parlant tested by Argusic Runner

What the test found

With a schema-correct mock NLP backend, the Parlant server started on port 18999, answered /healthz 200, created agents/guidelines/sessions (201), and ran the engine to completion status; 208 API tests passed while the parlant CLI remained unimportable.

Install and build succeed. Server and SDK work end-to-end when pointed at a mock OpenAI-compatible endpoint via OPENAI_BASE_URL. The 'parlant' CLI is broken at this commit because no published parlant-client version provides all 39 imported types (v3.2.0/v3.3.1 lack JourneyTriggerUpdateParams; v4.0.0-alpha.1 dropped 14 others). Tests that require genuine LLM semantic judgment cannot pass against a schema-only mock; only structural/API behavior was verified. The one mixed-suite failure is a wall-clock cron freshness flake reproducible without any mock.

Argusic installed parlant in 12 minutes and launched it; verification reached Verified with mock services. 6 of 8 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of parlant

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.