feat(agents): zdr and vendorKey options for createAI

[mattzcarey]

Adds a gateway option and a model option to createAI, for vendor models routed through AI Gateway:

• zdr turns Zero Data Retention on or off for one request on unified billing, whatever the gateway's own setting.
• vendorKey: "request" (AI SDK only, per model) forwards the key the vendor's provider put on the request, instead of stripping it.

const ai = createAI({ binding: env.AI, zdr: true });

const anthropic = createAnthropic({ apiKey: env.ANTHROPIC_API_KEY });
ai(anthropic("claude-opus-4-8"), { vendorKey: "request" });

ai-gateway-provider and workers-ai-provider/gateway have both of these and createAI didn't (#2569, cloudflare/ai#675).

• zdr is an ordinary gateway option: flat or nested, on any layer, inherited by fallback legs. The gateway reads cf-aig-zdr off the universal request itself (Universal.prepare), not off a provider entry, so the core transport sends it in the binding's extraHeaders. pi-ai gets it too. The Workers AI run path doesn't send it.
• vendorKey belongs to the model it was set on. A fallback leg doesn't inherit it, so a chain can mix a model on your own key with one on unified billing. A re-wrapped model keeps it. With a key on the entry, the gateway uses it and turns unified billing off for that request.

pnpm run check and the model tests (src/tests/models) pass.

[changeset-bot]

🦋 Changeset detected

Latest commit: 324f536

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages

Name	Type
agents	Patch
@cloudflare/agent-think	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[devin-ai-integration]

Devin Review found 2 potential issues.

[devin-ai-integration]

🔍 Check upstream documentation sync

Both model reference pages changed. The docs rules require matching updates in cloudflare-docs, which this repository cannot verify.

---

Was this helpful? React with 👍 or 👎 to provide feedback.

[devin-ai-integration]

🟥 Vendor keys exposed to gateway logs

With vendorKey: "request", forwardedHeaders passes the vendor credential in the universal request. Gateway request logging can retain that credential, exposing it to log readers.

---

Was this helpful? React with 👍 or 👎 to provide feedback.

[agent-think]

🟡 agents import sizes: 6 entry points grew

	Entry point	Exports	Largest gzip change	Size now
🟡	agents/mcp	15 resized	up to +3.8 KiB (+0.98%)	396.8 KiB
🟡	agents/mcp/server	1 resized	+2.3 KiB (+2.8%)	82.8 KiB
🟡	agents/chat-sdk	5 resized	up to +1.3 KiB (+0.49%)	267 KiB
🟡	agents	30 resized	up to +1.3 KiB (+0.49%)	264.5 KiB
🟡	agents/workflows	2 resized	up to +1.3 KiB (+0.49%)	265.8 KiB
🟡	agents/mcp/client	1 resized	+1.3 KiB (+0.81%)	160.1 KiB

Changed exports (54)

	Import	Gzip change	Size now
🟡	agents/mcp#createMcpHandler	+3.8 KiB (+0.98%)	396.8 KiB
🟡	agents/mcp#experimental_createMcpHandler	+2.3 KiB (+0.61%)	383.1 KiB
🟡	agents/mcp#createLegacyMcpHandler	+2.3 KiB (+0.6%)	383 KiB
🟡	agents/mcp/server#createMcpHandler	+2.3 KiB (+2.8%)	82.8 KiB
🟡	agents/mcp#WorkerTransport	+2.2 KiB (+0.63%)	352.9 KiB
🟡	agents/mcp#SSEEdgeClientTransport	+1.9 KiB (+0.54%)	349.2 KiB
🟡	agents/mcp#StreamableHTTPEdgeClientTransport	+1.9 KiB (+0.53%)	349.2 KiB
🟡	agents/mcp#getMcpAuthContext	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#MCP_SERVER_ID_MAX_LENGTH	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#RPCClientTransport	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#normalizeServerId	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#RPCServerTransport	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#DurableObjectEventStore	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#McpAgent	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#ElicitRequestSchema	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/mcp#RPC_DO_PREFIX	+1.8 KiB (+0.53%)	349.1 KiB
🟡	agents/chat-sdk#ChatSdkStateAdapter	+1.3 KiB (+0.49%)	267 KiB
🟡	agents/chat-sdk#createChatSdkState	+1.3 KiB (+0.49%)	267.1 KiB
🟡	agents#getCurrentAgent	+1.3 KiB (+0.49%)	264.5 KiB
🟡	agents#__DO_NOT_USE_WILL_BREAK__withInvocationScope	+1.3 KiB (+0.49%)	264.5 KiB
🟡	agents#isDurableObjectStorageReset	+1.3 KiB (+0.49%)	264.5 KiB
🟡	agents/workflows#AgentWorkflow	+1.3 KiB (+0.49%)	265.8 KiB
🟡	agents/chat-sdk#ChatSdkStateAgent	+1.3 KiB (+0.49%)	266.3 KiB
🟡	agents/mcp/client#MCPClientManager	+1.3 KiB (+0.81%)	160.1 KiB
🟡	agents#unstable_callable	+1.3 KiB (+0.49%)	264.6 KiB
🟡	agents#routeAgentRequest	+1.3 KiB (+0.48%)	265.2 KiB
🟡	agents#normalizeServerId	+1.3 KiB (+0.48%)	264.5 KiB
🟡	agents#isPlatformTransientError	+1.3 KiB (+0.48%)	264.5 KiB
🟡	agents#buildAgentUrl	+1.3 KiB (+0.48%)	265.2 KiB
🟡	agents#buildAgentPath	+1.3 KiB (+0.48%)	265 KiB
🟡	agents#getAgentByName	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#camelCaseToKebabCase	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#__DO_NOT_USE_WILL_BREAK__agentContext	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#DEFAULT_AGENT_STATIC_OPTIONS	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#isDurableObjectCodeUpdateReset	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#MCP_SERVER_ID_MAX_LENGTH	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#SqlError	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#routeAgentEmail	+1.3 KiB (+0.48%)	264.7 KiB
🟡	agents#parseSubAgentPath	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#isDurableObjectMemoryLimitReset	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents/chat-sdk#defaultThreadShard	+1.3 KiB (+0.48%)	264.5 KiB
🟡	agents/chat-sdk#defaultKeyShard	+1.3 KiB (+0.48%)	264.6 KiB
🟡	agents#DurableObjectOAuthClientProvider	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#AGENT_TOOL_MILESTONE_PART	+1.3 KiB (+0.48%)	264.4 KiB
🟡	agents#Agent	+1.3 KiB (+0.47%)	264.4 KiB
🟡	agents#StreamingResponse	+1.2 KiB (+0.47%)	264.4 KiB
🟡	agents#SUB_PREFIX	+1.2 KiB (+0.47%)	264.4 KiB
🟡	agents#createHeaderBasedEmailResolver	+1.2 KiB (+0.47%)	264.6 KiB
🟡	agents#MessageType	+1.2 KiB (+0.47%)	264.6 KiB
🟡	agents#AGENT_TOOL_PROGRESS_PART	+1.2 KiB (+0.47%)	264.4 KiB

…and 4 more exports in the workflow artifact.

How this works

Each runtime export is bundled on its own, minified, and gzipped. Changes smaller than 100 B, or smaller than 1% and 1 KiB, are ignored. Growth over 10% or 5 KiB is marked 🔴. This report is informational and does not fail CI. The workflow artifact contains every measurement.

_{Compared 7945da9c → 324f5365 · workflow run · reported by agent-think[bot]}

[pkg-pr-new]

Open in StackBlitz

agents

npm i https://pkg.pr.new/agents@2571

@cloudflare/ai-chat

npm i https://pkg.pr.new/@cloudflare/ai-chat@2571

@cloudflare/codemode

npm i https://pkg.pr.new/@cloudflare/codemode@2571

hono-agents

npm i https://pkg.pr.new/hono-agents@2571

@cloudflare/shell

npm i https://pkg.pr.new/@cloudflare/shell@2571

@cloudflare/think

npm i https://pkg.pr.new/@cloudflare/think@2571

@cloudflare/voice

npm i https://pkg.pr.new/@cloudflare/voice@2571

@cloudflare/worker-bundler

npm i https://pkg.pr.new/@cloudflare/worker-bundler@2571

commit: 324f536