@oh-my-pi/pi-catalog 16.1.8 → 16.1.9

package/CHANGELOG.md

@@ -2,6 +2,17 @@
 
 ## [Unreleased]
 
+## [16.1.9] - 2026-06-21
+
+### Fixed
+
+- Fixed the `moonshot` provider with no path to the Kimi China API: model discovery now honors a `MOONSHOT_BASE_URL` override (redirecting to `api.moonshot.cn`), and `KIMI_API_KEY` resolves as a fallback for `MOONSHOT_API_KEY`. ([#2883](https://github.com/can1357/oh-my-pi/issues/2883))
+- Fixed LiteLLM model discovery preserving colliding models.dev transport metadata (for example `ollama-cloud` `deepseek-v4-flash`) instead of keeping the LiteLLM `openai-completions` provider transport. ([#3162](https://github.com/can1357/oh-my-pi/issues/3162))
+
+### Removed
+
+- Removed bundled Wafer Pass (`wafer-pass`) catalog entries and generation support; Wafer Serverless remains available as `wafer-serverless`.
+
 ## [16.1.8] - 2026-06-20
 
 ### Fixed

package/dist/types/provider-models/descriptors.d.ts

@@ -173,7 +173,7 @@ export declare const CATALOG_PROVIDERS: readonly [{
 }, {
     readonly id: "moonshot";
     readonly defaultModel: "kimi-k2.7-code";
-    readonly envVars: readonly ["MOONSHOT_API_KEY"];
+    readonly envVars: readonly ["MOONSHOT_API_KEY", "KIMI_API_KEY"];
     readonly createModelManagerOptions: (config: ModelManagerConfig) => import("..").ModelManagerOptions<"openai-completions", unknown>;
     readonly catalogDiscovery: {
         readonly label: "Moonshot";
@@ -310,15 +310,6 @@ export declare const CATALOG_PROVIDERS: readonly [{
         readonly label: "vLLM";
         readonly allowUnauthenticated: true;
     };
-}, {
-    readonly id: "wafer-pass";
-    readonly defaultModel: "GLM-5.1";
-    readonly envVars: readonly ["WAFER_PASS_API_KEY"];
-    readonly createModelManagerOptions: (config: ModelManagerConfig) => import("..").ModelManagerOptions<"openai-completions", unknown>;
-    readonly catalogDiscovery: {
-        readonly label: "Wafer Pass";
-        readonly oauthProvider: "wafer-pass";
-    };
 }, {
     readonly id: "wafer-serverless";
     readonly defaultModel: "GLM-5.1";

package/dist/types/provider-models/openai-compat.d.ts

@@ -215,7 +215,6 @@ export interface WaferModelManagerConfig {
     baseUrl?: string;
     fetch?: FetchImpl;
 }
-export declare function waferPassModelManagerOptions(config?: WaferModelManagerConfig): ModelManagerOptions<"openai-completions">;
 export declare function waferServerlessModelManagerOptions(config?: WaferModelManagerConfig): ModelManagerOptions<"openai-completions">;
 export interface MistralModelManagerConfig {
     apiKey?: string;

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "16.1.8",
+	"version": "16.1.9",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -34,12 +34,12 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-utils": "16.1.8",
+		"@oh-my-pi/pi-utils": "16.1.9",
 		"arktype": "^2.2.0",
 		"zod": "^4"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "16.1.8",
+		"@oh-my-pi/pi-ai": "16.1.9",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/models.json

@@ -77590,64 +77590,6 @@
 			}
 		}
 	},
-	"wafer-pass": {
-		"GLM-5.1": {
-			"id": "GLM-5.1",
-			"name": "GLM-5.1",
-			"api": "openai-completions",
-			"provider": "wafer-pass",
-			"baseUrl": "https://pass.wafer.ai/v1",
-			"reasoning": true,
-			"input": [
-				"text"
-			],
-			"cost": {
-				"input": 0,
-				"output": 0,
-				"cacheRead": 0,
-				"cacheWrite": 0
-			},
-			"contextWindow": 202752,
-			"maxTokens": 65536,
-			"compat": {
-				"supportsDeveloperRole": false,
-				"thinkingFormat": "zai",
-				"reasoningContentField": "reasoning_content"
-			},
-			"thinking": {
-				"mode": "effort",
-				"efforts": [
-					"minimal",
-					"low",
-					"medium",
-					"high"
-				]
-			}
-		},
-		"Qwen3.5-397B-A17B": {
-			"id": "Qwen3.5-397B-A17B",
-			"name": "Qwen3.5-397B-A17B",
-			"api": "openai-completions",
-			"provider": "wafer-pass",
-			"baseUrl": "https://pass.wafer.ai/v1",
-			"reasoning": false,
-			"input": [
-				"text",
-				"image"
-			],
-			"cost": {
-				"input": 0,
-				"output": 0,
-				"cacheRead": 0,
-				"cacheWrite": 0
-			},
-			"contextWindow": 262144,
-			"maxTokens": 65536,
-			"compat": {
-				"supportsDeveloperRole": false
-			}
-		}
-	},
 	"wafer-serverless": {
 		"deepseek-v4-flash": {
 			"id": "deepseek-v4-flash",

package/src/provider-models/descriptors.ts

@@ -41,7 +41,6 @@ import {
 	veniceModelManagerOptions,
 	vercelAiGatewayModelManagerOptions,
 	vllmModelManagerOptions,
-	waferPassModelManagerOptions,
 	waferServerlessModelManagerOptions,
 	xaiModelManagerOptions,
 	xaiOAuthModelManagerOptions,
@@ -219,7 +218,9 @@ export const CATALOG_PROVIDERS = [
 	{
 		id: "moonshot",
 		defaultModel: "kimi-k2.7-code",
-		envVars: ["MOONSHOT_API_KEY"],
+		// KIMI_API_KEY is the most intuitive name for a Kimi/Moonshot key; accept it
+		// as a fallback so China users need not learn MOONSHOT_API_KEY. (#2883)
+		envVars: ["MOONSHOT_API_KEY", "KIMI_API_KEY"],
 		createModelManagerOptions: (config: ModelManagerConfig) => moonshotModelManagerOptions(config),
 		catalogDiscovery: { label: "Moonshot" },
 	},
@@ -347,13 +348,6 @@ export const CATALOG_PROVIDERS = [
 		createModelManagerOptions: (config: ModelManagerConfig) => vllmModelManagerOptions(config),
 		catalogDiscovery: { label: "vLLM", allowUnauthenticated: true },
 	},
-	{
-		id: "wafer-pass",
-		defaultModel: "GLM-5.1",
-		envVars: ["WAFER_PASS_API_KEY"],
-		createModelManagerOptions: (config: ModelManagerConfig) => waferPassModelManagerOptions(config),
-		catalogDiscovery: { label: "Wafer Pass", oauthProvider: "wafer-pass" },
-	},
 	{
 		id: "wafer-serverless",
 		defaultModel: "GLM-5.1",

package/src/provider-models/openai-compat.ts

@@ -197,6 +197,8 @@ function mapWithBundledReference<TApi extends Api>(
 		...reference,
 		id: defaults.id,
 		name,
+		api: defaults.api,
+		provider: defaults.provider,
 		baseUrl: defaults.baseUrl,
 		contextWindow: toPositiveNumber(entry.context_length, reference.contextWindow),
 		maxTokens: toPositiveNumber(entry.max_completion_tokens, reference.maxTokens),
@@ -1568,7 +1570,7 @@ export function firepassModelManagerOptions(
 }
 
 // ---------------------------------------------------------------------------
-// 7.7 Wafer (Pass + Serverless)
+// 7.7 Wafer Serverless
 // ---------------------------------------------------------------------------
 
 export interface WaferModelManagerConfig {
@@ -1581,13 +1583,14 @@ const WAFER_DEFAULT_BASE_URL = "https://pass.wafer.ai/v1";
 const WAFER_MAX_TOKENS_CAP = 65536;
 
 /**
- * Shared mapper for Wafer's `/v1/models` records.
+ * Mapper for Wafer Serverless `/v1/models` records.
  *
- * Wafer wraps each entry with a `wafer` envelope describing tier, capabilities,
- * and cents-per-million pricing. The mapper folds that metadata into the
- * canonical `ModelSpec<"openai-completions">` shape and applies zai-family thinking
- * compat when the entry advertises reasoning support (GLM-family on the Pass
- * SKU). Cents-per-million → dollars-per-million via /100.
+ * Wafer wraps each entry with a `wafer` envelope describing capabilities and
+ * pricing. The mapper folds that metadata into the canonical
+ * `ModelSpec<"openai-completions">` shape and applies upstream-specific thinking
+ * compat when the entry advertises reasoning support. Wafer pricing is exposed
+ * through internal wholesale units; the public Serverless rate equals
+ * `cents × 125 / 10000`.
  */
 interface WaferRecord {
 	context_length?: unknown;
@@ -1608,7 +1611,7 @@ function readWaferRecord(entry: OpenAICompatibleModelRecord): WaferRecord | unde
 }
 
 function mapWaferModel(
-	providerId: "wafer-pass" | "wafer-serverless",
+	providerId: "wafer-serverless",
 	baseUrl: string,
 	entry: OpenAICompatibleModelRecord,
 	defaults: ModelSpec<"openai-completions">,
@@ -1624,25 +1627,12 @@ function mapWaferModel(
 	);
 	const maxTokens = contextWindow !== null ? Math.min(contextWindow, WAFER_MAX_TOKENS_CAP) : null;
 	const pricing = wafer?.pricing ?? {};
-	// Wafer's `/v1/models` exposes pricing through `*_cents_per_million` fields,
-	// but the values are an internal wholesale unit, not literal cents — across
-	// every published Serverless model on wafer.ai the user-facing rate equals
-	// `cents × 125 / 10000` (i.e. wholesale × 1.25 / 100; GLM-5.1's `120` →
-	// $1.50/M, Kimi-K2.6's `88` → $1.10/M, etc.). The multiply-first form keeps
-	// the result a finite dyadic for every observed value.
-	// For the Pass SKU the per-token rate is bundled in the flat-rate
-	// subscription, so we follow the convention shared with
-	// `kimi-code`/`firepass`/`alibaba-coding-plan` and seed every Pass model with
-	// `cost: 0` regardless of what the upstream envelope says.
-	const isPassSku = providerId === "wafer-pass";
-	const cost = isPassSku
-		? { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }
-		: {
-				input: (toPositiveNumber(pricing.input_cents_per_million, 0) * 125) / 10000,
-				output: (toPositiveNumber(pricing.output_cents_per_million, 0) * 125) / 10000,
-				cacheRead: (toPositiveNumber(pricing.cache_read_cents_per_million, 0) * 125) / 10000,
-				cacheWrite: 0,
-			};
+	const cost = {
+		input: (toPositiveNumber(pricing.input_cents_per_million, 0) * 125) / 10000,
+		output: (toPositiveNumber(pricing.output_cents_per_million, 0) * 125) / 10000,
+		cacheRead: (toPositiveNumber(pricing.cache_read_cents_per_million, 0) * 125) / 10000,
+		cacheWrite: 0,
+	};
 	const name = toModelName(wafer?.display_name, defaults.name);
 	const base: ModelSpec<"openai-completions"> = {
 		...defaults,
@@ -1688,13 +1678,12 @@ function mapWaferModel(
 	};
 }
 
-function createWaferOptions(
-	providerId: "wafer-pass" | "wafer-serverless",
-	config: WaferModelManagerConfig | undefined,
+export function waferServerlessModelManagerOptions(
+	config?: WaferModelManagerConfig,
 ): ModelManagerOptions<"openai-completions"> {
 	const apiKey = config?.apiKey;
 	const baseUrl = config?.baseUrl ?? WAFER_DEFAULT_BASE_URL;
-	const passOnly = providerId === "wafer-pass";
+	const providerId = "wafer-serverless" as const;
 	return {
 		providerId,
 		...(apiKey && {
@@ -1704,11 +1693,6 @@ function createWaferOptions(
 					provider: providerId,
 					baseUrl,
 					apiKey,
-					filterModel: entry => {
-						if (!passOnly) return true;
-						const wafer = readWaferRecord(entry);
-						return wafer?.tier === "pass_included";
-					},
 					mapModel: (entry, defaults) => mapWaferModel(providerId, baseUrl, entry, defaults),
 					fetch: config?.fetch,
 				}),
@@ -1716,18 +1700,6 @@ function createWaferOptions(
 	};
 }
 
-export function waferPassModelManagerOptions(
-	config?: WaferModelManagerConfig,
-): ModelManagerOptions<"openai-completions"> {
-	return createWaferOptions("wafer-pass", config);
-}
-
-export function waferServerlessModelManagerOptions(
-	config?: WaferModelManagerConfig,
-): ModelManagerOptions<"openai-completions"> {
-	return createWaferOptions("wafer-serverless", config);
-}
-
 // ---------------------------------------------------------------------------
 // 7. Mistral
 // ---------------------------------------------------------------------------
@@ -2493,7 +2465,10 @@ export function moonshotModelManagerOptions(
 	config?: MoonshotModelManagerConfig,
 ): ModelManagerOptions<"openai-completions"> {
 	const apiKey = config?.apiKey;
-	const baseUrl = config?.baseUrl ?? "https://api.moonshot.ai/v1";
+	// `MOONSHOT_BASE_URL` redirects discovery (and the streaming request that
+	// inherits this baseUrl) at the Kimi China platform `api.moonshot.cn`; an
+	// explicit `config.baseUrl` still wins. Mirrors LITELLM_BASE_URL/LM_STUDIO_BASE_URL. (#2883)
+	const baseUrl = config?.baseUrl ?? Bun.env.MOONSHOT_BASE_URL ?? "https://api.moonshot.ai/v1";
 	const references = createBundledReferenceMap<"openai-completions">("moonshot");
 	return {
 		providerId: "moonshot",