RongJie G e01314442c

fix(mcp): scope sessions and task access by thread incarnation (#5556) ...

* fix(mcp): scope sessions and task access by thread incarnation

* fix(mcp): preserve thread incarnation in delegated subagents

* fix(mcp): preserve incarnation in durable batches

* fix(mcp): bind standalone graph lifecycle context

* fix(studio): preserve implicit thread creation metadata

---------

Co-authored-by: CorgiBoyG <CorgiBoyG@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-09-23 08:33:20 +08:00

..

lead_agent

fix(mcp): scope sessions and task access by thread incarnation (#5556)

2026-09-23 08:33:20 +08:00

memory

fix(memory): report malformed backend_config values by key name (#5555)

2026-09-20 16:43:54 +08:00

middlewares

fix: discard stale todo reminders during context compaction (#5614)

2026-09-22 17:45:01 +08:00

task_continuity

feat: add opt-in task notes and compacted history recall (#5382)

2026-09-12 21:01:46 +08:00

__init__.py

fix: restore standalone LangGraph Studio compatibility (#4760)

2026-08-15 21:20:34 +08:00

AGENTS.md

fix(agents): distinguish undeclared and empty skill allowed-tools (#5669)

2026-09-22 11:36:28 +08:00

assembly_descriptor.py

fix(agents): distinguish undeclared and empty skill allowed-tools (#5669)

2026-09-22 11:36:28 +08:00

factory.py

fix(agents): make create_deerflow_agent's subagent limit, summarization and token_budget features take effect (#5488)

2026-09-17 09:35:50 +08:00

features.py

feat(memory): add memory tool sets (#4023)

2026-07-11 15:28:16 +08:00

goal_state.py

feat(runtime): implement goal continuations (#3858)

2026-07-03 08:49:33 +08:00

human_input.py

feat(frontend):enhance the ask_clarification interaction with visualized card (#3956)

2026-07-06 22:34:41 +08:00

interaction_policy.py

fix(agent): align unattended prompt with tool policy (#4919)

2026-09-20 18:57:49 +08:00

thread_state.py

feat: add opt-in task notes and compacted history recall (#5382)

2026-09-12 21:01:46 +08:00