Agent support · Hooks & Lifecycle

Agent complete (stop)

Hook that fires when the agent finishes a turn — implement quality gates, force continuation, or trigger follow-up workflows

Observation Hooks Hooks & Lifecycle
Supported
Partial
No
Unknown
Claude Code Current · May 2026
Cline Current · May 2026
Codex CLI Current · Apr 2026
Copilot Current · Apr 2026
Cursor Current · Apr 2026
Windsurf Current · Apr 2026
2.1.72 - 2.1.143
3.82.0 - 3.83.0
0.114.0 - 0.128.0
2026.03 - 2026.05
2.5 - 3.2
1.13.3 - 2.1.29
2.1.10 - 2.1.72
3.82.0
0.88.0 - 0.113.0
2025.10 - 2026.03
2.4 - 2.5
1.13.3
1.0.38 - 2.1.10
3.82.0
0.2.0 - 0.88.0
2025.06 - 2025.10
1.0 - 2.0
1.2.1 - 1.13.3
0.2.54 - 1.0.0
3.36.0 - 3.82.0
2025.06
0.45 - 1.0
1.2.1
0.2.31 - 0.2.54
1.5.0 - 3.33.0
0.45
1.0.2 - 1.2.1

Supported by 4 of 6 agents.

HoverTap any cell for version details.

Agent event mapping

  • claude-code Stop, StopFailure
  • cline TaskComplete, TaskCancel
  • codex-cli Stop
  • cursor stop

Sub-capabilities

  • Force the agent to keep working by returning a continuation signal
  • Implement quality checks before accepting the agent's work
  • Claude Code: StopFailure fires on API errors
  • Cursor: followup_message for auto-continue with configurable loop_limit
  • Cline: TaskComplete on success, TaskCancel when user stops a running task