The test suite just stopped needing a model. tester-army's e2e, trending on github oct 6, lets an…
the test suite just stopped needing a model. tester-army's e2e, trending on github oct 6, lets an agent drive your app tests once, then replays them with zero model calls.
the verification step now runs on a recording.
Context
Verified source: tester-army's e2e is a TypeScript end-to-end test runner where each test can be fully deterministic, fully agent-driven from natural-language goals, or a mix. Its docs say every agent step has a deadline and a model-call budget, and its security page says a replay cache committed to the repository lets the runner replay recorded actions.
The security page also warns that everything the runner executes, including a committed replay cache, has the user's OS authority and should be treated as trusted code.
The agent-driven tests and the replay cache match the e2e docs. 'Zero model calls' on replay and the 'trending on github oct 6' date were not seen in the pages read and are not seen in the excerpts read, so unsupported here, not refuted. The security page says a committed replay cache is code-trust, which matters for 'the verification step now runs on a recording'.
'the test suite just stopped needing a model' is the author's opinion.
Related work
- tester-army: e2e ↗Project page.
- e2e docs: How agent steps work ↗Docs.
- GitHub: tester-army/e2e security ↗Security notes.
Watch next
- Read the docs for exactly when a replay makes model calls.
Sources
- tester-army, e2etester.army
- e2e docs, agent stepse2e.tester.army
- e2e docs, debugging a rune2e.tester.army
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 09:06 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →