pi-freeflow 1.11.2 → 1.12.0

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.12.0
+
+### Minor Changes
+
+- Free-model picker grows from 24 to 26: adds Nex N2.5 Pro, Nex N2.5 Mini, and Ling 3.0 Flash VL, and removes the discontinued Inkling entry. A new Stealth Models Watchlist docs page tracks masked preview IDs users ask about.
+
 ## 1.11.2
 
 ### Patch Changes

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow 🌊
 
-> **24 free models. Up to 1M context. Zero API keys. Infinite scale via your own relay pool.**
+> **26 free models. Up to 1M context. Zero API keys. Infinite scale via your own relay pool.**
 
 Thin by design: model list + dumb relay + log. Host `pi-ai` owns thinking, normalization & provider magic. We just make it free, fast, and unbreakable.
 
@@ -18,7 +18,7 @@ Join devs bypassing rate limits with their own relay pools. BYO, add as many as
 
 | Feature | Description | Value | Cost |
 | :--- | :--- | :--- | :--- |
-| **24 Curated Free Models** | 7 OpenCode Zen + 17 KiloCode Gateway models, up to 1M context & 512K output | Ceiling Unlocked | **$0** |
+| **26 Curated Free Models** | 7 OpenCode Zen + 19 KiloCode Gateway models, up to 1M context & 512K output | Ceiling Unlocked | **$0** |
 | **BYO Relay Pool** | Round-robin load balancing across your Cloudflare Workers & Vercel Edges | Zero Rate Limits | **$0** (your free tiers) |
 | **Adaptive Health & Error Detection** | Auto-cooldown on 429 rate limits, 504 timeouts, and socket drops | 0ms Wasted Latency | **$0** |
 | **Stream Truncation Resilience** | Stateful SSE terminal tracking (`response.failed` / `response.incomplete` injection) | Zero Host Crashes | **$0** |
@@ -32,7 +32,7 @@ Philosophy: **Thin by design.** We only ship model list + relay proxy + log. Hos
 
 ---
 
-### 24 Curated Models, One Command
+### 26 Curated Models, One Command
 
 ```bash
 /model → freeflow → pick
@@ -51,7 +51,7 @@ Optimized for deep reasoning, long-horizon coding & autonomous agentic workflows
 | `big-pickle` | Big Pickle | **200K** (200.000) | **32K** (32.000) | `high / max` | ❌ |
 | `ling-3.0-flash-fin-free` | Inclusion AI | **262K** (262.144) | **131K** (131.072) | `minimal … xhigh` | ❌ |
 
-#### KiloCode Gateway (17 Models), OpenRouter Compatible
+#### KiloCode Gateway (19 Models), OpenRouter Compatible
 Keyless access with `Bearer kilo-free`. Clean slash-free and colon-free CLI aliases supported.
 
 | Model ID | Creator / Lab | Context | Max Output | Thinking | Vision |
@@ -70,8 +70,10 @@ Keyless access with `Bearer kilo-free`. Clean slash-free and colon-free CLI alia
 | `openrouter` (`openrouter/free`) | OpenRouter Free | **200K** (200.000) | **65K** (65.536) | `minimal…xhigh`\* | ✅ |
 | `content-safety` (`nvidia/...:free`) | NVIDIA | **128K** (128.000) | **8K** (8.192) | ❌ *(non-thinking)* | ✅ |
 | `ling-3.0-flash-fin` (`inclusionai/ling-3.0-flash-fin:free`) | Inclusion AI | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
-| `inkling` (`thinkingmachines/inkling:free`) | Thinking Machines | **1M** (1.048.576) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
 | `ling-3.0-flash-sante` (`inclusionai/ling-3.0-flash-sante:free`) | Inclusion AI | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
+| `nex-n2.5-pro` (`nex-agi/nex-n2.5-pro:free`) | Nex AGI | **262K** (262.144) | **235K** (235.929) | `minimal…xhigh`\* | ✅ |
+| `nex-n2.5-mini` (`nex-agi/nex-n2.5-mini:free`) | Nex AGI | **262K** (262.144) | **235K** (235.929) | `minimal…xhigh`\* | ✅ |
+| `ling-3.0-flash-vl` (`inclusionai/ling-3.0-flash-vl:free`) | Inclusion AI | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ✅ |
 | `inkling-small` (`thinkingmachines/inkling-small:free`) | Thinking Machines | **1M** (1.048.576) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
 
 \* Levels are forwarded as-is through the OpenRouter-style nested `reasoning` parameter; effort mapping is decided by each model. MiMo collapses `minimal→low` and `xhigh→high` upstream, so its selector shows 5 labels but only 3 distinct effort values.
@@ -340,7 +342,7 @@ pnpm smoke       # verifies extensions/index.ts loads without crashing
 ```
 src/
 ├── index.ts          # extension entry, lifecycle hooks
-├── models.ts         # 24-model catalog definitions
+├── models.ts         # 26-model catalog definitions
 ├── catalog.ts        # model catalog cache (24h disk)
 ├── proxy.ts          # local proxy server (127.0.0.1:28180)
 ├── relay.ts          # relay selection & round-robin

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.11.2",
+  "version": "1.12.0",
   "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/catalog.ts

@@ -40,6 +40,7 @@ export const DEAD_MODEL_IDS = new Set<string>([
 	"laguna-s-2.1-free",
 	"minimax/minimax-m2.7:free",
 	"minimax/minimax-m3:free",
+	"thinkingmachines/inkling:free",
 ]);
 /**
  * Free-tier allowlist for anything entering the picker via network or stale disk.
@@ -76,7 +77,7 @@ export function sanitizeCatalogModels(models: RegisteredModel[]): RegisteredMode
 }
 /**
  * In-memory cache of currently active/available free models.
- * Initialized with all 24 verified models for 0ms instant availability.
+ * Initialized with all 26 verified models for 0ms instant availability.
  */
 let aliveCatalog: RegisteredModel[] = ALL_MODELS.map((m) => ({
 	...m,
@@ -399,6 +400,6 @@ export async function refreshCatalog(force = false): Promise<RegisteredModel[]>
 	} catch (err) {
 		logDebug("Failed reading stale catalog cache", { error: String(err) });
 	}
-	// No valid cache — return in-memory static 24 (host will refresh if needed)
+	// No valid cache — return in-memory static 26 (host will refresh if needed)
 	return aliveCatalog;
 }

package/src/index.ts

@@ -1,7 +1,7 @@
 /**
  * pi-freeflow — Modular, high-resiliency LLM extension for Pi & Oh My Pi (OMP)
  *
- * Provides access to 24 free models (7 OpenCode Zen + 17 KiloCode Gateway) with:
+ * Provides access to 26 free models (7 OpenCode Zen + 19 KiloCode Gateway) 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 24 verified free models:
+ * Defines the 26 verified free models:
  * - 7 OpenCode Zen models (2 Responses API + 5 Chat Completions)
- * - 17 KiloCode Keyless Gateway models (16 OpenRouter format + 1 Standard format)
+ * - 19 KiloCode Keyless Gateway models (18 OpenRouter format + 1 Standard format)
  */
 
 import type { ModelDef, ThinkingLevelMap, Upstream } from "./types.ts";
@@ -290,11 +290,21 @@ export const KILO_MODELS: ModelDef[] = [
 	thinkingLevelMap: KILO_REASONING_MAP,
 },
 {
-	id: "thinkingmachines/inkling:free",
-	name: "Inkling (1M)",
+	id: "nex-agi/nex-n2.5-pro:free",
+	name: "Nex N2.5 Pro",
 	reasoning: true,
-	contextWindow: 1_048_576,
-	maxTokens: 262_144,
+	contextWindow: 262_144,
+	maxTokens: 235_929,
+	input: ["text", "image"],
+	thinkingFormat: "openrouter",
+	thinkingLevelMap: KILO_REASONING_MAP,
+},
+{
+	id: "nex-agi/nex-n2.5-mini:free",
+	name: "Nex N2.5 Mini",
+	reasoning: true,
+	contextWindow: 262_144,
+	maxTokens: 235_929,
 	input: ["text", "image"],
 	thinkingFormat: "openrouter",
 	thinkingLevelMap: KILO_REASONING_MAP,
@@ -319,6 +329,16 @@ export const KILO_MODELS: ModelDef[] = [
 		thinkingFormat: "openrouter",
 		thinkingLevelMap: KILO_REASONING_MAP,
 	},
+	{
+		id: "inclusionai/ling-3.0-flash-vl:free",
+		name: "Ling 3.0 Flash VL",
+		reasoning: true,
+		contextWindow: 262_144,
+		maxTokens: 32_768,
+		input: ["text", "image"],
+		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
+	},
 ];
 
 /**
@@ -329,7 +349,6 @@ export const KILO_MODELS: ModelDef[] = [
  * - Hy3 = Tencent Hunyuan (not Alibaba Qwen) → removed qwen3-coder alias
  */
 export const MODEL_ALIASES: Record<string, string> = {
-	// Kilo Gateway — slash-free & colon-free clean aliases (one per model)
 	"dots-3-note-preview": "dots-studio/dots-3-note-preview:free",
 	"step-3.7-flash": "stepfun/step-3.7-flash:free",
 	"nemotron-3-nano-omni": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -341,7 +360,9 @@ 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",
-	"inkling": "thinkingmachines/inkling:free",
+	"ling-3.0-flash-vl": "inclusionai/ling-3.0-flash-vl:free",
+	"nex-n2.5-pro": "nex-agi/nex-n2.5-pro:free",
+	"nex-n2.5-mini": "nex-agi/nex-n2.5-mini:free",
 	"inkling-small": "thinkingmachines/inkling-small:free",
 	// provider-prefixed short aliases (slash-normalized)
 	"laguna-s-2.1:free": "poolside/laguna-s-2.1:free",
@@ -357,7 +378,6 @@ export function resolveCanonicalModelId(id: string): string {
 	const clean = (id || "").trim();
 	return MODEL_ALIASES[clean] || clean;
 }
-
 /**
  * Set of all KiloCode model IDs (including aliases) for fast lookup
  */
@@ -369,7 +389,7 @@ export const KILO_MODEL_IDS = new Set<string>([
 ]);
 
 /**
- * Combined list of all 24 static free models (canonical)
+ * Combined list of all 26 static free models (canonical)
  */
 export const ALL_MODELS: ModelDef[] = [...OPENCODE_MODELS, ...KILO_MODELS];