feat: Add OpenAI Compatible embedder for codebase indexing (#4066)

* feat: Add OpenAI Compatible embedder for codebase indexing

- Implement OpenAiCompatibleEmbedder with batching and retry logic
- Add configuration support for base URL and API key
- Update UI with provider selection and input fields
- Add comprehensive test coverage
- Support for all OpenAI-compatible endpoints (LiteLLM, LMStudio, Ollama, etc.)
- Add internationalization for 17 languages

* fix: Update CodeIndexSettings tests for OpenAI Compatible provider

- Fix field count expectations (4 fields including Qdrant)
- Use specific test IDs for button selection
- Fix input handling with clear() before type()
- Use toHaveBeenLastCalledWith for better assertions
- Fix status text matching with regex pattern

* fix: resolve UI test failures and ESLint errors

- Remove unused waitFor import to fix ESLint error
- Fix test expectations to match actual component behavior for input fields
- Simplify provider selection test by removing complex mock interactions
- All CodeIndexSettings tests now pass (20/20)

* feat: add custom model infrastructure for OpenAI-compatible embedder

- Add manual model ID and embedding dimension configuration
- Enable custom model input via text field in settings UI
- Add modelDimension parameter to OpenAiCompatibleEmbedder
- Update configuration management to persist dimension setting
- Prioritize manual dimension over hardcoded model profiles
- Add comprehensive test coverage for new functionality

This allows users to specify any custom embedding model and its
dimension for OpenAI-compatible providers, removing dependency
on hardcoded model profiles.

* Add missing translations for OpenAI-compatible model dimension settings in all locales

* refactor: remove unused modelDimension parameter from OpenAiCompatibleEmbedder

- Remove modelDimension property and constructor parameter from OpenAiCompatibleEmbedder class
- Update ServiceFactory to not pass dimension to embedder constructor
- Update tests to match new constructor signature
- The dimension is still used for QdrantVectorStore configuration

* chore: bot suggestion

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* chore: bot suggestion

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* refactor: rename OpenAiCompatibleEmbedder to OpenAICompatibleEmbedder for consistency

* feat: add model dimension validation for OpenAI-compatible settings

* refactor: improve default model ID retrieval logic for embedding providers

* feat: add default model ID retrieval for openai-compatible provider

* refactor: update default model ID retrieval to use shared utility function

* fix: Remove unnecessary type assertion in OpenAICompatibleEmbedder

* feat: add model dimension input for openai-compatible provider

---------

Co-authored-by: Daniel Riccio <[email protected]>
Co-authored-by: Daniel <[email protected]>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

Author: 3 people

packages/types/src/__tests__/index.test.ts

@@ -14,4 +14,12 @@ describe("GLOBAL_STATE_KEYS", () => {
 	it("should not contain secret state keys", () => {
 		expect(GLOBAL_STATE_KEYS).not.toContain("openRouterApiKey")
 	})
+
+	it("should contain OpenAI Compatible base URL setting", () => {
+		expect(GLOBAL_STATE_KEYS).toContain("codebaseIndexOpenAiCompatibleBaseUrl")
+	})
+
+	it("should not contain OpenAI Compatible API key (secret)", () => {
+		expect(GLOBAL_STATE_KEYS).not.toContain("codebaseIndexOpenAiCompatibleApiKey")
+	})
 })

packages/types/src/codebase-index.ts

@@ -7,7 +7,7 @@ import { z } from "zod"
 export const codebaseIndexConfigSchema = z.object({
 	codebaseIndexEnabled: z.boolean().optional(),
 	codebaseIndexQdrantUrl: z.string().optional(),
-	codebaseIndexEmbedderProvider: z.enum(["openai", "ollama"]).optional(),
+	codebaseIndexEmbedderProvider: z.enum(["openai", "ollama", "openai-compatible"]).optional(),
 	codebaseIndexEmbedderBaseUrl: z.string().optional(),
 	codebaseIndexEmbedderModelId: z.string().optional(),
 })
@@ -21,6 +21,7 @@ export type CodebaseIndexConfig = z.infer<typeof codebaseIndexConfigSchema>
 export const codebaseIndexModelsSchema = z.object({
 	openai: z.record(z.string(), z.object({ dimension: z.number() })).optional(),
 	ollama: z.record(z.string(), z.object({ dimension: z.number() })).optional(),
+	"openai-compatible": z.record(z.string(), z.object({ dimension: z.number() })).optional(),
 })
 
 export type CodebaseIndexModels = z.infer<typeof codebaseIndexModelsSchema>
@@ -32,6 +33,9 @@ export type CodebaseIndexModels = z.infer<typeof codebaseIndexModelsSchema>
 export const codebaseIndexProviderSchema = z.object({
 	codeIndexOpenAiKey: z.string().optional(),
 	codeIndexQdrantApiKey: z.string().optional(),
+	codebaseIndexOpenAiCompatibleBaseUrl: z.string().optional(),
+	codebaseIndexOpenAiCompatibleApiKey: z.string().optional(),
+	codebaseIndexOpenAiCompatibleModelDimension: z.number().optional(),
 })
 
 export type CodebaseIndexProvider = z.infer<typeof codebaseIndexProviderSchema>

packages/types/src/global-settings.ts

@@ -223,6 +223,7 @@ export type SecretState = Pick<
 	| "litellmApiKey"
 	| "codeIndexOpenAiKey"
 	| "codeIndexQdrantApiKey"
+	| "codebaseIndexOpenAiCompatibleApiKey"
 >
 
 export const SECRET_STATE_KEYS = keysOf<SecretState>()([
@@ -245,6 +246,7 @@ export const SECRET_STATE_KEYS = keysOf<SecretState>()([
 	"litellmApiKey",
 	"codeIndexOpenAiKey",
 	"codeIndexQdrantApiKey",
+	"codebaseIndexOpenAiCompatibleApiKey",
 ])
 
 export const isSecretStateKey = (key: string): key is Keys<SecretState> =>

packages/types/src/provider-settings.ts

@@ -336,6 +336,9 @@ export const PROVIDER_SETTINGS_KEYS = keysOf<ProviderSettings>()([
 	// Code Index
 	"codeIndexOpenAiKey",
 	"codeIndexQdrantApiKey",
+	"codebaseIndexOpenAiCompatibleBaseUrl",
+	"codebaseIndexOpenAiCompatibleApiKey",
+	"codebaseIndexOpenAiCompatibleModelDimension",
 	// Reasoning
 	"enableReasoningEffort",
 	"reasoningEffort",