pi-openmodel-provider 0.2.9 → 0.2.11

package/.agents/skills/pi-openmodel-info/SKILL.md

@@ -17,6 +17,21 @@ pi-openmodel-provider is a custom provider that connects pi to [OpenModel.ai](ht
 - **DeepSeek-V4-Flash** with 1M context window
 - **NOT** OpenRouter — this is a different service called OpenModel.ai
 
+## Model discovery
+
+Models are fetched live from OpenModel's API at startup:
+
+- **Pricing & capabilities:** `https://api.openmodel.ai/web/v1/models` (public, no auth needed)
+- **Protocol info:** `https://api.openmodel.ai/v1/models` (requires API key — if unavailable, protocols are inferred from provider)
+
+If the API key is not configured yet, models still load — protocols are inferred automatically from the provider name.
+
+## Thinking levels
+
+Reasoning models support thinking levels:
+- **Messages protocol:** minimal → low, low → medium, medium → high
+- **Responses protocol:** `reasoning_effort` levels (low, medium, high)
+
 ## Available commands
 
 - `/openmodel` — Show provider status

package/AGENTS.md

@@ -2,6 +2,8 @@
 
 - This package is **pi-openmodel-provider** for OpenModel.ai, **NOT** OpenRouter.
 - OpenModel is a multi-model AI gateway, similar to OpenRouter but a different service.
+- Models are fetched dynamically from OpenModel's API at startup — no hardcoded model list.
+- If the `/v1/models` endpoint fails (no API key), protocols are inferred from the provider.
 - See `.agents/skills/pi-openmodel-info/SKILL.md` for full documentation.
 - Follow [CONTRIBUTING.md](CONTRIBUTING.md) before changing code.
 - Use [RELEASE.md](RELEASE.md) for release process.

package/CHANGELOG.md

@@ -5,6 +5,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.10] - 2026-06-22
+
+### Fixed
+- Legacy `/v1/models` endpoint failing without API key (models now load without auth)
+- `require("node:os")` bug in `/openmodel` command (ESM compatibility)
+- Added fallback protocol inference when legacy endpoint unavailable
+
+### Added
+- Test: recovers when legacy endpoint fails with 401
+
 ## [0.2.9] - 2026-06-20
 
 ### Added
@@ -109,6 +119,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Import path extensions (.ts → .js)
 - Process import in models.ts
 
+[0.2.10]: https://github.com/IvanGabrielYarupaitanRivera/pi-openmodel-provider/releases/tag/v0.2.10
 [0.2.9]: https://github.com/IvanGabrielYarupaitanRivera/pi-openmodel-provider/releases/tag/v0.2.9
 [0.2.6]: https://github.com/IvanGabrielYarupaitanRivera/pi-openmodel-provider/releases/tag/v0.2.6
 [0.2.5]: https://github.com/IvanGabrielYarupaitanRivera/pi-openmodel-provider/releases/tag/v0.2.5

package/README.md

@@ -2,7 +2,7 @@
 
 A [pi](https://github.com/earendil-works/pi-mono) custom provider that connects pi to [OpenModel.ai](https://www.openmodel.ai) — a unified AI API gateway.
 
-[![npm version](https://badge.fury.io/js/pi-openmodel-provider.svg)](https://www.npmjs.com/package/pi-openmodel-provider)
+[![npm version](https://img.shields.io/npm/v/pi-openmodel-provider)](https://www.npmjs.com/package/pi-openmodel-provider)
 
 > **Disclaimer:** This is an unofficial, community-maintained package. I am not affiliated with, endorsed by, or connected to OpenModel in any way. This provider simply forwards requests to the public OpenModel API using your own API key.
 
@@ -57,10 +57,10 @@ Models are fetched live from OpenModel's API at startup, so new models show up w
 
 ## Model discovery
 
-On startup, the provider fetches models from two public endpoints (no authentication required):
+On startup, the provider fetches models from two endpoints:
 
-- **Model list & protocols:** `https://api.openmodel.ai/v1/models`
-- **Pricing & capabilities:** `https://api.openmodel.ai/web/v1/models`
+- **Pricing & capabilities:** `https://api.openmodel.ai/web/v1/models` (public, no auth needed)
+- **Protocol info:** `https://api.openmodel.ai/v1/models` (requires API key — if unavailable, protocols are inferred from the provider)
 
 Pricing, context window, reasoning support, and vision capabilities are all provided by the API — no hardcoded data.
 
@@ -148,6 +148,7 @@ npm run test:models
 npm run test:auth
 npm run test:pricing
 npm run test:stability
+npm run test:edge
 ```
 
 ## Contributing

package/index.ts

@@ -13,6 +13,7 @@ import {
   formatHealthStatus,
 } from "./src/stability.ts"
 import { friendlyMessage } from "./src/errors.ts"
+import { homedir } from "node:os"
 
 export default async function (pi: ExtensionAPI) {
   let models: Awaited<ReturnType<typeof fetchOpenModelModels>> = []
@@ -70,7 +71,7 @@ export default async function (pi: ExtensionAPI) {
       let hasApiKey = false
       try {
         const { readFileSync } = await import("node:fs")
-        const authPath = `${require("node:os").homedir()}/.pi/agent/auth.json`
+        const authPath = `${homedir()}/.pi/agent/auth.json`
         const content = readFileSync(authPath, "utf-8")
         const data = JSON.parse(content)
         hasApiKey = !!(data.openmodel?.access || data.openmodel?.refresh)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-openmodel-provider",
-  "version": "0.2.9",
+  "version": "0.2.11",
   "description": "pi custom provider for OpenModel.ai - Multi-model AI gateway",
   "type": "module",
   "keywords": [

package/src/models.ts

@@ -172,7 +172,7 @@ export async function fetchOpenModelModels(options?: {
 
   const [webModels, legacyModels] = await Promise.all([
     fetchWebModels({ fetchImpl }),
-    fetchLegacyModels({ fetchImpl }),
+    fetchLegacyModels({ fetchImpl }).catch(() => new Map()),
   ])
 
   const models: OpenModelProviderModel[] = []
@@ -185,8 +185,13 @@ export async function fetchOpenModelModels(options?: {
 
     const legacy = legacyModels.get(id)
     const protocols = legacy?.supported_protocols ?? []
-    const api = determineApi(protocols, web.provider_key)
-    if (!api) continue
+    let api = determineApi(protocols, web.provider_key)
+    if (!api) {
+      // Fallback: infer protocol from provider
+      if (["openai"].includes(web.provider_key)) api = "openai-responses"
+      else if (["gemini"].includes(web.provider_key)) api = "google-generative-ai"
+      else api = "anthropic-messages"
+    }
 
     const inputPrice = pricePerMillion(web.prices.input_cost_per_token as number)
     const outputPrice = pricePerMillion(web.prices.output_cost_per_token as number)