Framework agents require `OPENAI_API_KEY` on the server even when the model is Anthropic

[ambiorix2099]

Files: examples/agents/93_openai_runner_hello_world.py, 94_openai_runner_tools.py, 95_openai_runner_handoffs.py, 96_openai_runner_streaming.py (the conductor.ai Runner / framework-agent path)

Symptom: With no OPENAI_API_KEY in the server process's environment:

$ CONDUCTOR_AGENT_LLM_MODEL=anthropic/claude-sonnet-4-6 python examples/agents/93_openai_runner_hello_world.py
Framework agent 'Assistant' execution FAILED
None

96 is worse — it exits 0 having printed only an execution id, so exit-code-based tooling scores it green.

Cause: The framework-agent path needs an OpenAI key server-side regardless of the configured model. Confirmed by controlled comparison on one server, changing only the server's environment:

Server env	model	result
no OPENAI_API_KEY	anthropic/claude-sonnet-4-6	FAILED
no OPENAI_API_KEY	anthropic/claude-opus-4-6	FAILED
OPENAI_API_KEY present	anthropic/claude-sonnet-4-6	pass
OPENAI_API_KEY present	anthropic/claude-opus-4-6	pass

Ruled out: the client's environment (passes with the client key unset), and langchain-anthropic being installed (passes with it uninstalled). Only the server's env matters.

Fix: Either drop the OpenAI dependency when the target model is not OpenAI, or fail with a message naming the missing key. Silent failure with None is the worst outcome.

Verify: Start the server with no OPENAI_API_KEY, run 93 with an Anthropic model — it should either work or say why.

Note: These examples document CONDUCTOR_AGENT_LLM_MODEL=openai/gpt-4o (or anthropic/claude-opus-4-6), so a user following the Anthropic option with an Anthropic-only server hits this immediately.