Yansong Zhang 2de2a8fd3a fix(api): resolve multi-turn memory failure in Agent apps ... - Auto-resolve parent_message_id when not provided by client, querying the latest message in the conversation to maintain the thread chain that extract_thread_messages() relies on. - Add AppMode.AGENT to TokenBufferMemory mode checks so file attachments in memory are handled via the workflow branch. - Add debug logging for memory injection in node_factory and node. Made-with: Cursor		2026-04-09 16:27:38 +08:00
..
app_config	refactor(api): migrate consumers to shared RAG domain entities from core/rag/entities/ (#34692)	2026-04-07 23:22:56 +00:00
apps	fix(api): resolve multi-turn memory failure in Agent apps	2026-04-09 16:27:38 +08:00
entities	feat(api): enable all sandbox/skill controller routes and resolve dependencies (P0)	2026-04-09 09:36:16 +08:00
features	refactor(api): use standalone graphon package (#34209)	2026-03-27 21:05:32 +00:00
file_access	refactor(api): continue decoupling dify_graph from API concerns (#33580)	2026-03-25 20:32:24 +08:00
layers	feat(api): port Sandbox + VirtualEnvironment + Skill system from feat/support-agent-sandbox (Phase 5-6)	2026-04-08 17:39:02 +08:00
llm	refactor: use EnumText for Provider.quota_type and consolidate ProviderQuotaType (#34299)	2026-03-31 00:29:57 +00:00
task_pipeline	refactor: migrate session.query to select API in core misc modules (#34608)	2026-04-07 04:08:34 +00:00
workflow	chore(api): align Python support with 3.12 (#34419)	2026-04-02 05:07:32 +00:00
__init__.py	FEAT: NEW WORKFLOW ENGINE (#3160)	2024-04-08 18:51:46 +08:00