pi-freeflow 1.28.0 → 1.28.1

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 1.28.1
+
+### Patch Changes
+
+- Retry relay reachability checks after deployment so edge routing propagation delays do not show a fresh relay as unreachable — the check retries with progress notices and only warns if the relay stays dark.
+
+  Fix upstream drift alerts to stop flagging commercial paid model families as free candidates, while known alpha and stealth free models keep their free status.
+
 ## 1.28.0
 
 ### Minor Changes

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.28.0",
+  "version": "1.28.1",
   "description": "Thin provider for OMP/Pi — model list + dumb relay proxy + log; host pi-ai owns thinking/normalization",
   "main": "extensions/index.ts",
   "types": "src/index.ts",

package/src/probe.ts

@@ -1,153 +1,153 @@
-import { opencodeHeaders } from "./config.ts";
-import { ensureChatFingerprintTools } from "./opencode-fingerprint.ts";
-
-/**
- * Relay reachability probe: verifies a deployed relay answers requests
- * by issuing a minimal round trip through it and timing the response.
- */
-
-export interface RelayProbeResult {
- ok: boolean;
- status: number;
- latencyMs: number;
- error?: string;
-}
-
-export interface RelayProbeOptions {
- /**
-  * Probe mode:
-  * - "models" (default): GET /v1/models (reachability probe)
-  * - "chat": POST /zen/v1/chat/completions (verifies free tier inference & spoofing)
-  */
- endpoint?: "models" | "chat";
- /** Model to use for chat probe (defaults to "nemotron-3.5-lightning-free") */
- model?: string;
- /** Timeout in milliseconds (defaults to 5000) */
- timeoutMs?: number;
- /**
-  * Number of retry attempts when the probe returns !ok or throws.
-  * Defaults to 0 (single attempt). Useful post-deploy for edge DNS propagation.
-  */
- retries?: number;
- /** Delay between retries in milliseconds (defaults to 2000). */
- retryDelayMs?: number;
- /** Optional progress callback before each retry */
- onRetry?: (attempt: number, maxRetries: number, lastResult: RelayProbeResult) => void;
-}
-
-/**
- * Probe a relay endpoint to confirm it is reachable.
- *
- * Sends a minimal request to `<url>/v1/models` carrying the x-relay-target /
- * x-relay-path headers the relay expects, timing the round trip. Never
- * throws: network failures, timeouts, and non-2xx statuses are all reported
- * on the returned result instead.
- *
- * The path mirrors the proxy's real relay contract (`relayFetch` in relay.ts):
- * `x-relay-target` is the upstream origin and `x-relay-path` the full path
- * including the `/zen` prefix — the workers only allow the exact origins
- * `https://opencode.ai` / `https://api.kilo.ai` and forward `target + path`.
- * @param auth Optional per-relay shared secret; sent as x-relay-auth so
- *   deployed relays (which enforce it) answer the probe instead of 401.
- */
-async function probeRelayOnce(
- url: string,
- auth?: string,
- opts?: RelayProbeOptions,
-): Promise<RelayProbeResult> {
- const cleanUrl = url.trim().replace(/\/+$/, "");
- const isDirectOpenCode =
-  cleanUrl === "https://opencode.ai" ||
-  cleanUrl === "opencode" ||
-  cleanUrl === "direct";
- const isChat = opts?.endpoint === "chat";
- const timeout = opts?.timeoutMs ?? (isChat ? 15_000 : 5_000);
- const start = Date.now();
-
- try {
-  const headers: Record<string, string> = {
-   ...opencodeHeaders(),
-   ...(auth ? { "x-relay-auth": auth } : {}),
-  };
-
-  let fetchUrl: string;
-  let method = "GET";
-  let body: string | undefined;
-
-  if (isDirectOpenCode) {
-   if (isChat) {
-    fetchUrl = "https://opencode.ai/zen/v1/chat/completions";
-    method = "POST";
-    headers["content-type"] = "application/json";
-    const probePayload: Record<string, unknown> = {
-     model: opts?.model || "nemotron-3.5-lightning-free",
-     max_tokens: 1,
-     stream: true,
-     messages: [{ role: "user", content: "ping" }],
-    };
-    ensureChatFingerprintTools(probePayload);
-    body = JSON.stringify(probePayload);
-   } else {
-    fetchUrl = "https://opencode.ai/zen/v1/models";
-   }
-  } else {
-   if (isChat) {
-    fetchUrl = `${cleanUrl}/zen/v1/chat/completions`;
-    method = "POST";
-    headers["content-type"] = "application/json";
-    headers["x-relay-target"] = "https://opencode.ai";
-    headers["x-relay-path"] = "/zen/v1/chat/completions";
-    const probePayload: Record<string, unknown> = {
-     model: opts?.model || "nemotron-3.5-lightning-free",
-     max_tokens: 1,
-     stream: true,
-     messages: [{ role: "user", content: "ping" }],
-    };
-    ensureChatFingerprintTools(probePayload);
-    body = JSON.stringify(probePayload);
-   } else {
-    fetchUrl = `${cleanUrl}/v1/models`;
-    headers["x-relay-target"] = "https://opencode.ai";
-    headers["x-relay-path"] = "/zen/v1/models";
-   }
-  }
-
-  const res = await fetch(fetchUrl, {
-   method,
-   headers,
-   body,
-   signal: AbortSignal.timeout(timeout),
-  });
-  return { ok: res.ok, status: res.status, latencyMs: Date.now() - start };
- } catch (e) {
-  return {
-   ok: false,
-   status: 0,
-   latencyMs: Date.now() - start,
-   error: (e as Error)?.message || String(e),
-  };
- }
-}
-
-export async function probeRelay(
- url: string,
- auth?: string,
- opts?: RelayProbeOptions,
-): Promise<RelayProbeResult> {
- const retries = Math.max(0, opts?.retries ?? 0);
- const retryDelay = Math.max(10, opts?.retryDelayMs ?? 2000);
-
- for (let attempt = 0; attempt <= retries; attempt++) {
-  if (attempt > 0) {
-   const { promise, resolve } = Promise.withResolvers<void>();
-   setTimeout(resolve, retryDelay);
-   await promise;
-  }
-  const result = await probeRelayOnce(url, auth, opts);
-  if (result.ok || attempt === retries) {
-   return result;
-  }
-  opts?.onRetry?.(attempt + 1, retries, result);
- }
- return { ok: false, status: 0, latencyMs: 0, error: "Probe failed" };
-}
+import { opencodeHeaders } from "./config.ts";
+import { ensureChatFingerprintTools } from "./opencode-fingerprint.ts";
+
+/**
+ * Relay reachability probe: verifies a deployed relay answers requests
+ * by issuing a minimal round trip through it and timing the response.
+ */
+
+export interface RelayProbeResult {
+ ok: boolean;
+ status: number;
+ latencyMs: number;
+ error?: string;
+}
+
+export interface RelayProbeOptions {
+ /**
+  * Probe mode:
+  * - "models" (default): GET /v1/models (reachability probe)
+  * - "chat": POST /zen/v1/chat/completions (verifies free tier inference & spoofing)
+  */
+ endpoint?: "models" | "chat";
+ /** Model to use for chat probe (defaults to "nemotron-3.5-lightning-free") */
+ model?: string;
+ /** Timeout in milliseconds (defaults to 5000) */
+ timeoutMs?: number;
+ /**
+  * Number of retry attempts when the probe returns !ok or throws.
+  * Defaults to 0 (single attempt). Useful post-deploy for edge DNS propagation.
+  */
+ retries?: number;
+ /** Delay between retries in milliseconds (defaults to 2000). */
+ retryDelayMs?: number;
+ /** Optional progress callback before each retry */
+ onRetry?: (attempt: number, maxRetries: number, lastResult: RelayProbeResult) => void;
+}
+
+/**
+ * Probe a relay endpoint to confirm it is reachable.
+ *
+ * Sends a minimal request to `<url>/v1/models` carrying the x-relay-target /
+ * x-relay-path headers the relay expects, timing the round trip. Never
+ * throws: network failures, timeouts, and non-2xx statuses are all reported
+ * on the returned result instead.
+ *
+ * The path mirrors the proxy's real relay contract (`relayFetch` in relay.ts):
+ * `x-relay-target` is the upstream origin and `x-relay-path` the full path
+ * including the `/zen` prefix — the workers only allow the exact origins
+ * `https://opencode.ai` / `https://api.kilo.ai` and forward `target + path`.
+ * @param auth Optional per-relay shared secret; sent as x-relay-auth so
+ *   deployed relays (which enforce it) answer the probe instead of 401.
+ */
+async function probeRelayOnce(
+ url: string,
+ auth?: string,
+ opts?: RelayProbeOptions,
+): Promise<RelayProbeResult> {
+ const cleanUrl = url.trim().replace(/\/+$/, "");
+ const isDirectOpenCode =
+  cleanUrl === "https://opencode.ai" ||
+  cleanUrl === "opencode" ||
+  cleanUrl === "direct";
+ const isChat = opts?.endpoint === "chat";
+ const timeout = opts?.timeoutMs ?? (isChat ? 15_000 : 5_000);
+ const start = Date.now();
+
+ try {
+  const headers: Record<string, string> = {
+   ...opencodeHeaders(),
+   ...(auth ? { "x-relay-auth": auth } : {}),
+  };
+
+  let fetchUrl: string;
+  let method = "GET";
+  let body: string | undefined;
+
+  if (isDirectOpenCode) {
+   if (isChat) {
+    fetchUrl = "https://opencode.ai/zen/v1/chat/completions";
+    method = "POST";
+    headers["content-type"] = "application/json";
+    const probePayload: Record<string, unknown> = {
+     model: opts?.model || "nemotron-3.5-lightning-free",
+     max_tokens: 1,
+     stream: true,
+     messages: [{ role: "user", content: "ping" }],
+    };
+    ensureChatFingerprintTools(probePayload);
+    body = JSON.stringify(probePayload);
+   } else {
+    fetchUrl = "https://opencode.ai/zen/v1/models";
+   }
+  } else {
+   if (isChat) {
+    fetchUrl = `${cleanUrl}/zen/v1/chat/completions`;
+    method = "POST";
+    headers["content-type"] = "application/json";
+    headers["x-relay-target"] = "https://opencode.ai";
+    headers["x-relay-path"] = "/zen/v1/chat/completions";
+    const probePayload: Record<string, unknown> = {
+     model: opts?.model || "nemotron-3.5-lightning-free",
+     max_tokens: 1,
+     stream: true,
+     messages: [{ role: "user", content: "ping" }],
+    };
+    ensureChatFingerprintTools(probePayload);
+    body = JSON.stringify(probePayload);
+   } else {
+    fetchUrl = `${cleanUrl}/v1/models`;
+    headers["x-relay-target"] = "https://opencode.ai";
+    headers["x-relay-path"] = "/zen/v1/models";
+   }
+  }
+
+  const res = await fetch(fetchUrl, {
+   method,
+   headers,
+   body,
+   signal: AbortSignal.timeout(timeout),
+  });
+  return { ok: res.ok, status: res.status, latencyMs: Date.now() - start };
+ } catch (e) {
+  return {
+   ok: false,
+   status: 0,
+   latencyMs: Date.now() - start,
+   error: (e as Error)?.message || String(e),
+  };
+ }
+}
+
+export async function probeRelay(
+ url: string,
+ auth?: string,
+ opts?: RelayProbeOptions,
+): Promise<RelayProbeResult> {
+ const retries = Math.max(0, opts?.retries ?? 0);
+ const retryDelay = Math.max(10, opts?.retryDelayMs ?? 2000);
+
+ for (let attempt = 0; attempt <= retries; attempt++) {
+  if (attempt > 0) {
+   const { promise, resolve } = Promise.withResolvers<void>();
+   setTimeout(resolve, retryDelay);
+   await promise;
+  }
+  const result = await probeRelayOnce(url, auth, opts);
+  if (result.ok || attempt === retries) {
+   return result;
+  }
+  opts?.onRetry?.(attempt + 1, retries, result);
+ }
+ return { ok: false, status: 0, latencyMs: 0, error: "Probe failed" };
+}