pi-freeflow 1.33.0 → 1.33.1

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.33.1
+
+### Patch Changes
+
+- Removed one free model from the catalog that could never be used in a coding session. It answers a plain chat request fine, but rejects any request that carries tool definitions — and coding agents always send tools, so picking it failed on every turn with a "no endpoints found that support tool use" error. The catalog is now 30 models.
+
 ## 1.33.0
 
 ### Minor Changes

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow
 
-> 31 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
+> 30 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
 
 Thin by design: a model list, a relay proxy, and a log. The host (`pi-ai`) handles thinking, normalization, and provider behavior.
 
@@ -16,7 +16,7 @@ Thin by design: a model list, a relay proxy, and a log. The host (`pi-ai`) handl
 
 | Feature | What it does | Cost |
 | :--- | :--- | :--- |
-| **31 free models** | 10 from OpenCode Zen, 16 from KiloCode Gateway, 5 from Cline, context windows up to 1M. Full list below. | **$0** |
+| **30 free models** | 10 from OpenCode Zen, 15 from KiloCode Gateway, 5 from Cline, context windows up to 1M. Full list below. | **$0** |
 | **Relay pool** | Route requests through your own Cloudflare Workers and Vercel Edge relays. Traffic spreads across the pool, or stays on one sticky relay. A relay that rate-limits, times out, or drops the connection cools down while healthy ones take its traffic. | **$0** beyond your platforms' free tiers |
 | **Automatic fallback** | When every relay is cooling down, requests go direct to upstream instead of failing. | **$0** |
 | **Short model names** | Every model has a slash-free, colon-free alias, plus an optional `:effort` suffix for thinking depth. You type `freeflow/<name>`. | **$0** |
@@ -185,7 +185,7 @@ The same command set works identically in OMP and Pi:
 
 ---
 
-### 31 models, one command
+### 30 models, one command
 
 ```bash
 /model → freeflow → pick
@@ -225,7 +225,6 @@ Keyless access. Short aliases work for every row (the full ID is in parentheses)
 | `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)* | ✅ |
 | `ling-3.0-flash-sante` (`inclusionai/ling-3.0-flash-sante:free`) | Inclusion AI | **262K** (262.144) | **32K** (32.768) | `minimal…xhigh`\* | ❌ |
 | `step-3.7-flash` (`stepfun/...:free`) | StepFun | **262K** (262.144) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
 | `inkling-small` (`thinkingmachines/inkling-small:free`) | Thinking Machines | **1M** (1.048.576) | **262K** (262.144) | `minimal…xhigh`\* | ✅ |
@@ -342,7 +341,7 @@ pnpm smoke       # verifies extensions/index.ts loads without crashing
 ```
 src/
 ├── index.ts          # extension entry, lifecycle hooks
-├── models.ts         # 31-model catalog definitions
+├── models.ts         # 30-model catalog definitions
 ├── catalog.ts        # model catalog cache (24h disk)
 ├── proxy.ts          # local proxy server (127.0.0.1:28180)
 ├── relay.ts          # relay fetch, rolling on retryable failures

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.33.0",
+  "version": "1.33.1",
   "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/catalog.ts

@@ -46,6 +46,14 @@ import type {
  * - exo-free: unserved upstream (2026-10-07) — HTTP 503 "Error from provider (Console): Upstream request failed: Endpoint is unavailable.".
  * - stealth/space-bunny-alpha: gone from Kilo (2026-10-07) — keyless chat 404 "The requested model ... does not exist".
  * - qwen/qwen3.8-27b:free: gone from Kilo (2026-10-07) — keyless chat 404 "The requested model is currently unavailable.".
+ * - nvidia/nemotron-3.5-content-safety:free: tool-less guardrail model (2026-10-08),
+ *   NOT decommissioned — it answers 200 keyless chat with no tools, but every
+ *   tool-bearing request 404s "No endpoints found that support tool use" (Kilo
+ *   `supported_parameters` lists reasoning only, no tools). It is a 4B
+ *   moderation classifier fine-tuned from Gemma-3-4B that "moderates inputs to
+ *   and responses from LLMs", not a chat model. Same exclusion class as
+ *   jev-1.13-free: live, wrong shape for an agentic harness, so it must never
+ *   re-enter the picker via disk cache or upstream merge.
  */
 export const DEAD_MODEL_IDS = new Set<string>([
  "jev-1.13-free",
@@ -69,6 +77,7 @@ export const DEAD_MODEL_IDS = new Set<string>([
  "exo-free",
  "stealth/space-bunny-alpha",
  "qwen/qwen3.8-27b:free",
+ "nvidia/nemotron-3.5-content-safety:free",
 ]);
 /**
  * Free-tier allowlist for anything entering the picker via network or stale disk.
@@ -108,7 +117,7 @@ export function sanitizeCatalogModels(models: RegisteredModel[]): RegisteredMode
 }
 /**
  * In-memory cache of currently active/available free models.
- * Initialized with all 31 verified models for 0ms instant availability.
+ * Initialized with all 30 verified models for 0ms instant availability.
  */
 let aliveCatalog: RegisteredModel[] = ALL_MODELS.map((m) => ({
  ...m,

package/src/index.ts

@@ -1,7 +1,7 @@
 /**
  * pi-freeflow — Modular, high-resiliency LLM extension for Pi & Oh My Pi (OMP)
  *
- * Provides access to 31 free models (10 OpenCode Zen + 16 KiloCode Gateway + 5 Cline) with:
+ * Provides access to 30 free models (10 OpenCode Zen + 15 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 31 verified free models (live-verified 2026-10-07):
+ * Defines the 30 verified free models (live-verified 2026-10-08):
  * - 10 OpenCode Zen models (2 Responses API + 8 Chat Completions)
- * - 16 KiloCode Keyless Gateway models (OpenRouter format)
+ * - 15 KiloCode Keyless Gateway models (OpenRouter format)
  * - 5 Cline direct-only models (per-user pool)
  */
 
@@ -319,14 +319,6 @@ export const KILO_MODELS: ModelDef[] = [
   thinkingFormat: "openrouter",
   thinkingLevelMap: KILO_REASONING_MAP,
  },
- {
-  id: "nvidia/nemotron-3.5-content-safety:free",
-  name: "Nemotron Content Safety [Kilo]",
-  reasoning: false,
-  contextWindow: 128_000,
-  maxTokens: 8_192,
-  input: ["text", "image"],
- },
  {
   // Resurrected 2026-09-28: back on the live Kilo free list
   // (isFree:true, 0/0 pricing, no expiry) + keyless chat 200.
@@ -485,7 +477,6 @@ export const MODEL_ALIASES: Record<string, string> = {
  "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",
  "ling-3.0-flash-sante": "inclusionai/ling-3.0-flash-sante:free",
  "step-3.7-flash": "stepfun/step-3.7-flash:free",
  "inkling-small": "thinkingmachines/inkling-small:free",
@@ -530,7 +521,7 @@ export const CLINE_MODEL_IDS = new Set<string>([
   .map(([alias]) => alias),
 ]);
 /**
- * Combined list of all 31 static free models (canonical)
+ * Combined list of all 30 static free models (canonical)
  */
 export const ALL_MODELS: ModelDef[] = [...OPENCODE_MODELS, ...KILO_MODELS, ...CLINE_MODELS];