WeiCHENandCursor 7615beeaf9 fix(agent): scope Task 2 to SSE phases/errors without dialogue_llm leak ...

- untrack internal/coordinator/dialogue_llm.go (kept on disk untracked as local WIP for a future dialogue-LLM commit with its own tests; it depends on engine.go fields (dialogueBackend, ReplySource) not yet committed)
- slim internal/chat/session.go back to Task 2 scope relative to bfa6889: keep EmitErrorInfo(stream.ClassifyError(...)) for intent+coordination errors and the dialogue_generating EmitPhase before ProcessIntent; drop sync.Mutex/mu, ChatResponse.ReplySource, preference/RecentDialogue injection block, and collectRecentDialogue helper (unrelated WIP for the dialogue-LLM feature)

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-09-13 02:50:20 +00:00

..

context_test.go

feat(coordinator): 实现L2统一上下文组装器与意图校验调度引擎

2026-09-13 02:50:18 +00:00

context.go

docs(test): archive test report for dialogue-driven content and hierarchical intent system

2026-09-13 02:50:19 +00:00

engine_test.go

fix(coordinator): chain expectation for card confirmation and add ttl lifecycle cleanup

2026-09-13 02:50:19 +00:00

engine.go

fix(coordinator): chain expectation for card confirmation and add ttl lifecycle cleanup

2026-09-13 02:50:19 +00:00