infra-lead/molecule-core
1
0
Fork 0
forked from molecule-ai/molecule-core
Code Pull Requests Activity

fix(e2e): MODEL_PROVIDER is provider:model slug, not just provider

Browse Source 
workspace/config.py:258 reads MODEL_PROVIDER as the full model string
(format 'provider:model', e.g. 'anthropic:claude-opus-4-7'). My prior
'openai' alone got parsed as the model name → 404 model_not_found.

Use 'openai:gpt-4o' and also set OPENAI_BASE_URL to api.openai.com
(default was openrouter.ai which takes different key format).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hongming Wang 2026-04-21 10:33:27 -07:00
parent 392282c518
commit b8b3d5ce1f
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
tests/e2e/test_staging_full_saas.sh
View File

@ -238,11 +238,12 @@ tenant_call() {
# expected and actionable.
SECRETS_JSON='{}'
if [ -n "${E2E_OPENAI_API_KEY:-}" ]; then
# MODEL_PROVIDER=openai forces Hermes's resolver to pick the OpenAI
# path. Without it Hermes defaults to Claude (resolution order puts
# anthropic before openai) and you get 404 model_not_found because
# the OpenAI endpoint doesn't serve claude-sonnet-* models.
SECRETS_JSON="{\"OPENAI_API_KEY\":\"$E2E_OPENAI_API_KEY\",\"MODEL_PROVIDER\":\"openai\"}"
# MODEL_PROVIDER is a full model slug in 'provider:model' format per
# workspace/config.py:258. Using just "openai" gets parsed as the
# model name → 404 model_not_found. Also set OPENAI_BASE_URL to
# OpenAI's own endpoint — default is openrouter.ai which would need
# a different key format.
SECRETS_JSON="{\"OPENAI_API_KEY\":\"$E2E_OPENAI_API_KEY\",\"OPENAI_BASE_URL\":\"https://api.openai.com/v1\",\"MODEL_PROVIDER\":\"openai:gpt-4o\"}"
fi
log "5/11 Provisioning parent workspace (runtime=$RUNTIME)..."