agent tracing

Data Community

Skill notes

How It Works

In NODE_ENV=development, AgentRuntimeService.executeStep() automatically records each step to .agent-tracing/ as partial snapshots. When the operation completes, the partial is finalized into a complete ExecutionSnapshot JSON file. Data flow: executeStep loop -> build StepPresentationData -> write partial snapshot to disk -> on completion, finalize to .agent-tracing/{timestamp}_{traceId}.json

Data Storage

Completed snapshots: .agent-tracing/{ISO-timestamp}_{traceId-short}.json Latest symlink: .agent-tracing/latest.json In-progress partials: .agent-tracing/_partial/{operationId}.json FileSnapshotStore resolves from process.cwd() — run CLI from the repo root

CLI Commands

All commands run from the repo root:

Inspect Flag Reference

Flag · Short · Description · Default Step --step <n> · -s · Target a specific step · — --messages · -m · Messages context (CE input → params → LLM payload) · — --tools · -t · Tool calls & results (what agent invoked) · — --events · -e · Raw events (llm_start, llm_result, etc.) · —

--messages Output Structure

When using --messages, the output shows three sections (if context engine data is available): Context Engine Input — DB messages passed to the engine, with [0], [1], ... indices. Use --msg-input N to view full content. Context Engine Params — systemRole, model, provider, knowledge, tools, userMemory, etc. Final LLM Payload — Processed messages after context engine (system date injection, user memory, history truncation, etc.), with [0], [1], ... indices. Use --msg N to view full content.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Data
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@lobehub · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Linux · Windows
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Output preview agent-tracing.preview
# --messages Output Structure

1. **Context Engine Input** — DB messages passed to the engine, with `[0]`, `[1]`, ... indices. Use `--msg-input N` to view full content.
2. **Context Engine Params** — systemRole, model, provider, knowledge, tools, userMemory, etc.
3. **Final LLM Payload** — Processed messages after context engine (system date injection, user memory, history truncation, etc.), with `[0]`, `[1]`, ... indices. Use `--msg N` to view full content.

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.