no_human tested by Argusic Runner

Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100

all runs of no_humanagentagent-harnessagent-orchestrationagentic-aiai-agentai-code-review

Session recording

Loading recording...

Download the original recording · fingerprint 5757dfe356af52d8...

What the test found

no_human v0.2.0 is installed from source with all Python dependencies and the React board built; the CLI, API server, and web board all respond successfully, and the test suite passes except for 14 environment-limited or pre-existing failures (7 bwrap sandbox, 7 orchestrator logic).

Real end-to-end task execution requires a Claude subscription token (CLAUDE_CODE_OAUTH_TOKEN), which is not available in this container. All local non-slow, non-nightly, non-repoguard tests pass (verified across ~5,000+ executed tests). The server starts on port 8420/8422 delivering HTTP 200 with the React board and an 89-endpoint OpenAPI schema. The `nh` CLI responds to --help, --version, status, doctor, config, and mcp-serve commands.

Argusic installed no_human in 13.5 minutes and launched it; verification reached Verified with mock services. 4 of 4 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of no_human

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