146 lines
4.8 KiB
JavaScript
146 lines
4.8 KiB
JavaScript
/**
|
|
* Hermes-Proxy cli-to-openai Adapter.
|
|
*
|
|
* 1:1 uebernommen aus dem ARIA-Proxy (/root/ARIA-AGENT/proxy-patches/cli-to-openai.js) —
|
|
* dieser Teil ist generisch, kein ARIA-spezifischer Code drin. Erweitert die
|
|
* npm-Version von claude-max-api-proxy um:
|
|
* - normalizeModelName ist null-safe (Original-Patch der vorher per sed lief).
|
|
* - Parser fuer <tool_call name="X">{json}</tool_call>-Bloecke im Result-Text:
|
|
* Wenn welche gefunden werden, wandert das in `message.tool_calls`
|
|
* (OpenAI-Format) und finish_reason=tool_calls. Der restliche Text
|
|
* (alles ausserhalb der Bloecke) wird verworfen, weil das interner
|
|
* Tool-Use-Schritt war, nicht User-facing.
|
|
*
|
|
* Wird zur Container-Startzeit ueber die npm-Version geschrieben
|
|
* (siehe docker-compose.yml hermes-proxy-Block).
|
|
*/
|
|
|
|
import { randomUUID } from "crypto";
|
|
|
|
export function extractTextContent(message) {
|
|
return message.message.content
|
|
.filter((c) => c.type === "text")
|
|
.map((c) => c.text)
|
|
.join("");
|
|
}
|
|
|
|
export function cliToOpenaiChunk(message, requestId, isFirst = false) {
|
|
const text = extractTextContent(message);
|
|
return {
|
|
id: `chatcmpl-${requestId}`,
|
|
object: "chat.completion.chunk",
|
|
created: Math.floor(Date.now() / 1000),
|
|
model: normalizeModelName(message.message.model),
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {
|
|
role: isFirst ? "assistant" : undefined,
|
|
content: text,
|
|
},
|
|
finish_reason: message.message.stop_reason ? "stop" : null,
|
|
},
|
|
],
|
|
};
|
|
}
|
|
|
|
export function createDoneChunk(requestId, model) {
|
|
return {
|
|
id: `chatcmpl-${requestId}`,
|
|
object: "chat.completion.chunk",
|
|
created: Math.floor(Date.now() / 1000),
|
|
model: normalizeModelName(model),
|
|
choices: [
|
|
{
|
|
index: 0,
|
|
delta: {},
|
|
finish_reason: "stop",
|
|
},
|
|
],
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Sucht im Result-Text alle <tool_call name="...">{json}</tool_call>
|
|
* Bloecke. Gibt [{id, name, arguments(json-string)}, restText] zurueck.
|
|
*
|
|
* Defensiv:
|
|
* - "name"-Attribut sowohl in Doppel- als auch Einzelhochkommata
|
|
* - Whitespace beim JSON tolerant
|
|
* - Bei JSON-Parse-Fehler: das Argument wird als _raw weitergereicht
|
|
* (Empfaenger-seitiger Parser kennt das)
|
|
*/
|
|
function _parseToolCalls(text) {
|
|
if (!text || typeof text !== "string") return { tool_calls: [], rest: text || "" };
|
|
const re = /<tool_call\s+name=["']([^"']+)["']\s*>([\s\S]*?)<\/tool_call>/gi;
|
|
const tcs = [];
|
|
let lastIndex = 0;
|
|
const restParts = [];
|
|
let m;
|
|
while ((m = re.exec(text)) !== null) {
|
|
restParts.push(text.slice(lastIndex, m.index));
|
|
const name = m[1];
|
|
let argsBody = (m[2] || "").trim();
|
|
// Fences entfernen falls Claude welche eingebaut hat
|
|
argsBody = argsBody.replace(/^```(?:json)?\s*/i, "").replace(/```\s*$/, "").trim();
|
|
if (!argsBody) argsBody = "{}";
|
|
// Validieren — aber in OpenAI-Format ist arguments immer ein STRING
|
|
try {
|
|
JSON.parse(argsBody);
|
|
} catch (_) {
|
|
// Behalten als Roh-String
|
|
}
|
|
tcs.push({
|
|
id: `call_${randomUUID().replace(/-/g, "").slice(0, 24)}`,
|
|
type: "function",
|
|
function: { name, arguments: argsBody },
|
|
});
|
|
lastIndex = re.lastIndex;
|
|
}
|
|
restParts.push(text.slice(lastIndex));
|
|
return { tool_calls: tcs, rest: restParts.join("").trim() };
|
|
}
|
|
|
|
export function cliResultToOpenai(result, requestId) {
|
|
const modelName = result.modelUsage
|
|
? Object.keys(result.modelUsage)[0]
|
|
: "claude-sonnet-4";
|
|
|
|
const rawText = result.result || "";
|
|
const { tool_calls, rest } = _parseToolCalls(rawText);
|
|
|
|
const message = { role: "assistant" };
|
|
let finishReason = "stop";
|
|
if (tool_calls.length > 0) {
|
|
message.tool_calls = tool_calls;
|
|
message.content = rest || null;
|
|
finishReason = "tool_calls";
|
|
} else {
|
|
message.content = rawText;
|
|
}
|
|
|
|
return {
|
|
id: `chatcmpl-${requestId}`,
|
|
object: "chat.completion",
|
|
created: Math.floor(Date.now() / 1000),
|
|
model: normalizeModelName(modelName),
|
|
choices: [
|
|
{ index: 0, message, finish_reason: finishReason },
|
|
],
|
|
usage: {
|
|
prompt_tokens: result.usage?.input_tokens || 0,
|
|
completion_tokens: result.usage?.output_tokens || 0,
|
|
total_tokens:
|
|
(result.usage?.input_tokens || 0) + (result.usage?.output_tokens || 0),
|
|
},
|
|
};
|
|
}
|
|
|
|
function normalizeModelName(model) {
|
|
const m = model || "claude-sonnet-4";
|
|
if (m.includes("opus")) return "claude-opus-4";
|
|
if (m.includes("sonnet")) return "claude-sonnet-4";
|
|
if (m.includes("haiku")) return "claude-haiku-4";
|
|
return m;
|
|
}
|