feat(ai): add Cloudflare Workers AI as a provider (#3851)

* feat(ai): add Cloudflare Workers AI as a provider Cloudflare Workers AI hosts open-weight LLMs (Kimi K2.6, GPT-OSS, GLM-4.7, Llama 4, Gemma 4, Nemotron 3) on Cloudflare's GPU network with an OpenAI-compatible endpoint. Reuses the openai-completions API protocol; the per-account URL contains a {CLOUDFLARE_ACCOUNT_ID} placeholder resolved at request time by a small helper. Pi automatically sets x-session-affinity for prefix caching: https://developers.cloudflare.com/workers-ai/features/prompt-caching/ Auth: CLOUDFLARE_API_KEY (matches pi's *_API_KEY convention) + CLOUDFLARE_ACCOUNT_ID. The User-Agent identifies traffic as 'pi-coding-agent' in Cloudflare analytics. Verified end-to-end against a real Cloudflare account: 17 e2e tests pass across stream/empty/tokens/unicode/tool-call-without-result/ total-tokens against @cf/moonshotai/kimi-k2.6. Cloudflare AI Gateway is a separate, larger change (it requires routing through provider-specific subpaths with the matching API protocol per upstream) and will land in a follow-up PR. * refactor(ai): move Cloudflare User-Agent and session-affinity flag to per-model metadata Instead of conditionally setting them in openai-completions.ts based on provider detection, declare them as model-level fields in the catalog (headers + compat). This is consistent with how the github-copilot and kimi-coding entries already declare their static headers. packages/ai/scripts/generate-models.ts: emit headers and compat fields on each cloudflare-workers-ai entry (CLOUDFLARE_STATIC_HEADERS). packages/ai/src/providers/openai-completions.ts: drop the isCloudflareProvider conditional that injected User-Agent and the isCloudflareWorkersAI override of sendSessionAffinityHeaders. packages/ai/src/models.generated.ts: re-spliced 8 cloudflare-workers-ai entries with headers + compat. Behavior is unchanged - verified via fetch interceptor that User-Agent and x-session-affinity / session_id / x-client-request-id are still sent on outbound requests. 5/5 e2e tests pass.
2026-04-27 17:41:54 -04:00
parent 31b48dec23
commit d6e08b3da0
19 changed files with 367 additions and 4 deletions
--- a/packages/ai/src/env-api-keys.ts
+++ b/packages/ai/src/env-api-keys.ts
@@ -118,6 +118,7 @@ function getApiKeyEnvVars(provider: string): readonly string[] | undefined {
 		opencode: "OPENCODE_API_KEY",
 		"opencode-go": "OPENCODE_API_KEY",
 		"kimi-coding": "KIMI_API_KEY",
+		"cloudflare-workers-ai": "CLOUDFLARE_API_KEY",
 	};

 	const envVar = envMap[provider];
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -15374,4 +15374,158 @@ export const MODELS = {
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 	},
+	"cloudflare-workers-ai": {
+		"@cf/google/gemma-4-26b-a4b-it": {
+			id: "@cf/google/gemma-4-26b-a4b-it",
+			name: "Gemma 4 26B A4B IT",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"@cf/meta/llama-4-scout-17b-16e-instruct": {
+			id: "@cf/meta/llama-4-scout-17b-16e-instruct",
+			name: "Llama 4 Scout 17B 16E Instruct",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.27,
+				output: 0.85,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"@cf/moonshotai/kimi-k2.5": {
+			id: "@cf/moonshotai/kimi-k2.5",
+			name: "Kimi K2.5",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 3,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"@cf/moonshotai/kimi-k2.6": {
+			id: "@cf/moonshotai/kimi-k2.6",
+			name: "Kimi K2.6",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.95,
+				output: 4,
+				cacheRead: 0.16,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"@cf/nvidia/nemotron-3-120b-a12b": {
+			id: "@cf/nvidia/nemotron-3-120b-a12b",
+			name: "Nemotron 3 Super 120B",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"@cf/openai/gpt-oss-120b": {
+			id: "@cf/openai/gpt-oss-120b",
+			name: "GPT OSS 120B",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.35,
+				output: 0.75,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"@cf/openai/gpt-oss-20b": {
+			id: "@cf/openai/gpt-oss-20b",
+			name: "GPT OSS 20B",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"@cf/zai-org/glm-4.7-flash": {
+			id: "@cf/zai-org/glm-4.7-flash",
+			name: "GLM-4.7-Flash",
+			api: "openai-completions",
+			provider: "cloudflare-workers-ai",
+			baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+			headers: {"User-Agent":"pi-coding-agent"},
+			compat: {"sendSessionAffinityHeaders":true},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.06,
+				output: 0.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+	},
 } as const;
--- a/packages/ai/src/providers/cloudflare.ts
+++ b/packages/ai/src/providers/cloudflare.ts
@@ -0,0 +1,22 @@
+import type { Model } from "../types.js";
+
+/** Workers AI endpoint. `{CLOUDFLARE_ACCOUNT_ID}` is substituted at request time. */
+export const CLOUDFLARE_WORKERS_AI_BASE_URL =
+	"https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1";
+
+export function isCloudflareProvider(provider: string): boolean {
+	return provider === "cloudflare-workers-ai";
+}
+
+/** Substitute `{VAR}` placeholders in a Cloudflare baseUrl from process.env. */
+export function resolveCloudflareBaseUrl(model: Model<"openai-completions">): string {
+	const url = model.baseUrl;
+	if (!url.includes("{")) return url;
+	return url.replace(/\{([A-Z_][A-Z0-9_]*)\}/g, (_match, name: string) => {
+		const value = process.env[name];
+		if (!value) {
+			throw new Error(`${name} is required for provider ${model.provider} but is not set.`);
+		}
+		return value;
+	});
+}
--- a/packages/ai/src/providers/openai-completions.ts
+++ b/packages/ai/src/providers/openai-completions.ts
@@ -34,6 +34,7 @@ import { AssistantMessageEventStream } from "../utils/event-stream.js";
 import { headersToRecord } from "../utils/headers.js";
 import { parseStreamingJson } from "../utils/json-parse.js";
 import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
+import { isCloudflareProvider, resolveCloudflareBaseUrl } from "./cloudflare.js";
 import { buildCopilotDynamicHeaders, hasCopilotVisionInput } from "./github-copilot-headers.js";
 import { buildBaseOptions, clampReasoning } from "./simple-options.js";
 import { transformMessages } from "./transform-messages.js";
@@ -456,7 +457,7 @@ function createClient(

 	return new OpenAI({
 		apiKey,
-		baseURL: model.baseUrl,
+		baseURL: isCloudflareProvider(model.provider) ? resolveCloudflareBaseUrl(model) : model.baseUrl,
 		dangerouslyAllowBrowser: true,
 		defaultHeaders: headers,
 	});
@@ -1022,6 +1023,7 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 	const baseUrl = model.baseUrl;

 	const isZai = provider === "zai" || baseUrl.includes("api.z.ai");
+	const isCloudflareWorkersAI = provider === "cloudflare-workers-ai" || baseUrl.includes("api.cloudflare.com");

 	const isNonStandard =
 		provider === "cerebras" ||
@@ -1032,7 +1034,8 @@ function detectCompat(model: Model<"openai-completions">): ResolvedOpenAIComplet
 		baseUrl.includes("deepseek.com") ||
 		isZai ||
 		provider === "opencode" ||
-		baseUrl.includes("opencode.ai");
+		baseUrl.includes("opencode.ai") ||
+		isCloudflareWorkersAI;

 	const useMaxTokens = baseUrl.includes("chutes.ai");

--- a/packages/ai/src/types.ts
+++ b/packages/ai/src/types.ts
@@ -41,7 +41,8 @@ export type KnownProvider =
 	| "fireworks"
 	| "opencode"
 	| "opencode-go"
-	| "kimi-coding";
+	| "kimi-coding"
+	| "cloudflare-workers-ai";
 export type Provider = KnownProvider | string;

 export type ThinkingLevel = "minimal" | "low" | "medium" | "high" | "xhigh";