fix(session): sync session edge fixes#308
Merged
Merged
Conversation
Contributor
📝 WalkthroughWalkthroughRefactors shell startup, interrupt and cancellation flows across runner and prompt layers; changes shell argv/cwd handling; adds optional Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant Prompt
participant Runner
participant ShellFiber
participant Sessions
Client->>Prompt: start shell (cwd, args)
Prompt->>Runner: startShell()
Runner->>ShellFiber: fork shell effect
ShellFiber-->>Sessions: emit stdout chunk (part)
Sessions-->>Prompt: updatePart(part) (awaited)
Client->>Runner: request cancel
Runner->>Runner: complete shell.cancelled deferred
Runner->>ShellFiber: interrupt fiber
alt interrupt-shaped exit
Runner->>Runner: if onInterrupt provided -> run onInterrupt
Runner-->>Client: onInterrupt result or Cancelled error
else non-interrupt failure
Runner-->>Client: propagate original failure
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested labels
Poem
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Code Review
This pull request enhances shell execution by introducing an explicit cancellation state in the runner and improving directory change handling within shell commands. It also adds an optional query parameter to the LSP tool's workspaceSymbol operation and updates the session compaction template for improved structure. Furthermore, new tests verify shell cancellation behavior, directory persistence, and the omission of optional fields in session routes. I have no feedback to provide.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
packages/opencode/src/session/prompt.ts (1)
964-990:⚠️ Potential issue | 🟠 MajorDon't expose the injected cwd as
$1to the user's command.For
bash -c/zsh -c, the extra argv becomes the shell's positional parameters. Becauseeval ${JSON.stringify(input.command)}runs in that same shell,$1,$@, and$#now include the injected cwd, which changes command behavior.Suggested fix
zsh: { args: [ "-l", "-c", ` [[ -f ~/.zshenv ]] && source ~/.zshenv >/dev/null 2>&1 || true [[ -f "\${ZDOTDIR:-$HOME}/.zshrc" ]] && source "\${ZDOTDIR:-$HOME}/.zshrc" >/dev/null 2>&1 || true - cd -- "$1" + __pw_cwd="$1" + shift + cd -- "$__pw_cwd" eval ${JSON.stringify(input.command)} `, "pawwork", cwd, ], }, bash: { args: [ "-l", "-c", ` shopt -s expand_aliases [[ -f ~/.bashrc ]] && source ~/.bashrc >/dev/null 2>&1 || true - cd -- "$1" + __pw_cwd="$1" + shift + cd -- "$__pw_cwd" eval ${JSON.stringify(input.command)} `, "pawwork", cwd, ], },🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@packages/opencode/src/session/prompt.ts` around lines 964 - 990, The current zsh and bash blocks pass cwd as an extra argv (third item) so the invoked shell sees it as $1 and thus contaminates positional parameters used by eval ${JSON.stringify(input.command)}; remove the injected cwd argv and instead hard-code the working directory into the script (e.g. cd -- ${JSON.stringify(cwd)} or cd -- "$PWD_FROM_INPUT" safely quoted) inside the multiline command before eval; update both the zsh and bash argument arrays (the objects named zsh and bash containing args and eval ${JSON.stringify(input.command)}) to omit the trailing cwd entry and place the cwd via a safely quoted literal in the here-script.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/opencode/src/effect/runner.ts`:
- Around line 170-175: The current cancellation branch treats mixed
interrupt+failure causes as pure cancellations; change the condition so it only
matches interrupt-only causes (use Cause.hasInterruptsOnly(exit.cause) for both
checks) and let mixed causes fall through to failure handling by returning
Effect.failCause(exit.cause) instead of collapsing them into Cancelled; update
the block around Deferred.isDone(cancelled), the existing use of
Cause.hasInterrupts/Cause.hasDies, and the return paths involving onInterrupt,
Effect.die(new Cancelled()), and ensure a fallback to
Effect.failCause(exit.cause) for non-interrupt-only causes so that functions
like the runner properly surface typed failures.
In `@packages/opencode/test/session/prompt-effect.test.ts`:
- Around line 1272-1294: The test may not exercise the login-shell branch
because prompt.shell() only uses the modified -l -c path when Shell.preferred()
returns bash or zsh; update the test (in the prompt-effect.test around the
unix(...) case) to force a login shell or skip when bash/zsh aren't available:
either set the environment variable SHELL to a known login shell (e.g.,
/bin/bash or /bin/zsh) before calling prompt.shell()/boot(), or call
Shell.preferred() (or detect availability) and skip the test unless bash or zsh
is present; reference the prompt.shell call and
Shell.preferred/boot/run/assertNotBusy to locate where to inject the env
override or conditional skip.
---
Outside diff comments:
In `@packages/opencode/src/session/prompt.ts`:
- Around line 964-990: The current zsh and bash blocks pass cwd as an extra argv
(third item) so the invoked shell sees it as $1 and thus contaminates positional
parameters used by eval ${JSON.stringify(input.command)}; remove the injected
cwd argv and instead hard-code the working directory into the script (e.g. cd --
${JSON.stringify(cwd)} or cd -- "$PWD_FROM_INPUT" safely quoted) inside the
multiline command before eval; update both the zsh and bash argument arrays (the
objects named zsh and bash containing args and eval
${JSON.stringify(input.command)}) to omit the trailing cwd entry and place the
cwd via a safely quoted literal in the here-script.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: a8cf3b47-bc4b-4557-be03-d4d841e7883f
⛔ Files ignored due to path filters (1)
packages/opencode/test/tool/__snapshots__/parameters.test.ts.snapis excluded by!**/*.snap
📒 Files selected for processing (9)
packages/opencode/src/effect/runner.tspackages/opencode/src/session/compaction.tspackages/opencode/src/session/prompt.tspackages/opencode/src/tool/lsp.tspackages/opencode/src/tool/lsp.txtpackages/opencode/test/effect/runner.test.tspackages/opencode/test/server/global-session-list.test.tspackages/opencode/test/session/prompt-effect.test.tspackages/opencode/test/tool/lsp.test.ts
4228a96 to
3f1a915
Compare
Owner
Author
|
Handled the outside-diff cwd argv finding: bash/zsh login shell scripts no longer pass cwd as shell argv, so user commands do not see it as |
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/opencode/test/server/global-session-list.test.ts`:
- Around line 236-237: The tests access body[0] and globalBody[0] without first
asserting the JSON response is a non-empty array; add explicit non-empty array
assertions before any indexing to produce clearer failures—e.g., assert
Array.isArray(body) and body.length > 0 (or use
expect(body).toBeInstanceOf(Array) and expect(body.length).toBeGreaterThan(0))
immediately after const body = (await response.json())... and do the same for
globalBody at the other occurrence (lines referenced around the current body[0]
and the second instance), then proceed to index into body[0]/globalBody[0].
- Around line 224-257: The test uses Effect.promise(async () => ...) inside
it.live but repo convention requires Effect.gen(function* () { ... }) style;
update the "session routes omit undefined optional fields" test to use
Effect.gen generator syntax for the it.live body (replace Effect.promise(async
() => { ... }) with Effect.gen(function* () { ... })) and keep all existing
await/async operations converted to yield where appropriate so the test uses the
Effect-based flows (refer to symbols it.live and Effect.gen in the test).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 9b7ac140-477c-43db-838d-ed6261943b57
⛔ Files ignored due to path filters (1)
packages/opencode/test/tool/__snapshots__/parameters.test.ts.snapis excluded by!**/*.snap
📒 Files selected for processing (9)
packages/opencode/src/effect/runner.tspackages/opencode/src/session/compaction.tspackages/opencode/src/session/prompt.tspackages/opencode/src/tool/lsp.tspackages/opencode/src/tool/lsp.txtpackages/opencode/test/effect/runner.test.tspackages/opencode/test/server/global-session-list.test.tspackages/opencode/test/session/prompt-effect.test.tspackages/opencode/test/tool/lsp.test.ts
3f1a915 to
b36ec85
Compare
Contributor
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
packages/opencode/src/session/compaction.ts (1)
40-69: 🧹 Nitpick | 🔵 TrivialLGTM! Clear template boundaries improve LLM instruction following.
The
<template>...</template>wrapper clarifies the exact structure the model should output, and the explicit "do not include the tags" instruction is clear. Modern LLMs handle these delimiters well.Optional: Defensive validation
If you observe tag leakage in practice, you could add a defensive strip in
summaryText():function summaryText(message: MessageV2.WithParts) { const text = message.parts .filter((part): part is MessageV2.TextPart => part.type === "text") .map((part) => part.text.trim()) .filter(Boolean) .join("\n\n") .trim() + .replace(/<\/?template>/g, '') return text || undefined }However, this is not necessary unless the model actually produces the tags in responses.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@packages/opencode/src/session/compaction.ts` around lines 40 - 69, Add a defensive strip in summaryText() to remove any literal "<template>" and "</template>" tags that might leak into model output even though SUMMARY_TEMPLATE defines the expected format; locate the SUMMARY_TEMPLATE constant and implement a small sanitization step inside summaryText() that trims whitespace and strips a single outer "<template>...<\/template>" wrapper (e.g., via a simple startsWith/endsWith check or a safe regex) before further processing so downstream code never sees the tags.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@packages/opencode/src/session/compaction.ts`:
- Around line 40-69: Add a defensive strip in summaryText() to remove any
literal "<template>" and "</template>" tags that might leak into model output
even though SUMMARY_TEMPLATE defines the expected format; locate the
SUMMARY_TEMPLATE constant and implement a small sanitization step inside
summaryText() that trims whitespace and strips a single outer
"<template>...<\/template>" wrapper (e.g., via a simple startsWith/endsWith
check or a safe regex) before further processing so downstream code never sees
the tags.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 6dfa02c1-3549-44b6-a765-f5a930f50e65
📒 Files selected for processing (2)
packages/opencode/src/session/compaction.tspackages/opencode/test/server/global-session-list.test.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)
- GitHub Check: unit-windows-desktop
- GitHub Check: unit-windows-opencode-server-tools
- GitHub Check: unit-windows-app
- GitHub Check: unit-windows-opencode-config-project
- GitHub Check: unit-windows-opencode-session
- GitHub Check: unit-opencode
🧰 Additional context used
📓 Path-based instructions (2)
packages/opencode/**/*.ts
📄 CodeRabbit inference engine (packages/opencode/AGENTS.md)
packages/opencode/**/*.ts: UseEffect.gen(function* () { ... })for Effect composition
UseEffect.fn("Domain.method")for named/traced effects andEffect.fnUntracedfor internal helpers; these accept pipeable operators as extra arguments to avoid unnecessary outer.pipe()wrappers
UseEffect.callbackfor callback-based APIs
PreferDateTime.nowAsDateovernew Date(yield* Clock.currentTimeMillis)when you need aDatein Effect code
UseSchema.Classfor multi-field data in Effect schemas
Use branded schemas (Schema.brand) for single-value types in Effect
UseSchema.TaggedErrorClassfor typed errors in Effect schemas
UseSchema.Defectinstead ofunknownfor defect-like causes in Effect code
InEffect.gen/Effect.fn, preferyield* new MyError(...)overyield* Effect.fail(new MyError(...))for direct early-failure branches
UsemakeRuntimefromsrc/effect/run-service.tsfor all services; it returns{ runPromise, runFork, runCallback }backed by a sharedmemoMapthat deduplicates layers
UseInstanceStatefromsrc/effect/instance-state.tsfor per-directory or per-project state that needs per-instance cleanup; do work directly in theInstanceState.makeclosure whereScopedCachehandles run-once semantics
UseEffect.addFinalizerorEffect.acquireReleaseinside theInstanceState.makeclosure for cleanup (subscriptions, process teardown, etc.)
UseEffect.forkScopedinside theInstanceState.makeclosure for background stream consumers — the fiber is interrupted when the instance is disposed
PreferFileSystem.FileSysteminstead of rawfs/promisesfor effectful file I/O in Effect services
PreferChildProcessSpawner.ChildProcessSpawnerwithChildProcess.make(...)instead of custom process wrappers in Effect services
PreferHttpClient.HttpClientinstead of rawfetchin Effect services
PreferPath.Path,Config,Clock, andDateTimeservices when those concerns are already inside Effect code
For backgroun...
Files:
packages/opencode/test/server/global-session-list.test.tspackages/opencode/src/session/compaction.ts
packages/opencode/test/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (packages/opencode/test/AGENTS.md)
packages/opencode/test/**/*.test.{ts,tsx}: Use thetmpdirfunction fromfixture/fixture.tsto create temporary directories for tests with automatic cleanup. Useawait usingsyntax to ensure automatic cleanup when the variable goes out of scope.
When using thetmpdirfunction with git repository support, pass thegit: trueoption to initialize a git repo with a root commit.
Use theconfigoption intmpdirto write anopencode.jsonconfig file during test setup by passing a partial Config.Info object.
Use theinitoption intmpdirto define custom setup functions that can return extra data accessible viatmp.extra, and use thedisposeoption for custom cleanup logic.
UsetestEffect(...)fromtest/lib/effect.tsfor tests that exercise Effect services or Effect-based workflows.
Useit.effect(...)when the test should run withTestClockandTestConsole. Useit.live(...)when the test depends on real time, filesystem mtimes, child processes, git, locks, or other live OS behavior.
Prefer Effect-aware helpers fromfixture/fixture.tsover building manual runtimes in tests: usetmpdirScoped()for scoped temp directories,provideInstance(dir)(effect)for low-level binding without directory creation,provideTmpdirInstance(...)for single temp instance binding, orprovideTmpdirServer(...)for tests that also need the test LLM server.
Defineconst it = testEffect(...)near the top of the test file and keep the test body insideEffect.gen(function* () { ... }). Yield services directly withyield* MyService.Serviceoryield* MyTool.
Avoid customManagedRuntime,attach(...), or ad hocrun(...)wrappers in Effect tests whentestEffect(...)already provides the runtime.
When a test needs instance-local state, preferprovideTmpdirInstance(...)orprovideInstance(...)over manualInstance.provide(...)inside Promise-style tests.
Files:
packages/opencode/test/server/global-session-list.test.ts
🧠 Learnings (40)
📓 Common learnings
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/edit.ts:35-45
Timestamp: 2026-04-28T04:38:11.727Z
Learning: In `packages/opencode/src/tool/edit.ts` (Astro-Han/pawwork, PR `#270`), the module-scoped `Map<string, Semaphore.Semaphore>` (`locks`) and `lock(filePath)` helper are intentionally left as a global, never-cleaned registry. PR `#270` is a pure upstream-sync graft and mixing in a bugfix would drift the diff from the upstream baseline. The fix (moving per-file semaphores into `InstanceState`/`ScopedCache` for per-instance lifecycle management) is tracked as a follow-up to land in its own PR or be reported upstream. Do NOT re-flag the absence of InstanceState wiring for the lock map in this file until the follow-up PR is opened.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/lsp.ts:23-32
Timestamp: 2026-04-28T07:28:14.317Z
Learning: In `packages/opencode/src/tool/lsp.ts` (Astro-Han/pawwork, PR `#270`), the `Parameters` schema requires `line` and `character` for all operations, including `workspaceSymbol` and `documentSymbol` which never use coordinates. This matches the upstream `dev:packages/opencode/src/tool/lsp.ts:23-32` baseline exactly — both fields are declared as required `Schema.Number` with `>= 1` checks. The fix (per-operation schema split, or making `line`/`character` optional with handler-side presence validation for operations that need them like `goToDefinition`/`findReferences`) is deferred to a follow-up PR or upstream report to avoid mixing refactor + bug-fix intents and drifting the diff from the upstream baseline. Do NOT re-flag the required coordinates on `workspaceSymbol`/`documentSymbol` in upstream-sync PRs; flag it only in a PawWork-authored PR that directly touches `lsp.ts` parameter validation.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/agent.ts:23-27
Timestamp: 2026-04-28T04:38:11.771Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/tool/agent.ts`), the `subagent_session_id` field in the `Parameters` schema accepts any `Schema.String` rather than a branded `SessionID`. This is inherited upstream behavior (adopted in PR `#270`, an upstream-sync graft of upstream PR `#23244`). The fix — validating `subagent_session_id` as a `SessionID` brand up front so malformed/typo'd IDs fail explicitly rather than silently forking a new subagent session — is intentionally deferred to a follow-up PR or upstream report. Do NOT re-flag this as a blocking issue in PR `#270` or in future upstream-sync PRs that carry the same schema; flag it only in a PawWork-authored PR that touches `agent.ts` parameter validation.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/test/session/subagent-lifecycle-integration.test.ts:41-47
Timestamp: 2026-04-28T11:24:35.312Z
Learning: In `packages/opencode/test/session/subagent-lifecycle-integration.test.ts` (Astro-Han/pawwork, PR `#287`), the test suite intentionally uses a manual `run` helper (`Effect.runPromise(program.pipe(Effect.provide(Layer.mergeAll(SubagentRun.defaultLayer, Session.defaultLayer)), Effect.orDie))`) and raw `bun:test` test cases rather than the `testEffect(...)` harness. All 27 lifecycle tests pass with this pattern. Migration to `testEffect` + `it.live(...)` is deferred to a dedicated test-harness sweep PR to avoid fixture drift before merge. Do NOT re-flag the manual `Effect.runPromise` runner in this file as needing harness migration until that sweep PR lands.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/patch/index.ts:337-346
Timestamp: 2026-04-28T04:38:05.946Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/patch/index.ts`), the BOM-transition surfacing gap — where `Bom.split` strips BOM before building `unified_diff`/`new_content` but `Bom.join` later re-attaches BOM on disk write, meaning BOM changes are not reflected in the diff payload — is intentionally deferred. PR `#270` is an upstream-sync graft; fixing the issue here would mix refactor + bugfix intents and drift the diff from the upstream baseline needed for clean future grafts. A dedicated follow-up PR (or upstream report) will address this. Do NOT re-flag the missing BOM-change surfacing in `ApplyPatchFileUpdate`/`ApplyPatchFileChange` as a blocking issue in PR `#270` or in future sync PRs that carry the same upstream baseline.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:172-175
Timestamp: 2026-04-28T04:56:18.533Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), the `files dies on nonexistent directory` test hardcodes `/tmp/nonexistent-dir-12345` as the missing-directory path. This is upstream-inherited behaviour adopted wholesale via the graft strategy (`project_upstream_strategy.md`). The fix — replacing the hardcoded path with a platform-neutral guaranteed-nonexistent child path derived from the `tmpdir` fixture — is intentionally deferred to a follow-up PR or upstream report, to avoid mixing bugfix + refactor intents and drifting the diff from the upstream baseline future syncs need. Do NOT re-flag the hardcoded `/tmp/nonexistent-dir-12345` path in this file as a blocking or actionable issue until the follow-up PR lands.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/edit.ts:48-48
Timestamp: 2026-04-28T08:14:31.436Z
Learning: In `packages/opencode/src/tool/edit.ts` (Astro-Han/pawwork), the `filePath` schema description (`"The absolute path to the file to modify"`) is upstream-inherited from `dev:packages/opencode/src/tool/edit.ts:48`. The runtime actually accepts relative paths (resolved via `Instance.directory` at lines 79-81), but the description fix is intentionally deferred to a single PawWork-authored description-cleanup PR that will also cover the identical mismatch in `packages/opencode/src/tool/write.ts:24`. Do NOT re-flag the too-narrow `filePath` description in upstream-sync PRs; flag it only in the dedicated description-cleanup PR.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/prompt.ts:108-169
Timestamp: 2026-04-27T10:33:12.228Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/session/prompt.ts` and `packages/opencode/src/session/processor.ts`, PR `#264`), the loop-gate race condition between `buildLoopContext()` and `recordSyntheticBlock`/`recordSyntheticStop` is intentionally handled via idempotence guards (re-check sigKey presence / `hasStopped` inside the record helpers) rather than a full per-parent `Effect.Mutex`. Threading a `Map<MessageID, Mutex>` through the processor was considered too large a surface change for this edge case; the residual TOCTOU window only produces extra synthetic parts with no behavioral drift on the "turn ends" contract. A code comment documents the trade-off and points to a full-mutex follow-up if the race is observed in practice. Do NOT re-flag the absence of a per-parent mutex as a blocking issue in future reviews.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/file/ripgrep.ts:364-368
Timestamp: 2026-04-28T07:27:59.666Z
Learning: In `packages/opencode/src/file/ripgrep.ts` (Astro-Han/pawwork, PR `#270`), both `files()` and `search()` do not short-circuit on an already-aborted `AbortSignal` before `spawner.spawn(...)`. The `check(input.cwd)` effect before spawn already provides a natural cancellation point for interrupted fibers. Upstream `dev:packages/opencode/src/file/ripgrep.ts` has identical ordering with no pre-spawn `signal.aborted` guard; adding one would diverge from the graft baseline. The fix (explicit pre-spawn `signal.aborted` check) is deferred to a dedicated PawWork ripgrep cancellation pass or upstream PR. Do NOT re-flag the missing pre-spawn cancellation short-circuit in `files()`/`search()` in upstream-sync PRs.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/file/ripgrep.ts:469-470
Timestamp: 2026-04-28T08:29:02.858Z
Learning: In `packages/opencode/src/file/ripgrep.ts` (Astro-Han/pawwork, PR `#270`), the `tree()` function filters files with `if (file.includes(".opencode")) continue`, which is a raw substring match that would also drop unrelated paths whose names merely contain `.opencode` (e.g., `.opencode-backup`). The correct fix is `if (file.split(path.sep).includes(".opencode")) continue` to match only the exact path segment. However, upstream `dev:packages/opencode/src/file/ripgrep.ts` carries the identical false-positive filter. PR `#270` is an upstream-sync graft; fixing it here would diverge from the baseline. The fix is deferred to a PawWork ripgrep filter cleanup PR or an upstream-first fix, to land alongside the other ripgrep deferrals (Schema.Class, bytes-union, abort short-circuit, mixed-separator). Do NOT re-flag the `.opencode` substring filter in upstream-sync PRs.
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 208
File: packages/app/src/components/prompt-input.tsx:1569-1611
Timestamp: 2026-04-24T05:39:58.329Z
Learning: In Astro-Han/pawwork `packages/app/src/components/prompt-input.tsx`, after the composer unification in PR `#208` (fixed in commit 5d810aa):
- `SendButton.disabled` does NOT gate on `store.mode !== "normal"`. Shell mode has a fully visible, clickable orange submit button that calls `handleSubmit` directly (same path as the Enter key in `handleKeyDown`). Do NOT suggest re-adding the mode gate.
- `SendButton` does NOT use the `buttons()` spring opacity animation (`style={buttons()}`). It is always fully visible regardless of mode.
- `WorkspaceChip` is gated on `props.homeMode && store.mode === "normal"` so it hides in shell mode (preventing it from appearing isolated/bright while neighboring controls fade).
- The left-side chip group (`aria-hidden={store.mode !== "normal"}`) covers attach/model/variant/workspace controls only; `SendButton` remains in a separate right-side sibling div.
📚 Learning: 2026-04-28T18:53:46.234Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 308
File: packages/opencode/test/server/global-session-list.test.ts:224-259
Timestamp: 2026-04-28T18:53:46.234Z
Learning: In `packages/opencode/test/server/global-session-list.test.ts` (Astro-Han/pawwork), all `it.live(...)` test bodies intentionally use `Effect.promise(async () => { ... })` rather than `Effect.gen(function* () { ... })`. This is the established local convention for the route/pagination tests in this file (e.g., "supports cursor pagination", "session route orders by creation time", "session routes omit undefined optional fields"). Do NOT flag individual `it.live` cases in this file as needing conversion to `Effect.gen`; any harness-style migration would need to cover the entire file.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T11:24:35.312Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/test/session/subagent-lifecycle-integration.test.ts:41-47
Timestamp: 2026-04-28T11:24:35.312Z
Learning: In `packages/opencode/test/session/subagent-lifecycle-integration.test.ts` (Astro-Han/pawwork, PR `#287`), the test suite intentionally uses a manual `run` helper (`Effect.runPromise(program.pipe(Effect.provide(Layer.mergeAll(SubagentRun.defaultLayer, Session.defaultLayer)), Effect.orDie))`) and raw `bun:test` test cases rather than the `testEffect(...)` harness. All 27 lifecycle tests pass with this pattern. Migration to `testEffect` + `it.live(...)` is deferred to a dedicated test-harness sweep PR to avoid fixture drift before merge. Do NOT re-flag the manual `Effect.runPromise` runner in this file as needing harness migration until that sweep PR lands.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Call `project.trackSession(sessionID, directory?)` and `project.trackDirectory(directory)` for any resources created outside the fixture so teardown can clean them up
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T14:46:41.449Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 302
File: packages/opencode/test/session/retry.test.ts:298-315
Timestamp: 2026-04-28T14:46:41.449Z
Learning: In Astro-Han/pawwork (PR `#302`, `packages/opencode/src/provider/error.ts` + `packages/opencode/test/session/retry.test.ts`), upstream anomalyco/opencode#24063 intentionally treats ALL OpenAI streaming `server_error` chunks as retryable (`isRetryable: true`). Do NOT request a test asserting `isRetryable: false` for a `server_error` stream chunk; the only negative regression needed is a non-`server_error` code (e.g. `bad_request`) to confirm the retry gate stays closed for other error codes.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-24T03:51:56.211Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 206
File: packages/app/e2e/prompt/prompt-footer-focus.spec.ts:131-143
Timestamp: 2026-04-24T03:51:56.211Z
Learning: In Astro-Han/pawwork E2E tests (packages/app/e2e/fixtures.ts), `project.prompt(text)` internally calls `trackSession(next.sessionID, active.directory)` after the prompt submission is observed and the active session is resolved. Tests that obtain a `sessionID` from `project.prompt()` do NOT need to call `project.trackSession(sessionID)` manually — it is already registered for teardown. Calling it again would be duplicate ownership.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T12:01:16.559Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/session/session.ts:518-542
Timestamp: 2026-04-28T12:01:16.559Z
Learning: In `packages/opencode/src/session/session.ts` (Astro-Han/pawwork, PR `#287`), the `updatePart` subtask guard intentionally allows first writes (where `existing === undefined`) to pass through without calling `lifecycleFieldsChanged`. This is required for `Session.fork()`, migration, and import paths that replay historical `SubtaskPart` rows via `updatePart()` outside any `SubagentRunWriterContext`. Only mutations of an already-persisted row (`existing` is defined) are policed. Do NOT suggest adding a lifecycle check on first-write in this guard.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T05:36:24.561Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:0-0
Timestamp: 2026-04-28T05:36:24.561Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), after the streaming-Service refactor of `ripgrep.ts`, there is only one code path that strips `RIPGREP_CONFIG_PATH` from the spawned environment (`delete env.RIPGREP_CONFIG_PATH` at `src/file/ripgrep.ts` line ~155). There is no longer a separate "worker" vs "direct" execution mode, so a single test titled "ignores RIPGREP_CONFIG_PATH from spawned env" (with an explanatory comment) is the correct and complete coverage. Do NOT flag the absence of a separate worker-mode RIPGREP_CONFIG_PATH test as a gap.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-27T10:08:57.448Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/test/session/diagnostics.test.ts:313-318
Timestamp: 2026-04-27T10:08:57.448Z
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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Use fixture-managed cleanup with `withSession(sdk, title, callback)` for temporary sessions instead of calling `sdk.session.delete(...)` directly
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-27T11:19:24.963Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/tool/websearch-auth.test.ts:0-0
Timestamp: 2026-04-27T11:19:24.963Z
Learning: In `packages/opencode/test/tool/websearch-auth.test.ts` (Astro-Han/pawwork), the tests intentionally use a small local `runWith` runner with raw `bun:test` and `Effect.runPromise` rather than the `testEffect` harness. Each test case injects a custom in-memory `Auth.Service` layer; switching to `testEffect` would be style-only churn without changing risk coverage. Do not flag these tests as needing harness migration.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : 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`.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T04:38:21.935Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:9-10
Timestamp: 2026-04-28T04:38:21.935Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), the tests intentionally use a local `run` helper (`effect.pipe(Effect.provide(Ripgrep.defaultLayer), Effect.runPromise)`) rather than the `testEffect(...)` harness. This file was adopted from upstream wholesale as part of an upstream-sync graft; migrating to `testEffect` + `it.live(...)` was deferred to a separate follow-up PR to avoid mixing refactor and harness-migration intents within the sync. Do NOT re-flag the local `run` wrapper as needing harness migration until that follow-up lands.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : 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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T05:36:22.128Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/session/compaction.ts:169-191
Timestamp: 2026-04-28T05:36:22.128Z
Learning: In `packages/opencode/src/session/compaction.ts` (Astro-Han/pawwork), the internal helper `splitTurn` intentionally returns a raw `Effect.gen(...)` rather than being wrapped with `Effect.fnUntraced`. Converting `splitTurn` (and similar plain-Effect.gen internal helpers in this file, e.g. `turns`, `completedCompactions`, `buildPrompt`) to `Effect.fnUntraced` is a repo-wide convention sweep deferred to a dedicated follow-up PR. The same sweep covers `tool/tool.ts` and other helpers flagged in the same sync. Do NOT re-flag the absence of `Effect.fnUntraced` on `splitTurn` or other internal helpers in `compaction.ts` during upstream-sync PRs; flag it only in the dedicated convention-sweep PR.
Applied to files:
packages/opencode/test/server/global-session-list.test.tspackages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : Use `testEffect(...)` from `test/lib/effect.ts` for tests that exercise Effect services or Effect-based workflows.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T04:56:21.338Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/tool/tool-define.test.ts:2-9
Timestamp: 2026-04-28T04:56:21.338Z
Learning: In `packages/opencode/test/tool/tool-define.test.ts` (Astro-Han/pawwork, PR `#270`), the test suite intentionally uses a `ManagedRuntime.make(Layer.mergeAll(Truncate.defaultLayer, Agent.defaultLayer))` wrapper and raw `bun:test` `test(...)` cases rather than the `testEffect(...)` harness. This code was adopted wholesale from upstream via the graft strategy (per `project_upstream_strategy.md`). Migrating to `testEffect` is deferred to a follow-up PR so as not to mix refactor + harness-migration intents and to avoid drifting the diff from the upstream baseline needed for clean future grafts. Do NOT re-flag the `ManagedRuntime.make` usage in this file as needing harness migration until that follow-up lands.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-27T11:18:47.332Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/tool/mcp-exa.test.ts:1-186
Timestamp: 2026-04-27T11:18:47.332Z
Learning: In `packages/opencode/test/tool/mcp-exa.test.ts` (Astro-Han/pawwork), the tests intentionally use raw `bun:test` async cases with `Effect.runPromise(...)` and per-case `HttpClient.make(...)` fakes rather than the `testEffect(...)` harness. The maintainer has explicitly decided not to migrate, because the HttpClient fake wiring is itself the behavior under test and switching to `testEffect` would be style churn without changing risk coverage. Do not flag these tests as needing harness migration.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-22T08:49:47.800Z
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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T04:38:11.771Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/agent.ts:23-27
Timestamp: 2026-04-28T04:38:11.771Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/tool/agent.ts`), the `subagent_session_id` field in the `Parameters` schema accepts any `Schema.String` rather than a branded `SessionID`. This is inherited upstream behavior (adopted in PR `#270`, an upstream-sync graft of upstream PR `#23244`). The fix — validating `subagent_session_id` as a `SessionID` brand up front so malformed/typo'd IDs fail explicitly rather than silently forking a new subagent session — is intentionally deferred to a follow-up PR or upstream report. Do NOT re-flag this as a blocking issue in PR `#270` or in future upstream-sync PRs that carry the same schema; flag it only in a PawWork-authored PR that touches `agent.ts` parameter validation.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-21T12:14:29.062Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 93
File: packages/opencode/test/server/cors-middleware.test.ts:15-23
Timestamp: 2026-04-21T12:14:29.062Z
Learning: In Hono-based test files under packages/opencode/test/server (including cors-middleware.test.ts), note that `app.request(...)` on a `Hono` app returns `Promise<Response> | Response` (a union that can include the non-PromiseLike `Response` branch). When passing this value to `Effect.promise(...)`, wrap it with `Promise.resolve(app.request(...))` to normalize the type to `PromiseLike` and avoid TS2322 typecheck errors in packages/opencode.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T04:56:18.533Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/file/ripgrep.test.ts:172-175
Timestamp: 2026-04-28T04:56:18.533Z
Learning: In `packages/opencode/test/file/ripgrep.test.ts` (Astro-Han/pawwork, PR `#270`), the `files dies on nonexistent directory` test hardcodes `/tmp/nonexistent-dir-12345` as the missing-directory path. This is upstream-inherited behaviour adopted wholesale via the graft strategy (`project_upstream_strategy.md`). The fix — replacing the hardcoded path with a platform-neutral guaranteed-nonexistent child path derived from the `tmpdir` fixture — is intentionally deferred to a follow-up PR or upstream report, to avoid mixing bugfix + refactor intents and drifting the diff from the upstream baseline future syncs need. Do NOT re-flag the hardcoded `/tmp/nonexistent-dir-12345` path in this file as a blocking or actionable issue until the follow-up PR lands.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-24T00:02:53.315Z
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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T07:27:49.810Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/file/ripgrep.ts:45-72
Timestamp: 2026-04-28T07:27:49.810Z
Learning: In `packages/opencode/src/file/ripgrep.ts` (Astro-Han/pawwork), `PathText`, the `lines` field inside `SearchMatch`, and `submatches[].match` accept only `{text: string}` and do NOT handle ripgrep's `{bytes: base64}` JSON variant (emitted for non-UTF-8 paths/match text). This matches the upstream `dev:packages/opencode/src/file/ripgrep.ts` baseline exactly. The fix — adding `Schema.Union([Schema.Struct({text: Schema.String}), Schema.Struct({bytes: Schema.String})])` for each location plus base64-decode in downstream consumers — is intentionally deferred to either a dedicated PawWork PR or an upstream-first fix inherited via the next sync. Do NOT re-flag the missing `{bytes: ...}` union variants in upstream-sync PRs; flag it only in a PawWork-authored PR that directly touches these schema definitions or their downstream consumers.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:04.113Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/app/e2e/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:04.113Z
Learning: Applies to packages/app/e2e/**/*.spec.ts : Use locator assertions like `toBeVisible()`, `toHaveCount(0)`, and `toHaveAttribute(...)` for normal UI state verification
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-22T09:32:54.556Z
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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-27T11:18:47.298Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 271
File: packages/opencode/test/tool/websearch.test.ts:21-78
Timestamp: 2026-04-27T11:18:47.298Z
Learning: In `packages/opencode/test/tool/websearch.test.ts`, the tests intentionally use manual `Effect.runPromise` with explicit `Effect.provide(...)` chains (including `Layer.succeed(Auth.Service, ...)`, `Layer.succeed(HttpClient.HttpClient, http)`, `WebSearchAuth.layer`, `Truncate.defaultLayer`, and `Agent.defaultLayer`) rather than the `testEffect(...)` harness. This is by design: the fake Auth and HTTP recovery-metadata layers must be explicitly injected and kept visible/scoped at the test site. Do NOT suggest migrating these tests to `testEffect` or removing the manual layer provides.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T05:36:25.456Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/test/tool/grep.test.ts:16-22
Timestamp: 2026-04-28T05:36:25.456Z
Learning: In `packages/opencode/test/tool/grep.test.ts` (Astro-Han/pawwork, PR `#270`), the test suite intentionally uses a manual `ManagedRuntime.make(Layer.mergeAll(...))` setup and raw `bun:test` test cases rather than the `testEffect(...)` harness. The migration to `testEffect` + `it.live(...)` + `provideTmpdirInstance(...)` is a whole-file rewrite deferred to a dedicated sweep PR that will migrate all tool tests still on the manual ManagedRuntime pattern together. Do NOT re-flag the ManagedRuntime setup in this file as needing harness migration until that sweep PR lands.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-28T06:47:20.342Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/question.ts:6-16
Timestamp: 2026-04-28T06:47:20.342Z
Learning: In Astro-Han/pawwork, `packages/opencode/src/tool/question.ts` is a permanent PawWork carve-out: `Question.Prompt` (defined in `packages/opencode/src/question/index.ts`) remains a Zod schema, NOT an Effect Schema. The `ts-expect-error` boundary in `tool/registry.ts` marks the Zod ↔ Effect Schema seam. The dropped `packages/opencode/test/tool/question.test.ts` covered the old Zod-mixed surface. Schema-bound regression tests for this tool are intentionally deferred until `question/index.ts` migrates to Effect Schema in its own dedicated PR. Do NOT request restoring question tool tests in upstream-sync PRs; flag it only in the PR that migrates `question/index.ts` to Effect Schema.
Applied to files:
packages/opencode/test/server/global-session-list.test.tspackages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-28T04:38:11.727Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 270
File: packages/opencode/src/tool/edit.ts:35-45
Timestamp: 2026-04-28T04:38:11.727Z
Learning: In `packages/opencode/src/tool/edit.ts` (Astro-Han/pawwork, PR `#270`), the module-scoped `Map<string, Semaphore.Semaphore>` (`locks`) and `lock(filePath)` helper are intentionally left as a global, never-cleaned registry. PR `#270` is a pure upstream-sync graft and mixing in a bugfix would drift the diff from the upstream baseline. The fix (moving per-file semaphores into `InstanceState`/`ScopedCache` for per-instance lifecycle management) is tracked as a follow-up to land in its own PR or be reported upstream. Do NOT re-flag the absence of InstanceState wiring for the lock map in this file until the follow-up PR is opened.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-23T08:51:00.819Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 186
File: packages/opencode/test/plugin/workspace-adaptor.test.ts:139-144
Timestamp: 2026-04-23T08:51:00.819Z
Learning: For pawwork tests under packages/opencode/test/**, auth.json teardown may intentionally combine `Filesystem.write` (from `packages/opencode/src/util/filesystem.ts`) with `node:fs/promises` `unlink` for cleanup. Do not flag this as inconsistent style; it is the established/intentional pattern because `Filesystem` does not provide a `remove`/`unlink` helper.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : 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.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-20T14:36:31.032Z
Learnt from: CR
Repo: Astro-Han/pawwork PR: 0
File: packages/opencode/test/AGENTS.md:0-0
Timestamp: 2026-04-20T14:36:31.032Z
Learning: Applies to packages/opencode/test/**/*.test.{ts,tsx} : When a test needs instance-local state, prefer `provideTmpdirInstance(...)` or `provideInstance(...)` over manual `Instance.provide(...)` inside Promise-style tests.
Applied to files:
packages/opencode/test/server/global-session-list.test.ts
📚 Learning: 2026-04-27T12:59:49.844Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/test/session/prompt-effect.test.ts:0-0
Timestamp: 2026-04-27T12:59:49.844Z
Learning: In `packages/opencode/test/session/prompt-effect.test.ts` and `packages/opencode/src/session/diagnostics.ts` (PR `#264`), the recovery reminder copy differs between signature kinds: the input-repeat variant says "repeated the same tool input 3 times" (uses a literal count), while the target-repeat variant says "failed against the same target multiple times" (uses "multiple times" with no count). Assertions that check for injected reminder text in LLM inputs must accept both phrasings when a scenario produces both `input:` and `target:` signatures (e.g., `read` tool with a `filePath` parameter). Do NOT narrow the assertion to only the input-variant phrasing.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-26T15:35:36.505Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 245
File: packages/opencode/src/question/index.ts:21-24
Timestamp: 2026-04-26T15:35:36.505Z
Learning: In Astro-Han/pawwork (`packages/opencode/src/question/index.ts`), `Question.Option.description` is intentionally **required** (`z.string()`, not `.optional()`). This matches the upstream opencode contract and all current callers (e.g. `PlanExitTool`) always supply a description. The defensive `<Show when={props.description}>` rendering in `session-question-dock.tsx` is a standard guard, not a signal that the field is intended to be optional. Do NOT suggest making `Option.description` optional without a dedicated follow-up that covers schema + tool description + dock copy + tests.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-27T08:58:00.665Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/prompt.ts:531-538
Timestamp: 2026-04-27T08:58:00.665Z
Learning: When using Effect (e.g., `yield*` with `Effect`-style generator yielding), only use `yield* new SomeErrorClass(...)` if `SomeErrorClass` extends `Schema.TaggedErrorClass` (i.e., it implements Effect’s Yieldable interface). For plain `Error` subclasses (like `BlockedLoopError` / `LoopStopError`) or inline `new Error(...)` values, they are not yieldable and must be wrapped as `yield* Effect.fail(new PlainError(...))`. Do not recommend changing `yield* Effect.fail(new SomePlainError(...))` to `yield* new SomePlainError(...)` unless the error class extends `Schema.TaggedErrorClass`.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-28T12:49:09.792Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/session/subagent-run.ts:445-445
Timestamp: 2026-04-28T12:49:09.792Z
Learning: In this repo’s `packages/opencode/src` module files, the canonical module-as-namespace pattern is load-bearing: at the bottom of each module file, add a self-reexport in the form `export * as <ModuleName> from "./<module-file>"` (e.g., in `subagent-run.ts`: `export * as SubagentRun from "./subagent-run"`). Consumers must import the namespace via a named binding (e.g., `import { SubagentRun } from ".../subagent-run"`) and then access members as `SubagentRun.Service`, `SubagentRun.defaultLayer`, `SubagentRun.AgentListFilter`, etc. During code review, do NOT flag these self-reexports as dead code or redundant; removing or altering them will break the consumer named binding.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-27T10:32:59.274Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/diagnostics.ts:245-252
Timestamp: 2026-04-27T10:32:59.274Z
Learning: In pawwork’s session diagnostics/loop error handling (e.g., packages/opencode/src/session/diagnostics.ts), keep `loopLastError` stored as raw/unscrubbed error text in loop metadata. The intended trust boundary for sensitive-data scrubbing is the renderer: `LoopRenderer.render` must apply `scrubErrorText` before any user/model-facing output. Do not recommend scrubbing `loopLastError` at the `observeToolError` call site, because failed tool parts already store raw errors in `state.error` (pre-existing leak) and scrubbing only `loopLastError` would be lossy without closing the gap. If export-side hardening is required, implement a single sanitizer pass in the export layer over both `state.error` and the loop/metadata fields, rather than sanitizing only `loopLastError` earlier in the storage path.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-28T11:24:23.345Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 287
File: packages/opencode/src/session/subagent-run.ts:8-16
Timestamp: 2026-04-28T11:24:23.345Z
Learning: In this repo’s service-internal code (e.g., session modules), follow the established error-class convention: use plain classes with a `readonly _tag` discriminant and/or `NamedError.create` (zod-based) for service-internal errors. Do NOT request one-off conversions of such plain/service-internal errors to `Schema.TaggedErrorClass`; that migration is intentionally deferred until the dedicated repo-wide error-class sweep PR lands.
Applied to files:
packages/opencode/src/session/compaction.ts
📚 Learning: 2026-04-27T10:33:08.974Z
Learnt from: Astro-Han
Repo: Astro-Han/pawwork PR: 264
File: packages/opencode/src/session/prompt.ts:108-169
Timestamp: 2026-04-27T10:33:08.974Z
Learning: For Astro-Han/pawwork session processing code under packages/opencode/src/session/ (e.g., prompt.ts and processor.ts), this specific loop-gate TOCTOU/race between buildLoopContext() and recordSyntheticBlock/recordSyntheticStop is intentionally handled via idempotence guards (re-check sigKey presence and hasStopped inside the record helpers). Do not treat the absence of a per-parent Effect.Mutex as a blocking review issue for this known edge case; the residual window should only create extra synthetic parts and must not change the "turn ends" contract. Respect the existing code comment documenting the trade-off, and only escalate to a full-mutex approach if the race is observed in practice.
Applied to files:
packages/opencode/src/session/compaction.ts
🔇 Additional comments (1)
packages/opencode/test/server/global-session-list.test.ts (1)
224-259: Good regression coverage for optional-field omission in session routes.This test validates both route variants and includes explicit length checks before indexing, which keeps failures clear.
This was referenced Apr 28, 2026
11 tasks
13 tasks
13 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
workspaceSymbolqueries through the LSP tool and update its parameter schema and description.Refs #298
Upstream coverage
Deferredready flow.workspaceSymbol.query.Verification
bun install --frozen-lockfilebun --cwd packages/opencode test test/session/prompt-effect.test.ts -t "shell commands can change directory after login startup|cancel"bun --cwd packages/opencode test test/effect/runner.test.ts -t "cancel"bun --cwd packages/opencode test test/tool/lsp.test.tsbun --cwd packages/opencode test test/server/global-session-list.test.ts -t "session routes omit undefined optional fields"bun --cwd packages/opencode test test/session/compaction.test.tsbun run --cwd packages/opencode typecheckSummary by CodeRabbit
New Features
Bug Fixes
Documentation
Tests