Skip to main content

Agent Observability

Observability in Codebolt is how you see what an agent did, what it's doing right now, and why it made a particular choice. It spans running processes, historical runs, and LLM-level traces, with execution replays linked from Code Observability.

Panels in this section

PanelPurpose
Agent DebugPer-instance log stream: LLM calls, tool calls, status events, errors — with filters and history mode
AI Debug & ConsoleRaw LLM inputs/outputs, token counts, latency, cost estimates, plus agent stdout/stderr console

Other views that live alongside the agent lifecycle:

PanelLocation
Running Agents (currently executing processes)Agents → Running Agents
Background Agents (trigger-started, detached runs)Agents → Running Agents
Thread Panel (conversation and run history)Agents → Thread Panel
Narrative Graph (visual run replay)Code Observability → Narrative Graph

When to reach for which

  • Something is still running and you want to watch itRunning Agents
  • An agent started itself (cron, webhook, file-change trigger)Background Agents
  • You want to see why the agent did what it didNarrative Graph
  • You want the exact prompt the LLM receivedAI Debug
  • You want the full per-instance log streamAgent Debug