mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-07 07:42:13 +03:00
* chore(release): open v3.8.10 development cycle Bump 3.8.9 → 3.8.10 across package.json, lockfile, electron, open-sse, and docs/reference/openapi.yaml; add the [3.8.10] CHANGELOG section (root + 41 i18n mirrors) as the integration target for the cycle. Entries land here as work merges into release/v3.8.10; finalized by the release flow. * fix(providers): resolve web provider alias collisions Assign unique aliases to HuggingChat, Kimi Web, and Qwen Web so they no longer shadow primary providers or trigger startup warnings. Add a unit test to enforce provider alias uniqueness and prevent future collisions. Also expand local ignore and VS Code exclude rules for agent, build, and worktree artifacts. * fix(responses): normalize image_url parts across input paths (#3150) Normalize image_url parts across all Responses input paths. Integrated into release/v3.8.10. * fix(api-manager): preserve API key expiration local time (#3146) Preserve API key expiration local time + clear button. Integrated into release/v3.8.10. * Strip previous_response_id for stateless Responses upstreams (#3143) Strip previous_response_id for stateless Responses upstreams (auto/strip/preserve). Integrated into release/v3.8.10. * fix(opencode-plugin): map thinking cap to interleaved in model+combo (#3138) Map caps.thinking to ModelV2.capabilities.interleaved for opencode-plugin. Integrated into release/v3.8.10. * fix(providers): use synced models as fallback for all providers (#3148) Use synced models as authoritative local catalog for all providers (+regression test). Integrated into release/v3.8.10. * fix(qoder): bifurcate validation by token type — PAT→Cosy, regular API key→dashscope (#3149) Bifurcate Qoder validation by token type (PAT→Cosy, regular→dashscope) +regression test. Integrated into release/v3.8.10. * fix(antigravity): dynamic model resolution via MITM alias table (#3144) Dynamic antigravity MITM model resolution in the executor (+bug fix +regression test; DB import dropped from client-reachable config). Integrated into release/v3.8.10. * Feature/batch allow big (#3128) Podman deployment options + larger upload body-size limits (+CONTAINER_HOST docs). Integrated into release/v3.8.10. * fix(fireworks): preserve fully-qualified router/model IDs (#3133) (#3160) Fireworks router IDs (accounts/fireworks/routers/...) were double-prefixed with accounts/fireworks/models/ → upstream 404. Add optional acceptedModelIdPrefixes to the registry entry and skip the prepend when the model already starts with an accepted prefix. Co-authored-by: KooshaPari <KooshaPari@users.noreply.github.com> * fix(llama-cpp): route to configured local baseUrl instead of OpenAI (#3136) (#3161) llama-cpp was missing from the local-provider group in buildUrl(), so it fell through to the OpenAI baseUrl and returned an OpenAI 401. Add the case to resolve the connection's providerSpecificData.baseUrl. Co-authored-by: tjengbudi <tjengbudi@users.noreply.github.com> * fix(t3-chat-web): parse cookies + convexSessionId from stored credential (#3007) (#3162) The executor read credentials.cookies/convexSessionId, but the pipeline only stores the pasted string under apiKey → t3.chat always 400'd. Parse both values from apiKey (fallback accessToken), mirroring validation.ts. Co-authored-by: minhtran162 <minhtran162@users.noreply.github.com> * fix(minimax): stop capping MiniMax-M3 / M2.7 max_tokens at 8192 (#3141) (#3163) MiniMax-M3 had no MODEL_SPECS entry and capitalized MiniMax-M2.7 missed its lowercase spec (case-sensitive lookup) → both fell to the 8192 default cap. Add the M3 spec (512K output), alias the capitalized ids, and make getModelSpec lookups case-insensitive. Co-authored-by: totaltube <totaltube@users.noreply.github.com> * fix(github-copilot): discover model catalog live from api.githubcopilot.com (#3120, #3121) (#3164) The github (Copilot) provider had a static hardcoded catalog with no discovery source, so Import Models never refreshed (#3120) and advertised non-entitled models that 400 on use (#3121). Add a live /models fetch with fallback to the static list. Co-authored-by: gabrielmoreira <gabrielmoreira@users.noreply.github.com> * fix(combo): invalidate nested-combo cache on edits + log DATA_DIR (#3147) (#3165) Editing a combo did not invalidate the 10s nested-combo expansion caches (chat.ts getCombosCachedForChat + chatCore.ts getCombosCached; the exported clearCombosCache was dead code), so a removed nested target/model could be served as a phantom for up to 10s. Wire a shared monotonic combos-cache version in readCache (bumped by invalidateDbCache("combos") on every combo write); both cache layers treat a version mismatch as a miss. Also log the resolved DATA_DIR/SQLITE_FILE absolute path at DB init so the reporter's 'persists across restart + volume wipe' symptom (a multi-replica Docker volume/DATA_DIR mismatch, not a routing bug) is diagnosable from logs. Includes consolidated CHANGELOG entries for #3133/#3136/#3007/#3141/#3120/#3121. Co-authored-by: ViFigueiredo <ViFigueiredo@users.noreply.github.com> * fix(web-tools): parse bare JSON tool calls (#3157) Parse bare JSON tool calls for deepseek-web (#2820) + fuzzy tool-name matching. Integrated into release/v3.8.10. * fix(misc): minor fixes across reasoning cache, account fallback, binary manager (#3177) Misc: ProviderProfile export, DeepSeek reasoning regex, binary guard. Integrated into release/v3.8.10. * fix(kiro): minor OAuth social exchange tweaks (#3176) Kiro social OAuth: optional targetProvider passthrough. Integrated into release/v3.8.10. * deps: bump hono from 4.12.18 to 4.12.23 (#3179) Bump hono to 4.12.23. Integrated into release/v3.8.10. * fix(providerRegistry): update kilocode format and executor (#3166) kilocode: openai format + default executor (matches kilo-gateway) + registry test. Integrated into release/v3.8.10. * feat(metrics): cross-request TTFT and gap latency after tool calls (#3173) Cross-request TTFT + gap-after-tool latency metrics (+test). Integrated into release/v3.8.10. * feat(dashboard): provider stats API endpoint and dashboard page (#3175) Provider stats dashboard + API (SQL moved to db module per Hard Rule #5, +test). Integrated into release/v3.8.10. * fix(usage): sequential+spaced OAuth quota sync, reactive force-refresh, actionable 401 (#3156) Sequential+spaced OAuth quota sync, reactive force-refresh on 401, actionable 401 in UI. Integrated into release/v3.8.10. * fix(healthcheck): per-provider proactive-refresh skip list (rescue short-TTL OAuth) (#3159) Per-provider proactive-refresh skip list (OMNIROUTE_HEALTHCHECK_SKIP_PROVIDERS) to rescue short-TTL OAuth. Integrated into release/v3.8.10. * feat(quota): show OAuth token expiry on provider cards (small, blue, informative) (#3178) Show OAuth token expiry on provider cards (small, blue, informative). Integrated into release/v3.8.10. * fix(providers): empty refresh must not resurface just-cleared synced models (#3181) Empty refresh must not resurface just-cleared synced models (fixes the release-blocking provider-models-route test). Integrated into release/v3.8.10. * chore(release): v3.8.10 — 2026-06-04 (finalize CHANGELOG) --------- Co-authored-by: Wilson <pedbookmed@gmail.com> Co-authored-by: Xiangzhe <32761048+xz-dev@users.noreply.github.com> Co-authored-by: Jan Leon <Jan.gaschler@gmail.com> Co-authored-by: M.M <mr.maatoug@gmail.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: Markus Hartung <mail@hartmark.se> Co-authored-by: KooshaPari <KooshaPari@users.noreply.github.com> Co-authored-by: tjengbudi <tjengbudi@users.noreply.github.com> Co-authored-by: minhtran162 <minhtran162@users.noreply.github.com> Co-authored-by: totaltube <totaltube@users.noreply.github.com> Co-authored-by: gabrielmoreira <gabrielmoreira@users.noreply.github.com> Co-authored-by: ViFigueiredo <ViFigueiredo@users.noreply.github.com> Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Nicolas Lorin <androw95220@gmail.com>
608 lines
22 KiB
TypeScript
608 lines
22 KiB
TypeScript
import { BaseExecutor, setUserAgentHeader, type ExecuteInput } from "./base.ts";
|
|
import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.ts";
|
|
import { getAccessToken } from "../services/tokenRefresh.ts";
|
|
import {
|
|
getRotatingApiKey,
|
|
getValidApiKey,
|
|
resolveKeyForRequest,
|
|
} from "../services/apiKeyRotator.ts";
|
|
import type { KeyHealth } from "../services/apiKeyRotator.ts";
|
|
import {
|
|
buildClaudeCodeCompatibleHeaders,
|
|
CLAUDE_CODE_COMPATIBLE_DEFAULT_CHAT_PATH,
|
|
joinClaudeCodeCompatibleUrl,
|
|
} from "../services/claudeCodeCompatible.ts";
|
|
import { getGigachatAccessToken } from "../services/gigachatAuth.ts";
|
|
import { getRegistryEntry } from "../config/providerRegistry.ts";
|
|
import { applyProviderRequestDefaults } from "../services/providerRequestDefaults.ts";
|
|
import {
|
|
detectFormat,
|
|
getOpenAICompatibleType,
|
|
getTargetFormat,
|
|
isClaudeCodeCompatible,
|
|
} from "../services/provider.ts";
|
|
import { sanitizeQwenThinkingToolChoice } from "../services/qwenThinking.ts";
|
|
import { buildDataRobotChatUrl } from "../config/datarobot.ts";
|
|
import { buildAzureAiChatUrl } from "../config/azureAi.ts";
|
|
import { buildWatsonxChatUrl } from "../config/watsonx.ts";
|
|
import { buildOciChatUrl } from "../config/oci.ts";
|
|
import { buildSapChatUrl, getSapResourceGroup } from "../config/sap.ts";
|
|
import { buildMaritalkChatUrl } from "../config/maritalk.ts";
|
|
|
|
import type { PoolConfig } from "../services/sessionPool/types.ts";
|
|
|
|
function normalizeBaseUrl(baseUrl) {
|
|
return (baseUrl || "").trim().replace(/\/$/, "");
|
|
}
|
|
|
|
function normalizeBailianMessagesUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl).replace(/\?beta=true$/, "");
|
|
const messagesUrl = normalized.endsWith("/messages") ? normalized : `${normalized}/messages`;
|
|
return messagesUrl;
|
|
}
|
|
|
|
function normalizeHerokuChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl);
|
|
if (normalized.endsWith("/v1/chat/completions")) return normalized;
|
|
return `${normalized}/v1/chat/completions`;
|
|
}
|
|
|
|
function normalizeDatabricksChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl);
|
|
if (normalized.endsWith("/chat/completions")) return normalized;
|
|
return `${normalized}/chat/completions`;
|
|
}
|
|
|
|
function normalizeDataRobotChatUrl(baseUrl) {
|
|
return buildDataRobotChatUrl(baseUrl);
|
|
}
|
|
|
|
function normalizeAzureAiChatUrl(baseUrl: string, apiType: "chat" | "responses" = "chat") {
|
|
return buildAzureAiChatUrl(baseUrl, apiType);
|
|
}
|
|
|
|
function normalizeWatsonxChatUrl(baseUrl: string) {
|
|
return buildWatsonxChatUrl(baseUrl);
|
|
}
|
|
|
|
function normalizeOciChatUrl(baseUrl: string, apiType: "chat" | "responses" = "chat") {
|
|
return buildOciChatUrl(baseUrl, apiType);
|
|
}
|
|
|
|
function normalizeSapChatUrl(baseUrl) {
|
|
return buildSapChatUrl(baseUrl);
|
|
}
|
|
|
|
function normalizeXiaomiMimoChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl).replace(/\/chat\/completions$/, "");
|
|
return `${normalized}/chat/completions`;
|
|
}
|
|
|
|
function normalizeSnowflakeChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl)
|
|
.replace(/\/cortex\/inference:complete$/, "")
|
|
.replace(/\/api\/v2$/, "");
|
|
return `${normalized}/api/v2/cortex/inference:complete`;
|
|
}
|
|
|
|
function normalizeGigachatChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl).replace(/\/chat\/completions$/, "");
|
|
return `${normalized}/chat/completions`;
|
|
}
|
|
|
|
function normalizeOpenAIChatUrl(baseUrl) {
|
|
const normalized = normalizeBaseUrl(baseUrl);
|
|
if (
|
|
normalized.endsWith("/chat/completions") ||
|
|
normalized.endsWith("/responses") ||
|
|
normalized.endsWith("/chat")
|
|
) {
|
|
return normalized;
|
|
}
|
|
return normalized.endsWith("/v1") ? `${normalized}/chat/completions` : normalized;
|
|
}
|
|
|
|
export class DefaultExecutor extends BaseExecutor {
|
|
constructor(provider) {
|
|
super(provider, PROVIDERS[provider] || PROVIDERS.openai);
|
|
const registryEntry = getRegistryEntry(provider);
|
|
if (registryEntry?.poolConfig) {
|
|
this.poolConfig = registryEntry.poolConfig as PoolConfig;
|
|
}
|
|
}
|
|
|
|
buildUrl(model, stream, urlIndex = 0, credentials = null) {
|
|
void model;
|
|
void stream;
|
|
void urlIndex;
|
|
if (this.provider?.startsWith?.("openai-compatible-")) {
|
|
const psd = credentials?.providerSpecificData;
|
|
const baseUrl = psd?.baseUrl || "https://api.openai.com/v1";
|
|
const normalized = baseUrl.replace(/\/$/, "");
|
|
const customPath = typeof psd?.chatPath === "string" && psd.chatPath ? psd.chatPath : null;
|
|
if (customPath) return `${normalized}${customPath}`;
|
|
const path =
|
|
getOpenAICompatibleType(this.provider, psd) === "responses"
|
|
? "/responses"
|
|
: "/chat/completions";
|
|
return `${normalized}${path}`;
|
|
}
|
|
if (this.provider?.startsWith?.("anthropic-compatible-")) {
|
|
const psd = credentials?.providerSpecificData;
|
|
const baseUrl = psd?.baseUrl || "https://api.anthropic.com/v1";
|
|
const customPath = typeof psd?.chatPath === "string" && psd.chatPath ? psd.chatPath : null;
|
|
if (isClaudeCodeCompatible(this.provider)) {
|
|
return joinClaudeCodeCompatibleUrl(
|
|
baseUrl,
|
|
customPath || CLAUDE_CODE_COMPATIBLE_DEFAULT_CHAT_PATH
|
|
);
|
|
}
|
|
const normalized = baseUrl.replace(/\/$/, "");
|
|
return `${normalized}${customPath || "/messages"}`;
|
|
}
|
|
switch (this.provider) {
|
|
case "bailian-coding-plan": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeBailianMessagesUrl(baseUrl);
|
|
}
|
|
case "heroku": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeHerokuChatUrl(baseUrl);
|
|
}
|
|
case "databricks": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeDatabricksChatUrl(baseUrl);
|
|
}
|
|
case "datarobot": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeDataRobotChatUrl(baseUrl);
|
|
}
|
|
case "azure-ai": {
|
|
const forceResponses =
|
|
credentials?.providerSpecificData?._omnirouteForceResponsesUpstream === true;
|
|
const apiType =
|
|
forceResponses || credentials?.providerSpecificData?.apiType === "responses"
|
|
? "responses"
|
|
: "chat";
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeAzureAiChatUrl(baseUrl, apiType);
|
|
}
|
|
case "watsonx": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeWatsonxChatUrl(baseUrl);
|
|
}
|
|
case "oci": {
|
|
const forceResponses =
|
|
credentials?.providerSpecificData?._omnirouteForceResponsesUpstream === true;
|
|
const apiType =
|
|
forceResponses || credentials?.providerSpecificData?.apiType === "responses"
|
|
? "responses"
|
|
: "chat";
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeOciChatUrl(baseUrl, apiType);
|
|
}
|
|
case "sap": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeSapChatUrl(baseUrl);
|
|
}
|
|
case "xiaomi-mimo": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeXiaomiMimoChatUrl(baseUrl);
|
|
}
|
|
case "snowflake": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeSnowflakeChatUrl(baseUrl);
|
|
}
|
|
case "gigachat": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeGigachatChatUrl(baseUrl);
|
|
}
|
|
case "maritalk": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return buildMaritalkChatUrl(baseUrl);
|
|
}
|
|
case "siliconflow": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeOpenAIChatUrl(baseUrl);
|
|
}
|
|
case "llama-cpp":
|
|
case "lm-studio":
|
|
case "modal":
|
|
case "reka":
|
|
case "vllm":
|
|
case "lemonade":
|
|
case "llamafile":
|
|
case "triton":
|
|
case "docker-model-runner":
|
|
case "xinference":
|
|
case "oobabooga": {
|
|
const baseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return normalizeOpenAIChatUrl(baseUrl);
|
|
}
|
|
case "zai":
|
|
case "glm-coding-apikey": {
|
|
const zaiBaseUrl = credentials?.providerSpecificData?.baseUrl || this.config.baseUrl;
|
|
return `${zaiBaseUrl}?beta=true`;
|
|
}
|
|
case "claude":
|
|
case "glm":
|
|
case "glmt":
|
|
case "kimi-coding":
|
|
case "minimax":
|
|
case "minimax-cn":
|
|
return `${this.config.baseUrl}?beta=true`;
|
|
case "gemini":
|
|
return `${this.config.baseUrl}/${model}:${stream ? "streamGenerateContent?alt=sse" : "generateContent"}`;
|
|
case "qwen": {
|
|
const resourceUrl = credentials?.providerSpecificData?.resourceUrl;
|
|
return `https://${resourceUrl || "portal.qwen.ai"}/v1/chat/completions`;
|
|
}
|
|
default: {
|
|
const url = this.config.baseUrl;
|
|
const entry = getRegistryEntry(this.provider);
|
|
return entry?.urlSuffix ? `${url}${entry.urlSuffix}` : url;
|
|
}
|
|
}
|
|
}
|
|
|
|
buildHeaders(credentials, stream = true, clientHeaders?: Record<string, string> | null) {
|
|
const headers = { "Content-Type": "application/json", ...this.config.headers };
|
|
|
|
// Allow per-provider User-Agent override via environment variable.
|
|
const providerId = this.config?.id || this.provider;
|
|
if (providerId) {
|
|
const envKey = `${providerId.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_USER_AGENT`;
|
|
const envUA = process.env[envKey]?.trim();
|
|
if (envUA) {
|
|
headers["User-Agent"] = envUA;
|
|
if ("user-agent" in headers) {
|
|
headers["user-agent"] = envUA;
|
|
}
|
|
}
|
|
}
|
|
|
|
// T07: resolve extra keys round-robin locally since DefaultExecutor overrides BaseExecutor buildHeaders
|
|
const extraKeys =
|
|
(credentials.providerSpecificData?.extraApiKeys as string[] | undefined) ?? [];
|
|
const selectedKeyId = (credentials.providerSpecificData as Record<string, unknown> | undefined)
|
|
?.selectedKeyId as string | undefined;
|
|
let effectiveKey = credentials.apiKey;
|
|
if (extraKeys.length > 0 && credentials.connectionId && credentials.apiKey) {
|
|
const resolved = resolveKeyForRequest(
|
|
credentials.connectionId,
|
|
credentials.apiKey,
|
|
extraKeys,
|
|
selectedKeyId ?? null
|
|
);
|
|
effectiveKey = resolved?.key ?? credentials.apiKey;
|
|
if (resolved && credentials.providerSpecificData) {
|
|
(credentials.providerSpecificData as Record<string, unknown>).selectedKeyId =
|
|
resolved.keyId;
|
|
}
|
|
}
|
|
|
|
switch (this.provider) {
|
|
case "gemini":
|
|
effectiveKey
|
|
? (headers["x-goog-api-key"] = effectiveKey)
|
|
: (headers["Authorization"] = `Bearer ${credentials.accessToken}`);
|
|
break;
|
|
case "snowflake": {
|
|
const rawToken = effectiveKey || credentials.accessToken || "";
|
|
const usesProgrammaticAccessToken = rawToken.startsWith("pat/");
|
|
headers["Authorization"] =
|
|
`Bearer ${usesProgrammaticAccessToken ? rawToken.slice(4) : rawToken}`;
|
|
headers["X-Snowflake-Authorization-Token-Type"] = usesProgrammaticAccessToken
|
|
? "PROGRAMMATIC_ACCESS_TOKEN"
|
|
: "KEYPAIR_JWT";
|
|
break;
|
|
}
|
|
case "gigachat":
|
|
headers["Authorization"] = `Bearer ${credentials.accessToken || effectiveKey}`;
|
|
break;
|
|
case "clarifai": {
|
|
const clarifaiToken = effectiveKey || credentials.accessToken;
|
|
if (clarifaiToken) {
|
|
headers["Authorization"] = `Key ${clarifaiToken}`;
|
|
}
|
|
break;
|
|
}
|
|
case "azure-ai":
|
|
if (effectiveKey || credentials.accessToken) {
|
|
headers["api-key"] = effectiveKey || credentials.accessToken;
|
|
}
|
|
delete headers["Authorization"];
|
|
break;
|
|
case "oci": {
|
|
const bearerToken = effectiveKey || credentials.accessToken;
|
|
if (bearerToken) {
|
|
headers["Authorization"] = `Bearer ${bearerToken}`;
|
|
}
|
|
const projectId =
|
|
credentials.projectId ||
|
|
credentials?.providerSpecificData?.projectId ||
|
|
credentials?.providerSpecificData?.project;
|
|
if (projectId) {
|
|
headers["OpenAI-Project"] = projectId;
|
|
}
|
|
break;
|
|
}
|
|
case "sap": {
|
|
const bearerToken = effectiveKey || credentials.accessToken;
|
|
if (bearerToken) {
|
|
headers["Authorization"] = `Bearer ${bearerToken}`;
|
|
}
|
|
headers["AI-Resource-Group"] = getSapResourceGroup(credentials?.providerSpecificData);
|
|
break;
|
|
}
|
|
case "reka": {
|
|
const bearerToken = effectiveKey || credentials.accessToken;
|
|
if (bearerToken) {
|
|
headers["Authorization"] = `Bearer ${bearerToken}`;
|
|
headers["X-Api-Key"] = bearerToken;
|
|
}
|
|
break;
|
|
}
|
|
case "maritalk": {
|
|
const token = effectiveKey || credentials.accessToken;
|
|
if (token) {
|
|
headers["Authorization"] = `Key ${token}`;
|
|
}
|
|
break;
|
|
}
|
|
case "claude":
|
|
case "anthropic":
|
|
effectiveKey
|
|
? (headers["x-api-key"] = effectiveKey)
|
|
: (headers["Authorization"] = `Bearer ${credentials.accessToken}`);
|
|
break;
|
|
case "glm":
|
|
case "glmt":
|
|
case "kimi-coding":
|
|
case "bailian-coding-plan":
|
|
case "kimi-coding-apikey":
|
|
case "zai":
|
|
case "glm-coding-apikey":
|
|
headers["x-api-key"] = effectiveKey || credentials.accessToken;
|
|
break;
|
|
default:
|
|
if (isClaudeCodeCompatible(this.provider)) {
|
|
return buildClaudeCodeCompatibleHeaders(
|
|
effectiveKey || credentials.accessToken || "",
|
|
stream,
|
|
credentials?.providerSpecificData?.ccSessionId
|
|
);
|
|
}
|
|
if (this.provider?.startsWith?.("anthropic-compatible-")) {
|
|
if (effectiveKey) {
|
|
headers["x-api-key"] = effectiveKey;
|
|
} else if (credentials.accessToken) {
|
|
headers["Authorization"] = `Bearer ${credentials.accessToken}`;
|
|
}
|
|
if (!headers["anthropic-version"]) {
|
|
headers["anthropic-version"] = "2023-06-01";
|
|
}
|
|
} else {
|
|
// Use registry authHeader if available, otherwise default to bearer
|
|
const entry = getRegistryEntry(this.provider);
|
|
const authHeader = entry?.authHeader || "bearer";
|
|
const token = effectiveKey || credentials.accessToken;
|
|
if (token) {
|
|
if (authHeader === "x-api-key") {
|
|
headers["x-api-key"] = token;
|
|
} else if (authHeader === "x-goog-api-key") {
|
|
headers["x-goog-api-key"] = token;
|
|
} else {
|
|
headers["Authorization"] = `Bearer ${token}`;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
headers["Accept"] = stream ? "text/event-stream" : "application/json";
|
|
|
|
// Qwen header cleanup: Remove X-Dashscope-* headers if using an API key (DashScope compatible mode).
|
|
// If using OAuth (Qwen Code), we MUST keep them for portal.qwen.ai to accept the request.
|
|
if (this.provider === "qwen" && effectiveKey) {
|
|
for (const key of Object.keys(headers)) {
|
|
if (key.toLowerCase().startsWith("x-dashscope-")) {
|
|
delete headers[key];
|
|
}
|
|
}
|
|
}
|
|
|
|
// Forward client request metadata headers (from OpenCode or similar clients)
|
|
// Allowlist-based: only specific x-opencode-* headers and User-Agent are forwarded
|
|
if (clientHeaders) {
|
|
const clientUA = clientHeaders["User-Agent"] || clientHeaders["user-agent"];
|
|
if (clientUA) {
|
|
setUserAgentHeader(headers, clientUA);
|
|
}
|
|
|
|
const opencodeHeaderKeys = [
|
|
"x-opencode-session",
|
|
"x-opencode-request",
|
|
"x-opencode-project",
|
|
"x-opencode-client",
|
|
];
|
|
for (const headerName of opencodeHeaderKeys) {
|
|
const value = Object.entries(clientHeaders).find(
|
|
([key]) => key.toLowerCase() === headerName.toLowerCase()
|
|
)?.[1];
|
|
if (value) {
|
|
headers[headerName] = value;
|
|
}
|
|
}
|
|
}
|
|
|
|
return headers;
|
|
}
|
|
|
|
/**
|
|
* For compatible providers, the model name is already clean by the time
|
|
* it reaches the executor (chatCore sets body.model = modelInfo.model,
|
|
* which is the parsed model ID without internal routing prefixes).
|
|
*
|
|
* Models may legitimately contain "/" as part of their ID (e.g. "zai-org/GLM-5-FP8",
|
|
* "org/model-name") — we must NOT strip path segments. (Fix #493)
|
|
*/
|
|
transformRequest(model, body, stream, credentials) {
|
|
const cleanedBody = super.transformRequest(model, body, stream, credentials);
|
|
let withDefaults = applyProviderRequestDefaults(cleanedBody, this.config.requestDefaults);
|
|
const targetFormat = getTargetFormat(this.provider, credentials?.providerSpecificData);
|
|
const requestFormat =
|
|
withDefaults && typeof withDefaults === "object" && !Array.isArray(withDefaults)
|
|
? detectFormat(withDefaults as Record<string, unknown>)
|
|
: "openai";
|
|
|
|
if (typeof withDefaults === "object" && withDefaults !== null && !Array.isArray(withDefaults)) {
|
|
if (this.provider?.startsWith?.("anthropic-compatible-")) {
|
|
if (Object.prototype.hasOwnProperty.call(withDefaults, "stream_options")) {
|
|
const withoutStreamOptions = { ...withDefaults } as Record<string, unknown>;
|
|
delete withoutStreamOptions.stream_options;
|
|
withDefaults = withoutStreamOptions;
|
|
}
|
|
} else if (stream && targetFormat === "openai" && requestFormat !== "openai-responses") {
|
|
if (!credentials?.providerSpecificData?.disableStreamOptions) {
|
|
withDefaults = {
|
|
...withDefaults,
|
|
stream_options: {
|
|
...(((withDefaults as Record<string, unknown>).stream_options as object) || {}),
|
|
include_usage: true,
|
|
},
|
|
};
|
|
} else if (Object.prototype.hasOwnProperty.call(withDefaults, "stream_options")) {
|
|
const withoutStreamOptions = { ...withDefaults } as Record<string, unknown>;
|
|
delete withoutStreamOptions.stream_options;
|
|
withDefaults = withoutStreamOptions;
|
|
}
|
|
} else if (
|
|
(targetFormat === "openai-responses" || requestFormat === "openai-responses") &&
|
|
Object.prototype.hasOwnProperty.call(withDefaults, "stream_options")
|
|
) {
|
|
const withoutStreamOptions = { ...withDefaults } as Record<string, unknown>;
|
|
delete withoutStreamOptions.stream_options;
|
|
withDefaults = withoutStreamOptions;
|
|
}
|
|
|
|
// #1961: Map max_tokens -> max_completion_tokens for recent OpenAI models
|
|
if (targetFormat === "openai") {
|
|
const isRecentOpenAI = /^(o1|o3|o4|gpt-5)/i.test(model);
|
|
if (isRecentOpenAI && withDefaults && typeof withDefaults === "object") {
|
|
const defaultsRecord = withDefaults as Record<string, unknown>;
|
|
if ("max_tokens" in defaultsRecord) {
|
|
defaultsRecord.max_completion_tokens = defaultsRecord.max_tokens;
|
|
delete defaultsRecord.max_tokens;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
if (this.provider === "qwen" && typeof withDefaults === "object" && withDefaults !== null) {
|
|
return sanitizeQwenThinkingToolChoice(
|
|
withDefaults as Record<string, unknown>,
|
|
"QwenExecutor"
|
|
);
|
|
}
|
|
|
|
// Apply modelIdPrefix from RegistryEntry (e.g. "accounts/fireworks/models/")
|
|
// so registry can store short model IDs while the upstream API receives the full path.
|
|
if (typeof withDefaults === "object" && withDefaults !== null) {
|
|
const entry = getRegistryEntry(this.provider);
|
|
if (entry?.modelIdPrefix) {
|
|
const body = withDefaults as Record<string, unknown>;
|
|
if (typeof body.model === "string") {
|
|
// Skip prepending when the model already carries the canonical prefix OR any
|
|
// other accepted fully-qualified prefix (e.g. Fireworks router IDs). #3133.
|
|
const acceptedPrefixes = [entry.modelIdPrefix, ...(entry.acceptedModelIdPrefixes ?? [])];
|
|
const alreadyQualified = acceptedPrefixes.some((prefix) =>
|
|
(body.model as string).startsWith(prefix)
|
|
);
|
|
if (!alreadyQualified) {
|
|
body.model = `${entry.modelIdPrefix}${body.model}`;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
return withDefaults;
|
|
}
|
|
|
|
/**
|
|
* Refresh credentials via the centralized tokenRefresh service.
|
|
* Delegates to getAccessToken() which handles all providers with
|
|
* race-condition protection (deduplication via refreshPromiseCache).
|
|
*/
|
|
async refreshCredentials(credentials, log) {
|
|
if (this.provider === "gigachat") {
|
|
if (!credentials.apiKey) return null;
|
|
try {
|
|
return await getGigachatAccessToken({
|
|
credentials: credentials.apiKey,
|
|
});
|
|
} catch (error) {
|
|
log?.error?.("TOKEN", `gigachat refresh error: ${error.message}`);
|
|
return null;
|
|
}
|
|
}
|
|
if (!credentials.refreshToken) return null;
|
|
try {
|
|
return await getAccessToken(this.provider, credentials, log);
|
|
} catch (error) {
|
|
log?.error?.("TOKEN", `${this.provider} refresh error: ${error.message}`);
|
|
return null;
|
|
}
|
|
}
|
|
|
|
needsRefresh(credentials) {
|
|
if (this.provider === "gigachat") {
|
|
if (credentials.apiKey && !credentials.accessToken) return true;
|
|
if (!credentials.expiresAt) return false;
|
|
}
|
|
return super.needsRefresh(credentials);
|
|
}
|
|
|
|
async execute(input: ExecuteInput) {
|
|
const pool = this.getPool();
|
|
if (!pool) return super.execute(input);
|
|
|
|
const session = pool.acquire();
|
|
if (session) {
|
|
input.upstreamExtraHeaders = {
|
|
...session.buildHeaders(),
|
|
...input.upstreamExtraHeaders,
|
|
};
|
|
}
|
|
|
|
let result;
|
|
try {
|
|
result = await super.execute(input);
|
|
} catch (err) {
|
|
if (session) {
|
|
pool.reportCooldown(session);
|
|
session.release();
|
|
}
|
|
throw err;
|
|
}
|
|
|
|
if (session) {
|
|
try {
|
|
const status = result?.response?.status;
|
|
if (status === 429) {
|
|
pool.reportCooldown(session);
|
|
} else if (status >= 500) {
|
|
pool.reportDead(session);
|
|
} else {
|
|
pool.reportSuccess(session);
|
|
}
|
|
} finally {
|
|
session.release();
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
}
|
|
|
|
export default DefaultExecutor;
|