pi-freeflow 1.4.9 → 1.4.11

package/README.md

@@ -25,7 +25,7 @@ Join devs bypassing rate limits with their own relay pools. BYO, add as many as
 | **Smart Model Aliasing** | Clean slash-free & colon-free CLI model names compatible with thinking selectors | DX Optimized | **$0** |
 | **Auto-Enabled on Session** | Relay stays enabled in `auto` mode on session start and model switch | Zero Friction | **$0** |
 | **Interactive CLI Management** | 10+ `/freeflow` subcommands (`status`, `list`, `use`, `add`, `label`, `remove`, `deploy`, `logs`, `debug`) | Full Control | **$0** |
-| **Dumb Proxy That Never Breaks** | `127.0.0.1:18080`, host-normalized, pathname-guarded `/v1/models` | 100% Uptime | **$0** |
+| **Dumb Proxy That Never Breaks** | `127.0.0.1:28180`, host-normalized, pathname-guarded `/v1/models` | 100% Uptime | **$0** |
 | **Observable Real Logs** | `~/.pi/agent/pi-freeflow.log`, 5MB auto-rotation, real-time debug toggle | Observable | **$0** |
 
 Philosophy: **Thin by design.** We only ship model list + relay proxy + log. Host owns thinking & normalization.
@@ -78,7 +78,7 @@ Keyless access with `Bearer kilo-free`. Clean slash-free and colon-free CLI alia
 ### How It Works: BYO Relays, Zero Rate Limits
 
 ```
-You → 127.0.0.1:18080 (dumb proxy, host-normalized) → x-relay-target → N egress IPs (your pool) → opencode.ai / api.kilo.ai
+You → 127.0.0.1:28180 (dumb proxy, host-normalized) → x-relay-target → N egress IPs (your pool) → opencode.ai / api.kilo.ai
                                      ↑ host already normalized thinking → proxy just forwards
 ```
 
@@ -176,6 +176,34 @@ export default {
 /freeflow deploy vercel  # prompts token in-memory, auto-adds to pool
 # or shorthand: /freeflow deploy
 ```
+*Manual fallback:* Push 2 files (`api/relay.js` + `vercel.json`) to GitHub $\to$ Import on `vercel.com` $\to$ `/freeflow add https://your.vercel.app vercel-relay-1`
+
+```js
+// api/relay.js
+const ALLOWED_TARGETS = ["https://opencode.ai", "https://api.kilo.ai"];
+export const config = { runtime: "edge" };
+export default async function handler(req) {
+  const target = req.headers.get("x-relay-target");
+  const relayPath = req.headers.get("x-relay-path") || "/";
+  if (!target || !ALLOWED_TARGETS.includes(target.replace(/\/$/, ""))) {
+    return new Response(JSON.stringify({ error: "Forbidden target" }), { status: 403 });
+  }
+  const headers = new Headers(req.headers);
+  headers.delete("x-relay-target"); headers.delete("x-relay-path"); headers.delete("host");
+  const res = await fetch(target.replace(/\/$/, "") + relayPath, {
+    method: req.method,
+    headers,
+    body: req.method !== "GET" && req.method !== "HEAD" ? req.body : undefined,
+    duplex: "half",
+  });
+  return new Response(res.body, { status: res.status, headers: res.headers });
+}
+```
+
+```json
+// vercel.json
+{ "rewrites": [{ "source": "/(.*)", "destination": "/api/relay" }] }
+```
 
 **Option C: Deno Deploy (100k req/day) — Auto Deploy**
 ```bash
@@ -279,7 +307,7 @@ src/
 ├── index.ts          # extension entry, lifecycle hooks
 ├── models.ts         # 21-model catalog definitions
 ├── catalog.ts        # model catalog cache (24h disk)
-├── proxy.ts          # local proxy server (127.0.0.1:18080)
+├── proxy.ts          # local proxy server (127.0.0.1:28180)
 ├── relay.ts          # relay selection & round-robin
 ├── relay-state.ts    # relay pool state, health tracking
 ├── rate-limiter.ts   # adaptive cooldown on 429/504/socket errors

package/package.json

@@ -1,55 +1,55 @@
-{
-	"name": "pi-freeflow",
-	"type": "module",
-	"version": "1.4.9",
-	"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",
-	"keywords": [
-		"pi-package",
-		"pi-extension",
-		"oh-my-pi",
-		"omp",
-		"free-models",
-		"opencode",
-		"kilocode",
-		"ai-models",
-		"relay"
-	],
-	"author": "trefeon",
-	"license": "MIT",
-	"repository": {
-		"type": "git",
-		"url": "git+https://github.com/trefeon/pi-freeflow.git"
-	},
-	"homepage": "https://github.com/trefeon/pi-freeflow#readme",
-	"engines": {
-		"node": ">=22.6.0"
-	},
-	"omp": {
-		"extensions": [
-			"./extensions"
-		]
-	},
-	"pi": {
-		"extensions": [
-			"./extensions"
-		]
-	},
-	"files": [
-		"extensions",
-		"src",
-		"README.md",
-		"LICENSE"
-	],
-	"scripts": {
-		"test": "node --experimental-strip-types --test --test-concurrency=1 test/**/*.test.ts",
-		"typecheck": "tsc --noEmit",
-		"smoke": "node --experimental-strip-types -e \"import('./extensions/index.ts').then(() => console.log('✓ Smoke test passed: extensions/index.ts loaded successfully')).catch(err => { console.error(err); process.exit(1); })\""
-	},
-	"devDependencies": {
-		"@earendil-works/pi-coding-agent": "^0.84.3",
-		"@types/node": "^22.13.9",
-		"typescript": "^5.8.2"
-	}
-}
+{
+  "name": "pi-freeflow",
+  "type": "module",
+  "version": "1.4.11",
+  "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",
+  "keywords": [
+    "pi-package",
+    "pi-extension",
+    "oh-my-pi",
+    "omp",
+    "free-models",
+    "opencode",
+    "kilocode",
+    "ai-models",
+    "relay"
+  ],
+  "author": "trefeon",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/trefeon/pi-freeflow.git"
+  },
+  "homepage": "https://github.com/trefeon/pi-freeflow#readme",
+  "engines": {
+    "node": ">=22.6.0"
+  },
+  "omp": {
+    "extensions": [
+      "./extensions"
+    ]
+  },
+  "pi": {
+    "extensions": [
+      "./extensions"
+    ]
+  },
+  "files": [
+    "extensions",
+    "src",
+    "README.md",
+    "LICENSE"
+  ],
+  "scripts": {
+    "test": "node --experimental-strip-types --test --test-concurrency=1 test/**/*.test.ts",
+    "typecheck": "tsc --noEmit",
+    "smoke": "node --experimental-strip-types -e \"import('./extensions/index.ts').then(() => console.log('✓ Smoke test passed: extensions/index.ts loaded successfully')).catch(err => { console.error(err); process.exit(1); })\""
+  },
+  "devDependencies": {
+    "@earendil-works/pi-coding-agent": "^0.84.3",
+    "@types/node": "^22.13.9",
+    "typescript": "^5.8.2"
+  }
+}

package/src/config.ts

@@ -14,7 +14,8 @@ export const KILO_CHAT_URL = "https://api.kilo.ai/api/gateway/chat/completions";
 export const OPENCODE_API_URL = `${UPSTREAM_OPENCODE}/v1`;
 
 // ── Network & Server defaults ───────────────────────────────────────
-export const DEFAULT_PORT = 18080;
+export const DEFAULT_PORT = 28180;
+export const LEGACY_PORT = 18080;
 export const HOST = "127.0.0.1";
 export const DEFAULT_HOST = "127.0.0.1";
 

package/src/index.ts

@@ -2,7 +2,7 @@
  * pi-freeflow — Modular, high-resiliency LLM extension for Pi & Oh My Pi (OMP)
  *
  * Provides access to 21 free models (7 OpenCode Zen + 14 KiloCode Gateway) with:
- * - Single-port daemon reuse on 18080 across concurrent subagents
+ * - 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
  * - Per-model thinking/reasoning translation and streaming SSE pass-through
@@ -17,7 +17,7 @@ import {
 	setAliveCatalog,
 } from "./catalog.ts";
 import { createCommandSpec, updateStatusBar } from "./commands.ts";
-import { DEFAULT_HOST, HOST, PORT } from "./config.ts";
+import { DEFAULT_HOST, HOST, LEGACY_PORT, PORT } from "./config.ts";
 import { log, logInfo, logWarn } from "./logger.ts";
 import { ALL_MODELS, KILO_MODEL_IDS, MODEL_MAP, getAllRegisteredModels, resolveCanonicalModelId } from "./models.ts";
 import { isProxyAlive, startProxy } from "./proxy.ts";
@@ -117,12 +117,20 @@ export default async function (pi: ExtensionAPI): Promise<void> {
 	let actualPort = PORT;
 
 	// 2. Single-Port Shared Pattern: Check if daemon is already running (e.g. parent session)
-	const alreadyRunning = await isProxyAlive(PORT);
+	// Dual-probe: probe current PORT first; if missing, check LEGACY_PORT so existing v1.4.9
+	// sessions on 18080 are seamlessly reused without split-brain or duplicate daemons.
+	let alreadyRunning = await isProxyAlive(PORT);
 	if (alreadyRunning) {
 		logInfo(
 			`Reusing existing pi-freeflow proxy daemon on http://${HOST}:${PORT}`,
 		);
 		actualPort = PORT;
+	} else if (PORT !== LEGACY_PORT && (await isProxyAlive(LEGACY_PORT))) {
+		logInfo(
+			`Reusing existing legacy pi-freeflow proxy daemon on http://${HOST}:${LEGACY_PORT}`,
+		);
+		alreadyRunning = true;
+		actualPort = LEGACY_PORT;
 	} else {
 		try {
 			const r = await startProxy();
@@ -161,6 +169,19 @@ export default async function (pi: ExtensionAPI): Promise<void> {
 		ensuringDaemon = true;
 		try {
 			if (await isProxyAlive(actualPort)) return;
+			// If actualPort died, check if another daemon is alive on PORT or LEGACY_PORT before binding
+			if (await isProxyAlive(PORT)) {
+				actualPort = PORT;
+				registerCatalog(getAliveCatalog());
+				logInfo(`Re-attached to proxy daemon on http://${HOST}:${PORT}`);
+				return;
+			}
+			if (PORT !== LEGACY_PORT && (await isProxyAlive(LEGACY_PORT))) {
+				actualPort = LEGACY_PORT;
+				registerCatalog(getAliveCatalog());
+				logInfo(`Re-attached to legacy proxy daemon on http://${HOST}:${LEGACY_PORT}`);
+				return;
+			}
 			const r = await startProxy();
 			if (r.server) server = r.server;
 			if (r.port) actualPort = r.port;

package/src/proxy.ts

@@ -1,7 +1,7 @@
 /**
  * Single-port local HTTP proxy and dynamic upstream router for pi-freeflow
  *
- * Provides loopback proxying on port 18080 (shared across parent and subagents),
+ * Provides loopback proxying on port 28180 (shared across parent and subagents),
  * intelligent routing to OpenCode Zen and KiloCode Gateway, and failover support.
  */
 
@@ -111,9 +111,8 @@ export async function isProxyAlive(port: number): Promise<boolean> {
 
 /**
  * Start the local HTTP proxy daemon.
- *
- * Implements master/worker single-port reuse: if port 18080 is already held by a live
- * parent or sibling OMP session, resolves immediately with { server: null, port: 18080 }.
+ * Implements master/worker single-port reuse: if port 28180 is already held by a live
+ * parent or sibling OMP session, resolves immediately with { server: null, port: 28180 }.
  */
 export function startProxy(
 	overridePort?: number,

package/src/stream-pipe.ts

@@ -175,7 +175,8 @@ export function pipeUpstreamStream(
 			if (!res.headersSent) {
 				res.writeHead(502, { "content-type": "application/json" });
 			} else {
-				ensureTerminalEvent(true, errorMsg);
+				const isSubstantial = totalChunks > 50 && totalBytes > 100 * 1024;
+				ensureTerminalEvent(!isSubstantial, errorMsg, true);
 			}
 			if (!res.writableEnded) {
 				res.end();