mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-02 05:12:11 +03:00
Allow image generation requests to omit prompts for models that only accept image input, and validate required inputs from model metadata instead of enforcing a text prompt for every request. Treat authless search providers as executable with built-in defaults so SearXNG can run without stored credentials, including during provider auto-selection. Also align runtime support with Node.js 24 LTS, harden thinking tag compression and proxy wildcard matching, and update tests for the new route and runtime behavior.
821 lines
25 KiB
TypeScript
821 lines
25 KiB
TypeScript
/**
|
|
* PerplexityWebExecutor — Perplexity Web Session Provider
|
|
*
|
|
* Routes requests through Perplexity's internal SSE API using a Pro/Max
|
|
* subscription session cookie or JWT, translating between OpenAI chat
|
|
* completions format and Perplexity's internal protocol.
|
|
*/
|
|
|
|
import { BaseExecutor, type ExecuteInput } from "./base.ts";
|
|
|
|
const PPLX_SSE_ENDPOINT = "https://www.perplexity.ai/rest/sse/perplexity_ask";
|
|
const PPLX_API_VERSION = "2.18";
|
|
const PPLX_USER_AGENT =
|
|
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36";
|
|
|
|
const MODEL_MAP: Record<string, [string, string]> = {
|
|
"pplx-auto": ["concise", "pplx_pro"],
|
|
"pplx-sonar": ["copilot", "experimental"],
|
|
"pplx-gpt": ["copilot", "gpt54"],
|
|
"pplx-gemini": ["copilot", "gemini31pro_high"],
|
|
"pplx-sonnet": ["copilot", "claude46sonnet"],
|
|
"pplx-opus": ["copilot", "claude46opus"],
|
|
"pplx-nemotron": ["copilot", "nv_nemotron_3_super"],
|
|
};
|
|
|
|
const THINKING_MAP: Record<string, string> = {
|
|
"pplx-gpt": "gpt54_thinking",
|
|
"pplx-sonnet": "claude46sonnetthinking",
|
|
"pplx-opus": "claude46opusthinking",
|
|
};
|
|
|
|
const CITATION_RE = /\[\d+\]/g;
|
|
const GROK_TAG_RE = /<grok:[^>]*>.*?<\/grok:[^>]*>/gs;
|
|
const GROK_SELF_RE = /<grok:[^>]*\/>/g;
|
|
const XML_DECL_RE = /<[?]xml[^?]*[?]>/g;
|
|
const RESPONSE_TAG_RE = /<\/?response\b[^>]*>/gi;
|
|
const MULTI_SPACE = / {2,}/g;
|
|
const MULTI_NL = /\n{3,}/g;
|
|
|
|
// ─── Session continuity ─────────────────────────────────────────────────────
|
|
|
|
const SESSION_MAX_AGE_MS = 3600_000;
|
|
const SESSION_MAX_ENTRIES = 200;
|
|
|
|
interface SessionEntry {
|
|
backendUuid: string;
|
|
ts: number;
|
|
}
|
|
|
|
const sessionCache = new Map<string, SessionEntry>();
|
|
|
|
function sessionKey(history: Array<{ role: string; content: string }>): string {
|
|
const parts = history.map((h) => `${h.role}:${h.content}`).join("\n");
|
|
let hash = 0x811c9dc5;
|
|
for (let i = 0; i < parts.length; i++) {
|
|
hash ^= parts.charCodeAt(i);
|
|
hash = (hash * 0x01000193) >>> 0;
|
|
}
|
|
return hash.toString(16).padStart(8, "0");
|
|
}
|
|
|
|
function sessionLookup(history: Array<{ role: string; content: string }>): string | null {
|
|
if (history.length === 0) return null;
|
|
const key = sessionKey(history);
|
|
const entry = sessionCache.get(key);
|
|
if (!entry) return null;
|
|
if (Date.now() - entry.ts > SESSION_MAX_AGE_MS) {
|
|
sessionCache.delete(key);
|
|
return null;
|
|
}
|
|
return entry.backendUuid;
|
|
}
|
|
|
|
function sessionStore(
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
responseText: string,
|
|
backendUuid: string | null
|
|
): void {
|
|
if (!backendUuid) return;
|
|
const full = [
|
|
...history,
|
|
{ role: "user", content: currentMsg },
|
|
{ role: "assistant", content: responseText },
|
|
];
|
|
const key = sessionKey(full);
|
|
sessionCache.set(key, { backendUuid, ts: Date.now() });
|
|
if (sessionCache.size > SESSION_MAX_ENTRIES) {
|
|
let oldestKey: string | null = null;
|
|
let oldestTs = Infinity;
|
|
for (const [k, v] of sessionCache) {
|
|
if (v.ts < oldestTs) {
|
|
oldestTs = v.ts;
|
|
oldestKey = k;
|
|
}
|
|
}
|
|
if (oldestKey) sessionCache.delete(oldestKey);
|
|
}
|
|
}
|
|
|
|
// ─── Helpers ────────────────────────────────────────────────────────────────
|
|
|
|
function cleanResponse(text: string, strip = true): string {
|
|
let t = text;
|
|
t = t.replace(XML_DECL_RE, "");
|
|
t = t.replace(CITATION_RE, "");
|
|
t = t.replace(GROK_TAG_RE, "");
|
|
t = t.replace(GROK_SELF_RE, "");
|
|
t = t.replace(RESPONSE_TAG_RE, "");
|
|
if (strip) {
|
|
t = t.replace(MULTI_SPACE, " ");
|
|
t = t.replace(MULTI_NL, "\n\n");
|
|
t = t.trim();
|
|
}
|
|
return t;
|
|
}
|
|
|
|
// ─── SSE types ──────────────────────────────────────────────────────────────
|
|
|
|
interface PplxBlock {
|
|
intended_usage?: string;
|
|
markdown_block?: {
|
|
answer?: string;
|
|
chunks?: string[];
|
|
progress?: string;
|
|
chunk_starting_offset?: number;
|
|
};
|
|
web_result_block?: {
|
|
web_results?: Array<{ url?: string; name?: string; snippet?: string }>;
|
|
};
|
|
plan_block?: {
|
|
steps?: Array<{
|
|
step_type?: string;
|
|
search_web_content?: { queries?: Array<{ query?: string }> };
|
|
read_results_content?: { urls?: string[] };
|
|
}>;
|
|
goals?: Array<{ description?: string }>;
|
|
};
|
|
}
|
|
|
|
interface PplxStreamEvent {
|
|
status?: string;
|
|
final?: boolean;
|
|
text?: string;
|
|
blocks?: PplxBlock[];
|
|
backend_uuid?: string;
|
|
web_results?: Array<{ url?: string; name?: string }>;
|
|
error_code?: string;
|
|
error_message?: string;
|
|
display_model?: string;
|
|
}
|
|
|
|
// ─── SSE parsing ────────────────────────────────────────────────────────────
|
|
|
|
async function* readPplxSseEvents(
|
|
body: ReadableStream<Uint8Array>,
|
|
signal?: AbortSignal | null
|
|
): AsyncGenerator<PplxStreamEvent> {
|
|
const reader = body.getReader();
|
|
const decoder = new TextDecoder();
|
|
let buffer = "";
|
|
let dataLines: string[] = [];
|
|
|
|
function flush(): PplxStreamEvent | null | "done" {
|
|
if (dataLines.length === 0) return null;
|
|
const payload = dataLines.join("\n");
|
|
dataLines = [];
|
|
const trimmed = payload.trim();
|
|
if (!trimmed || trimmed === "[DONE]") return "done";
|
|
try {
|
|
return JSON.parse(trimmed) as PplxStreamEvent;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
try {
|
|
while (true) {
|
|
if (signal?.aborted) return;
|
|
const { value, done } = await reader.read();
|
|
if (done) break;
|
|
buffer += decoder.decode(value, { stream: true });
|
|
|
|
while (true) {
|
|
const idx = buffer.indexOf("\n");
|
|
if (idx < 0) break;
|
|
const rawLine = buffer.slice(0, idx);
|
|
buffer = buffer.slice(idx + 1);
|
|
const line = rawLine.endsWith("\r") ? rawLine.slice(0, -1) : rawLine;
|
|
|
|
if (line === "") {
|
|
const parsed = flush();
|
|
if (parsed === "done") return;
|
|
if (parsed) yield parsed;
|
|
continue;
|
|
}
|
|
if (line.startsWith("data:")) {
|
|
dataLines.push(line.slice(5).trimStart());
|
|
}
|
|
if (line === "event: end_of_stream") {
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
|
|
buffer += decoder.decode();
|
|
if (buffer.trim().startsWith("data:")) {
|
|
dataLines.push(buffer.trim().slice(5).trimStart());
|
|
}
|
|
const tail = flush();
|
|
if (tail && tail !== "done") yield tail;
|
|
} finally {
|
|
reader.releaseLock();
|
|
}
|
|
}
|
|
|
|
// ─── OpenAI → Perplexity translation ────────────────────────────────────────
|
|
|
|
interface ParsedMessages {
|
|
systemMsg: string;
|
|
history: Array<{ role: string; content: string }>;
|
|
currentMsg: string;
|
|
}
|
|
|
|
function parseOpenAIMessages(messages: Array<Record<string, unknown>>): ParsedMessages {
|
|
let systemMsg = "";
|
|
const history: Array<{ role: string; content: string }> = [];
|
|
|
|
for (const msg of messages) {
|
|
let role = String(msg.role || "user");
|
|
if (role === "developer") role = "system";
|
|
|
|
let content = "";
|
|
if (typeof msg.content === "string") {
|
|
content = msg.content;
|
|
} else if (Array.isArray(msg.content)) {
|
|
content = (msg.content as Array<Record<string, unknown>>)
|
|
.filter((c) => c.type === "text")
|
|
.map((c) => String(c.text || ""))
|
|
.join(" ");
|
|
}
|
|
if (!content.trim()) continue;
|
|
|
|
if (role === "system") {
|
|
systemMsg += content + "\n";
|
|
} else if (role === "user" || role === "assistant") {
|
|
history.push({ role, content });
|
|
}
|
|
}
|
|
|
|
let currentMsg = "";
|
|
if (history.length > 0 && history[history.length - 1].role === "user") {
|
|
currentMsg = history.pop()!.content;
|
|
}
|
|
|
|
return { systemMsg, history, currentMsg };
|
|
}
|
|
|
|
function buildPplxRequestBody(
|
|
query: string,
|
|
mode: string,
|
|
modelPref: string,
|
|
followUpUuid: string | null
|
|
): Record<string, unknown> {
|
|
const tz = typeof Intl !== "undefined" ? Intl.DateTimeFormat().resolvedOptions().timeZone : "UTC";
|
|
|
|
return {
|
|
query_str: query,
|
|
params: {
|
|
query_str: query,
|
|
search_focus: "internet",
|
|
mode,
|
|
model_preference: modelPref,
|
|
sources: ["web"],
|
|
attachments: [],
|
|
frontend_uuid: crypto.randomUUID(),
|
|
frontend_context_uuid: crypto.randomUUID(),
|
|
version: PPLX_API_VERSION,
|
|
language: "en-US",
|
|
timezone: tz,
|
|
search_recency_filter: null,
|
|
is_incognito: true,
|
|
use_schematized_api: true,
|
|
last_backend_uuid: followUpUuid,
|
|
},
|
|
};
|
|
}
|
|
|
|
function buildQuery(parsed: ParsedMessages, followUpUuid: string | null): string {
|
|
if (followUpUuid) return parsed.currentMsg;
|
|
|
|
const obj: Record<string, unknown> = {};
|
|
if (parsed.systemMsg.trim()) {
|
|
obj.instructions = [
|
|
parsed.systemMsg.trim(),
|
|
"You have built-in web search. Answer questions directly using search results.",
|
|
];
|
|
}
|
|
if (parsed.history.length > 0) {
|
|
obj.history = parsed.history;
|
|
}
|
|
if (parsed.currentMsg) {
|
|
obj.query = parsed.currentMsg;
|
|
} else if (parsed.history.length === 0) {
|
|
obj.query = "";
|
|
}
|
|
const json = JSON.stringify(obj);
|
|
return json.length > 96000 ? json.slice(-96000) : json;
|
|
}
|
|
|
|
// ─── Content extraction ─────────────────────────────────────────────────────
|
|
|
|
interface ContentChunk {
|
|
delta?: string;
|
|
answer?: string;
|
|
backendUuid?: string;
|
|
thinking?: string;
|
|
error?: string;
|
|
done?: boolean;
|
|
}
|
|
|
|
async function* extractContent(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
signal?: AbortSignal | null
|
|
): AsyncGenerator<ContentChunk> {
|
|
let fullAnswer = "";
|
|
let backendUuid: string | null = null;
|
|
let seenLen = 0;
|
|
const seenThinking = new Set<string>();
|
|
|
|
for await (const event of readPplxSseEvents(eventStream, signal)) {
|
|
if (event.error_code || event.error_message) {
|
|
yield {
|
|
error: event.error_message || `Perplexity error: ${event.error_code}`,
|
|
done: true,
|
|
};
|
|
return;
|
|
}
|
|
|
|
if (event.backend_uuid) backendUuid = event.backend_uuid;
|
|
|
|
const blocks = event.blocks ?? [];
|
|
for (const block of blocks) {
|
|
const usage = block.intended_usage ?? "";
|
|
|
|
// Thinking: search steps
|
|
if (usage === "pro_search_steps" && block.plan_block?.steps) {
|
|
for (const step of block.plan_block.steps) {
|
|
if (step.step_type === "SEARCH_WEB") {
|
|
for (const q of step.search_web_content?.queries ?? []) {
|
|
const qr = q.query ?? "";
|
|
if (qr && !seenThinking.has(qr)) {
|
|
seenThinking.add(qr);
|
|
yield { thinking: `Searching: ${qr}`, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
} else if (step.step_type === "READ_RESULTS") {
|
|
for (const u of (step.read_results_content?.urls ?? []).slice(0, 3)) {
|
|
if (u && !seenThinking.has(u)) {
|
|
seenThinking.add(u);
|
|
yield { thinking: `Reading: ${u}`, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Thinking: plan goals
|
|
if (usage === "plan" && block.plan_block?.goals) {
|
|
for (const goal of block.plan_block.goals) {
|
|
const desc = goal.description ?? "";
|
|
if (desc && !seenThinking.has(desc)) {
|
|
seenThinking.add(desc);
|
|
yield { thinking: desc, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
}
|
|
|
|
// Content: markdown blocks
|
|
if (!usage.includes("markdown")) continue;
|
|
const mb = block.markdown_block;
|
|
if (!mb) continue;
|
|
const chunks = mb.chunks ?? [];
|
|
if (chunks.length === 0) continue;
|
|
|
|
if (mb.progress === "DONE") {
|
|
fullAnswer = chunks.join("");
|
|
} else {
|
|
const chunkText = chunks.join("");
|
|
const cumulative = fullAnswer + chunkText;
|
|
if (cumulative.length > seenLen) {
|
|
const delta = cumulative.slice(seenLen);
|
|
fullAnswer = cumulative;
|
|
seenLen = cumulative.length;
|
|
yield { delta, answer: fullAnswer, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
}
|
|
|
|
// Fallback: text field
|
|
if (blocks.length === 0 && event.text) {
|
|
const t = event.text.trim();
|
|
if (t.length > seenLen) {
|
|
const delta = t.slice(seenLen);
|
|
fullAnswer = t;
|
|
seenLen = t.length;
|
|
yield { delta, answer: fullAnswer, backendUuid: backendUuid ?? undefined };
|
|
}
|
|
}
|
|
|
|
if (event.final || event.status === "COMPLETED") break;
|
|
}
|
|
|
|
yield { delta: "", answer: fullAnswer, backendUuid: backendUuid ?? undefined, done: true };
|
|
}
|
|
|
|
// ─── OpenAI SSE format ──────────────────────────────────────────────────────
|
|
|
|
function sseChunk(data: unknown): string {
|
|
return `data: ${JSON.stringify(data)}\n\n`;
|
|
}
|
|
|
|
function buildStreamingResponse(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
model: string,
|
|
cid: string,
|
|
created: number,
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
signal?: AbortSignal | null
|
|
): ReadableStream<Uint8Array> {
|
|
const encoder = new TextEncoder();
|
|
|
|
return new ReadableStream({
|
|
async start(controller) {
|
|
try {
|
|
// Initial role chunk
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{ index: 0, delta: { role: "assistant" }, finish_reason: null, logprobs: null },
|
|
],
|
|
})
|
|
)
|
|
);
|
|
|
|
let fullAnswer = "";
|
|
let respBackendUuid: string | null = null;
|
|
|
|
for await (const chunk of extractContent(eventStream, signal)) {
|
|
if (chunk.backendUuid) respBackendUuid = chunk.backendUuid;
|
|
|
|
if (chunk.error) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { content: `[Error: ${chunk.error}]` },
|
|
finish_reason: null,
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
break;
|
|
}
|
|
|
|
if (chunk.thinking) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: { reasoning_content: chunk.thinking + "\n" },
|
|
finish_reason: null,
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
continue;
|
|
}
|
|
|
|
if (chunk.done) {
|
|
fullAnswer = chunk.answer || fullAnswer;
|
|
break;
|
|
}
|
|
|
|
let dt = chunk.delta || "";
|
|
if (dt) {
|
|
dt = cleanResponse(dt, false);
|
|
if (dt) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{ index: 0, delta: { content: dt }, finish_reason: null, logprobs: null },
|
|
],
|
|
})
|
|
)
|
|
);
|
|
}
|
|
}
|
|
if (chunk.answer) fullAnswer = chunk.answer;
|
|
}
|
|
|
|
// Stop chunk
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [{ index: 0, delta: {}, finish_reason: "stop", logprobs: null }],
|
|
})
|
|
)
|
|
);
|
|
controller.enqueue(encoder.encode("data: [DONE]\n\n"));
|
|
|
|
sessionStore(history, currentMsg, cleanResponse(fullAnswer), respBackendUuid);
|
|
} catch (err) {
|
|
controller.enqueue(
|
|
encoder.encode(
|
|
sseChunk({
|
|
id: cid,
|
|
object: "chat.completion.chunk",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
content: `[Stream error: ${err instanceof Error ? err.message : String(err)}]`,
|
|
},
|
|
finish_reason: "stop",
|
|
logprobs: null,
|
|
},
|
|
],
|
|
})
|
|
)
|
|
);
|
|
controller.enqueue(encoder.encode("data: [DONE]\n\n"));
|
|
} finally {
|
|
controller.close();
|
|
}
|
|
},
|
|
});
|
|
}
|
|
|
|
async function buildNonStreamingResponse(
|
|
eventStream: ReadableStream<Uint8Array>,
|
|
model: string,
|
|
cid: string,
|
|
created: number,
|
|
history: Array<{ role: string; content: string }>,
|
|
currentMsg: string,
|
|
signal?: AbortSignal | null
|
|
): Promise<Response> {
|
|
let fullAnswer = "";
|
|
let respBackendUuid: string | null = null;
|
|
const thinkingParts: string[] = [];
|
|
|
|
for await (const chunk of extractContent(eventStream, signal)) {
|
|
if (chunk.backendUuid) respBackendUuid = chunk.backendUuid;
|
|
if (chunk.error) {
|
|
return new Response(
|
|
JSON.stringify({
|
|
error: { message: chunk.error, type: "upstream_error", code: "PPLX_ERROR" },
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
}
|
|
if (chunk.thinking) {
|
|
thinkingParts.push(chunk.thinking);
|
|
continue;
|
|
}
|
|
if (chunk.done) {
|
|
fullAnswer = chunk.answer || fullAnswer;
|
|
break;
|
|
}
|
|
if (chunk.answer) fullAnswer = chunk.answer;
|
|
}
|
|
|
|
fullAnswer = cleanResponse(fullAnswer);
|
|
sessionStore(history, currentMsg, fullAnswer, respBackendUuid);
|
|
|
|
const reasoningContent = thinkingParts.length > 0 ? thinkingParts.join("\n") : undefined;
|
|
const msg: Record<string, unknown> = { role: "assistant", content: fullAnswer };
|
|
if (reasoningContent) msg.reasoning_content = reasoningContent;
|
|
|
|
const promptTokens = Math.ceil(currentMsg.length / 4);
|
|
const completionTokens = Math.ceil(fullAnswer.length / 4);
|
|
|
|
return new Response(
|
|
JSON.stringify({
|
|
id: cid,
|
|
object: "chat.completion",
|
|
created,
|
|
model,
|
|
system_fingerprint: null,
|
|
choices: [{ index: 0, message: msg, finish_reason: "stop", logprobs: null }],
|
|
usage: {
|
|
prompt_tokens: promptTokens,
|
|
completion_tokens: completionTokens,
|
|
total_tokens: promptTokens + completionTokens,
|
|
},
|
|
}),
|
|
{ status: 200, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
}
|
|
|
|
// ─── Executor ───────────────────────────────────────────────────────────────
|
|
|
|
export class PerplexityWebExecutor extends BaseExecutor {
|
|
constructor() {
|
|
super("perplexity-web", { id: "perplexity-web", baseUrl: PPLX_SSE_ENDPOINT });
|
|
}
|
|
|
|
async execute({ model, body, stream, credentials, signal, log }: ExecuteInput) {
|
|
const messages = (body as Record<string, unknown>).messages as
|
|
| Array<Record<string, unknown>>
|
|
| undefined;
|
|
if (!messages || !Array.isArray(messages) || messages.length === 0) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Missing or empty messages array", type: "invalid_request" },
|
|
}),
|
|
{ status: 400, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers: {}, transformedBody: body };
|
|
}
|
|
|
|
// Resolve thinking mode
|
|
const bodyObj = body as Record<string, unknown>;
|
|
const thinking =
|
|
bodyObj.thinking === true ||
|
|
(bodyObj.reasoning_effort != null && bodyObj.reasoning_effort !== "none");
|
|
|
|
let pplxMode: string;
|
|
let modelPref: string;
|
|
if (thinking && THINKING_MAP[model]) {
|
|
pplxMode = "copilot";
|
|
modelPref = THINKING_MAP[model];
|
|
log?.info?.("PPLX-WEB", `Thinking mode → ${model} using ${modelPref}`);
|
|
} else if (MODEL_MAP[model]) {
|
|
[pplxMode, modelPref] = MODEL_MAP[model];
|
|
} else {
|
|
pplxMode = "copilot";
|
|
modelPref = model;
|
|
log?.info?.("PPLX-WEB", `Unmapped model ${model}, using as raw preference`);
|
|
}
|
|
|
|
// Parse messages and check session continuity
|
|
const parsed = parseOpenAIMessages(messages);
|
|
const followUpUuid = sessionLookup(parsed.history);
|
|
if (followUpUuid) {
|
|
log?.info?.("PPLX-WEB", `Session continue: ${followUpUuid.slice(0, 12)}...`);
|
|
}
|
|
|
|
const query = buildQuery(parsed, followUpUuid);
|
|
if (!query.trim()) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Empty query after processing", type: "invalid_request" },
|
|
}),
|
|
{ status: 400, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers: {}, transformedBody: body };
|
|
}
|
|
|
|
// Build Perplexity request
|
|
const pplxBody = buildPplxRequestBody(query, pplxMode, modelPref, followUpUuid);
|
|
|
|
const headers: Record<string, string> = {
|
|
"Content-Type": "application/json",
|
|
Accept: "text/event-stream",
|
|
Origin: "https://www.perplexity.ai",
|
|
Referer: "https://www.perplexity.ai/",
|
|
"User-Agent": PPLX_USER_AGENT,
|
|
"X-App-ApiClient": "default",
|
|
"X-App-ApiVersion": PPLX_API_VERSION,
|
|
};
|
|
|
|
if (credentials.accessToken) {
|
|
headers["Authorization"] = `Bearer ${credentials.accessToken}`;
|
|
} else if (credentials.apiKey) {
|
|
headers["Cookie"] = `__Secure-next-auth.session-token=${credentials.apiKey}`;
|
|
}
|
|
|
|
log?.info?.(
|
|
"PPLX-WEB",
|
|
`Query to ${model} (pref=${modelPref}, mode=${pplxMode}), len=${query.length}`
|
|
);
|
|
|
|
// Fetch from Perplexity
|
|
const fetchOptions: RequestInit = {
|
|
method: "POST",
|
|
headers,
|
|
body: JSON.stringify(pplxBody),
|
|
};
|
|
if (signal) fetchOptions.signal = signal;
|
|
|
|
let response: Response;
|
|
try {
|
|
response = await fetch(PPLX_SSE_ENDPOINT, fetchOptions);
|
|
} catch (err) {
|
|
log?.error?.("PPLX-WEB", `Fetch failed: ${err instanceof Error ? err.message : String(err)}`);
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: `Perplexity connection failed: ${err instanceof Error ? err.message : String(err)}`,
|
|
type: "upstream_error",
|
|
},
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
if (!response.ok) {
|
|
const status = response.status;
|
|
let errMsg = `Perplexity returned HTTP ${status}`;
|
|
if (status === 401 || status === 403) {
|
|
errMsg =
|
|
"Perplexity auth failed — session cookie may be expired. Re-paste your __Secure-next-auth.session-token.";
|
|
} else if (status === 429) {
|
|
errMsg = "Perplexity rate limited. Wait a moment and retry.";
|
|
}
|
|
log?.warn?.("PPLX-WEB", errMsg);
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: errMsg, type: "upstream_error", code: `HTTP_${status}` },
|
|
}),
|
|
{ status, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
if (!response.body) {
|
|
const errResp = new Response(
|
|
JSON.stringify({
|
|
error: { message: "Perplexity returned empty response body", type: "upstream_error" },
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
);
|
|
return { response: errResp, url: PPLX_SSE_ENDPOINT, headers, transformedBody: pplxBody };
|
|
}
|
|
|
|
// Build OpenAI-compatible response
|
|
const cid = `chatcmpl-pplx-${crypto.randomUUID().slice(0, 12)}`;
|
|
const created = Math.floor(Date.now() / 1000);
|
|
|
|
let finalResponse: Response;
|
|
if (stream) {
|
|
const sseStream = buildStreamingResponse(
|
|
response.body,
|
|
model,
|
|
cid,
|
|
created,
|
|
parsed.history,
|
|
parsed.currentMsg,
|
|
signal
|
|
);
|
|
finalResponse = new Response(sseStream, {
|
|
status: 200,
|
|
headers: {
|
|
"Content-Type": "text/event-stream",
|
|
"Cache-Control": "no-cache",
|
|
"X-Accel-Buffering": "no",
|
|
},
|
|
});
|
|
} else {
|
|
finalResponse = await buildNonStreamingResponse(
|
|
response.body,
|
|
model,
|
|
cid,
|
|
created,
|
|
parsed.history,
|
|
parsed.currentMsg,
|
|
signal
|
|
);
|
|
}
|
|
|
|
return {
|
|
response: finalResponse,
|
|
url: PPLX_SSE_ENDPOINT,
|
|
headers,
|
|
transformedBody: pplxBody,
|
|
};
|
|
}
|
|
}
|