dify/api/core/app/apps/advanced_chat
Yansong Zhang 5cdae671d5 feat(api): integrate Sandbox Provider into Agent V2 execution pipeline
Close 3 integration gaps between the ported Sandbox system and Agent V2:

1. Fix _invoke_tool_in_sandbox to use SandboxBashSession context manager
   API correctly (keyword args, bash_tool, ToolReference), with graceful
   fallback to direct invocation when DifyCli binary is unavailable.

2. Inject sandbox into run_context via _resolve_sandbox_context() in
   WorkflowBasedAppRunner — automatically creates a sandbox when a
   tenant has an active sandbox provider configured.

3. Register SandboxLayer in both advanced_chat and workflow app runners
   for proper sandbox lifecycle cleanup on graph end.

Also: make SkillInitializer non-fatal when no skill bundle exists,
add node_id to ExecutionContext for sandbox session scoping.

Made-with: Cursor
2026-04-10 10:14:42 +08:00
..
__init__.py FEAT: NEW WORKFLOW ENGINE (#3160) 2024-04-08 18:51:46 +08:00
app_config_manager.py feat: enhance start node object value check (#30732) 2026-01-09 16:13:17 +08:00
app_generator.py fix(api): resolve multi-turn memory failure in Agent apps 2026-04-09 16:27:38 +08:00
app_runner.py feat(api): integrate Sandbox Provider into Agent V2 execution pipeline 2026-04-10 10:14:42 +08:00
generate_response_converter.py test: unit test cases for core.app.apps module (#32482) 2026-03-12 11:23:25 +08:00
generate_task_pipeline.py refactor(api): use standalone graphon package (#34209) 2026-03-27 21:05:32 +00:00