Add o1 to verfied models

[mamoodi]

End-user friendly description of the problem this fixes or functionality that this introduces

• Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below

Add o1 to verified models

---

Give a summary of what the PR does, explaining any non-trivial design decisions

Tested setting provider to OpenAI and model to o1 and it works. Do we want it in the "verified models"?

---

Link of any specific issues this addresses
#6030

---

To run this PR locally, use the following command:

docker run -it --rm   -p 3000:3000   -v /var/run/docker.sock:/var/run/docker.sock   --add-host host.docker.internal:host-gateway   -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:69a2435-nikolaik   --name openhands-app-69a2435   docker.all-hands.dev/all-hands-ai/openhands:69a2435

[mamoodi]

Does it need to be added anywhere in this file?

OpenHands/openhands/llm/llm.py

Lines 44 to 98 in 6655ec0

	LLM_RETRY_EXCEPTIONS: tuple[type[Exception], ...] = (
	APIConnectionError,
	# FIXME: APIError is useful on 502 from a proxy for example,
	# but it also retries on other errors that are permanent
	APIError,
	InternalServerError,
	RateLimitError,
	ServiceUnavailableError,
	)
	# cache prompt supporting models
	# remove this when we gemini and deepseek are supported
	CACHE_PROMPT_SUPPORTED_MODELS = [
	'claude-3-5-sonnet-20241022',
	'claude-3-5-sonnet-20240620',
	'claude-3-5-haiku-20241022',
	'claude-3-haiku-20240307',
	'claude-3-opus-20240229',
	]
	# function calling supporting models
	FUNCTION_CALLING_SUPPORTED_MODELS = [
	'claude-3-5-sonnet',
	'claude-3-5-sonnet-20240620',
	'claude-3-5-sonnet-20241022',
	'claude-3.5-haiku',
	'claude-3-5-haiku-20241022',
	'gpt-4o-mini',
	'gpt-4o',
	'o1-2024-12-17',
	'o3-mini-2025-01-31',
	'o3-mini',
	]
	# visual browsing tool supported models
	# This flag is needed since gpt-4o and gpt-4o-mini do not allow passing image_urls with role='tool'
	VISUAL_BROWSING_TOOL_SUPPORTED_MODELS = [
	'claude-3-5-sonnet',
	'claude-3-5-sonnet-20240620',
	'claude-3-5-sonnet-20241022',
	'o1-2024-12-17',
	]
	REASONING_EFFORT_SUPPORTED_MODELS = [
	'o1-2024-12-17',
	'o1',
	'o3-mini-2025-01-31',
	'o3-mini',
	]
	MODELS_WITHOUT_STOP_WORDS = [
	'o1-mini',
	'o1-preview',
	]

[enyst]

I don't think it needs to be in more places in llm.py.

Maybe we can remove o1-preview from verified, if we add o1?

[mamoodi]

I don't think it needs to be in more places in llm.py.

Maybe we can remove o1-preview from verified, if we add o1?

You know better. Should I remove it?

[enyst]

Yes, I don't think there's a great use anymore, and anyway people can add it themselves in advanced settings