shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
* 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.
This commit is contained in:
MC
2026-04-27 17:41:54 -04:00
committed by GitHub
parent 31b48dec23
commit d6e08b3da0
19 changed files with 367 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
packages/ai/src/providers/openai-completions.ts
View File

@@ -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");