mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-02 13:22:11 +03:00
* feat(qoder): native cosy integration * feat(qoder): implement native COSY encryption algorithm and remove CLI child instances, plus workflow bumps * feat(resilience): context overflow fallback, OAuth token detection, empty content guard & context-optimized combo strategy - Add isContextOverflowError + isContextOverflow detectors (400 + token-limit signals) - Auto-fallback to next family model on context overflow in chatCore - Add isEmptyContentResponse to catch fake-success empty responses, trigger fallback + recursive retry - Add OAUTH_INVALID_TOKEN error type (T11) with isOAuthInvalidToken signal matching; warn instead of deactivating node - Add getModelContextLimit helper in modelsDevSync (reads limit_context from synced capabilities) - Upgrade getTokenLimit in contextManager to check models.dev DB before registry (fixes gemini-2.5-pro: 1000000→1048576) - Add findLargerContextModel in modelFamilyFallback for context-aware model selection - Add sortModelsByContextSize + context-optimized combo strategy in combo.ts - Update context-manager unit test for corrected gemini-2.5-pro limit Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(review): address Gemini code review — tool_calls path, infinite recursion, dedup signals, findLargerContextModel - Fix isEmptyContentResponse: check message.tool_calls/delta.tool_calls instead of firstChoice.tool_calls (wrong OpenAI API path, caused tool-call responses to be falsely flagged as empty) - Fix empty content fallback: replace recursive handleChatCore call (infinite recursion risk + wrong model due to original body.model) with non-recursive pattern — call executeProviderRequest, parse fallback response body, reassign responseBody and fall through to existing processing - Fix context overflow: use findLargerContextModel over family candidates first, fall back to getNextFamilyFallback — ensures we pick a model with actually larger context window on overflow - Fix signal dedup: export CONTEXT_OVERFLOW_SIGNALS + CONTEXT_OVERFLOW_REGEX from errorClassifier.ts; import shared regex in modelFamilyFallback.ts, removing duplicate signal list and per-call RegExp construction Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(UI): add context-optimized strategy to frontend schema and options * fix(sse): preserve Responses API events in stream translation When translating Claude-format responses (e.g. GLM) to Responses API format for Codex CLI, the sanitizer stripped {event, data} structured items to {"object":"chat.completion.chunk"}, losing all content and the critical response.completed event. Only run sanitizeStreamingChunk on OpenAI Chat Completions chunks, skipping items that have the Responses API {event, data} structure. * test(sse): add regression test for Claude→Responses stream sanitization Verifies that {event,data} structured items from the Responses API translator bypass sanitizeStreamingChunk when translating Claude-format providers (e.g. GLM) to Responses API format for Codex CLI. * fix(sse): strengthen Responses API event detection with response. prefix check Use explicit `response.` prefix check instead of generic `event && data` presence check, as recommended in PR review. * fix: pin Next.js to 16.0.10 to prevent Turbopack hashed module bug Remove ^ prefix from next and eslint-config-next to prevent automatic upgrades to 16.1.x+ which introduced content-based hashing for external module references in Turbopack. Also remove duplicate Material Symbols @import from globals.css (font already loaded via <link> in layout.tsx). Fixes #509 * align cc-compatible cache handling with client passthrough * chore: integrate resilience and turbopack fixes (PRs #992, #990, #987) * chore(release): bump to v3.5.2 — changelog, docs, version sync * docs(i18n): sync documentation updates to 33 languages * fix(qoder): replace any with unknown to comply with strict any-budget --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: oyi77 <oyi77@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> Co-authored-by: Chris Staley <christopher-s@users.noreply.github.com> Co-authored-by: Ivan <shanin-i2011@yandex.ru> Co-authored-by: R.D. <rogerproself@gmail.com>
159 lines
5.1 KiB
TypeScript
159 lines
5.1 KiB
TypeScript
import {
|
|
BaseExecutor,
|
|
mergeUpstreamExtraHeaders,
|
|
type ExecuteInput,
|
|
type ProviderCredentials,
|
|
} from "./base.ts";
|
|
import { PROVIDERS } from "../config/constants.ts";
|
|
|
|
function getAuthToken(credentials: ProviderCredentials): string {
|
|
if (typeof credentials.apiKey === "string" && credentials.apiKey.trim()) {
|
|
return credentials.apiKey.trim();
|
|
}
|
|
if (typeof credentials.accessToken === "string" && credentials.accessToken.trim()) {
|
|
return credentials.accessToken.trim();
|
|
}
|
|
if (typeof credentials.refreshToken === "string" && credentials.refreshToken.trim()) {
|
|
return credentials.refreshToken.trim();
|
|
}
|
|
return "";
|
|
}
|
|
|
|
export class QoderExecutor extends BaseExecutor {
|
|
constructor() {
|
|
super("qoder", PROVIDERS.qoder);
|
|
}
|
|
|
|
async execute({ model, body, stream, credentials, signal, upstreamExtraHeaders }: ExecuteInput) {
|
|
const token = getAuthToken(credentials);
|
|
|
|
if (!token) {
|
|
return {
|
|
response: new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: "Qoder access token or API Key is required. Please sign in or set a PAT.",
|
|
type: "authentication_error",
|
|
code: "token_required",
|
|
},
|
|
}),
|
|
{ status: 401, headers: { "Content-Type": "application/json" } }
|
|
),
|
|
url: "https://dashscope.aliyuncs.com",
|
|
headers: { "Content-Type": "application/json" },
|
|
transformedBody: body,
|
|
};
|
|
}
|
|
|
|
const resolvedModel = model || "qwen3-coder-plus";
|
|
|
|
// Check if it's a model-alias matching QwenCode
|
|
let mappedModel = resolvedModel;
|
|
if (resolvedModel === "qwen3.5-plus" || resolvedModel === "qwen3.6-plus") {
|
|
mappedModel = "coder-model"; // Translate alias to what DashScope compatible endpoint accepts via QwenCode tokens
|
|
} else if (resolvedModel === "vision-model") {
|
|
mappedModel = "qwen3-vl-plus";
|
|
}
|
|
|
|
// Determine the resource URL: Qwen CLI tokens usually target portal.qwen.ai natively,
|
|
// but the DashScope compatible endpoint works out of the box when authtype is set.
|
|
// If the token was mapped to a custom `resource_url`, we should use it. Otherwise default to dashscope Aliyun.
|
|
let endpointUrl = "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions";
|
|
|
|
// We allow setting custom API base via credentials
|
|
let credentialsApiBase: unknown;
|
|
if (typeof credentials === "object" && credentials !== null) {
|
|
const credsObj = credentials as Record<string, unknown>;
|
|
credentialsApiBase = credsObj.customApiBase || credsObj.resourceUrl;
|
|
}
|
|
if (typeof credentialsApiBase === "string" && credentialsApiBase.trim()) {
|
|
let base = credentialsApiBase.trim();
|
|
if (!base.startsWith("http")) base = `https://${base}`;
|
|
if (!base.endsWith("/v1")) base = base.endsWith("/") ? `${base}v1` : `${base}/v1`;
|
|
endpointUrl = `${base}/chat/completions`;
|
|
}
|
|
|
|
const headers: Record<string, string> = {
|
|
"Content-Type": "application/json",
|
|
Authorization: `Bearer ${token}`,
|
|
"x-dashscope-authtype": "qwen-oauth",
|
|
"x-dashscope-cachecontrol": "enable",
|
|
"user-agent": "QwenCode/0.11.1 (linux; x64)",
|
|
"x-dashscope-useragent": "QwenCode/0.11.1 (linux; x64)",
|
|
"x-stainless-arch": "x64",
|
|
"x-stainless-lang": "js",
|
|
"x-stainless-os": "Linux",
|
|
};
|
|
|
|
mergeUpstreamExtraHeaders(headers, upstreamExtraHeaders);
|
|
|
|
const payload = {
|
|
...(typeof body === "object" && body !== null ? body : {}),
|
|
model: mappedModel,
|
|
};
|
|
|
|
const bodyStr = JSON.stringify(payload);
|
|
|
|
try {
|
|
const response = await fetch(endpointUrl, {
|
|
method: "POST",
|
|
headers,
|
|
body: bodyStr,
|
|
signal,
|
|
});
|
|
|
|
const newHeaders = new Headers(response.headers);
|
|
|
|
if (!response.ok) {
|
|
let errText = await response.text();
|
|
return {
|
|
response: new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: `Qoder API failed with status ${response.status}: ${errText}`,
|
|
type: response.status === 401 ? "authentication_error" : "provider_error",
|
|
},
|
|
}),
|
|
{ status: response.status, headers: { "Content-Type": "application/json" } }
|
|
),
|
|
url: endpointUrl,
|
|
headers,
|
|
transformedBody: payload,
|
|
};
|
|
}
|
|
|
|
return {
|
|
response: new Response(response.body, {
|
|
status: response.status,
|
|
statusText: response.statusText,
|
|
headers: newHeaders,
|
|
}),
|
|
url: endpointUrl,
|
|
headers,
|
|
transformedBody: payload,
|
|
};
|
|
} catch (e: unknown) {
|
|
const error = e as Error;
|
|
if (error.name === "AbortError") {
|
|
throw error;
|
|
}
|
|
return {
|
|
response: new Response(
|
|
JSON.stringify({
|
|
error: {
|
|
message: `Qoder fetch error: ${error.message}`,
|
|
type: "provider_error",
|
|
},
|
|
}),
|
|
{ status: 502, headers: { "Content-Type": "application/json" } }
|
|
),
|
|
url: endpointUrl,
|
|
headers,
|
|
transformedBody: payload,
|
|
};
|
|
}
|
|
}
|
|
}
|
|
|
|
export default QoderExecutor;
|