provider.test.ts`, `amazon-bedrock.test.ts`, `workspace-adaptor.test.ts`) is to combine `Filesystem.write` with `node:fs/promises unlink`. Do not flag this mixed usage as inconsistent — it is the correct and intentional pattern.

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 : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 `Schema.Defect` instead of `unknown` for defect-like causes in Effect code

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: 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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

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} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

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 `Schema.TaggedErrorClass` for typed errors in Effect schemas

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:291-304
Timestamp: 2026-04-24T06:50:04.597Z
Learning: In `packages/opencode/src/provider/models.ts`, the `getWithVersion()` function intentionally uses an unbounded `while (true)` retry loop. It only retries when `catalogVersion` changes between the pre- and post-`Data()` read, which is tied to refresh races. The maintainer (Astro-Han) explicitly rejected adding a MAX_RETRIES cap because a hard failure on provider state bootstrap (due to an arbitrary retry limit) is a worse failure mode than retrying until the catalog stabilizes. The loop is expected to self-settle once concurrent writes stop.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:113-179
Timestamp: 2026-04-24T06:50:02.712Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/provider/models.ts`), `PublishModel` and `PublishProvider` intentionally duplicate fields from `Model` and `Provider` with looser optionality. The split is a deliberate behavior boundary: `PublishModel`/`PublishProvider` (with `.passthrough()`) are used for lenient publish-time validation of incoming catalogs, while `Model`/`Provider` are used for strict runtime normalization. Do not flag this duplication as a maintenance burden or suggest extracting a shared base schema — the explicit separation is intentional and tied to the models-refresh reliability path introduced in PR `#211`.

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: In `packages/opencode/src/session/prompt.ts` (and the broader Astro-Han/pawwork codebase), `yield* new ErrorClass()` is ONLY valid for classes that extend `Schema.TaggedErrorClass` (which implements Effect's Yieldable interface). Plain `Error` subclasses (e.g. `BlockedLoopError`, `LoopStopError` in prompt.ts, or inline `new Error(...)` instances) are NOT yieldable and MUST be wrapped: `yield* Effect.fail(new PlainError(...))`. Do NOT suggest replacing `yield* Effect.fail(new SomePlainError(...))` with `yield* new SomePlainError(...)` unless the class extends `Schema.TaggedErrorClass`.

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 `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

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: Astro-Han
Repo: Astro-Han/pawwork PR: 73
File: packages/opencode/src/cli/cmd/tui/context/sync.tsx:486-489
Timestamp: 2026-04-20T17:03:40.214Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/cli/cmd/tui/context/sync.tsx`), `sync.ready` returning `true` when `process.env.OPENCODE_FAST_BOOT` is set is intentional. The plugin-facing data properties `state.config` (initialized to `{}`) and `state.provider` (initialized to `[]`) expose safe-empty defaults, so they are safe to access before bootstrap completes. Do not flag these as needing null-guards or conditional patterns to match `vcs` — the difference is intentional because `vcs` starts as `undefined` while the others have initialized defaults. Changing this would alter the plugin API contract without a concrete failing case.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 264
File: packages/opencode/test/session/diagnostics.test.ts:313-318
Timestamp: 2026-04-27T10:08:52.777Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/session/diagnostics.ts`, PR `#264`), `SessionDiagnostics.LoopAction` is a TypeScript string literal union type (`"observe" | "block" | "stop"`), NOT a runtime enum. There is no runtime form to introspect via `Object.values()`. The test pattern `const all: SessionDiagnostics.LoopAction[] = ["observe", "block", "stop"]; expect(all).toHaveLength(3)` is intentional and correct — it provides compile-time exhaustiveness via the type annotation. Do NOT suggest replacing this with `Object.values()` introspection or flag the runtime length check as insufficient.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 264
File: packages/opencode/src/session/diagnostics.ts:255-279
Timestamp: 2026-04-27T08:27:40.791Z
Learning: In `packages/opencode/src/session/diagnostics.ts` (PR `#264`, issue `#229`), target-level loop detection is intentionally tool-scoped. The `real` filter includes `r.tool === input.tool` and target signature keys are formatted as `target:${tool}:${targetHash}`. Cross-tool retries on the same URL/path/query are considered legitimate exploration (e.g., webfetch failed → switch to a different tool), NOT a stuck loop. Only same-tool + same-target accumulation counts toward block/stop. Do NOT suggest removing the tool scope from target signature keys or the `real` filter.

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/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : Prefer Effect-aware helpers from `fixture/fixture.ts` over building manual runtimes in tests: use `tmpdirScoped()` for scoped temp directories, `provideInstance(dir)(effect)` for low-level binding without directory creation, `provideTmpdirInstance(...)` for single temp instance binding, or `provideTmpdirServer(...)` for tests that also need the test LLM server.

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 (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: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/test/session/diagnostics.test.ts:313-318
Timestamp: 2026-04-27T10:08:52.777Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/session/diagnostics.ts`, PR `#264`), `SessionDiagnostics.LoopAction` is a TypeScript string literal union type (`"observe" | "block" | "stop"`), NOT a runtime enum. There is no runtime form to introspect via `Object.values()`. The test pattern `const all: SessionDiagnostics.LoopAction[] = ["observe", "block", "stop"]; expect(all).toHaveLength(3)` is intentional and correct — it provides compile-time exhaustiveness via the type annotation. Do NOT suggest replacing this with `Object.values()` introspection or flag the runtime length check as insufficient.

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: 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} : Define `const it = testEffect(...)` near the top of the test file and keep the test body inside `Effect.gen(function* () { ... })`. Yield services directly with `yield* MyService.Service` or `yield* MyTool`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 126
File: packages/opencode/test/provider/provider.test.ts:64-85
Timestamp: 2026-04-22T09:32:54.556Z
Learning: In `packages/opencode/test/provider/provider.test.ts`, the file intentionally uses AppRuntime-based async helpers (`run`, `list`, `getProvider`, etc.) rather than `testEffect(...)` for all tests. Converting individual tests to `testEffect` while leaving the rest on the async pattern would create internal inconsistency. A full harness migration of this file is the right approach if the pattern needs to change, but that should be a separate PR.

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.

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/packages/app/src/testing/**/*.ts : Test-only hooks must be inert unless explicitly enabled and should not add normal-runtime listeners, reactive subscriptions, or per-update allocations

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 the `tmpdir` function from `fixture/fixture.ts` to create temporary directories for tests with automatic cleanup. Use `await using` syntax to ensure automatic cleanup when the variable goes out of scope.

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.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 247
File: packages/ui/src/components/message-part.tsx:1322-1324
Timestamp: 2026-04-26T16:34:54.895Z
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: 224
File: packages/app/src/i18n/zh.ts:0-0
Timestamp: 2026-04-24T17:08:44.294Z
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: 233
File: packages/desktop-electron/src/main/server.ts:60-60
Timestamp: 2026-04-25T11:52:40.349Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/index.ts`), `ensureLoopbackNoProxy()` (defined at line 551) is called inside `setupApp()` at line 263, which runs synchronously before `initialize()` (line 321) and `spawnLocalServer()` (line 395). It unconditionally upserts `127.0.0.1`, `localhost`, and `::1` into both `process.env.NO_PROXY` and `process.env.no_proxy`. This guarantees that `configureProxyDispatcher(process.env)` in `server.ts` always receives a `process.env` that already excludes loopback from proxying. Do not flag the absence of a loopback-merge inside `configureProxyDispatcher` or `normalizeProxyConfig` — the exclusion is already enforced at a higher layer before those functions are ever called.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 203
File: packages/app/e2e/sidebar/sidebar-session-links.spec.ts:34-55
Timestamp: 2026-04-24T00:02:53.315Z
Learning: In Astro-Han/pawwork E2E tests (`packages/app/e2e/**/*.spec.ts`), `project.trackDirectory()` and `project.trackSession()` cannot be called before `project.open()` — the `project` fixture throws until `open()` initializes its internal state. The correct pattern is: call `project.trackSession(sessionID)` from inside the `beforeGoto` callback (where state already exists), call `project.trackDirectory(directory)` and cross-workspace `project.trackSession(id, directory)` immediately after `project.open()` returns, and rely on explicit `finally` cleanup (e.g. `cleanupSession` / `cleanupTestProject`) for any resources created before `open()` that cannot yet be tracked via the fixture.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:31.757Z
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: 71
File: packages/app/src/components/session/session-status-connections.tsx:146-147
Timestamp: 2026-04-20T14:21:56.373Z
Learning: In the Astro-Han/pawwork repository (SolidJS app), `sync.data.config` is always initialized to `{}` at `packages/app/src/context/global-sync.tsx` line 71 and is never `undefined` at runtime. Non-optional property access like `sync.data.config.plugin` is intentional and consistent with the pattern used in `packages/app/src/components/status-popover-body.tsx` line 243. Do not flag `sync.data.config.plugin` as needing optional chaining.

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

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:56.086Z
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: 126
File: packages/ui/src/theme/context.tsx:11-16
Timestamp: 2026-04-22T09:32:58.310Z
Learning: In Astro-Han/pawwork (`packages/ui/src/theme/context.tsx` and related files), the renaming of localStorage theme keys from `opencode-*` to `pawwork-*` (THEME_ID, COLOR_SCHEME, THEME_CSS_LIGHT, THEME_CSS_DARK) is intentional and should NOT include a migration path from the old keys. Migrating would re-couple PawWork and OpenCode browser storage namespaces, which the PR is explicitly designed to avoid. A reset to the PawWork default theme on upgrade is acceptable by design.

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: 102
File: packages/opencode/src/config/agent.ts:108-119
Timestamp: 2026-04-21T16:57:25.580Z
Learning: In `packages/opencode/src/config/agent.ts` (Astro-Han/pawwork), `ConfigPermission.Info` only accepts permission objects or the three action strings `"ask"`, `"allow"`, `"deny"`, and transforms those action strings into `{ "*": action }` before `normalize()` runs. By the time `normalize()` is reached, `configuredPermission` is always either `undefined` or a `Record<string, Rule>` — never a raw arbitrary string. The `Object.assign(permission, configuredPermission)` pattern is therefore safe. Do not flag it as corrupting string permission references.

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`.

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 `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.

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: In `packages/opencode/src/session/prompt.ts` (and the broader Astro-Han/pawwork codebase), `yield* new ErrorClass()` is ONLY valid for classes that extend `Schema.TaggedErrorClass` (which implements Effect's Yieldable interface). Plain `Error` subclasses (e.g. `BlockedLoopError`, `LoopStopError` in prompt.ts, or inline `new Error(...)` instances) are NOT yieldable and MUST be wrapped: `yield* Effect.fail(new PlainError(...))`. Do NOT suggest replacing `yield* Effect.fail(new SomePlainError(...))` with `yield* new SomePlainError(...)` unless the class extends `Schema.TaggedErrorClass`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 222
File: packages/desktop-electron/src/main/index.ts:686-692
Timestamp: 2026-04-24T13:03:10.835Z
Learning: In `packages/desktop-electron/src/main/index.ts`, the `checkForUpdates()` function intentionally uses recursive self-invocation for the "Retry" path in the update-check failure dialog. This is mandated by the v5.2 design spec (`#213`): "Await the retry recursion and log any rejection so support can see repeated failures." Because retries are user-paced (require a button click), all prior async frames have already unwound through microtasks before the next attempt, so there is no stack/frame-nesting problem in practice. Do not suggest refactoring this to an iterative loop.

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/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : Avoid custom `ManagedRuntime`, `attach(...)`, or ad hoc `run(...)` wrappers in Effect tests when `testEffect(...)` already provides the runtime.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/opencode/src/session/export.ts:75-88
Timestamp: 2026-04-25T12:52:36.999Z
Learning: In `packages/opencode/src/session/export.ts` (Astro-Han/pawwork), the `extractReasonFromCause` function intentionally uses a lightweight cast-based inspection of the Cause `reasons` array instead of `Cause.failures()` / `Cause.defects()` utilities. This is a deliberate choice: the function is diagnostic-only (used to populate a best-effort reason string for export diagnostics), and the maintainer explicitly prefers not to add coupling to Effect's Cause API surface for this purpose. Do not flag this pattern as fragile or suggest replacing it with Cause utilities.

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: 208
File: packages/app/e2e/app/composer-parity.spec.ts:0-0
Timestamp: 2026-04-24T05:48:36.205Z
Learning: In Astro-Han/pawwork `packages/app/src/components/prompt-input.tsx`, the Model chip trigger button carries `data-action="prompt-model"` (around line 1187) and the Variant chip trigger button carries `data-action="prompt-model-variant"` (around line 1231), both set via `triggerProps`. These are therefore already captured by any `[data-action]` selector sweep in E2E tests and do not need a separate `[data-component]` query to be included in parity assertions — though unioning both is kept as belt-and-suspenders in `collectBarSet`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 93
File: packages/opencode/test/server/cors-middleware.test.ts:15-23
Timestamp: 2026-04-21T12:14:30.524Z
Learning: In `packages/opencode/test/server/cors-middleware.test.ts` (and similar Hono-based test files), `app.request(...)` on the Hono `Hono` app type returns `Promise<Response> | Response` — a union that includes a non-PromiseLike branch. `Effect.promise(...)` requires a `PromiseLike`, so wrapping with `Promise.resolve(app.request(...))` is necessary to normalize the union type. Removing the wrapper causes a TS2322 typecheck error in `packages/opencode`.

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: 234
File: packages/opencode/src/share/session.ts:27-27
Timestamp: 2026-04-25T12:52:47.074Z
Learning: In `packages/opencode/src/share/session.ts`, the local `ensureEnabled` closure is intentionally duplicated from `ShareRuntime.ensureEnabled` in `runtime.ts`. Using the shared `ShareRuntime.ensureEnabled` effect directly would leak `CloudShareGate` back into the `R` (requirement) type of `share`, `unshare`, and `create`, because the shared effect re-yields the service rather than capturing an already-resolved gate reference. The current pattern resolves `gate` once at the top of the outer `Effect.gen` and then closes over it in a local `ensureEnabled`, keeping the inner effects' requirement types clean. A comment in the file points to `runtime.ts` to make the intentional duplication discoverable. The real fix would be refactoring `ensureEnabled` to accept a gate parameter, but that change is larger than the DRY benefit warrants. Do not flag this duplication as a maintenance issue.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 234
File: packages/desktop-electron/src/main/ipc.ts:238-263
Timestamp: 2026-04-25T12:52:32.462Z
Learning: In Astro-Han/pawwork (`packages/desktop-electron/src/main/ipc.ts`), `deps.getServerReadyData()` (backed by `serverReady.promise` in `index.ts`) resolves once at server startup and remains settled; it is not expected to reject in practice. Do not flag the absence of a try-catch around it in the `export-session` IPC handler — the network/fetch layer in `server-client.ts` already has a 10-second AbortController timeout and returns a typed `{ok: false, error}` payload, covering the real failure modes.

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 : In `Effect.gen` / `Effect.fn`, prefer `yield* new MyError(...)` over `yield* Effect.fail(new MyError(...))` for direct early-failure branches

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 `Schema.Defect` instead of `unknown` for defect-like causes in Effect code

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: 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 : For background loops or scheduled tasks, use `Effect.repeat` or `Effect.schedule` with `Effect.forkScoped` in the layer definition

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 `Schema.TaggedErrorClass` for typed errors in Effect schemas

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 198
File: packages/ui/src/theme/themes/pawwork.json:32-33
Timestamp: 2026-04-23T17:02:39.474Z
Learning: In Astro-Han/pawwork, `#FF5910` is the locked PawWork brand orange used for `button-primary-base` (and `--accent-brand` in `index.css`, theme token `interactive`/`primary`). The `text-on-interactive-base: `#FFFFFF`` on `button-primary-base: `#FF5910`` combination produces a contrast ratio of ~3.14:1. This intentionally fails WCAG AA normal-text (4.5:1) but passes AA non-text (SC 1.4.11, 3:1) and AA large-text (SC 1.4.3, 3:1). The tradeoff is accepted for brand consistency; do NOT flag this contrast pair as a WCAG violation in future reviews. If a specific surface requires stricter contrast, it should be addressed individually (e.g., larger text, ghost variant, outline button) rather than changing the palette.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:291-304
Timestamp: 2026-04-24T06:50:04.597Z
Learning: In `packages/opencode/src/provider/models.ts`, the `getWithVersion()` function intentionally uses an unbounded `while (true)` retry loop. It only retries when `catalogVersion` changes between the pre- and post-`Data()` read, which is tied to refresh races. The maintainer (Astro-Han) explicitly rejected adding a MAX_RETRIES cap because a hard failure on provider state bootstrap (due to an arbitrary retry limit) is a worse failure mode than retrying until the catalog stabilizes. The loop is expected to self-settle once concurrent writes stop.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 211
File: packages/opencode/src/provider/models.ts:113-179
Timestamp: 2026-04-24T06:50:02.712Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/provider/models.ts`), `PublishModel` and `PublishProvider` intentionally duplicate fields from `Model` and `Provider` with looser optionality. The split is a deliberate behavior boundary: `PublishModel`/`PublishProvider` (with `.passthrough()`) are used for lenient publish-time validation of incoming catalogs, while `Model`/`Provider` are used for strict runtime normalization. Do not flag this duplication as a maintenance burden or suggest extracting a shared base schema — the explicit separation is intentional and tied to the models-refresh reliability path introduced in PR `#211`.

Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:04.230Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/util/filesystem.ts`), the `Filesystem` utility does NOT expose a `remove` or `unlink` helper. The established repository pattern for auth.json teardown in tests (e.g. `provider.test.ts`, `amazon-bedrock.test.ts`, `workspace-adaptor.test.ts`) is to combine `Filesystem.write` with `node:fs/promises unlink`. Do not flag this mixed usage as inconsistent — it is the correct and intentional pattern.