Yansong Zhang b21a443d56 fix(api): resolve all remaining known issues ...

1. Fix workflow-level total_tokens=0:
   Call graph_runtime_state.add_tokens(usage.total_tokens) in both
   _run_without_tools and _run_with_tools paths after node execution.
   Previously only graphon's internal ModelInvokeCompletedEvent handler
   called add_tokens, which agent-v2 doesn't emit.

2. Fix Turn 2 SSE empty response:
   Set PUBSUB_REDIS_CHANNEL_TYPE=streams in .env. Redis Streams
   provides durable event delivery (consumers can replay past events),
   solving the pub/sub at-most-once timing issue.

3. Skill -> Agent runtime integration:
   SandboxBuilder.build() now auto-includes SkillInitializer if not
   already present. This ensures sandbox.attrs has the skill bundle
   loaded for downstream consumers (tool execution in sandbox).

4. LegacyResponseAdapter:
   New module at core/app/apps/common/legacy_response_adapter.py.
   Filters workflow-specific SSE events (workflow_started, node_started,
   node_finished, workflow_finished) from the stream, passing through
   only message/message_end/agent_log/error/ping events that old
   clients expect.

46 unit tests pass.

Made-with: Cursor

2026-04-09 12:53:11 +08:00

..

__init__.py

feat: Split WorkflowCycleManager (#20071)

2025-05-22 09:49:25 +08:00

graph_runtime_state_support.py

refactor(api): use standalone graphon package (#34209)

2026-03-27 21:05:32 +00:00

legacy_response_adapter.py

fix(api): resolve all remaining known issues

2026-04-09 12:53:11 +08:00

workflow_response_converter.py

refactor(api): use standalone graphon package (#34209)

2026-03-27 21:05:32 +00:00