chore: update docs for ollama endpoint (#992)

crates/goose/src/providers/ollama.rs

@@ -53,6 +53,7 @@ impl OllamaProvider {
     }
 
     async fn post(&self, payload: Value) -> Result<Value, ProviderError> {
+        // TODO: remove this later when the UI handles provider config refresh
         // OLLAMA_HOST is sometimes just the 'host' or 'host:port' without a scheme
         let base = if self.host.starts_with("http://") || self.host.starts_with("https://") {
             self.host.clone()

documentation/docs/getting-started/providers.md

@@ -164,6 +164,12 @@ Ollama provides local LLMs, which requires a bit more set up before you can use
 1. [Download Ollama](https://ollama.com/download). 
 2. Run any [model supporting tool-calling](https://ollama.com/search?c=tools):
 
+
+:::info Ollama Endpoint Construction
+For Ollama, we set default host to `localhost` and port to `11434` if you don't provide it. When constructing the URL, we preprend `"http://"` if the scheme is not http or https.
+If you're running Ollama on port 80 or 443, you have to set `OLLMA_HOST=http://host:port`
+:::
+
 :::warning Limited Support for models without tool calling
 Goose extensively uses tool calling, so models without it (e.g. `DeepSeek-r1`) can only do chat completion. If using models without tool calling, all Goose [extensions must be disabled](/docs/getting-started/using-extensions#enablingdisabling-extensions). As an alternative, you can use a [custom DeepSeek-r1 model](/docs/getting-started/providers#deepseek-r1) we've made specifically for Goose.
 :::