add new ai config keys (#66)

docs/config.mdx

@@ -15,8 +15,11 @@ use ":" as level separators.
 |----------|------|----------|
 | ai:baseurl | string | Set the AI Base Url (must be OpenAI compatible) |
 | ai:apitoken | string | your AI api token |
+| ai:apitype | string | defaults to "open_ai", but can also set to "azure" for special Azure AI handling |
 | ai:name | string | string to display in the Wave AI block header |
 | ai:model | string | model name to pass to API |
+| ai:apiversion | string | for Azure AI only (when apitype is "azure", this will default to "2023-05-15") |
+| ai:orgid | string ||
 | ai:maxtokens | int | max tokens to pass to API |
 | ai:timeoutms | int | timeout (in milliseconds) for AI calls |
 | term:fontsize | float | the fontsize for the terminal block |
@@ -50,8 +53,8 @@ For reference this is the current default configuration (v0.8.8):
 ```json
 {
     "ai:model": "gpt-4o-mini",
-    "ai:maxtokens": 1000,
-    "ai:timeoutms": 10000,
+    "ai:maxtokens": 2048,
+    "ai:timeoutms": 60000,
     "autoupdate:enabled": true,
     "autoupdate:installonquit": true,
     "autoupdate:intervalms": 3600000,

docs/faq.mdx

@@ -34,6 +34,14 @@ Here are the ollma open AI compatibility docs: https://github.com/ollama/ollama/
 }
 ```
 
+### How can I connect to Azure AI
+
+You must manually edit the [config file](./config) located at `~/.waveterm/config/settings.json`.
+
+You'll need to set your `ai:baseurl` to your Azure AI Base URL (do not include query parameters or `api-version`).
+You'll also need to set `ai:apitype` to `azure`.  You can then set the `ai:model`, and `ai:apitoken` appropriately
+for your setup.
+
 ### How can I see the block numbers?
 
 The block numbers will appear when you hold down Ctrl-Shift (and disappear once you release the key combo).
@@ -54,3 +62,4 @@ Just remember in JSON, backslashes need to be escaped.  So add this to your [set
 ```
 
 
+

docs/wsh.mdx

@@ -1,7 +1,7 @@
 ---
 sidebar_position: 4
 id: "wsh"
-title: "Wsh"
+title: "wsh command"
 ---
 # wsh command