Jobs_Applier_AI_Agent_AIHawk tested by Argusic Runner
Attempt 2 of 3 · Runs with mocks · Argusic Score 92.0 of 100
all runs of Jobs_Applier_AI_Agent_AIHawkai-agentai-agentsautomationbrowser-automationjob-applicationjob-board
Session recording
Download the original recording · fingerprint 97c2b40fb358c903...
What the test found
The repository installs from source with all dependencies, the full automated suite passes (266 non-browser + 6 real-browser), and an end-to-end search-and-apply run through a mock OrcaRouter over a real local job index fills and submits a live Greenhouse application form, writing a decoded proof screenshot.
Installed locally via pip with the dev extra (no root; no system packages needed) and verified the CLI: `aihawk --version` prints `1.0.0`. Ran the repo suite: 266 non-browser tests passed (6 deselected) and the 6 real-browser tests of tests/test_real_browser.py passed. End-to-end against a schema-correct OrcaRouter mock plus a local job index built with duckdb: resume loaded, 600 jobs fetched, 25 shortlisted, 25 scored, a real form on a live Greenhouse posting filled and submitted with a proof PNG saved and decoded. Two job postings I tried were closed/404/redirecting (Paylocity details page and one Greenhouse posting), which is external-site state; another live Greenhouse posting submitted cleanly. The TUI itself was exercised through the underlying Session/funnel/score/apply flows since the keying prompt and Textual screen are interactive; the repository's own TUI tests cover the prompts. Only the mock relied on tier2; the browser, model gateway, job DB, and form submission were real against real sites.
Argusic installed Jobs_Applier_AI_Agent_AIHawk in 4 minutes and launched it; verification reached Verified with mock services. 2 of 2 recorded errors were worked through (see the timeline below).
Runs with mocksall runs of Jobs_Applier_AI_Agent_AIHawk
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.