pi-freeflow 1.37.0 → 1.37.1

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 1.37.1
+
+### Patch Changes
+
+- **DeepSeek V4.1 Flash (`deepseek-v4.1-flash-free`)**: Added to the OpenCode Zen lane (catalog 34 → 35 models). Configured with full **1,000,000 context window**, **384,000 max output tokens**, vision support (`input: ["text", "image"]`), and reasoning ladder (`minimal..max`).
+- **Sources of Truth & Highest-Spec Twin Policy**: Documented model reconciliation against [models.dev](https://models.dev/), [OpenRouter](https://openrouter.ai/), and OMP's built-in catalog, ensuring models are configured to the highest capability across twin models rather than artificially truncated limits.
+- **Automated OpenCode Model Health Bot**: Added dedicated GitHub Actions workflow and probe engine to continuously detect affected or degraded OpenCode free-tier models.
+
 ## 1.37.0
 
 ### Minor Changes

package/README.md

@@ -1,6 +1,6 @@
 # pi-freeflow
 
-> 34 free models with up to 1M context. No API keys to manage. Add your own relays to spread requests across more IPs.
+> 35 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 |
 | :--- | :--- | :--- |
-| **34 free models** | 10 from OpenCode Zen, 14 from KiloCode Gateway, 2 from Cline, 8 from OVHcloud AI Endpoints, context windows up to 1M. Full list below. | **$0** |
+| **35 free models** | 11 from OpenCode Zen, 14 from KiloCode Gateway, 2 from Cline, 8 from OVHcloud AI Endpoints, context windows up to 1M. Full list below. | **$0** |
 | **Relay pool** | Route requests through your own Cloudflare Workers, Deno Deploy, 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** | Most models have a slash-free, colon-free alias, plus an optional `:effort` suffix for thinking depth. You type `freeflow/<name>`; the two Cline models have no alias and must be typed in full. | **$0** |
@@ -197,13 +197,14 @@ The same command set works identically in OMP and Pi:
 
 ---
 
-### 34 models, one command
+### 35 models, one command
 
 ```bash
 /model → freeflow → pick
 ```
 
-#### OpenCode Zen (10 models), Responses and Chat API
+Every model specification is reconciled against [models.dev](https://models.dev/), [OpenRouter](https://openrouter.ai/), and OMP's built-in catalog, configured with the highest verified context, output ceiling, and reasoning capabilities across twin models.
+#### OpenCode Zen (11 models), Responses and Chat API
 
 Good defaults for long coding sessions and agentic work.
 
@@ -219,6 +220,7 @@ Good defaults for long coding sessions and agentic work.
 | `space-bunny-free` | Stealth preview (lab undisclosed) | **1M** (1.048.576) | **512K** (524.288) | `low … max` | ✅ |
 | `longcat-2.5-preview-free` | Meituan LongCat | **1M** (1.000.000) | **131K** (131.072) | `minimal … max` | ✅ |
 | `step-5-preview-free` | StepFun | **1M** (1.000.000) | **64K** (65.536) | `low … high` | ✅ |
+| `deepseek-v4.1-flash-free` | DeepSeek | **1M** (1.000.000) | **384K** (384.000) | `minimal … max` | ✅ |
 
 #### KiloCode Gateway (14 models), OpenRouter compatible
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-freeflow",
   "type": "module",
-  "version": "1.37.0",
+  "version": "1.37.1",
   "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/index.ts

@@ -1,7 +1,7 @@
 /**
  * pi-freeflow — Modular, high-resiliency LLM extension for Pi & Oh My Pi (OMP)
  *
- * Provides access to 37 free models (11 OpenCode Zen + 15 KiloCode Gateway + 2 Cline + 9 OVH) with:
+ * Provides access to 35 free models (11 OpenCode Zen + 14 KiloCode Gateway + 2 Cline + 8 OVH) 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

@@ -1,8 +1,8 @@
 /**
  * Static model definitions and upstream routing catalogs for pi-freeflow
  *
- * Defines the 34 verified free models (live-verified 2026-10-15):
- * - 10 OpenCode Zen models (2 Responses API + 8 Chat Completions)
+ * Defines the 35 verified free models (live-verified 2026-10-15):
+ * - 11 OpenCode Zen models (2 Responses API + 9 Chat Completions)
  * - 14 KiloCode Keyless Gateway models (OpenRouter format)
  * - 2 Cline direct-only models (per-user pool)
  * - 8 OVHcloud AI Endpoints models (keyless, direct-only)
@@ -200,6 +200,40 @@ export const OPENCODE_MODELS: ModelDef[] = [
   max: null,
  },
  },
+{
+  // Added 2026-10-15: new free model on the OpenCode Zen lane. Live-verified by
+  // probe, NOT copied from the published catalog — the entry for this exact
+  // free id claims 200,000 context, which the gateway contradicts (see below).
+  id: "deepseek-v4.1-flash-free",
+  name: "DeepSeek V4.1 Flash [OpenCode]",
+  reasoning: true,
+  // 1,048,576 measured, not assumed: a marker planted mid-prompt is still
+  // recalled through prompt_tokens=1,030,800, and the gateway turns an
+  // oversized request away with an empty-bodied 400 somewhere above ~1.05M.
+  // The published 200k belongs to the paid deepseek-v4-flash-free, a different
+  // model with a confusingly similar name. Acceptance is not capability; here
+  // the two agree, which is why this is the declared number.
+  contextWindow: 1_000_000,
+  // 384,000 output tokens per https://models.dev/models/deepseek/deepseek-v4.1-flash/
+  // and live gateway boundary probe (gateway accepts up to 393,216 = 384KiB, rejects 393,217+ with 400).
+  maxTokens: 384_000,
+  // Chat Completions only — a Responses-shaped request is refused with
+  // 400 ModelProtocolUnsupported. `api` left unset, which means chat.
+  input: ["text", "image"],
+  // Vision verified live (a 1x1 PNG reads back as "Pink"). Video is not
+  // advertised for this model upstream, so it is not offered here.
+  // Every effort level is accepted and visibly changes reasoning length, so
+  // the whole ladder stays selectable; `off` is always null.
+  thinkingLevelMap: {
+   off: null,
+   minimal: "minimal",
+   low: "low",
+   medium: "medium",
+   high: "high",
+   xhigh: "xhigh",
+   max: "max",
+  },
+},
 ];
 
 /**
@@ -589,6 +623,7 @@ export const MODEL_ALIASES: Record<string, string> = {
  "longcat-2.5-preview": "longcat-2.5-preview-free",
  "longcat": "longcat-2.5-preview-free",
  "step-5-preview": "step-5-preview-free",
+ "deepseek-v4.1-flash": "deepseek-v4.1-flash-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",