pi-freeflow 1.6.0 → 1.7.0

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow 🌊
 
-> **21 free models. Up to 1M context. Zero API keys. Infinite scale via your own relay pool.**
+> **25 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 |
 | :--- | :--- | :--- | :--- |
-| **21 Curated Free Models** | 7 OpenCode Zen + 14 KiloCode Gateway models, up to 1M context & 512K output | Ceiling Unlocked | **$0** |
+| **25 Curated Free Models** | 7 OpenCode Zen + 18 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
 
 ---
 
-### 21 Curated Models, One Command
+### 25 Curated Models, One Command
 
 ```bash
 /model → freeflow → pick
@@ -43,35 +43,39 @@ Optimized for deep reasoning, long-horizon coding & autonomous agentic workflows
 
 | Model ID | Creator / Lab | Context | Max Output | Thinking | Vision |
 | :--- | :--- | :--- | :--- | :--- | :--- |
-| `muse-spark-1.2-contributor-free` | Meta Superintelligence Labs | **1M** (1.048.576) | **131K** (131.072) | `minimal / low / medium / high / xhigh / max` | ✅ |
-| `mimo-v2.5-free` | Xiaomi MiMo | **1M** (1.048.576) | **131K** (131.072) | `low / medium / high` | ✅ |
-| `laguna-s-2.1-free` | Poolside | **1M** (1.048.576) | **131K** (131.072) | `low / high / max` | ❌ |
-| `nemotron-3.5-lightning-free` | NVIDIA | **1M** (1.000.000) | **262K** (262.144) | `low / high / max` | ❌ |
-| `nemotron-3-ultra-free` | NVIDIA | **1M** (1.000.000) | **128K** (128.000) | `low / high / max` | ❌ |
-| `hy3-free` | Tencent Hunyuan | **262K** (262.144) | **262K** (262.144) | `low / high / max` | ❌ |
+| `muse-spark-1.2-contributor-free` | Meta Superintelligence Labs | **1M** (1.048.576) | **131K** (131.072) | `minimal … xhigh` | ✅ |
+| `mimo-v2.5-free` | Xiaomi MiMo | **1M** (1.048.576) | **131K** (131.072) | `minimal … xhigh`\* | ✅ |
+| `laguna-s-2.1-free` | Poolside | **262K** (262.144) | **32K** (32.768) | `minimal … xhigh` | ❌ |
+| `nemotron-3.5-lightning-free` | NVIDIA | **1M** (1.000.000) | **262K** (262.144) | `minimal … xhigh` | ❌ |
+| `nemotron-3-ultra-free` | NVIDIA | **1M** (1.000.000) | **128K** (128.000) | `minimal … xhigh` | ❌ |
+| `hy3-free` | Tencent Hunyuan | **262K** (262.144) | **128K** (128.000) | `minimal … xhigh` | ❌ |
 | `big-pickle` | Big Pickle | **200K** (200.000) | **32K** (32.000) | `high / max` | ❌ |
 
-#### KiloCode Gateway (14 Models), OpenRouter Compatible
+#### KiloCode Gateway (18 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 |
 | :--- | :--- | :--- | :--- | :--- | :--- |
 | `dots-3-note-preview` (`dots-studio/...:free`) | Dots Studio | **512K** (512.000) | **512K** (512.000) | `minimal…xhigh`\* | ✅ |
 | `step-3.7-flash` (`stepfun/...:free`) | StepFun | **262K** (262.144) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
-| `nemotron-3-nano-omni` (`nvidia/...:free`) | NVIDIA | **256K** (256.000) | **65K** (65.536) | `minimal…xhigh`\* | ✅ |
-| `nemotron-3-ultra-550b` (`nvidia/...:free`) | NVIDIA | **1M** (1.000.000) | **65K** (65.536) | `minimal…xhigh`\* | ❌ |
-| `nvidia/nemotron-3.5-lightning:free` | NVIDIA | **1M** (1.000.000) | **131K** (131.072) | `minimal…xhigh`\* | ❌ |
+| `nemotron-3-nano-omni` (`nvidia/...:free`) | NVIDIA | **256K** (256.000) | **131K** (131.072) | `minimal…xhigh`\* | ✅ |
+| `nemotron-3-ultra-550b` (`nvidia/...:free`) | NVIDIA | **1M** (1.000.000) | **128K** (128.000) | `minimal…xhigh`\* | ❌ |
+| `nvidia/nemotron-3.5-lightning:free` | NVIDIA | **1M** (1.000.000) | **262K** (262.144) | `minimal…xhigh`\* | ❌ |
 | `nemotron-3-super` (`nvidia/...:free`) | NVIDIA | **262K** (262.144) | **262K** (262.144) | `minimal…xhigh`\* | ❌ |
-| `hy3:free` (`tencent/hy3:free`) | Tencent Hunyuan | **262K** (262.144) | **262K** (262.144) | ❌ *(none sent)* | ❌ |
+| `hy3:free` (`tencent/hy3:free`) | Tencent Hunyuan | **262K** (262.144) | **128K** (128.000) | `minimal…xhigh`\* | ❌ |
 | `north-mini-code` (`cohere/...:free`) | Cohere | **256K** (256.000) | **64K** (64.000) | `minimal…xhigh`\* | ❌ |
-| `laguna-s-2.1:free` (`poolside/...:free`) | Poolside | **1M** (1.048.576) | **131K** (131.072) | `minimal…xhigh`\* | ❌ |
+| `laguna-s-2.1:free` (`poolside/...:free`) | Poolside | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
 | `laguna-xs-2.1:free` (`poolside/...:free`) | Poolside | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
-| `lfm-2.5` (`liquid/lfm-2.5-2.6b:free`) | Liquid AI | **128K** (128.000) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
-| `kilo-auto` (`kilo-auto/free`) | Kilo Gateway Auto | **256K** (256.000) | **10K** (10.000) | ❌ *(non-thinking)* | ❌ |
-| `openrouter` (`openrouter/free`) | OpenRouter Free | **200K** (200.000) | **65K** (65.536) | ❌ *(non-thinking)* | ✅ |
+| `lfm-2.5` (`liquid/lfm-2.5-2.6b:free`) | Liquid AI | **65K** (65.536) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
+| `kilo-auto` (`kilo-auto/free`) | Kilo Gateway Auto | **256K** (256.000) | **10K** (10.000) | `minimal…xhigh`\* | ❌ |
+| `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)* | ✅ |
+| `longcat-2.0` (`meituan/longcat-2.0-free`) | Meituan | **1M** (1.048.756) | **262K** (262.144) | `minimal…xhigh`\* | ❌ |
+| `minimax-m2.7` (`minimax/minimax-m2.7:free`) | MiniMax | **196K** (196.608) | **196K** (196.608) | `minimal…xhigh`\* | ❌ |
+| `minimax-m3` (`minimax/minimax-m3:free`) | MiniMax | **1M** (1.048.576) | **512K** (524.288) | `minimal…xhigh`\* | ❌ |
+| `ling-3.0-flash-fin` (`inclusionai/ling-3.0-flash-fin:free`) | Inclusion AI | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
 
-\* Levels are forwarded as-is through the OpenRouter-style nested `reasoning` parameter; effort mapping is decided by each model. hy3 accepts no reasoning parameter today.
+\* Levels are forwarded as-is through the OpenRouter-style nested `reasoning` parameter; effort mapping is decided by each model. (Verified live 2026-08-29: hy3 accepts flat `reasoning_effort`/nested `reasoning` and returns thinking — README previously said otherwise.) MiMo collapses `minimal→low` and `xhigh→high` upstream, so its selector shows 5 labels but only 3 distinct effort values.
 
 ---
 
@@ -227,7 +231,7 @@ Log rotation at 10MB. Clean, parseable, real-time HTTP lifecycle tracking.
 
 This package stays thin. It ships three things: a model catalog, a relay proxy, and a log. There is no build step. The only runtime dependency is `undici`, which powers the upstream fetch agent. Thinking and prompt normalization stay with the host (`pi-ai`).
 
-Current size: about 11.3k lines including tests. 226 tests pass, typecheck clean.
+Current size: about 11.3k lines including tests. 228 tests pass, typecheck clean.
 
 ---
 
@@ -267,7 +271,7 @@ cd pi-freeflow
 pnpm install
 
 # run all three before opening a PR
-pnpm test        # 226 tests across 30 test files
+pnpm test        # 228 tests across 30 test files
 pnpm typecheck   # tsc --noEmit, must pass clean
 pnpm smoke       # verifies extensions/index.ts loads without crashing
 ```
@@ -277,7 +281,7 @@ pnpm smoke       # verifies extensions/index.ts loads without crashing
 ```
 src/
 ├── index.ts          # extension entry, lifecycle hooks
-├── models.ts         # 21-model catalog definitions
+├── models.ts         # 25-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": "1.6.0",
+  "version": "1.7.0",
   "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

@@ -34,7 +34,7 @@ import type {
 export const DEAD_MODEL_IDS = new Set<string>(["deepseek-v4-flash-free", "x-preview-f-free"]);
 /**
  * In-memory cache of currently active/available free models.
- * Initialized with all 21 verified models for 0ms instant availability.
+ * Initialized with all 25 verified models for 0ms instant availability.
  */
 let aliveCatalog: RegisteredModel[] = ALL_MODELS.map((m) => ({
 	...m,
@@ -328,6 +328,6 @@ 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 21 (host will refresh if needed)
+	// No valid cache — return in-memory static 25 (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 21 free models (7 OpenCode Zen + 14 KiloCode Gateway) with:
+ * Provides access to 25 free models (7 OpenCode Zen + 18 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
@@ -310,7 +310,7 @@ export default async function (pi: ExtensionAPI): Promise<void> {
 						? `Relay pool ready: ${freshRelayState.relays.length} relay(s). Run /freeflow for pool management.`
 						: "Relay pool empty — direct mode. Run /freeflow deploy to add your own egress.";
 				ctx.ui?.notify?.(
-					`freeflow ready: 21 free models via local proxy 127.0.0.1:28180. ${hint}`,
+					`freeflow ready: 25 free models via local proxy 127.0.0.1:28180. ${hint}`,
 					"info",
 				);
 			}

package/src/models.ts

@@ -1,12 +1,12 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 21 verified free models:
+ * Defines the 25 verified free models:
  * - 7 OpenCode Zen models (1 Responses API + 6 Chat Completions)
- * - 14 KiloCode Keyless Gateway models (10 OpenRouter format + 4 Standard format)
+ * - 18 KiloCode Keyless Gateway models (17 OpenRouter format + 1 Standard format)
  */
 
-import type { ModelDef, Upstream } from "./types.ts";
+import type { ModelDef, ThinkingLevelMap, Upstream } from "./types.ts";
 
 /**
  * OpenCode Zen free models verified against the live catalog and inference APIs.
@@ -51,7 +51,7 @@ export const OPENCODE_MODELS: ModelDef[] = [
 		name: "Hy3 (262K)",
 		reasoning: true,
 		contextWindow: 262_144,
-		maxTokens: 262_144,
+		maxTokens: 128_000,
 		input: ["text"],
 		thinkingLevelMap: {
 			off: null,
@@ -112,10 +112,10 @@ export const OPENCODE_MODELS: ModelDef[] = [
 	},
 	{
 		id: "laguna-s-2.1-free",
-		name: "Laguna S 2.1 (1M)",
+		name: "Laguna S 2.1 (256K)",
 		reasoning: true,
-		contextWindow: 1_048_576,
-		maxTokens: 131_072,
+		contextWindow: 262_144,
+		maxTokens: 32_768,
 		input: ["text"],
 		thinkingLevelMap: {
 			off: null,
@@ -128,6 +128,23 @@ export const OPENCODE_MODELS: ModelDef[] = [
 	},
 ];
 
+/**
+ * Shared effort map for Kilo reasoning models — verified live 2026-08-29:
+ * gateway accepts flat reasoning_effort minimal..xhigh for every reasoning
+ * model; stepfun/step-3.7-flash measured monotonic 77→313 thinking chars
+ * across minimal→xhigh. Declaring the map locks the picker (instead of
+ * host guessing) and matches the OpenCode-model pattern.
+ */
+const KILO_REASONING_MAP: ThinkingLevelMap = {
+	off: null,
+	minimal: "minimal",
+	low: "low",
+	medium: "medium",
+	high: "high",
+	xhigh: "xhigh",
+	max: null,
+};
+
 /**
  * KiloCode Gateway free models (keyless — https://kilo.ai/docs/gateway).
  * Endpoint: https://api.kilo.ai/api/gateway/chat/completions
@@ -141,6 +158,7 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 512_000,
 		input: ["text", "image"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "stepfun/step-3.7-flash:free",
@@ -150,24 +168,27 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 262_144,
 		input: ["text", "image"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
 		name: "Nemotron 3 Nano Omni",
 		reasoning: true,
 		contextWindow: 256_000,
-		maxTokens: 65_536,
+		maxTokens: 131_072,
 		input: ["text", "image"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "nvidia/nemotron-3-ultra-550b-a55b:free",
 		name: "Nemotron 3 Ultra 550B (1M)",
 		reasoning: true,
 		contextWindow: 1_000_000,
-		maxTokens: 65_536,
+		maxTokens: 128_000,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "nvidia/nemotron-3.5-lightning:free",
@@ -177,6 +198,7 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 262_144,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -186,15 +208,17 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 262_144,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "tencent/hy3:free",
 		name: "Tencent Hy3 (Kilo)",
 		reasoning: true,
 		contextWindow: 262_144,
-		maxTokens: 262_144,
+		maxTokens: 128_000,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "cohere/north-mini-code:free",
@@ -204,15 +228,17 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 64_000,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "poolside/laguna-s-2.1:free",
 		name: "Laguna S 2.1 (Kilo)",
 		reasoning: true,
-		contextWindow: 1_048_576,
-		maxTokens: 131_072,
+		contextWindow: 262_144,
+		maxTokens: 32_768,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "poolside/laguna-xs-2.1:free",
@@ -222,31 +248,37 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 32_768,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "liquid/lfm-2.5-2.6b:free",
 		name: "Liquid LFM 2.5",
 		reasoning: true,
-		contextWindow: 128_000,
+		contextWindow: 65_536,
 		maxTokens: 32_768,
 		input: ["text"],
 		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "kilo-auto/free",
 		name: "Kilo Auto",
-		reasoning: false,
+		reasoning: true,
 		contextWindow: 256_000,
 		maxTokens: 10_000,
 		input: ["text"],
+		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "openrouter/free",
 		name: "OpenRouter Auto",
-		reasoning: false,
+		reasoning: true,
 		contextWindow: 200_000,
 		maxTokens: 65_536,
 		input: ["text", "image"],
+		thinkingFormat: "openrouter",
+		thinkingLevelMap: KILO_REASONING_MAP,
 	},
 	{
 		id: "nvidia/nemotron-3.5-content-safety:free",
@@ -256,6 +288,46 @@ export const KILO_MODELS: ModelDef[] = [
 		maxTokens: 8_192,
 		input: ["text", "image"],
 	},
+{
+	id: "meituan/longcat-2.0-free",
+	name: "LongCat 2.0 (1M)",
+	reasoning: true,
+	contextWindow: 1_048_756,
+	maxTokens: 262_144,
+	input: ["text"],
+	thinkingFormat: "openrouter",
+	thinkingLevelMap: KILO_REASONING_MAP,
+},
+{
+	id: "minimax/minimax-m2.7:free",
+	name: "MiniMax M2.7 (free)",
+	reasoning: true,
+	contextWindow: 196_608,
+	maxTokens: 196_608,
+	input: ["text"],
+	thinkingFormat: "openrouter",
+	thinkingLevelMap: KILO_REASONING_MAP,
+},
+{
+	id: "minimax/minimax-m3:free",
+	name: "MiniMax M3 (free)",
+	reasoning: true,
+	contextWindow: 1_048_576,
+	maxTokens: 524_288,
+	input: ["text"],
+	thinkingFormat: "openrouter",
+	thinkingLevelMap: KILO_REASONING_MAP,
+},
+{
+	id: "inclusionai/ling-3.0-flash-fin:free",
+	name: "Ling 3.0 Flash Fin",
+	reasoning: true,
+	contextWindow: 262_144,
+	maxTokens: 32_768,
+	input: ["text"],
+	thinkingFormat: "openrouter",
+	thinkingLevelMap: KILO_REASONING_MAP,
+},
 ];
 
 /**
@@ -271,10 +343,15 @@ export const MODEL_ALIASES: Record<string, string> = {
 	"step-3.7-flash": "stepfun/step-3.7-flash:free",
 	"nemotron-3-nano-omni": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
 	"nemotron-3-ultra-550b": "nvidia/nemotron-3-ultra-550b-a55b:free",
+	"nemotron-3.5-lightning": "nvidia/nemotron-3.5-lightning:free",
 	"nemotron-3-super": "nvidia/nemotron-3-super-120b-a12b:free",
 	"north-mini-code": "cohere/north-mini-code:free",
 	"lfm-2.5": "liquid/lfm-2.5-2.6b:free",
 	"content-safety": "nvidia/nemotron-3.5-content-safety:free",
+	"longcat-2.0": "meituan/longcat-2.0-free",
+	"minimax-m2.7": "minimax/minimax-m2.7:free",
+	"minimax-m3": "minimax/minimax-m3:free",
+	"ling-3.0-flash-fin": "inclusionai/ling-3.0-flash-fin:free",
 	// provider-prefixed short aliases (slash-normalized)
 	"hy3:free": "tencent/hy3:free",
 	"laguna-s-2.1:free": "poolside/laguna-s-2.1:free",
@@ -302,7 +379,7 @@ export const KILO_MODEL_IDS = new Set<string>([
 ]);
 
 /**
- * Combined list of all 21 static free models (canonical)
+ * Combined list of all 25 static free models (canonical)
  */
 export const ALL_MODELS: ModelDef[] = [...OPENCODE_MODELS, ...KILO_MODELS];