Merge remote-tracking branch 'origin/master' into gitea/feature/end

Resolved conflicts taking origin/master (v0.5.55) as canonical, with local
features re-applied:
- runtime log level (LOG_LEVEL env + dashboard Settings → Logging, applied
  immediately and persisted across restarts)
- free/noAuth provider enable/disable toggle via providerStrategies.enabled
- parallel model testing (Test All Models / Test Selected Keys)
This commit is contained in:
2026-08-17 00:38:31 +07:00
parent e7470e955e
commit 7e45ead2ac
557 changed files with 53396 additions and 6935 deletions

View File

@@ -6,9 +6,10 @@ import { addBufferToUsage, filterUsageForFormat } from "../../utils/usageTrackin
import { createErrorResult } from "../../utils/error.js";
import { HTTP_STATUS } from "../../config/runtimeConfig.js";
import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats } from "./requestDetail.js";
import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
import { decloakToolNames } from "../../utils/claudeCloaking.js";
import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
function parseToolArguments(value) {
if (!value) return {};
@@ -60,11 +61,93 @@ function openAICompletionToClaudeMessage(responseBody) {
};
}
/**
* Convert an OpenAI Chat Completions non-streaming response body into the
* OpenAI Responses API shape. Used when a Responses-format client (e.g. Codex)
* is routed to a Chat Completions upstream and `stream:false` — the streaming
* path already emits Responses events, but the JSON path returned a raw
* `chat.completion` body, so tool_calls were invisible to Responses clients.
*/
function extractCustomToolInput(argumentsValue) {
const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
try {
const parsed = JSON.parse(argumentsText);
if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
} catch { /* raw freeform input */ }
return argumentsText;
}
function openAICompletionToResponses(responseBody, customToolNames = null) {
const choice = responseBody?.choices?.[0];
if (!choice) return responseBody;
const message = choice.message || {};
const output = [];
// Reasoning → a reasoning item (summary text), mirroring the streaming path.
const reasoning = message.reasoning_content || message.reasoning;
if (typeof reasoning === "string" && reasoning.length > 0) {
output.push({
type: RESPONSES_ITEM.REASONING,
summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
});
}
// Assistant text → a message item with output_text content.
const text = typeof message.content === "string" ? message.content : "";
if (text.length > 0) {
output.push({
type: RESPONSES_ITEM.MESSAGE,
role: ROLE.ASSISTANT,
content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
});
}
// tool_calls → function_call/custom_tool_call items (Responses-native tool shape).
for (const tc of message.tool_calls || []) {
const fn = tc.function || {};
const custom = customToolNames?.has(fn.name);
output.push({
type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
call_id: tc.id || "",
name: fn.name || "",
...(custom
? { input: extractCustomToolInput(fn.arguments) }
: { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
});
}
const usage = responseBody.usage || {};
const status = choice.finish_reason === "tool_calls" ? "completed" : (choice.finish_reason === "stop" ? "completed" : (choice.finish_reason || "completed"));
return {
id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
object: "response",
created_at: responseBody.created || Math.floor(Date.now() / 1000),
model: responseBody.model || "unknown",
status,
background: false,
error: null,
output,
usage: {
input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
output_tokens: usage.completion_tokens || usage.output_tokens || 0,
total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
},
};
}
/**
* Translate non-streaming response body from provider format → OpenAI format.
*/
export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames = null) {
if (targetFormat === sourceFormat) return responseBody;
// Provider responded in OpenAI Chat Completions shape but the client speaks
// Responses API — convert so tool_calls/text surface as Responses `output`.
if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.OPENAI_RESPONSES) {
return openAICompletionToResponses(responseBody, customToolNames);
}
if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.CLAUDE) {
return openAICompletionToClaudeMessage(responseBody);
}
@@ -198,7 +281,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
/**
* Handle non-streaming response from provider.
*/
export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog }) {
export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, trackDone, appendLog, pxpipe, reqTag, log }) {
trackDone();
const contentType = providerResponse.headers.get("content-type") || "";
let responseBody;
@@ -235,12 +318,16 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
const usage = extractUsageFromResponse(responseBody);
appendLog({ tokens: usage, status: "200 OK" });
saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint });
saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
const translatedResponse = needsTranslation(targetFormat, sourceFormat)
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames)
: responseBody;
const isClaudeMessageResponse = sourceFormat === FORMATS.CLAUDE && translatedResponse?.type === "message";
// Responses-format translation produces a `object:"response"` body with no
// `choices`; skip the Chat-Completions-specific post-processing below for it.
const isResponsesResponse = sourceFormat === FORMATS.OPENAI_RESPONSES && translatedResponse?.object === "response";
// Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
if (translatedResponse?.choices?.[0]) {
@@ -253,13 +340,13 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
}
// Ensure OpenAI-required fields
if (!isClaudeMessageResponse) {
if (!isClaudeMessageResponse && !isResponsesResponse) {
if (!translatedResponse.object) translatedResponse.object = "chat.completion";
if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
}
// Strip Azure-specific fields
if (!isClaudeMessageResponse) {
if (!isClaudeMessageResponse && !isResponsesResponse) {
delete translatedResponse.prompt_filter_results;
if (translatedResponse?.choices) {
for (const choice of translatedResponse.choices) delete choice.content_filter_results;
@@ -273,7 +360,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
// Strip reasoning_content only when content is non-empty.
// When content is empty (e.g. thinking models that used all tokens for reasoning),
// reasoning_content is the only useful output and must be preserved.
if (!isClaudeMessageResponse && translatedResponse?.choices) {
if (!isClaudeMessageResponse && !isResponsesResponse && translatedResponse?.choices) {
for (const choice of translatedResponse.choices) {
if (choice?.message?.reasoning_content && choice.message.content) {
delete choice.message.reasoning_content;
@@ -296,6 +383,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
thinking: translatedResponse?.choices?.[0]?.message?.reasoning_content || translatedResponse?.reasoning_content || null,
finish_reason: translatedResponse?.choices?.[0]?.finish_reason || "unknown"
},
pxpipe,
status: "success"
}, { endpoint: clientRawRequest?.endpoint || null })).catch(err => {
console.error("[RequestDetail] Failed to save:", err.message);