João Moura 1c64c84cd8 feat(tracing): carry task_prompt and output in agent_execution payloads (#7498) ...

`agent_execution_started` and `agent_execution_completed` are in
`complex_events`, so `_build_event_data` hand-builds their payloads. Those
payloads shipped only agent_role/goal/backstory and dropped two required bus
fields: `AgentExecutionStartedEvent.task_prompt` and
`AgentExecutionCompletedEvent.output`. A trace therefore said which agent ran
but not what it was asked or what it answered.

Add `task_prompt` to the started payload and `output` to the completed one,
whole and untruncated. No new event types, no TraceEvent change.

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Vidit Ostwal <110953813+Vidit-Ostwal@users.noreply.github.com>

2026-09-16 11:56:33 +05:30

..

cli

fix(events): Improve coding agents instructions (#7447)

2026-09-16 02:07:57 -03:00

crewai

feat(tracing): carry task_prompt and output in agent_execution payloads (#7498)

2026-09-16 11:56:33 +05:30

crewai-core

fix(events): Improve coding agents instructions (#7447)

2026-09-16 02:07:57 -03:00

crewai-files

feat: bump versions to 1.15.21 (#7362)

2026-09-09 22:29:18 +00:00

crewai-tools

feat: add platform tools to JSON crew wizard (#7384)

2026-09-11 12:13:55 -07:00

devtools

feat: bump versions to 1.15.21 (#7362)

2026-09-09 22:29:18 +00:00