feat: per-target API keys and add-target flow for /connect

README.md

@@ -11,17 +11,18 @@ It currently supports the following local backends:
 - llama-swap
 - oMLX
 - MLX-VLM
+- Any other server with an OpenAI-compatible `/v1/models` endpoint (`openai`, used when nothing more specific matches)
 
-Instead of creating one provider per server, this plugin keeps one `local` provider and lets you register multiple named targets. Each target is probed at runtime, and its currently loaded models are exposed automatically.
+Instead of creating one provider per server, this plugin keeps one `local` provider and lets you register multiple named targets. Each target is probed at runtime, and its models are exposed automatically.
 
 ## Features
 
 - Adds a `local` provider to OpenCode
-- Supports multiple local URLs under one provider
+- Supports multiple servers under one provider
 - Includes supported default `127.0.0.1` targets automatically
-- Detects loaded models at runtime
+- Detects models at runtime and fills in context size, tool calling, and vision support where the server reports them
 - Routes each model to the correct target URL
-- API key auth currently unsupported
+- Optional API key per target, sent as `Authorization: Bearer <key>`
 - Uses OpenCode global config, not project-local config
 
 ## Example
@@ -47,43 +48,49 @@ Default targets are enabled automatically for these backends and ports:
 - Exo: `http://127.0.0.1:52415`
 - llama-swap: `http://127.0.0.1:8080`
 - oMLX: `http://127.0.0.1:8000`
-- MLX-VLM: `http://127.0.0.1:8000`
+- MLX-VLM: `http://127.0.0.1:8080`
 
-If your local providers do not need auth, you can start using the `local` provider immediately.
+If your local servers run on these ports and do not need an API key, you can start using the `local` provider immediately.
 
-**Note: oMLX requires API authentication to be disabled in the web app settings for the plugin to detect and probe models.**
-
-**Note: API key authentication is currently unsupported.**
+**Note: oMLX with API authentication enabled needs a custom target with its API key set (see below).**
 
 ## Custom Targets
 
-If you need non-default hosts or ports, use the CLI auth flow to add an explicit target:
+Add a server on another host or port, or one that needs an API key, with **Add Custom Target**. Run it from the TUI with `/connect` → **Local LLM Provider**, or from the CLI:
 
 ```bash
 opencode auth login --provider local --method "Add Custom Target"
 ```
 
-This will prompt for:
+It asks for:
 
 - a target ID, like `studio` or `remote-ollama`
-- the local provider URL
-- the API key (enter `none` since API keys are currently unsupported)
+- the server URL, with or without `/v1`
+- the server's API key. Leave it empty if the server has none. Enter `{env:VAR_NAME}` to store a reference to an environment variable instead of the key itself
+- which models to list: only loaded models, or every model the server offers (useful for llama-swap, which loads models on demand)
+
+The plugin checks that the server answers before it saves anything, then adds the target to your OpenCode global config. Run it again to add more servers.
 
-The target is then stored in OpenCode global config.
+`/connect` only lists **Local LLM Provider** once the provider has at least one model. If none of your servers are reachable yet, add the first target from the CLI.
 
-You can also add explicit targets manually in config if needed:
+You can also add targets manually in config:
 
 ```json
 {
   "provider": {
     "local": {
-      "name": "Local Provider",
       "options": {
         "includeDefaults": true,
         "targets": {
           "studio": {
             "url": "http://192.168.1.10:1234/v1",
             "kind": "lmstudio"
+          },
+          "swap": {
+            "url": "https://llama-swap.example.com/v1",
+            "kind": "llamaswap",
+            "apiKey": "{env:LLAMA_SWAP_API_KEY}",
+            "includeUnloaded": true
           }
         }
       }
@@ -92,53 +99,34 @@ You can also add explicit targets manually in config if needed:
 }
 ```
 
-Explicit targets override the built-in defaults when they use the same ID.
-The CLI custom-target method is the supported way to add explicit targets without editing config directly.
-
-## Resulting Config
+Target fields:
 
-The plugin stores explicit targets in OpenCode global config under the `local` provider:
-
-```json
-{
-  "provider": {
-    "local": {
-      "name": "Local Provider",
-      "options": {
-        "includeDefaults": true,
-        "targets": {
-          "studio": {
-            "url": "http://127.0.0.1:1234/v1",
-            "kind": "lmstudio"
-          }
-        }
-      }
-    }
-  }
-}
-```
+- `url` (required): the server URL
+- `kind` (optional): one of `ollama`, `lmstudio`, `llamacpp`, `vllm`, `exo`, `llamaswap`, `omlx`, `mlxvlm`, `openai`. If you leave it out, the backend is detected. `openai` treats any server as a plain OpenAI-compatible endpoint
+- `apiKey` (optional): sent as `Authorization: Bearer <key>` when probing the server and with every chat request to its models. Use `{env:VAR_NAME}` to keep the key out of the config file
+- `includeUnloaded` (optional, llama-swap only): list every model llama-swap offers, not only the loaded ones. The plugin reads their details from `/v1/models` and does not load them
 
-With `includeDefaults: true`, the built-in default `127.0.0.1` targets are also checked at runtime even though they are not written into config.
+Explicit targets override the built-in defaults when they use the same ID. A key set in `provider.local.options.apiKey` applies to every target that has no `apiKey` of its own.
 
-**Note: API key authentication is currently unsupported.**
+With `includeDefaults: true`, the built-in default `127.0.0.1` targets are also checked at runtime even though they are not written into config. Set it to `false` if you only use custom targets.
 
 ## How Models Appear
 
-Models are discovered dynamically from each configured target. (Only **loaded** models)
+Models are discovered dynamically from each configured target. By default, only **loaded** models are listed.
 
 To avoid collisions, model IDs are prefixed with the target ID:
 
 - `ollama/llama3.2`
 - `studio/qwen2.5-coder`
 
-Each generated model keeps its own target URL internally, so requests go to the correct backend.
+Each generated model keeps its own target URL and API key internally, so requests go to the correct backend.
 
 ## Notes
 
 - Model detection is runtime-based, not static
 - If loaded models change in your local server, OpenCode will see the updated list on the next provider refresh
 - Built-in default `127.0.0.1` targets are enabled unless you set `includeDefaults` to `false`
-- **API key authentication is currently unsupported**
+- If a custom target cannot be probed, the reason (for example `HTTP 401` for a wrong key) is written to the OpenCode log
 
 ## Development