molecule-ai/molecule-core
35
0
Fork 2
Code Issues 16 Pull Requests 2 Actions 49 Packages Projects Releases Wiki Activity

fix(e2e): set MODEL_PROVIDER=openai for Hermes runtime

Browse Source 
Hermes's provider resolver checks ANTHROPIC_API_KEY first (resolution
order puts anthropic before openai). Without MODEL_PROVIDER=openai
explicitly set, Hermes defaults to claude-sonnet-4-6 against the
OpenAI endpoint and 404s with model_not_found.

Staging E2E run 2026-04-21T17:24Z hit this after every earlier fix
landed (workspace online, A2A ready) — last remaining blocker for
the happy path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hongming Wang 2026-04-21 10:24:58 -07:00
parent 5be20ac1cf
commit 392282c518
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/e2e/test_staging_full_saas.sh
View File

@ -238,7 +238,11 @@ tenant_call() {
# expected and actionable.
SECRETS_JSON='{}'
if [ -n "${E2E_OPENAI_API_KEY:-}" ]; then
SECRETS_JSON="{\"OPENAI_API_KEY\":\"$E2E_OPENAI_API_KEY\"}"
# MODEL_PROVIDER=openai forces Hermes's resolver to pick the OpenAI
# path. Without it Hermes defaults to Claude (resolution order puts
# anthropic before openai) and you get 404 model_not_found because
# the OpenAI endpoint doesn't serve claude-sonnet-* models.
SECRETS_JSON="{\"OPENAI_API_KEY\":\"$E2E_OPENAI_API_KEY\",\"MODEL_PROVIDER\":\"openai\"}"
fi
log "5/11 Provisioning parent workspace (runtime=$RUNTIME)..."