- emit opencode-compatible SSE events for questions and permissions
(flat shape with top-level session_id for wrapEventStream routing)
- adapt question API (/question, /question/:id/reply, /question/:id/reject)
for AskUserQuestion and elicitation workflows
- fix AskUserQuestion tool name matching and guard against double-wrapped events
- allow requiresUserInteraction tools to ask user even in bypassPermissions mode
- avoid blocking on session init to prevent cold-start timeout
- add /global/event SSE endpoint and cwdFilter support
- add question routes and session handle tests
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Refactor csc serve question endpoints to match opencode/app-ai-native
expected data models and request/response shapes:
- GET /question now returns QuestionRequest[] (direct array) instead of
{ questions: [...] }
- POST /question/:id/reply accepts { answers: string[][] } mapping to
selected option labels per question
- POST /question/:id/reject no longer requires a request body
- Support dual question sources:
- MCP Elicitation (converted to opencode format with enum→options)
- AskUserQuestionTool permissions exposed as questions
- Add conversion helpers: convertAskUserQuestionToOpencode,
convertElicitationToOpencode, buildElicitationContent
- Reply to AskUserQuestionTool via replyPermission('allow') with
constructed updatedInput.answers map
Also includes serve-mode infrastructure improvements:
- Session routes auto-create sessions on demand via getOrCreateSession
- Set CSC_SERVE_MODE env var in child process spawn
- Skip push-suggestion stream waiting in serve mode
Add comprehensive unit tests for question route opencode conversion.
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
QueryEngine previously guarded stream_event yields behind includePartialMessages,
which was undefined in serve mode. Remove the guard so stream_event messages
always flow to the child process stdout. Add stream_event handling in
sessionHandle.routeMessage to emit via EventBus for downstream consumers.
- Add _providerId field to SessionHandle, extracted from initData.account.apiProvider
- Include provider_id in user message emit, assistant message fallback, and session.ready
- Revert getProviderId normalization (keep raw value from subprocess)
The subprocess returns apiProvider='firstParty' for direct Anthropic access,
but the adapter hardcodes providerID='anthropic' in SSE events. This mismatch
causes the frontend's isModelValid check to fail, clearing the model selector.
- Remove process.stderr.write debug logs from sessionHandle and prompt_async
- Add model fallback in assistant message (use this._model if msg.model missing)
- Add model field to user message emit for adapter consumption
- Wait for session ready before setModel/prompt in prompt_async
- Return 200 JSON instead of 204 No Content from prompt_async
- Set Bun.serve idleTimeout to 255s to prevent connection drops
Replace per-turn detached workers with a file-backed queue consumed by
a single long-running batch worker (30s interval, 0-10s jitter).
- queue.ts, batchWorker.ts: file queue with pid-based lock for worker
singleton; tasks deduped by sessionID:messageID before processing
- worker.ts: retry with backoff (5s, 10s) for 429 and network errors;
update commit state per upload so partial failures resume cleanly;
export auth, loadSessionMessages, getSessionDirectory and upload*
helpers for batchWorker reuse
- git.ts: cap commit log at 50 entries within last 7 days; pause 500ms
every 10 commits to spread load
- worker.ts: resolve session jsonl via ~/.claude/projects/{normalized}
with fallbacks, scanning for the file containing the target session
- logger.ts: file + stderr logger gated by CSC_RAW_DUMP_DEBUG, default
silent
- sessionDataUploader.ts: implement createSessionTurnUploader to pick
the last assistant message; query.ts fires uploadSessionTurn after
query_api_streaming_end (non-blocking)
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
Introduce a framework-decoupled raw-dump module that uploads conversation, summary, and commits data to the CoStrict server in a non-blocking detached worker process.
- Add src/services/rawDump/ with index, types, state, spawn, git, worker, and README
- Implement reportTurn and reportSession entry points with in-memory dedup and env-based disable switch (CSC_DISABLE_RAW_DUMP / COSTRICT_DISABLE_RAW_DUMP)
- Replace sessionDataUploader stub with uploadSessionTurn that delegates to reportTurn
Signed-off-by: 林凯90331 <90331@sangfor.com>
Co-authored-by: CoStrict <zgsm@sangfor.com.cn>
* fix: keep UDS peer failures structured
CodeRabbit and Claude cross-review identified that timeout and raw peer connection failures should share one observable error contract. UDS peer failures now use UdsPeerConnectionError consistently, and connectToPeer hands the socket lifecycle back to the caller after a successful connection instead of retaining an internal timeout or error listener.
The tests cover the real socket paths with capability files, timeout behavior, connection failure structure, post-connect listener handoff, AgentSummary rescheduling observations, and platform-specific mailbox directory errno handling.
Constraint: Preserve the 5000ms production timeout default while allowing tests to exercise timeout paths quickly.
Rejected: Suppress CodeRabbit warnings in tests | would hide the real timeout/error contract gap.
Rejected: Keep connectToPeer post-connect error listener | it would silently swallow caller-owned socket errors.
Confidence: high
Scope-risk: narrow
Directive: Keep UDS send/connect timeout and socket-error paths on the same structured peer error contract.
Tested: bun test src/utils/__tests__/udsMessaging.test.ts src/services/AgentSummary/__tests__/agentSummary.test.ts src/utils/__tests__/teammateMailbox.test.ts
Tested: bunx tsc --noEmit --pretty false
Tested: bun run lint
Tested: bun run test:all
Tested: bun test --coverage --coverage-reporter lcov --coverage-dir coverage
Tested: bun run build
Tested: bun run build:vite
Tested: omx ask claude simplify review artifact .omx/artifacts/claude-review-only-cross-check-for-pr-374-on-branch-codex-codecov-r-2026-04-27T08-17-47-309Z.md
Tested: omx ask claude security review artifact .omx/artifacts/claude-security-review-cross-check-for-pr-374-current-working-tree--2026-04-27T08-26-54-079Z.md
Not-tested: GitHub-hosted CodeRabbit refresh until pushed.
* docs: clarify UDS peer socket ownership
CodeRabbit's #375 pass found that connectToPeer now correctly hands socket errors to the caller, but the JSDoc needed to spell out that contract. The lifecycle test also uses a less brittle post-connect timeout so slow CI does not turn the ownership check into a connection-speed race.
Constraint: The raw socket API intentionally detaches its internal listener after successful connect so caller-owned errors are not swallowed.
Rejected: Keep the test timeout at 50ms | it tests scheduler speed instead of socket lifecycle ownership.
Confidence: high
Scope-risk: narrow
Directive: connectToPeer callers must attach their own error listener immediately after awaiting the socket.
Tested: bun test src/utils/__tests__/udsMessaging.test.ts
Tested: bunx tsc --noEmit --pretty false
Tested: bun run lint
Tested: git diff --check
Tested: bun run test:all
Not-tested: GitHub-hosted CodeRabbit refresh until pushed.
* fix: close peer socket listener handoff window
CodeRabbit and Claude review found that documenting caller-owned raw socket errors still left a Promise handoff window and a stale timeout-listener risk. The peer connection API now requires a caller error handler and installs it before resolving, while cleanup removes internal error and timeout listeners on every path.
Constraint: Keep the fix precise to PR #375 review feedback and avoid warning suppression or fallback behavior.
Rejected: Leave the behavior documented only | still permits an unhandled socket error window between resolve and caller listener attachment.
Rejected: Keep a no-op internal error listener | would silently swallow caller-owned socket errors.
Confidence: high
Scope-risk: narrow
Directive: Do not add raw connectToPeer callers without providing a real onSocketError handler and capability handshake.
Tested: bun test src/utils/__tests__/udsMessaging.test.ts src/services/AgentSummary/__tests__/agentSummary.test.ts
Tested: bunx tsc --noEmit --pretty false
Tested: bun run lint
Tested: bun run test:all
Tested: bun test --coverage --coverage-reporter lcov --coverage-dir coverage
Tested: bun run build
Tested: bun run build:vite
Tested: bun audit
Not-tested: Manual external ACP peer runtime beyond repository tests.
* fix: use a deadline timer for peer connects
The raw socket handoff no longer needs Socket#setTimeout; an ordinary connection deadline keeps the timeout behavior while avoiding an internal socket timeout listener that has no reliable UDS integration path to exercise.
Constraint: Keep Codecov coverage honest without adding ignore pragmas, mocks, or fallback suppression.
Rejected: c8 ignore on the timeout listener | hides the uncovered branch instead of simplifying the lifecycle.
Rejected: keep Socket#setTimeout listener | leaves a socket listener lifecycle to manage for a connect-only deadline.
Confidence: high
Scope-risk: narrow
Directive: Keep connectToPeer errors caller-owned via onSocketError and reject pre-connect failures with UdsPeerConnectionError.
Tested: bun test src/utils/__tests__/udsMessaging.test.ts src/services/AgentSummary/__tests__/agentSummary.test.ts
Tested: bunx tsc --noEmit --pretty false
Tested: bun run lint
Tested: bun test src/utils/__tests__/udsMessaging.test.ts --coverage --coverage-reporter lcov --coverage-dir coverage-uds
Tested: bun run test:all
Tested: bun test --coverage --coverage-reporter lcov --coverage-dir coverage
Tested: bun run build
Tested: bun run build:vite
Tested: bun audit
Not-tested: Manual external ACP peer runtime beyond repository tests.
---------
Co-authored-by: unraid <local@unraid.local>
