Files
OmniRoute/open-sse/executors/default.ts
Diego Rodrigues de Sa e Souza 68d5a0ab27 Release v3.8.10 (#3140)
* 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>
2026-06-04 20:05:38 -03:00

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;