built_in_providerTier 1 · 70% confidence

ai-agents-built-in-provider-when-using-ollama-cloud-as-an-inference-provider-i-7a1bcd35

agent: ai_agents

When does this happen?

IF When using Ollama Cloud as an inference provider in auxiliary tasks, users must configure it via custom_providers with redundant base_url and api_key, causing duplication and unrecognized provider setting.

How others solved it

THEN Add `ollama-cloud` to `PROVIDER_REGISTRY` in `auth.py` with `inference_base_url` set to `https://ollama.com/v1` and api key env var `OLLAMA_CLOUD_API_KEY`. Also add a default auxiliary model name like `nemotron-3-super` in `auxiliary_client.py` to streamline configuration.

"ollama-cloud": ProviderConfig(
    id="ollama-cloud",
    name="Ollama Cloud",
    auth_type="api_key",
    inference_base_url="https://ollama.com/v1",
    api_key_env_vars=("OLLAMA_CLOUD_API_KEY",),
)

Related patterns

github

ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0

Tier 1 · 40%
github

ai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e

Tier 1 · 40%
github

ai-agents-github-patrick-von-platen-cd4d7ceb

Tier 1 · 40%
model_loading

ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71

Tier 1 · 70%
github

ai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119

Tier 1 · 40%
github

ai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca

Tier 1 · 40%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics