fix: add autocompleteOptions in the .yaml config

core/util/parameters.ts

@@ -20,6 +20,7 @@ export const DEFAULT_AUTOCOMPLETE_OPTS: TabAutocompleteOptions = {
   useImports: true,
   transform: true,
   showWhateverWeHaveAtXMs: 300,
+  // Experimental options: true = enabled, false = disabled, number = enabled w priority
   experimental_includeClipboard: true,
   experimental_includeRecentlyVisitedRanges: true,
   experimental_includeRecentlyEditedRanges: true,

docs/customize/deep-dives/autocomplete.mdx

@@ -84,15 +84,15 @@ Then, add the model to your configuration:
 
 Once the model has been downloaded, you should begin to see completions in VS Code.
 
-NOTE: Typically, thinking-type models are not recommended as they generate more slowly and are not suitable for scenarios that require speed. 
+NOTE: Typically, thinking-type models are not recommended as they generate more slowly and are not suitable for scenarios that require speed.
 
 However, if you use any thinking-switchable models, you can configure these models for autocomplete functions by turning off the thinking mode.
 
 For example:
 
 <Tabs>
   <Tab title="YAML">
-  ```yaml title="config.yaml"
+```yaml title="config.yaml"
   models:
     - name: Qwen3 without Thinking for Autocomplete
       provider: ollama
@@ -122,9 +122,32 @@ The following settings can be configured for autocompletion in the IDE extension
 - `Multiline Autocompletions`: Controls multiline completions for autocomplete. Can be set to `always`, `never`, or `auto`. Defaults to `auto`
 - `Disable autocomplete in files`: List of comma-separated glob pattern to disable autocomplete in matching files. E.g., "\_/.md, \*/.txt"
 
-### `config.json` Configuration
+### Autocomplete Configuration
+
+#### YAML Configuration
+
+The `config.yaml` format offers model-level configuration using the `autocompleteOptions` field. See the [YAML Reference](/reference#models) for more details.
+
+```yaml
+models:
+  - name: Codestral
+    provider: mistral
+    model: codestral-latest
+    roles:
+      - autocomplete
+    autocompleteOptions:
+      disable: false
+      maxPromptTokens: 1024
+      debounceDelay: 250
+      modelTimeout: 150
+      maxSuffixPercentage: 0.2
+      prefixPercentage: 0.3
+      onlyMyCode: true
+```
+
+#### JSON Configuration (Deprecated)
 
-The `config.json` configuration format (deprecated) offers further configuration options through `tabAutocompleteOptions`. See the [JSON Reference](/reference) for more details.
+The `config.json` configuration format offers configuration options through `tabAutocompleteOptions`. See the [JSON Reference](/reference/json-reference#tabautocomplete-options) for more details.
 
 ## FAQs
 

docs/reference.mdx

@@ -175,6 +175,7 @@ The `models` section defines the language models used in your configuration. Mod
 
 - `roles`: An array specifying the roles this model can fulfill, such as `chat`, `autocomplete`, `embed`, `rerank`, `edit`, `apply`, `summarize`. The default value is `[chat, edit, apply, summarize]`. Note that the `summarize` role is not currently used.
 
+
 - `capabilities`: Array of strings denoting model capabilities, which will overwrite Continue's autodetection based on provider and model. See the [Model Capabilities guide](/customize/deep-dives/model-capabilities) for detailed information. Supported capabilities include:
   - `tool_use`: Enables function/tool calling support (required for Agent mode)
   - `image_input`: Enables image upload and processing support
@@ -228,6 +229,21 @@ The `models` section defines the language models used in your configuration. Mod
     - `key`: Path to the client certificate key file.
     - `passphrase`: Optional passphrase for the client certificate key file.
 
+- `autocompleteOptions`: If the model includes role `autocomplete`, these settings apply for tab autocompletion:
+
+  - `disable`: If `true`, disables autocomplete for this model.
+  - `maxPromptTokens`: Maximum number of tokens for the autocomplete prompt.
+  - `debounceDelay`: Delay before triggering autocomplete in milliseconds.
+  - `modelTimeout`: Model timeout for autocomplete requests in milliseconds.
+  - `maxSuffixPercentage`: Maximum percentage of prompt allocated for suffix.
+  - `prefixPercentage`: Percentage of input allocated for prefix.
+  - `template`: Custom template for autocomplete using Mustache syntax. You can use the `{{{ prefix }}}`, `{{{ suffix }}}`, `{{{ filename }}}`, `{{{ reponame }}}`, and `{{{ language }}}` variables.
+  - `onlyMyCode`: Only includes code within the repository for context.
+  - `useCache`: If `true`, enables caching for completions.
+  - `useImports`: If `true`, includes imports in context.
+  - `useRecentlyEdited`: If `true`, includes recently edited files in context.
+  - `useRecentlyOpened`: If `true`, includes recently opened files in context.
+
 **Example:**
 
 ```yaml title="config.yaml"
@@ -247,6 +263,10 @@ models:
     model: codestral-latest
     roles:
       - autocomplete
+    autocompleteOptions:
+      debounceDelay: 250
+      maxPromptTokens: 1024
+      onlyMyCode: true
   - name: My Model - OpenAI-Compatible
     provider: openai
     apiBase: http://my-endpoint/v1
@@ -456,6 +476,10 @@ models:
     model: starcoder
     roles:
       - autocomplete
+    autocompleteOptions:
+      debounceDelay: 350
+      maxPromptTokens: 1024
+      onlyMyCode: true
     defaultCompletionOptions:
       temperature: 0.3
       stop:
@@ -531,4 +555,8 @@ models:
     useLegacyCompletionsEndpoint: false
     roles:
       - autocomplete
+    autocompleteOptions:
+      debounceDelay: 350
+      maxPromptTokens: 1024
+      onlyMyCode: true
 ```

docs/reference/json-reference.mdx

@@ -107,6 +107,12 @@ config.json
 
 Specifies options for tab autocompletion behavior.
 
+<Info>
+  **Note**: Many of these parameters can also be configured per-model using the
+  `autocompleteOptions` field in `config.yaml`. See the [YAML
+  Reference](/reference#models) for more details.
+</Info>
+
 **Properties:**
 
 - `disable`: If `true`, disables tab autocomplete (default: `false`).

packages/config-types/src/index.ts

@@ -151,6 +151,16 @@ export const tabAutocompleteOptionsSchema = z.object({
   useRecentlyEdited: z.boolean(),
   disableInFiles: z.array(z.string()).optional(),
   useImports: z.boolean().optional(),
+  // Experimental options: true = enabled, false = disabled, number = enabled w priority
+  experimental_includeClipboard: z.union([z.boolean(), z.number()]).optional(),
+  experimental_includeRecentlyVisitedRanges: z
+    .union([z.boolean(), z.number()])
+    .optional(),
+  experimental_includeRecentlyEditedRanges: z
+    .union([z.boolean(), z.number()])
+    .optional(),
+  experimental_includeDiff: z.union([z.boolean(), z.number()]).optional(),
+  experimental_enableStaticContextualization: z.boolean().optional(),
 });
 export type TabAutocompleteOptions = z.infer<
   typeof tabAutocompleteOptionsSchema

packages/config-yaml/src/schemas/models.ts

@@ -120,6 +120,16 @@ export const autocompleteOptionsSchema = z.object({
   prefixPercentage: z.number().optional(),
   template: z.string().optional(),
   onlyMyCode: z.boolean().optional(),
+  useCache: z.boolean().optional(),
+  useImports: z.boolean().optional(),
+  useRecentlyEdited: z.boolean().optional(),
+  useRecentlyOpened: z.boolean().optional(),
+  // Experimental options: true = enabled, false = disabled, number = enabled w priority
+  experimental_includeClipboard: z.boolean().optional(),
+  experimental_includeRecentlyVisitedRanges: z.boolean().optional(),
+  experimental_includeRecentlyEditedRanges: z.boolean().optional(),
+  experimental_includeDiff: z.boolean().optional(),
+  experimental_enableStaticContextualization: z.boolean().optional(),
 });
 
 /** Prompt templates use Handlebars syntax */