feat: add provider-scoped environment overrides (#5807)

packages/ai/src/providers/amazon-bedrock.ts

@@ -1,3 +1,4 @@
+import type { Agent as HttpsAgent } from "node:https";
 import {
 	BedrockRuntimeClient,
 	type BedrockRuntimeClientConfig,
@@ -23,6 +24,8 @@ import {
 } from "@aws-sdk/client-bedrock-runtime";
 import { NodeHttpHandler } from "@smithy/node-http-handler";
 import type { BuildMiddleware, DocumentType, MetadataBearer } from "@smithy/types";
+import { HttpProxyAgent } from "http-proxy-agent";
+import { HttpsProxyAgent } from "https-proxy-agent";
 import { calculateCost } from "../models.ts";
 import type {
 	Api,
@@ -31,6 +34,7 @@ import type {
 	Context,
 	ImageContent,
 	Model,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StopReason,
 	StreamFunction,
@@ -45,7 +49,8 @@ import type {
 } from "../types.ts";
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { parseStreamingJson } from "../utils/json-parse.ts";
-import { createHttpProxyAgentsForTarget } from "../utils/node-http-proxy.ts";
+import { resolveHttpProxyUrlForTarget } from "../utils/node-http-proxy.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
 import { adjustMaxTokensForThinking, buildBaseOptions, clampReasoning } from "./simple-options.ts";
 import { transformMessages } from "./transform-messages.ts";
@@ -119,18 +124,18 @@ export const streamBedrock: StreamFunction<"bedrock-converse-stream", BedrockOpt
 		const blocks = output.content as Block[];
 
 		const config: BedrockRuntimeClientConfig = {
-			profile: options.profile,
+			profile: options.profile || getProviderEnvValue("AWS_PROFILE", options.env),
 		};
 		const configuredRegion = getConfiguredBedrockRegion(options);
-		const hasConfiguredProfile = hasConfiguredBedrockProfile();
+		const hasAmbientConfiguredProfile = Boolean(getProviderEnvValue("AWS_PROFILE"));
 		const endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);
 		const useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(
 			model.baseUrl,
 			configuredRegion,
-			hasConfiguredProfile,
+			hasAmbientConfiguredProfile,
 		);
 
-		// Only pin standard AWS Bedrock runtime endpoints when no region/profile is configured.
+		// Only pin standard AWS Bedrock runtime endpoints when no region or ambient AWS_PROFILE is configured.
 		// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in
 		// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.
 		if (useExplicitEndpoint) {
@@ -138,8 +143,10 @@ export const streamBedrock: StreamFunction<"bedrock-converse-stream", BedrockOpt
 		}
 
 		// Resolve bearer token for Bedrock API key auth.
-		const bearerToken = options.bearerToken || process.env.AWS_BEARER_TOKEN_BEDROCK || undefined;
-		const useBearerToken = bearerToken !== undefined && process.env.AWS_BEDROCK_SKIP_AUTH !== "1";
+		const skipAuth = getProviderEnvValue("AWS_BEDROCK_SKIP_AUTH", options.env) === "1";
+		const bearerToken =
+			options.bearerToken || getProviderEnvValue("AWS_BEARER_TOKEN_BEDROCK", options.env) || undefined;
+		const useBearerToken = bearerToken !== undefined && !skipAuth;
 
 		// in Node.js/Bun environment only
 		if (typeof process !== "undefined" && (process.versions?.node || process.versions?.bun)) {
@@ -153,25 +160,33 @@ export const streamBedrock: StreamFunction<"bedrock-converse-stream", BedrockOpt
 				config.region = configuredRegion;
 			} else if (endpointRegion && useExplicitEndpoint) {
 				config.region = endpointRegion;
-			} else if (!hasConfiguredProfile) {
+			} else if (!hasAmbientConfiguredProfile) {
 				config.region = "us-east-1";
 			}
 
 			// Support proxies that don't need authentication
-			if (process.env.AWS_BEDROCK_SKIP_AUTH === "1") {
+			if (skipAuth) {
 				config.credentials = {
 					accessKeyId: "dummy-access-key",
 					secretAccessKey: "dummy-secret-key",
 				};
 			}
 
-			const proxyAgents = createHttpProxyAgentsForTarget(model.baseUrl);
-			if (proxyAgents) {
+			const credentials = getConfiguredBedrockCredentials(options.env);
+			if (!skipAuth && credentials) {
+				config.credentials = credentials;
+			}
+
+			const proxyUrl = resolveHttpProxyUrlForTarget(model.baseUrl, options.env);
+			if (proxyUrl) {
 				// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based
 				// on `http2` module and has no support for http agent.
 				// Use NodeHttpHandler to support HTTP(S) proxy agents.
-				config.requestHandler = new NodeHttpHandler(proxyAgents);
-			} else if (process.env.AWS_BEDROCK_FORCE_HTTP1 === "1") {
+				config.requestHandler = new NodeHttpHandler({
+					httpAgent: new HttpProxyAgent(proxyUrl),
+					httpsAgent: new HttpsProxyAgent(proxyUrl) as unknown as HttpsAgent,
+				});
+			} else if (getProviderEnvValue("AWS_BEDROCK_FORCE_HTTP1", options.env) === "1") {
 				// Some custom endpoints require HTTP/1.1 instead of HTTP/2
 				config.requestHandler = new NodeHttpHandler();
 			}
@@ -192,12 +207,12 @@ export const streamBedrock: StreamFunction<"bedrock-converse-stream", BedrockOpt
 			if (options.headers && Object.keys(options.headers).length > 0) {
 				addCustomHeadersMiddleware(client, options.headers);
 			}
-			const cacheRetention = resolveCacheRetention(options.cacheRetention);
+			const cacheRetention = resolveCacheRetention(options.cacheRetention, options.env);
 			const inferenceMaxTokens = options.maxTokens ?? (isAnthropicClaudeModel(model) ? model.maxTokens : undefined);
 			let commandInput = {
 				modelId: model.id,
-				messages: convertMessages(context, model, cacheRetention),
-				system: buildSystemPrompt(context.systemPrompt, model, cacheRetention),
+				messages: convertMessages(context, model, cacheRetention, options.env),
+				system: buildSystemPrompt(context.systemPrompt, model, cacheRetention, options.env),
 				inferenceConfig: {
 					...(inferenceMaxTokens !== undefined && { maxTokens: inferenceMaxTokens }),
 					...(options.temperature !== undefined && { temperature: options.temperature }),
@@ -578,11 +593,11 @@ function mapThinkingLevelToEffort(
  * Resolve cache retention preference.
  * Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
  */
-function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
+function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
 	if (cacheRetention) {
 		return cacheRetention;
 	}
-	if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
+	if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
 		return "long";
 	}
 	return "short";
@@ -617,14 +632,14 @@ function isAnthropicClaudeModel(model: Model<"bedrock-converse-stream">): boolea
  * As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.
  * Amazon Nova models have automatic caching and don't need explicit cache points.
  */
-function supportsPromptCaching(model: Model<"bedrock-converse-stream">): boolean {
+function supportsPromptCaching(model: Model<"bedrock-converse-stream">, env?: ProviderEnv): boolean {
 	const candidates = getModelMatchCandidates(model.id, model.name);
 
 	const hasClaudeRef = candidates.some((s) => s.includes("claude"));
 	if (!hasClaudeRef) {
 		// Application inference profiles don't contain the model name in the ARN.
 		// Allow users to force cache points via environment variable.
-		if (typeof process !== "undefined" && process.env.AWS_BEDROCK_FORCE_CACHE === "1") return true;
+		if (getProviderEnvValue("AWS_BEDROCK_FORCE_CACHE", env) === "1") return true;
 		return false;
 	}
 	// Claude 4.x models (opus-4, sonnet-4, haiku-4)
@@ -652,13 +667,14 @@ function buildSystemPrompt(
 	systemPrompt: string | undefined,
 	model: Model<"bedrock-converse-stream">,
 	cacheRetention: CacheRetention,
+	env?: ProviderEnv,
 ): SystemContentBlock[] | undefined {
 	if (!systemPrompt) return undefined;
 
 	const blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];
 
 	// Add cache point for supported Claude models when caching is enabled
-	if (cacheRetention !== "none" && supportsPromptCaching(model)) {
+	if (cacheRetention !== "none" && supportsPromptCaching(model, env)) {
 		blocks.push({
 			cachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === "long" ? { ttl: CacheTTL.ONE_HOUR } : {}) },
 		});
@@ -699,6 +715,7 @@ function convertMessages(
 	context: Context,
 	model: Model<"bedrock-converse-stream">,
 	cacheRetention: CacheRetention,
+	env?: ProviderEnv,
 ): Message[] {
 	const result: Message[] = [];
 	const transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);
@@ -844,7 +861,7 @@ function convertMessages(
 	}
 
 	// Add cache point to the last user message for supported Claude models when caching is enabled
-	if (cacheRetention !== "none" && supportsPromptCaching(model) && result.length > 0) {
+	if (cacheRetention !== "none" && supportsPromptCaching(model, env) && result.length > 0) {
 		const lastMessage = result[result.length - 1];
 		if (lastMessage.role === ConversationRole.USER && lastMessage.content) {
 			(lastMessage.content as ContentBlock[]).push({
@@ -906,19 +923,26 @@ function mapStopReason(reason: string | undefined): StopReason {
 }
 
 function getConfiguredBedrockRegion(options: BedrockOptions): string | undefined {
-	if (typeof process === "undefined") {
-		return options.region;
-	}
-
-	return options.region || process.env.AWS_REGION || process.env.AWS_DEFAULT_REGION || undefined;
+	return (
+		options.region ||
+		getProviderEnvValue("AWS_REGION", options.env) ||
+		getProviderEnvValue("AWS_DEFAULT_REGION", options.env) ||
+		undefined
+	);
 }
 
-function hasConfiguredBedrockProfile(): boolean {
-	if (typeof process === "undefined") {
-		return false;
+function getConfiguredBedrockCredentials(env?: ProviderEnv): BedrockRuntimeClientConfig["credentials"] | undefined {
+	const accessKeyId = getProviderEnvValue("AWS_ACCESS_KEY_ID", env);
+	const secretAccessKey = getProviderEnvValue("AWS_SECRET_ACCESS_KEY", env);
+	if (!accessKeyId || !secretAccessKey) {
+		return undefined;
 	}
-
-	return Boolean(process.env.AWS_PROFILE);
+	const sessionToken = getProviderEnvValue("AWS_SESSION_TOKEN", env);
+	return {
+		accessKeyId,
+		secretAccessKey,
+		...(sessionToken ? { sessionToken } : {}),
+	};
 }
 
 function getStandardBedrockEndpointRegion(baseUrl: string | undefined): string | undefined {
@@ -938,14 +962,14 @@ function getStandardBedrockEndpointRegion(baseUrl: string | undefined): string |
 function shouldUseExplicitBedrockEndpoint(
 	baseUrl: string,
 	configuredRegion: string | undefined,
-	hasConfiguredProfile: boolean,
+	hasAmbientConfiguredProfile: boolean,
 ): boolean {
 	const endpointRegion = getStandardBedrockEndpointRegion(baseUrl);
 	if (!endpointRegion) {
 		return true;
 	}
 
-	return !configuredRegion && !hasConfiguredProfile;
+	return !configuredRegion && !hasAmbientConfiguredProfile;
 }
 
 function isGovCloudBedrockTarget(model: Model<"bedrock-converse-stream">, options: BedrockOptions): boolean {

packages/ai/src/providers/anthropic.ts

@@ -17,6 +17,7 @@ import type {
 	ImageContent,
 	Message,
 	Model,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StopReason,
 	StreamFunction,
@@ -30,6 +31,7 @@ import type {
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { headersToRecord } from "../utils/headers.ts";
 import { parseJsonWithRepair, parseStreamingJson } from "../utils/json-parse.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
 
 import { resolveCloudflareBaseUrl } from "./cloudflare.ts";
@@ -41,11 +43,11 @@ import { transformMessages } from "./transform-messages.ts";
  * Resolve cache retention preference.
  * Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
  */
-function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
+function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
 	if (cacheRetention) {
 		return cacheRetention;
 	}
-	if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
+	if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
 		return "long";
 	}
 	return "short";
@@ -54,8 +56,9 @@ function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention
 function getCacheControl(
 	model: Model<"anthropic-messages">,
 	cacheRetention?: CacheRetention,
+	env?: ProviderEnv,
 ): { retention: CacheRetention; cacheControl?: CacheControlEphemeral } {
-	const retention = resolveCacheRetention(cacheRetention);
+	const retention = resolveCacheRetention(cacheRetention, env);
 	if (retention === "none") {
 		return { retention };
 	}
@@ -494,7 +497,7 @@ export const streamAnthropic: StreamFunction<"anthropic-messages", AnthropicOpti
 					});
 				}
 
-				const cacheRetention = options?.cacheRetention ?? resolveCacheRetention();
+				const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
 				const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
 
 				const created = createClient(
@@ -505,6 +508,7 @@ export const streamAnthropic: StreamFunction<"anthropic-messages", AnthropicOpti
 					options?.headers,
 					copilotDynamicHeaders,
 					cacheSessionId,
+					options?.env,
 				);
 				client = created.client;
 				isOAuth = created.isOAuthToken;
@@ -794,6 +798,7 @@ function createClient(
 	optionsHeaders?: Record<string, string>,
 	dynamicHeaders?: Record<string, string>,
 	sessionId?: string,
+	env?: ProviderEnv,
 ): { client: Anthropic; isOAuthToken: boolean } {
 	// Adaptive thinking models have interleaved thinking built in, so skip the beta header.
 	const needsInterleavedBeta = interleavedThinking && model.compat?.forceAdaptiveThinking !== true;
@@ -809,7 +814,7 @@ function createClient(
 		const client = new Anthropic({
 			apiKey: null,
 			authToken: null,
-			baseURL: resolveCloudflareBaseUrl(model),
+			baseURL: resolveCloudflareBaseUrl(model, env),
 			dangerouslyAllowBrowser: true,
 			defaultHeaders: mergeHeaders(
 				{
@@ -902,7 +907,7 @@ function buildParams(
 	isOAuthToken: boolean,
 	options?: AnthropicOptions,
 ): MessageCreateParamsStreaming {
-	const { cacheControl } = getCacheControl(model, options?.cacheRetention);
+	const { cacheControl } = getCacheControl(model, options?.cacheRetention, options?.env);
 	const compat = getAnthropicCompat(model);
 	const params: MessageCreateParamsStreaming = {
 		model: model.id,

packages/ai/src/providers/azure-openai-responses.ts

@@ -12,6 +12,7 @@ import type {
 } from "../types.ts";
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { headersToRecord } from "../utils/headers.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
 import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.ts";
 import { buildBaseOptions } from "./simple-options.ts";
@@ -36,7 +37,9 @@ function resolveDeploymentName(model: Model<"azure-openai-responses">, options?:
 	if (options?.azureDeploymentName) {
 		return options.azureDeploymentName;
 	}
-	const mappedDeployment = parseDeploymentNameMap(process.env.AZURE_OPENAI_DEPLOYMENT_NAME_MAP).get(model.id);
+	const mappedDeployment = parseDeploymentNameMap(
+		getProviderEnvValue("AZURE_OPENAI_DEPLOYMENT_NAME_MAP", options?.env),
+	).get(model.id);
 	return mappedDeployment || model.id;
 }
 
@@ -198,10 +201,14 @@ function resolveAzureConfig(
 	model: Model<"azure-openai-responses">,
 	options?: AzureOpenAIResponsesOptions,
 ): { baseUrl: string; apiVersion: string } {
-	const apiVersion = options?.azureApiVersion || process.env.AZURE_OPENAI_API_VERSION || DEFAULT_AZURE_API_VERSION;
+	const apiVersion =
+		options?.azureApiVersion ||
+		getProviderEnvValue("AZURE_OPENAI_API_VERSION", options?.env) ||
+		DEFAULT_AZURE_API_VERSION;
 
-	const baseUrl = options?.azureBaseUrl?.trim() || process.env.AZURE_OPENAI_BASE_URL?.trim() || undefined;
-	const resourceName = options?.azureResourceName || process.env.AZURE_OPENAI_RESOURCE_NAME;
+	const baseUrl =
+		options?.azureBaseUrl?.trim() || getProviderEnvValue("AZURE_OPENAI_BASE_URL", options?.env)?.trim() || undefined;
+	const resourceName = options?.azureResourceName || getProviderEnvValue("AZURE_OPENAI_RESOURCE_NAME", options?.env);
 
 	let resolvedBaseUrl = baseUrl;
 

packages/ai/src/providers/cloudflare.ts

@@ -1,4 +1,5 @@
-import type { Api, Model } from "../types.ts";
+import type { Api, Model, ProviderEnv } from "../types.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 
 /** Workers AI direct endpoint. */
 export const CLOUDFLARE_WORKERS_AI_BASE_URL =
@@ -20,12 +21,12 @@ export function isCloudflareProvider(provider: string): boolean {
 	return provider === "cloudflare-workers-ai" || provider === "cloudflare-ai-gateway";
 }
 
-/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from process.env. */
-export function resolveCloudflareBaseUrl(model: Model<Api>): string {
+/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from provider env or process.env. */
+export function resolveCloudflareBaseUrl(model: Model<Api>, env?: ProviderEnv): string {
 	const url = model.baseUrl;
 	if (!url.includes("{")) return url;
 	const baseUrl = url.replace(/\{([A-Z_][A-Z0-9_]*)\}/g, (_match, name: string) => {
-		const value = process.env[name];
+		const value = getProviderEnvValue(name, env);
 		if (!value) {
 			throw new Error(`${name} is required for provider ${model.provider} but is not set.`);
 		}

packages/ai/src/providers/google-vertex.ts

@@ -14,6 +14,7 @@ import type {
 	Context,
 	Model,
 	ThinkingLevel as PiThinkingLevel,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StreamFunction,
 	StreamOptions,
@@ -23,6 +24,7 @@ import type {
 	ToolCall,
 } from "../types.ts";
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
 import type { GoogleThinkingLevel } from "./google-shared.ts";
 import {
@@ -91,7 +93,7 @@ export const streamGoogleVertex: StreamFunction<"google-vertex", GoogleVertexOpt
 			// Create the client using either a Vertex API key, if provided, or ADC with project and location
 			const client = apiKey
 				? createClientWithApiKey(model, apiKey, options?.headers)
-				: createClient(model, resolveProject(options), resolveLocation(options), options?.headers);
+				: createClient(model, resolveProject(options), resolveLocation(options), options?.headers, options?.env);
 			let params = buildParams(model, context, options);
 			const nextParams = await options?.onPayload?.(params, model);
 			if (nextParams !== undefined) {
@@ -333,12 +335,15 @@ function createClient(
 	project: string,
 	location: string,
 	optionsHeaders?: Record<string, string>,
+	env?: ProviderEnv,
 ): GoogleGenAI {
+	const googleAuthOptions = buildGoogleAuthOptions(env);
 	return new GoogleGenAI({
 		vertexai: true,
 		project,
 		location,
 		apiVersion: API_VERSION,
+		...(googleAuthOptions ? { googleAuthOptions } : {}),
 		httpOptions: buildHttpOptions(model, optionsHeaders),
 	});
 }
@@ -394,6 +399,11 @@ function baseUrlIncludesApiVersion(baseUrl: string): boolean {
 	}
 }
 
+function buildGoogleAuthOptions(env?: ProviderEnv): { keyFilename: string } | undefined {
+	const keyFilename = getProviderEnvValue("GOOGLE_APPLICATION_CREDENTIALS", env);
+	return keyFilename ? { keyFilename } : undefined;
+}
+
 function resolveApiKey(options?: GoogleVertexOptions): string | undefined {
 	const apiKey = options?.apiKey?.trim();
 	if (!apiKey || apiKey === GCP_VERTEX_CREDENTIALS_MARKER || isPlaceholderApiKey(apiKey)) {
@@ -407,7 +417,10 @@ function isPlaceholderApiKey(apiKey: string): boolean {
 }
 
 function resolveProject(options?: GoogleVertexOptions): string {
-	const project = options?.project || process.env.GOOGLE_CLOUD_PROJECT || process.env.GCLOUD_PROJECT;
+	const project =
+		options?.project ||
+		getProviderEnvValue("GOOGLE_CLOUD_PROJECT", options?.env) ||
+		getProviderEnvValue("GCLOUD_PROJECT", options?.env);
 	if (!project) {
 		throw new Error(
 			"Vertex AI requires a project ID. Set GOOGLE_CLOUD_PROJECT/GCLOUD_PROJECT or pass project in options.",
@@ -417,7 +430,7 @@ function resolveProject(options?: GoogleVertexOptions): string {
 }
 
 function resolveLocation(options?: GoogleVertexOptions): string {
-	const location = options?.location || process.env.GOOGLE_CLOUD_LOCATION;
+	const location = options?.location || getProviderEnvValue("GOOGLE_CLOUD_LOCATION", options?.env);
 	if (!location) {
 		throw new Error("Vertex AI requires a location. Set GOOGLE_CLOUD_LOCATION or pass location in options.");
 	}

packages/ai/src/providers/openai-codex-responses.ts

@@ -27,6 +27,7 @@ import type {
 	AssistantMessage,
 	Context,
 	Model,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StreamFunction,
 	StreamOptions,
@@ -40,6 +41,7 @@ import {
 } from "../utils/diagnostics.ts";
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { headersToRecord } from "../utils/headers.ts";
+import { resolveHttpProxyUrlForTarget } from "../utils/node-http-proxy.ts";
 import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
 import { convertResponsesMessages, convertResponsesTools, processResponsesStream } from "./openai-responses-shared.ts";
 import { buildBaseOptions } from "./simple-options.ts";
@@ -814,19 +816,13 @@ type WebSocketConstructor = new (
 ) => WebSocketLike;
 
 let _cachedWebsocket: WebSocketConstructor | null = null;
-async function getWebSocketConstructor(): Promise<WebSocketConstructor | null> {
-	if (_cachedWebsocket) return _cachedWebsocket;
+async function getWebSocketConstructor(env?: ProviderEnv): Promise<WebSocketConstructor | null> {
+	if (!env && _cachedWebsocket) return _cachedWebsocket;
 
 	// bun doesn't respect http proxy envs, ref: https://github.com/oven-sh/bun/issues/15489
 	// TODO: remove this when bun supports proxy envs in websocket.
-	if (
-		process?.versions?.bun &&
-		(process.env.HTTP_PROXY || process.env.HTTPS_PROXY || process.env.http_proxy || process.env.https_proxy)
-	) {
-		const m = await dynamicImport("proxy-from-env");
-		const getProxyForUrl = (m as { getProxyForUrl: (url: string | object | URL) => string }).getProxyForUrl;
-
-		_cachedWebsocket = class extends WebSocket {
+	if (typeof process !== "undefined" && process.versions?.bun) {
+		const WebSocketWithProxy = class extends WebSocket {
 			constructor(url: string | URL, options?: string | string[] | Record<string, unknown>) {
 				let _opts: Record<string, unknown> = {};
 				if (Array.isArray(options) || typeof options === "string") {
@@ -835,11 +831,17 @@ async function getWebSocketConstructor(): Promise<WebSocketConstructor | null> {
 					_opts = { ...options };
 				}
 
-				const proxy = getProxyForUrl(url.toString().replace(/^wss:/, "https:").replace(/^ws:/, "http:"));
-				super(url, { ..._opts, ...(proxy ? { proxy } : {}) } as any);
+				const proxyUrl = resolveHttpProxyUrlForTarget(
+					url.toString().replace(/^wss:/, "https:").replace(/^ws:/, "http:"),
+					env,
+				);
+				super(url, { ..._opts, ...(proxyUrl ? { proxy: proxyUrl.toString() } : {}) } as any);
 			}
 		};
-		return _cachedWebsocket;
+		if (!env) {
+			_cachedWebsocket = WebSocketWithProxy;
+		}
+		return WebSocketWithProxy;
 	}
 
 	const ctor = (globalThis as { WebSocket?: unknown }).WebSocket;
@@ -894,8 +896,9 @@ async function connectWebSocket(
 	headers: Headers,
 	signal?: AbortSignal,
 	connectTimeoutMs = DEFAULT_WEBSOCKET_CONNECT_TIMEOUT_MS,
+	env?: ProviderEnv,
 ): Promise<WebSocketLike> {
-	const WebSocketCtor = await getWebSocketConstructor();
+	const WebSocketCtor = await getWebSocketConstructor(env);
 	if (!WebSocketCtor) {
 		throw new Error("WebSocket transport is not available in this runtime");
 	}
@@ -972,6 +975,7 @@ async function acquireWebSocket(
 	sessionId: string | undefined,
 	signal?: AbortSignal,
 	connectTimeoutMs?: number,
+	env?: ProviderEnv,
 ): Promise<{
 	socket: WebSocketLike;
 	entry?: CachedWebSocketConnection;
@@ -979,7 +983,7 @@ async function acquireWebSocket(
 	release: (options?: { keep?: boolean }) => void;
 }> {
 	if (!sessionId) {
-		const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
+		const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
 		return {
 			socket,
 			reused: false,
@@ -1011,7 +1015,7 @@ async function acquireWebSocket(
 			};
 		}
 		if (cached.busy) {
-			const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
+			const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
 			return {
 				socket,
 				reused: false,
@@ -1026,7 +1030,7 @@ async function acquireWebSocket(
 		}
 	}
 
-	const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs);
+	const socket = await connectWebSocket(url, headers, signal, connectTimeoutMs, env);
 	const entry: CachedWebSocketConnection = { socket, busy: true };
 	websocketSessionCache.set(sessionId, entry);
 	return {
@@ -1312,6 +1316,7 @@ async function processWebSocketStream(
 		options?.sessionId,
 		options?.signal,
 		websocketConnectTimeoutMs,
+		options?.env,
 	);
 	let keepConnection = true;
 	const useCachedContext = options?.transport === "websocket-cached" || options?.transport === "auto";

packages/ai/src/providers/openai-completions.ts

@@ -19,6 +19,7 @@ import type {
 	Message,
 	Model,
 	OpenAICompletionsCompat,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StopReason,
 	StreamFunction,
@@ -32,6 +33,7 @@ import type {
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { headersToRecord } from "../utils/headers.ts";
 import { parseStreamingJson } from "../utils/json-parse.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.ts";
 import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.ts";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.ts";
@@ -98,11 +100,11 @@ type ChatCompletionToolWithCacheControl = OpenAI.Chat.Completions.ChatCompletion
 	cache_control?: OpenAICompatCacheControl;
 };
 
-function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
+function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
 	if (cacheRetention) {
 		return cacheRetention;
 	}
-	if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
+	if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
 		return "long";
 	}
 	return "short";
@@ -140,9 +142,9 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions", OpenA
 				throw new Error(`No API key for provider: ${model.provider}`);
 			}
 			const compat = getCompat(model);
-			const cacheRetention = resolveCacheRetention(options?.cacheRetention);
+			const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
 			const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
-			const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, compat);
+			const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, compat, options?.env);
 			let params = buildParams(model, context, options, compat, cacheRetention);
 			const nextParams = await options?.onPayload?.(params, model);
 			if (nextParams !== undefined) {
@@ -454,6 +456,7 @@ function createClient(
 	optionsHeaders?: Record<string, string>,
 	sessionId?: string,
 	compat: ResolvedOpenAICompletionsCompat = getCompat(model),
+	env?: ProviderEnv,
 ) {
 	const headers = { ...model.headers };
 	if (model.provider === "github-copilot") {
@@ -487,7 +490,7 @@ function createClient(
 
 	return new OpenAI({
 		apiKey,
-		baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
+		baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model, env) : model.baseUrl,
 		dangerouslyAllowBrowser: true,
 		defaultHeaders,
 	});
@@ -498,7 +501,7 @@ function buildParams(
 	context: Context,
 	options?: OpenAICompletionsOptions,
 	compat: ResolvedOpenAICompletionsCompat = getCompat(model),
-	cacheRetention: CacheRetention = resolveCacheRetention(options?.cacheRetention),
+	cacheRetention: CacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env),
 ) {
 	const messages = convertMessages(model, context, compat);
 	const cacheControl = getCompatCacheControl(compat, cacheRetention);

packages/ai/src/providers/openai-responses.ts

@@ -8,6 +8,7 @@ import type {
 	Context,
 	Model,
 	OpenAIResponsesCompat,
+	ProviderEnv,
 	SimpleStreamOptions,
 	StreamFunction,
 	StreamOptions,
@@ -15,6 +16,7 @@ import type {
 } from "../types.ts";
 import { AssistantMessageEventStream } from "../utils/event-stream.ts";
 import { headersToRecord } from "../utils/headers.ts";
+import { getProviderEnvValue } from "../utils/provider-env.ts";
 import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.ts";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.ts";
 import { clampOpenAIPromptCacheKey } from "./openai-prompt-cache.ts";
@@ -27,11 +29,11 @@ const OPENAI_TOOL_CALL_PROVIDERS = new Set(["openai", "openai-codex", "opencode"
  * Resolve cache retention preference.
  * Defaults to "short" and uses PI_CACHE_RETENTION for backward compatibility.
  */
-function resolveCacheRetention(cacheRetention?: CacheRetention): CacheRetention {
+function resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {
 	if (cacheRetention) {
 		return cacheRetention;
 	}
-	if (typeof process !== "undefined" && process.env.PI_CACHE_RETENTION === "long") {
+	if (getProviderEnvValue("PI_CACHE_RETENTION", env) === "long") {
 		return "long";
 	}
 	return "short";
@@ -111,9 +113,9 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses", OpenAIRes
 			if (!apiKey) {
 				throw new Error(`No API key for provider: ${model.provider}`);
 			}
-			const cacheRetention = resolveCacheRetention(options?.cacheRetention);
+			const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
 			const cacheSessionId = cacheRetention === "none" ? undefined : options?.sessionId;
-			const client = createClient(model, context, apiKey, options?.headers, cacheSessionId);
+			const client = createClient(model, context, apiKey, options?.headers, cacheSessionId, options?.env);
 			let params = buildParams(model, context, options);
 			const nextParams = await options?.onPayload?.(params, model);
 			if (nextParams !== undefined) {
@@ -185,6 +187,7 @@ function createClient(
 	apiKey: string,
 	optionsHeaders?: Record<string, string>,
 	sessionId?: string,
+	env?: ProviderEnv,
 ) {
 	const compat = getCompat(model);
 	const headers = { ...model.headers };
@@ -220,7 +223,7 @@ function createClient(
 
 	return new OpenAI({
 		apiKey,
-		baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
+		baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model, env) : model.baseUrl,
 		dangerouslyAllowBrowser: true,
 		defaultHeaders,
 	});
@@ -229,7 +232,7 @@ function createClient(
 function buildParams(model: Model<"openai-responses">, context: Context, options?: OpenAIResponsesOptions) {
 	const messages = convertResponsesMessages(model, context, OPENAI_TOOL_CALL_PROVIDERS);
 
-	const cacheRetention = resolveCacheRetention(options?.cacheRetention);
+	const cacheRetention = resolveCacheRetention(options?.cacheRetention, options?.env);
 	const compat = getCompat(model);
 	const params: ResponseCreateParamsStreaming = {
 		model: model.id,

packages/ai/src/providers/simple-options.ts

@@ -17,6 +17,7 @@ export function buildBaseOptions(_model: Model<Api>, options?: SimpleStreamOptio
 		maxRetries: options?.maxRetries,
 		maxRetryDelayMs: options?.maxRetryDelayMs,
 		metadata: options?.metadata,
+		env: options?.env,
 	};
 }