Commit graph

5 commits

Author SHA1 Message Date
mubashir1osmani
13ecf55cd0
test(e2e): skip flaky OpenAI GPT cells; raise multi-window max_tokens (#33799)
OpenAI GPT-5.6 Claude Code cells burn minutes on CLI timeouts under the
full stage suite; gate them behind COMPAT_OPENAI_GPT_CELLS=1 like Mantle.
Multi-window budget e2e used max_tokens=1 which gpt-5.5 rejects mid-message
2026-07-17 19:07:18 -07:00
mateo-berri
bb04a1ed15 test(e2e/claude_code): run openai and azure GPT cells unconditionally, gate only bedrock_mantle
The openai and azure_openai columns have working credentials in every suite runner, so only the bedrock_mantle column still needs an opt-in flag while the AWS account waits on the Mantle allowlist; COMPAT_GPT_CELLS becomes COMPAT_MANTLE_CELLS. The six tool_use cells now resolve the proxy through claude_code._env like the basic_messaging cells instead of hardcoding LITELLM_PROXY_BASE_URL/LITELLM_PROXY_API_KEY.
2026-07-16 17:25:39 -07:00
mateo-berri
f93a84b01e test(e2e/claude_code): reuse AZURE_API_BASE/KEY for the azure_openai GPT column 2026-07-16 16:45:18 -07:00
mateo-berri
90f7807830 test(e2e/claude_code): scope the GPT cell opt-in rationale to the cron VM 2026-07-15 16:27:58 -07:00
mateo-berri
710a88eba7 test(e2e/claude_code): add GPT-5.6 Sol/Terra/Luna provider columns for OpenAI, Azure OpenAI, and Bedrock Mantle 2026-07-15 16:25:32 -07:00