Rebuilt on develop (after #176) and reworked per review: instead of inferring the provider from baseUrl (`if (baseUrl)`), the admin picks the chat provider EXPLICITLY via a new `chatApiStyle` ('openai-compatible' | 'openai'), mirroring the existing sttApiStyle. A custom baseURL can front real OpenAI too, so the heuristic was fragile. Why reasoning was missing: glm-5.2 (and DeepSeek etc.) stream their thinking as `reasoning_content`, but the official @ai-sdk/openai provider does not map that field. 'openai-compatible' uses @ai-sdk/openai-compatible, which does — so reasoning parts now stream (verified live: reasoning-start/delta/end appear, and disappear when set to 'openai'). - Default (unset) = 'openai-compatible', so existing openai+baseUrl workspaces surface reasoning with no admin action. No DB migration (field lives in the settings.ai.provider JSON blob). - includeUsage: true on the openai-compatible model — without it the provider omits streamed usage, zeroing the live token counter / reasoning-token metadata. The official provider always sent it; this keeps parity. (Confirmed live: usage.totalTokens present.) - openai-compatible has no default endpoint, so with no baseURL (real OpenAI, or a role's cross-driver override that cleared it) it falls back to the official provider. Plumbing: ai.types (ChatApiStyle / CHAT_API_STYLES + AiProviderSettings / MaskedAiSettings), update DTO (@IsIn), ai-settings.service (resolve / getMasked / update allowlist), workspace.repo updateAiProviderSettings ALLOWED (the second, SQL-level allowlist the review missed — without it the field never persisted), ai.service selector. Client: ai-settings-service types + a Protocol <Select> in the chat section + i18n (en/ru). Scope is chat-only (embeddings don't stream reasoning; STT already has sttApiStyle). Tests: ai.service.spec — 4 cases (openai-compatible+baseURL, openai+baseURL, default-unset, openai-compatible-without-baseURL fallback). Verified on the stand: default streams reasoning + usage; 'openai' drops reasoning; the setting round-trips. server + client tsc clean; 36 ai/settings specs green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
114 lines
4.0 KiB
TypeScript
114 lines
4.0 KiB
TypeScript
import api from "@/lib/api-client";
|
|
|
|
// Supported LLM providers/drivers.
|
|
export type AiDriver = "openai" | "gemini" | "ollama";
|
|
|
|
// How STT (speech-to-text) requests are encoded for the transcription endpoint.
|
|
// - 'multipart' -> OpenAI-compatible multipart/form-data (OpenAI, speaches,
|
|
// faster-whisper-server)
|
|
// - 'json' -> JSON body with base64-encoded audio (OpenRouter)
|
|
export type SttApiStyle = "multipart" | "json";
|
|
|
|
// Chat provider implementation for the `openai` driver (chosen explicitly):
|
|
// - 'openai-compatible' -> maps streamed reasoning_content to reasoning parts
|
|
// (z.ai/GLM, DeepSeek, OpenRouter, ...). Default.
|
|
// - 'openai' -> official provider; real-OpenAI reasoning-model shaping.
|
|
export type ChatApiStyle = "openai-compatible" | "openai";
|
|
|
|
// Masked AI provider settings returned by the server.
|
|
// No API key is ever returned; only `hasApiKey` / `hasEmbeddingApiKey` indicate
|
|
// whether one is stored. `embeddingBaseUrl` is the RAW stored value (empty means
|
|
// "uses the chat base URL").
|
|
export interface IAiSettings {
|
|
driver?: AiDriver;
|
|
chatModel?: string;
|
|
chatApiStyle?: ChatApiStyle;
|
|
// Cheap model id for the anonymous public-share assistant; empty = chatModel.
|
|
publicShareChatModel?: string;
|
|
// Agent-role id whose persona the public-share assistant adopts; empty =
|
|
// built-in locked persona.
|
|
publicShareAssistantRoleId?: string;
|
|
embeddingModel?: string;
|
|
baseUrl?: string;
|
|
embeddingBaseUrl?: string;
|
|
systemPrompt?: string;
|
|
hasApiKey: boolean;
|
|
hasEmbeddingApiKey: boolean;
|
|
// STT-specific settings. `sttBaseUrl` is the RAW stored value (empty means
|
|
// "uses the chat base URL"). `hasSttApiKey` indicates whether an STT-specific
|
|
// key is stored (empty means "uses the chat API key").
|
|
sttModel?: string;
|
|
sttBaseUrl?: string;
|
|
sttApiStyle?: SttApiStyle;
|
|
// ISO-639-1 dictation language; empty = auto-detect.
|
|
sttLanguage?: string;
|
|
hasSttApiKey: boolean;
|
|
// RAG indexing coverage (pages indexed for semantic search).
|
|
indexedPages: number;
|
|
totalPages: number;
|
|
}
|
|
|
|
// Update payload. Key semantics (same for `apiKey` and `embeddingApiKey`):
|
|
// - omit the key -> key unchanged
|
|
// - `key: ''` -> clear the stored key
|
|
// - `key: 'non-empty'` -> set the key
|
|
// Non-secret fields are saved as given.
|
|
export interface IAiSettingsUpdate {
|
|
driver?: AiDriver;
|
|
chatModel?: string;
|
|
chatApiStyle?: ChatApiStyle;
|
|
publicShareChatModel?: string;
|
|
// Agent-role id whose persona the public-share assistant adopts; empty =
|
|
// built-in locked persona.
|
|
publicShareAssistantRoleId?: string;
|
|
embeddingModel?: string;
|
|
baseUrl?: string;
|
|
embeddingBaseUrl?: string;
|
|
systemPrompt?: string;
|
|
apiKey?: string;
|
|
embeddingApiKey?: string;
|
|
sttModel?: string;
|
|
sttBaseUrl?: string;
|
|
sttApiStyle?: SttApiStyle;
|
|
// ISO-639-1 dictation language; empty = auto-detect.
|
|
sttLanguage?: string;
|
|
// Write-only STT key (same semantics as `apiKey` / `embeddingApiKey`).
|
|
sttApiKey?: string;
|
|
}
|
|
|
|
// Result of a connection test against the configured provider.
|
|
// The error string is already sanitized server-side.
|
|
export interface IAiTestResult {
|
|
ok: boolean;
|
|
error?: string;
|
|
}
|
|
|
|
// Which endpoint a connection test probes.
|
|
export type AiTestCapability = "chat" | "embeddings" | "stt";
|
|
|
|
export async function getAiSettings(): Promise<IAiSettings> {
|
|
const req = await api.post<IAiSettings>("/workspace/ai-settings");
|
|
return req.data;
|
|
}
|
|
|
|
export async function updateAiSettings(
|
|
data: IAiSettingsUpdate,
|
|
): Promise<IAiSettings> {
|
|
const req = await api.post<IAiSettings>("/workspace/ai-settings/update", data);
|
|
return req.data;
|
|
}
|
|
|
|
export async function testAiConnection(
|
|
capability: AiTestCapability,
|
|
): Promise<IAiTestResult> {
|
|
const req = await api.post<IAiTestResult>("/workspace/ai-settings/test", {
|
|
capability,
|
|
});
|
|
return req.data;
|
|
}
|
|
|
|
export async function reindexAiEmbeddings(): Promise<IAiSettings> {
|
|
const req = await api.post<IAiSettings>("/workspace/ai-settings/reindex");
|
|
return req.data;
|
|
}
|