Files
gitmost/apps/client/src/features/workspace/services/ai-settings-service.ts
a 72bb03918d fix(ai): show live reindex progress in semantic-search settings
The "Indexed X of Y pages" counter stayed stuck at "478 of 478" during a
manual "Reindex now" run instead of resetting to 0 and climbing. The status
reports indexedPages = countIndexedPages (DISTINCT pages with >=1 embedding
row), but reindex hard-replaces each page in its OWN small transaction, so
nearly all pages always have rows -> the count never drops.

Add a per-workspace live reindex-progress record in Redis (reusing the
existing global ioredis client via RedisService, no new Redis config):
- EmbeddingReindexProgressService: start/increment/clear/get over a Redis hash
  with a 1h TTL self-clean; all best-effort/cosmetic so a Redis failure degrades
  to the existing DB-count behavior.
- AiSettingsService.reindex seeds {total, done:0, startedAt} at enqueue time so
  the very first poll already reports done=0.
- EmbeddingIndexerService.reindexWorkspace overwrites total with the real page
  count at start, increments done per processed page (success or handled
  failure), and clears the record in a finally (covers success, fatal abort,
  and the unconfigured early-return) so a failed run never sticks.
- AiSettingsService.getMasked returns the live run numbers when a progress
  record is active (plus an optional reindexing flag), else falls back to
  countIndexedPages/countEmbeddablePages.

Per-page edits (reindexPage) never touch the workspace progress record, and no
mass up-front delete is introduced (search availability preserved).

Tests: indexer sets/increments/clears progress (incl. fatal abort and
unconfigured early-return); status reports run progress when active and falls
back when not.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-28 04:32:36 +03:00

121 lines
4.3 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;
// Max context window in tokens shown in the chat header badge; 0/unset = no limit.
chatContextWindow?: number;
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;
// True while a full workspace reindex is actively running; the counts above
// then reflect the live run progress (done climbs 0 -> total).
reindexing?: boolean;
}
// 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;
// Max context window in tokens for the chat header badge; 0 = clear the limit.
chatContextWindow?: number;
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;
}