Tianshu-harness tested by Argusic Runner

Attempt 1 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of Tianshu-harnessai-agentagent-harnessclicoding-agentcontext-managementdeepseek

Session recording

Loading recording...

Download the original recording · fingerprint 68337fc57178e274...

What the test found

The repo installs and builds on Node 24, its 19005-test suite passes with 0 failures, and the CLI runs end-to-end against a local mock OpenAI-compatible provider returning a real agent response.

Built from source on Node 24. Full unit/integration suite passed (19005 tests, 18983 pass/0 fail). End-to-end agent run verified through a self-stood-up schema-correct mock OpenAI-compatible provider since real providers require external API keys. Only package-lock.json changed in repo (dist/ is gitignored).

Argusic installed Tianshu-harness in 20 minutes and launched it; verification reached Verified with mock services. 3 of 3 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of Tianshu-harness

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