opencode-plugin-litellm - npm Package Compare versions

Comparing version 0.3.0 to 0.3.1

package.json

 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "opencode-plugin-litellm",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "OpenCode plugin for LiteLLM proxy support with auto-detection and dynamic model discovery",
@@ -6,0 +6,0 @@ "type": "module",

README.md

@@ -92,5 +92,5 @@ <div align="center">
 
-### Explicit provider
+### Explicit provider (custom URL or auth)
 
-Override the URL, set an API key, or pre-define curated models that the plugin will preserve:
+You **do not need to list any models** — the plugin still discovers them from `/v1/models` automatically. Use this form only when you need to point at a non-default URL or pass an API key:
 
@@ -108,2 +108,21 @@ ```jsonc
         "apiKey": "{env:LITELLM_API_KEY}"
+      }
+    }
+  }
+}
+```
+
+That's the whole config — every model in your LiteLLM `model_list` will appear in the picker.
+
+### Overriding or curating individual models (optional)
+
+If you want to rename a model in the picker, pin its `organizationOwner`, or otherwise hand-curate metadata, add it under `models`. The plugin **preserves your entries verbatim** and only injects discovered models whose key isn't already defined:
+
+```jsonc
+{
+  "provider": {
+    "litellm": {
+      "options": {
+        "baseURL": "http://litellm.internal.example.com/v1",
+        "apiKey": "{env:LITELLM_API_KEY}"
       },
@@ -121,3 +140,3 @@ "models": {
 
-The plugin will **keep your hand-defined `openai/gpt-4o`** and only inject models it discovers that aren't already there.
+Here, `openai/gpt-4o` keeps your custom name; every other model from the proxy is still discovered and added automatically.
 
@@ -124,0 +143,0 @@ ### Reasoning models (gpt-5, o1/o3/o4)

No alert changes

Improved metrics

Total package byte prevSize

42481

1.71%

Number of lines in readme file

369

5.43%

No dependency changes