trace — Investigation and Root Cause Analysis

trace — Investigation and Root Cause Analysis

Runtime syntax: invoke the plugin copy through the active runtime's owner-qualified skill selector; use a bare selector only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active runtime.

Investigate unknown failures: dispatch a trace subagent to reproduce, trace, and isolate root cause, then hand the report to fix. The deliverable is findings only — report and stop; never apply fixes, however obvious.

When to Use

• A failure exists but the cause is unknown
• Stack traces or error messages don't point to an obvious defect
• Multiple files or systems may be involved
• review hit a failure with unclear root cause and needs a diagnosis before fix

Flow

1. Collect symptoms: error messages, stack traces, logs, and expected vs actual behavior from the wish or reporter.
2. Dispatch tracer: native delegation surface → trace subagent, briefed with the symptoms, relevant context (files, recent changes, environment), and read-only stop conditions (see Dispatch).
3. Investigate: the tracer reproduces, hypothesizes, traces, and isolates root cause autonomously.
4. Receive report: the tracer's final message is the diagnosis (format below); the native team notifies you on completion — no polling.
5. Hand off: pass the report to fix, or escalate to the orchestrator.

Report Format

Root cause: <what's actually broken — file, line, condition>
Evidence: <reproduction steps, traces, proof>
Causal chain: <root cause → intermediate effects → observed symptom>
Recommended correction: <what to change, where, why>
Affected scope: <other files or features impacted>
Confidence: <high / medium / low>

Include file paths and line numbers in every root-cause claim so fix can act without re-investigating. If root cause spans multiple systems, report each separately with its own confidence level.

Dispatch

Trace runs through a fresh read-only scout/explorer role on the active runtime (runtime profile genie_scout when installed). It may search files and run non-mutating diagnostic commands, but it must not edit, stage, commit, or publish. Use native follow-up messaging to keep the same investigation context.

Rules

• Report findings and stop — investigation only. fix applies the correction; never combine the two.
• Reproduce before theorizing — if the failure can't be reproduced, the report must say so.
• Evidence required: every root-cause claim carries file paths, line numbers, and a causal chain grounded in tool output from this session — never inferred from memory.