izwi tested by Argusic Runner

Attempt 2 of 3 · Runs with mocks · Argusic Score 85.3 of 100

all runs of izwiasraudio-inferencelocal-firstopenai-compatible-apiself-hosted-aispeaker-diarization

Session recording

Loading recording...

Download the original recording · fingerprint 1f5b77f0a18823e1...

What the test found

Izwi CLI 0.1.0-beta-18 and HTTP API server compile and run on linux-x86_64 with CPU backend; all 3169+ unit tests pass across 7 workspace crates; server serves OpenAI-compatible /v1/ endpoints on port 8080 with proper health, metrics, model listing, OpenAPI docs, and web UI; desktop Tauri shell cannot build due to missing system GUI libraries.

System GTK3/WebKit libraries unavailable (no root) — desktop native shell cannot be built. Server + web UI + CLI + all non-desktop tests fully verified. CLI is 17 MB, server binary is 91 MB. Inference models require HuggingFace download (several GB per model) so end-to-end TTS/ASR inference is tier2. Server correctly rejects model requests with proper OpenAI-style 400/404 errors.

Argusic installed izwi in 10 minutes and launched it; verification reached Verified with mock services. 2 of 3 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of izwi

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.

Error and fix timeline

No errors were recorded for this run.

Discussion