pi-freeflow 1.26.1 → 1.28.0

package/src/deploy.ts

@@ -16,17 +16,20 @@ import { randomBytes } from "node:crypto";
  * whitelist, SSRF guard, path resolver, header denylist, auth gate and
  * streaming forward live exactly once.
  *
+ * The core ships inside String.raw, so backslashes below reach the deployed
+ * file verbatim — write them singly, never double them for the outer literal.
+ *
  * @param relayAuth Per-deployment shared secret. Empty string disables the
  *   auth gate (legacy/manual deploys); built-in deploys always embed one.
  */
 function buildRelayWorkerCore(relayAuth: string): string {
- return `// Only the 2 upstreams pi-freeflow talks to. Anything else = open proxy abuse.
+ return String.raw`// Only the 2 upstreams pi-freeflow talks to. Anything else = open proxy abuse.
 const ALLOWED_TARGETS = ["https://opencode.ai", "https://api.kilo.ai"];
 const RELAY_AUTH = ${JSON.stringify(relayAuth)};
 const resolveRelayTarget = function(target, relayPath) {
   let targetUrl;
   try { targetUrl = new URL(target); } catch { return { ok: false, status: 400, reason: "invalid x-relay-target" }; }
-  if (typeof relayPath !== "string" || relayPath.indexOf("@") !== -1 || relayPath.indexOf("\\\\") !== -1 || relayPath.charAt(0) !== "/") {
+  if (typeof relayPath !== "string" || relayPath.indexOf("@") !== -1 || relayPath.indexOf("\\") !== -1 || relayPath.charAt(0) !== "/") {
     return { ok: false, status: 403, reason: "forbidden x-relay-path" };
   }
   let finalUrl;
@@ -38,7 +41,7 @@ const resolveRelayTarget = function(target, relayPath) {
 };
 const isPrivateHostname = function(h) {
   if (!h) return true
-  let host = String(h).trim().toLowerCase().replace(/^\\[|\\]$/g, "")
+  let host = String(h).trim().toLowerCase().replace(/^\[|\]$/g, "")
   if (host.length > 1 && host.endsWith(".")) host = host.slice(0, -1)
   if (!host) return true
   // Numeric IP literals outside dotted-decimal (decimal 2130706433, short 127.1,
@@ -65,7 +68,7 @@ const isPrivateHostname = function(h) {
   }
   if (host === "localhost" || host === "0.0.0.0" || host === "127.0.0.1" || host.endsWith(".localhost") || host.endsWith(".local") || host.endsWith(".internal")) return true
   if (host.startsWith("::")) return true
-  const v4 = host.match(/^(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})\\.(\\d{1,3})$/)
+  const v4 = host.match(/^(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/)
   if (v4) {
     const a = Number(v4[1])
     const b = Number(v4[2])
@@ -109,7 +112,7 @@ async function relayHandler(req) {
   if (targetUrl.protocol !== "http:" && targetUrl.protocol !== "https:") return new Response(JSON.stringify({ error: "forbidden x-relay-target protocol" }), { status: 403, headers: { "content-type": "application/json" } });
   if (targetUrl.username || targetUrl.password) return new Response(JSON.stringify({ error: "forbidden x-relay-target (embedded credentials)" }), { status: 403, headers: { "content-type": "application/json" } });
   if (isPrivateHostname(targetUrl.hostname)) return new Response(JSON.stringify({ error: "forbidden x-relay-target (private/loopback host)" }), { status: 403, headers: { "content-type": "application/json" } });
-  const cleanTarget = target.replace(/\\/$/, "");
+  const cleanTarget = target.replace(/\/$/, "");
   if (!ALLOWED_TARGETS.includes(cleanTarget)) return new Response(JSON.stringify({ error: "Forbidden target" }), { status: 403, headers: { "content-type": "application/json" } });
   const relayPath = req.headers.get("x-relay-path") || "/";
   const resolved = resolveRelayTarget(target, relayPath);

package/src/index.ts

@@ -1,7 +1,7 @@
 /**
  * pi-freeflow — Modular, high-resiliency LLM extension for Pi & Oh My Pi (OMP)
  *
- * Provides access to 33 free models (9 OpenCode Zen + 19 KiloCode Gateway + 5 Cline) with:
+ * Provides access to 33 free models (10 OpenCode Zen + 18 KiloCode Gateway + 5 Cline) with:
  * - Single-port daemon reuse on 28180 across concurrent subagents
  * - Multi-cloud rolling egress relays (Vercel Edge, Cloudflare, Deno)
  * - 0ms instant startup with verified static catalog and background live health checks

package/src/models.ts

@@ -1,9 +1,9 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 33 verified free models:
- * - 9 OpenCode Zen models (2 Responses API + 7 Chat Completions)
- * - 19 KiloCode Keyless Gateway models (18 OpenRouter format + 1 Standard format)
+ * Defines the 33 verified free models (live-verified 2026-09-28):
+ * - 10 OpenCode Zen models (2 Responses API + 8 Chat Completions)
+ * - 18 KiloCode Keyless Gateway models (OpenRouter format)
  * - 5 Cline direct-only models (per-user pool)
  */
 
@@ -169,6 +169,23 @@ export const OPENCODE_MODELS: ModelDef[] = [
    max: "max",
   },
  },
+ {
+  id: "longcat-2.5-preview-free",
+  name: "LongCat 2.5 Preview (1M) [OpenCode]",
+  reasoning: true,
+  contextWindow: 1_000_000,
+  maxTokens: 131_072,
+  input: ["text", "image"],
+  thinkingLevelMap: {
+   off: null,
+   minimal: "minimal",
+   low: "low",
+   medium: "medium",
+   high: "high",
+   xhigh: "xhigh",
+   max: "max",
+  },
+ },
 ];
 
 /**
@@ -321,21 +338,26 @@ export const KILO_MODELS: ModelDef[] = [
   thinkingLevelMap: KILO_REASONING_MAP,
  },
  {
-  id: "nex-agi/nex-n2.5-pro:free",
-  name: "Nex N2.5 Pro [Kilo]",
+  // Resurrected 2026-09-28: back on the live Kilo free list
+  // (isFree:true, 0/0 pricing, no expiry) + keyless chat 200.
+  id: "stepfun/step-3.7-flash:free",
+  name: "Step 3.7 Flash [Kilo]",
   reasoning: true,
   contextWindow: 262_144,
-  maxTokens: 235_929,
+  maxTokens: 262_144,
   input: ["text", "image"],
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
  },
  {
-  id: "nex-agi/nex-n2.5-mini:free",
-  name: "Nex N2.5 Mini [Kilo]",
+  // Added 2026-09-28: live on the Kilo free list (isFree:true, 0/0
+  // pricing, 1M context, text+image in) + keyless chat 200. Passes
+  // isFreeCatalogId via MODEL_MAP (no :free suffix by design).
+  id: "stealth/space-bunny-alpha",
+  name: "Space Bunny Alpha (1M) [Kilo]",
   reasoning: true,
-  contextWindow: 262_144,
-  maxTokens: 235_929,
+  contextWindow: 1_000_000,
+  maxTokens: 524_288,
   input: ["text", "image"],
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
@@ -370,16 +392,6 @@ export const KILO_MODELS: ModelDef[] = [
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
  },
- {
-  id: "z-ai/glm-5.2:free",
-  name: "GLM 5.2 [Kilo]",
-  reasoning: true,
-  contextWindow: 32_768,
-  maxTokens: 29_491,
-  input: ["text"],
-  thinkingFormat: "openrouter",
-  thinkingLevelMap: KILO_REASONING_MAP,
- },
 ];
 
 /**
@@ -498,13 +510,14 @@ export const MODEL_ALIASES: Record<string, string> = {
  "content-safety": "nvidia/nemotron-3.5-content-safety:free",
  "ling-3.0-flash-fin": "inclusionai/ling-3.0-flash-fin:free",
  "ling-3.0-flash-sante": "inclusionai/ling-3.0-flash-sante:free",
- "nex-n2.5-pro": "nex-agi/nex-n2.5-pro:free",
- "nex-n2.5-mini": "nex-agi/nex-n2.5-mini:free",
+ "step-3.7-flash": "stepfun/step-3.7-flash:free",
+ "space-bunny-alpha": "stealth/space-bunny-alpha",
  "inkling-small": "thinkingmachines/inkling-small:free",
  "mimo-v2.6-flash": "mimo-v2.6-flash-free",
  "space-bunny": "space-bunny-free",
+ "longcat-2.5-preview": "longcat-2.5-preview-free",
+ "longcat": "longcat-2.5-preview-free",
  "qwen3.8-27b": "qwen/qwen3.8-27b:free",
- "glm-5.2": "z-ai/glm-5.2:free",
  // provider-prefixed short aliases (slash-normalized)
  "laguna-s-2.1:free": "poolside/laguna-s-2.1:free",
  "laguna-xs-2.1:free": "poolside/laguna-xs-2.1:free",

package/src/probe.ts

@@ -24,6 +24,15 @@ export interface RelayProbeOptions {
  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;
 }
 
 /**
@@ -41,7 +50,7 @@ export interface RelayProbeOptions {
  * @param auth Optional per-relay shared secret; sent as x-relay-auth so
  *   deployed relays (which enforce it) answer the probe instead of 401.
  */
-export async function probeRelay(
+async function probeRelayOnce(
  url: string,
  auth?: string,
  opts?: RelayProbeOptions,
@@ -119,3 +128,26 @@ export async function probeRelay(
   };
  }
 }
+
+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" };
+}

package/src/proxy.ts

@@ -126,6 +126,27 @@ function withRateLimitHint(status: number, data: string): string {
  } catch { }
  return data;
 }
+/**
+ * Exhausted-disabled relay verdict from the relay layer (HTTP 503 JSON with
+ * `error.code === "relay_disabled"`): every candidate rolled as disabled and
+ * the direct fallback is unavailable, so the host must retry/fail fast
+ * instead of parking on a provider wait. Passes through to the host
+ * unchanged — hint rewrites must never touch its code or guidance.
+ */
+export function isRelayDisabledError(status: number, data: string): boolean {
+ if (status !== 503) return false;
+ try {
+  const parsed: unknown = JSON.parse(data);
+  if (typeof parsed !== "object" || parsed === null || Array.isArray(parsed)) return false;
+  if (!("error" in parsed)) return false;
+  const err: unknown = parsed.error;
+  if (typeof err !== "object" || err === null || Array.isArray(err)) return false;
+  if (!("code" in err)) return false;
+  return err.code === "relay_disabled";
+ } catch {
+  return false;
+ }
+}
 /** Cline marker errors: each status carries account-actionable guidance. */
 const CLINE_RATE_LIMIT_HINT =
  "Cline free-use limit reached for this login. Wait for the reset or switch models.";
@@ -1300,7 +1321,7 @@ export function startProxy(
          );
         } else {
          if (!response.ok) {
-          log("warn", `upstream ${response.status} for model ${String((parsedBody as Record<string, unknown> | null)?.model ?? "?")} via relay`, { status: response.status, model: (parsedBody as Record<string, unknown> | null)?.model, path: req.url }, reqId);
+          log("warn", `upstream ${response.status} for model ${String((parsedBody as Record<string, unknown> | null)?.model ?? "?")} via relay ${relayState.url || "pool"}`, { status: response.status, model: (parsedBody as Record<string, unknown> | null)?.model, path: req.url, relay: relayState.url }, reqId);
          }
          let rawText = await response.text();
          let ct =
@@ -1310,7 +1331,9 @@ export function startProxy(
           rawText = convertSseToJson(rawText, target.pathname, callerHadTools, callerCaseRestore, callerFindGlob, callerInjected);
           ct = "application/json";
          }
-         const data = withFreeTierHint(response.status, withRateLimitHint(response.status, rawText));
+         const data = isRelayDisabledError(response.status, rawText)
+          ? rawText
+          : withFreeTierHint(response.status, withRateLimitHint(response.status, rawText));
          res.writeHead(response.status, { "content-type": ct });
          res.end(data);
         }