Commit graph

4 commits

Author SHA1 Message Date
mateo-berri
e95ed75614 test(e2e): run the client-apps OpenAI cells on gpt-5.6 and accept a Codex preamble message 2026-09-22 12:42:11 -07:00
mateo-berri
348ecf6556 test(e2e): register client-apps deployments per run and make the turns cache-proof
The suite now creates its own Anthropic and OpenAI deployments through
/model/new under run-unique names and deletes them at session end, so it no
longer depends on which aliases the proxy config serves. The names start
with the real model id because Claude Code 2.1.278 picks its request shape
from the model name and sends an unrecognized one a system-role probe that
Anthropic rejects with a 400 before the CLI falls back, which the proxy bills
as a failure row.

The echoed word is unique per run: the CI stack caches responses, and an
identical prompt across the three CI passes was served a $0 cache-hit row.
Tests move into the classes the e2e harness requires, the spend helper
asserts the row count it polls for, and the AI SDK cell accepts a single
text delta since the provider chunks the final sentence as it likes.
2026-09-22 11:03:30 -07:00
mateo-berri
c45f63216f fix(e2e): turn the Codex sandbox off so the tool turn runs on Linux CI 2026-09-21 22:36:16 -07:00
mateo-berri
173f4c45ed test(e2e): drive the proxy through the Claude Code CLI, the Codex CLI, and the Vercel AI SDK 2026-09-21 22:01:11 -07:00