pin all CLI installations to explicit versions and use pro models by default (#283)

* pin all CLI installations to explicit versions and use pro models by default

- codex: pin @openai/codex to 0.101.0 (was "latest")
- opencode: pin opencode-ai to 1.1.56 (was "latest")
- gemini: pin gemini-cli to v0.28.2 via new tag param on installFromGithub
- cursor: pin to 2026.01.28-fd13201 via direct tarball download (replaces curl install script)
- add installFromDirectTarball to install.ts for versioned tarball URLs
- gemini auto effort now uses pro-preview instead of flash-preview
- test runner model overrides updated to use pro-preview consistently

Co-authored-by: Cursor <cursoragent@cursor.com>

* increase activity timeout

* fix delegation timeout

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
David Blass
2026-02-12 22:48:29 +00:00
committed by pullfrog[bot]
parent 9071c0ae6c
commit ceadb3120a
8 changed files with 163 additions and 65 deletions
+3 -3
View File
@@ -311,12 +311,12 @@ async function runTestForAgent(ctx: RunContext): Promise<ValidationResult> {
env.PULLFROG_TEST_REPO_SETUP = testConfig.repoSetup;
}
// opencode: set model override so tests use a model with quota (avoids default picking one without quota)
// opencode: override to google/gemini-3-pro-preview to avoid flash's tight RPD quota limits
if (ctx.agent === "opencode") {
env.OPENCODE_MODEL = "google/gemini-3-flash-preview";
env.OPENCODE_MODEL = "google/gemini-3-pro-preview";
}
// gemini: use pro model for tests to avoid flash's tight RPD quota limits
// gemini: override to pro for all tests (including mini-effort) to avoid flash's tight RPD quota limits
if (ctx.agent === "gemini") {
env.GEMINI_MODEL = "gemini-3-pro-preview";
}