feat: add /v1/embeddings endpoint (OpenAI-compatible) (#146)

* feat: implement /v1/embeddings endpoint (#117) Add OpenAI-compatible POST /v1/embeddings endpoint that routes through the existing provider credential + fallback infrastructure. Changes: - open-sse/handlers/embeddingsCore.js: core handler (handleEmbeddingsCore) * Validates input (string or array), encoding_format * Builds provider-specific URL and headers for openai, openrouter, and openai-compatible providers * Handles 401/403 token refresh via executor.refreshCredentials * Returns normalized OpenAI-format response { object: 'list', data, model, usage } - cloud/src/handlers/embeddings.js: cloud Worker handler (handleEmbeddings) * Auth + machineId resolution identical to handleChat * Provider credential fallback loop with rate-limit tracking - cloud/src/index.js: wire new routes * POST /v1/embeddings (new format — machineId from API key) * POST /{machineId}/v1/embeddings (old format — machineId from URL) * test: add unit tests for /v1/embeddings endpoint - Setup vitest as test framework (tests/ directory) - embeddingsCore.test.js (36 tests): - buildEmbeddingsBody: single string, array, encoding_format, default float - buildEmbeddingsUrl: openai, openrouter, openai-compatible-*, unsupported - buildEmbeddingsHeaders: per-provider headers, accessToken fallback - handleEmbeddingsCore: input validation, success path, provider errors, network errors, invalid JSON, token refresh 401 handling - embeddings.cloud.test.js (23 tests): - CORS OPTIONS preflight - Auth: missing/invalid/old-format/wrong key → 401/400 - Body validation: bad JSON, missing model, missing input, bad model → 400 - Happy path: single string, array, delegation, CORS header, machineId override - Rate limiting: all-rate-limited → 429 + Retry-After, no credentials → 400 - Error propagation: non-fallback errors, 429 exhausts accounts Total: 59/59 tests passing Framework: vitest v4.0.18, Node v22.22.0 * feat: add Next.js API route for /v1/embeddings endpoint Wire the embeddings handler into Next.js App Router. - src/app/api/v1/embeddings/route.js: Next.js API route (POST + OPTIONS) - src/sse/handlers/embeddings.js: SSE-layer handler mirroring chat.js pattern Uses handleEmbeddingsCore from open-sse/handlers/embeddingsCore.js with the same auth, credential fallback, and token refresh logic as the chat handler. Supports REQUIRE_API_KEY env var, provider fallback loop, and consistent logging.
2026-09-22 20:00:47 +00:00 · 2026-02-18 13:24:02 +07:00
parent 05b09e6165
commit e1b836168a
11 changed files with 1875 additions and 0 deletions
@@ -0,0 +1,141 @@
+import {
+  getProviderCredentials,
+  markAccountUnavailable,
+  clearAccountError,
+  extractApiKey,
+  isValidApiKey,
+} from "../services/auth.js";
+import { getModelInfo } from "../services/model.js";
+import { handleEmbeddingsCore } from "open-sse/handlers/embeddingsCore.js";
+import { errorResponse, unavailableResponse } from "open-sse/utils/error.js";
+import { HTTP_STATUS } from "open-sse/config/constants.js";
+import * as log from "../utils/logger.js";
+import { updateProviderCredentials, checkAndRefreshToken } from "../services/tokenRefresh.js";
+
+/**
+ * Handle embeddings request for the SSE/Next.js server.
+ * Follows the same auth + fallback pattern as handleChat.
+ *
+ * @param {Request} request
+ */
+export async function handleEmbeddings(request) {
+  let body;
+  try {
+    body = await request.json();
+  } catch {
+    log.warn("EMBEDDINGS", "Invalid JSON body");
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid JSON body");
+  }
+
+  const url = new URL(request.url);
+  const modelStr = body.model;
+
+  log.request("POST", `${url.pathname} | ${modelStr}`);
+
+  // Log API key (masked)
+  const apiKey = extractApiKey(request);
+  if (apiKey) {
+    log.debug("AUTH", `API Key: ${log.maskKey(apiKey)}`);
+  } else {
+    log.debug("AUTH", "No API key provided (local mode)");
+  }
+
+  // Optional strict API key validation
+  if (process.env.REQUIRE_API_KEY === "true") {
+    if (!apiKey) {
+      log.warn("AUTH", "Missing API key while REQUIRE_API_KEY=true");
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Missing API key");
+    }
+    const valid = await isValidApiKey(apiKey);
+    if (!valid) {
+      log.warn("AUTH", "Invalid API key while REQUIRE_API_KEY=true");
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Invalid API key");
+    }
+  }
+
+  if (!modelStr) {
+    log.warn("EMBEDDINGS", "Missing model");
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Missing model");
+  }
+
+  if (!body.input) {
+    log.warn("EMBEDDINGS", "Missing input");
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Missing required field: input");
+  }
+
+  const modelInfo = await getModelInfo(modelStr);
+  if (!modelInfo.provider) {
+    log.warn("EMBEDDINGS", "Invalid model format", { model: modelStr });
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid model format");
+  }
+
+  const { provider, model } = modelInfo;
+
+  if (modelStr !== `${provider}/${model}`) {
+    log.info("ROUTING", `${modelStr} → ${provider}/${model}`);
+  } else {
+    log.info("ROUTING", `Provider: ${provider}, Model: ${model}`);
+  }
+
+  // Credential + fallback loop (mirrors handleChat)
+  let excludeConnectionId = null;
+  let lastError = null;
+  let lastStatus = null;
+
+  while (true) {
+    const credentials = await getProviderCredentials(provider, excludeConnectionId, model);
+
+    // All accounts unavailable
+    if (!credentials || credentials.allRateLimited) {
+      if (credentials?.allRateLimited) {
+        const errorMsg = lastError || credentials.lastError || "Unavailable";
+        const status = lastStatus || Number(credentials.lastErrorCode) || HTTP_STATUS.SERVICE_UNAVAILABLE;
+        log.warn("EMBEDDINGS", `[${provider}/${model}] ${errorMsg} (${credentials.retryAfterHuman})`);
+        return unavailableResponse(status, `[${provider}/${model}] ${errorMsg}`, credentials.retryAfter, credentials.retryAfterHuman);
+      }
+      if (!excludeConnectionId) {
+        log.error("AUTH", `No credentials for provider: ${provider}`);
+        return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for provider: ${provider}`);
+      }
+      log.warn("EMBEDDINGS", "No more accounts available", { provider });
+      return errorResponse(lastStatus || HTTP_STATUS.SERVICE_UNAVAILABLE, lastError || "All accounts unavailable");
+    }
+
+    const accountId = credentials.connectionId.slice(0, 8);
+    log.info("AUTH", `Using ${provider} account: ${accountId}...`);
+
+    const refreshedCredentials = await checkAndRefreshToken(provider, credentials);
+
+    const result = await handleEmbeddingsCore({
+      body: { ...body, model: `${provider}/${model}` },
+      modelInfo: { provider, model },
+      credentials: refreshedCredentials,
+      log,
+      onCredentialsRefreshed: async (newCreds) => {
+        await updateProviderCredentials(credentials.connectionId, {
+          accessToken: newCreds.accessToken,
+          refreshToken: newCreds.refreshToken,
+          providerSpecificData: newCreds.providerSpecificData,
+          testStatus: "active"
+        });
+      },
+      onRequestSuccess: async () => {
+        await clearAccountError(credentials.connectionId, credentials);
+      }
+    });
+
+    if (result.success) return result.response;
+
+    const { shouldFallback } = await markAccountUnavailable(credentials.connectionId, result.status, result.error, provider, model);
+
+    if (shouldFallback) {
+      log.warn("AUTH", `Account ${accountId}... unavailable (${result.status}), trying fallback`);
+      excludeConnectionId = credentials.connectionId;
+      lastError = result.error;
+      lastStatus = result.status;
+      continue;
+    }
+
+    return result.response;
+  }
+}