Skip to content

temporal — CLI Agent Evaluation

Evaluated against the CLI Agent Spec — a specification defining 71 failure modes for CLI tools used under AI agent orchestration.

CLI version: temporal version 1.7.2 (Server 1.31.1, UI 2.49.1) Evaluated: 2026-07-07 Scope: critical (22 of 71 failure modes)

Scores

Metric Result
Failure mode score 1.1/3 — 2 passing · 15 partial · 4 failing · 1 indeterminate
Readiness score 3/15 [F]
Observed bugs 4 confirmed during live evaluation
Worst gaps §1, §13, §25, §74

Key Findings

  • --output json works for success paths but not for validation, timeout, or connection failures.
  • Missing args, not-found, network, and timeout-like failures collapse to exit 1.
  • Destructive commands have partial prompt protection but no dry-run/effect contract.
  • No machine-readable schema, command manifest, required scopes, or check-permissions command was found.
  • API keys can be passed through argv, which is risky for agent traces and process listings.

Files

File What it is
report-index.md Full scorecard — all failure modes, readiness breakdown, links to all reports
report-issues.md Concrete bugs and gaps agents will hit when using this CLI as-is
report-runtime.md Compact operational brief — what to set, what to avoid, what to watch for
report-agent-dev.md Integration guide — invocation invariants and per-gap workarounds for agent developers
report-dev.md Fix list for CLI authors — what to implement, mapped to spec requirements
findings.md Raw scorecard — one row per evaluated failure mode
issues.md Observed bugs recorded during live evaluation
trace.md Audit trail — exact check commands, exit codes, stdout/stderr per §N
environment.md CLI environment profile — binary path, version, flags, timeout method
readiness.md Proactive readiness scores across 5 dimensions

Generated by cli-agent-audit · CLI Agent Spec