@oh-my-pi/pi-catalog 17.2.12 → 17.2.14

package/CHANGELOG.md

@@ -2,6 +2,17 @@
 
 ## [Unreleased]
 
+## [17.2.13] - 2026-08-11
+
+### Changed
+
+- Standardized catalog discovery User-Agent headers on `omp/<version>` via the shared `USER_AGENT` utility.
+
+### Fixed
+
+- Marked `meta/muse-spark-1.2` and `muse-spark-1.2-contributor` as image-capable (`input: ["text", "image"]`) with the same Responses reasoning, thinking, and cost metadata as `muse-spark-1.1` (contributor uses its discounted 0.1/0.2 pricing), so `omp models` no longer lists them as text-only.
+- Fixed GLM-5.2 thinking levels across Baseten, CoreWeave, HuggingFace, and other uppercase-ID resellers, which were getting the generic `xhigh` effort ladder instead of the GLM-5.2-specific tiers. Also added Baseten `zai-org/GLM-5.2-Fast` and Fireworks `glm-5.2-fast` as reasoning models ([#8200](https://github.com/can1357/oh-my-pi/pull/8200) by [@jcfrancisco](https://github.com/jcfrancisco)).
+
 ## [17.2.12] - 2026-08-08
 
 ### Fixed

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "17.2.12",
+	"version": "17.2.14",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -35,11 +35,11 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.1",
-		"@oh-my-pi/omptype": "17.2.12",
-		"@oh-my-pi/pi-utils": "17.2.12"
+		"@oh-my-pi/omptype": "17.2.14",
+		"@oh-my-pi/pi-utils": "17.2.14"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "17.2.12",
+		"@oh-my-pi/pi-ai": "17.2.14",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/identity/classify.ts

@@ -143,7 +143,7 @@ export const parseOpenAIModel = parser((modelId): OpenAIModel | null => {
  * `parseKnownModel`.
  */
 export const parseGlmModel = parser((modelId): GlmModel | null => {
-	const match = /glm-(\d{1,2}(?:\.\d+)?)(v)?(?:-(air|turbo|flashx|flash|preview))?\b/.exec(modelId);
+	const match = /glm-(\d{1,2}(?:\.\d+)?)(v)?(?:-(air|turbo|flashx|flash|preview))?\b/i.exec(modelId);
 	if (!match) {
 		return null;
 	}
@@ -153,8 +153,8 @@ export const parseGlmModel = parser((modelId): GlmModel | null => {
 	}
 	return {
 		family: "glm",
-		variant: (match[3] as GlmVariant | undefined) ?? "base",
-		vision: match[2] === "v",
+		variant: (match[3]?.toLowerCase() as GlmVariant | undefined) ?? "base",
+		vision: match[2]?.toLowerCase() === "v",
 		version,
 	};
 });

package/src/models.json

@@ -13793,11 +13793,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
 					"high",
-					"xhigh"
+					"max"
 				]
 			},
 			"supportsComputerUse": false,
@@ -13809,7 +13806,7 @@
 			"api": "openai-completions",
 			"provider": "baseten",
 			"baseUrl": "https://inference.baseten.co/v1",
-			"reasoning": false,
+			"reasoning": true,
 			"input": [
 				"text"
 			],
@@ -13822,7 +13819,14 @@
 			"contextWindow": 1048576,
 			"maxTokens": 262144,
 			"supportsComputerUse": false,
-			"supportsComputerUseConfig": false
+			"supportsComputerUseConfig": false,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"high",
+					"max"
+				]
+			}
 		}
 	},
 	"bedrock-mantle": {
@@ -16247,7 +16251,7 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				]
 			}
 		}
@@ -21875,6 +21879,40 @@
 				}
 			},
 			"supportsComputerUse": false
+		},
+		"glm-5.2-fast": {
+			"id": "glm-5.2-fast",
+			"name": "GLM-5.2 Fast",
+			"api": "openai-completions",
+			"provider": "fireworks",
+			"baseUrl": "https://api.fireworks.ai/inference/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 2.1,
+				"output": 6.6,
+				"cacheRead": 0.21,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"max"
+				],
+				"effortMap": {
+					"minimal": "none"
+				}
+			},
+			"supportsComputerUse": false,
+			"supportsComputerUseConfig": false
 		}
 	},
 	"github-copilot": {
@@ -28443,7 +28481,7 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				]
 			}
 		}
@@ -41098,6 +41136,74 @@
 				"supportsReasoningEffort": true,
 				"includeEncryptedReasoning": true
 			}
+		},
+		"muse-spark-1.2": {
+			"id": "muse-spark-1.2",
+			"name": "Muse Spark 1.2",
+			"api": "openai-responses",
+			"provider": "meta",
+			"baseUrl": "https://api.meta.ai/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 1.25,
+				"output": 4.25,
+				"cacheRead": 0.15,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			},
+			"compat": {
+				"supportsReasoningEffort": true,
+				"includeEncryptedReasoning": true
+			}
+		},
+		"muse-spark-1.2-contributor": {
+			"id": "muse-spark-1.2-contributor",
+			"name": "Muse Spark 1.2 Contributor (Data Used for Training)",
+			"api": "openai-responses",
+			"provider": "meta",
+			"baseUrl": "https://api.meta.ai/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.1,
+				"output": 0.2,
+				"cacheRead": 0.002,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 131072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			},
+			"compat": {
+				"supportsReasoningEffort": true,
+				"includeEncryptedReasoning": true
+			}
 		}
 	},
 	"minimax": {
@@ -89008,7 +89114,7 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				]
 			},
 			"supportsComputerUse": false,
@@ -90026,7 +90132,7 @@
 					"low",
 					"medium",
 					"high",
-					"xhigh"
+					"max"
 				]
 			}
 		}
@@ -100924,10 +101030,8 @@
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
-					"minimal",
-					"low",
-					"medium",
-					"high"
+					"high",
+					"max"
 				]
 			},
 			"supportsComputerUse": false,
@@ -109356,4 +109460,4 @@
 			}
 		}
 	}
-}
+}

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

@@ -1,4 +1,4 @@
-import { VERSION } from "@oh-my-pi/pi-utils";
+import { USER_AGENT } from "@oh-my-pi/pi-utils";
 import * as logger from "@oh-my-pi/pi-utils/logger";
 import {
 	fetchOpenAICompatibleModels,
@@ -111,7 +111,7 @@ const catalogSession: {
 	hasPayload: boolean;
 } = { inflight: null, payload: undefined, etag: null, hasPayload: false };
 
-const CATALOG_USER_AGENT = `omp/${VERSION} (+https://omp.sh)`;
+const CATALOG_USER_AGENT = USER_AGENT;
 
 /**
  * Fetches the models.dev catalog via catalog.stencil.so, which serves a
@@ -1812,6 +1812,7 @@ const FIREWORKS_FAST_VARIANT_SPECS: ReadonlyArray<{
 	{ base: "kimi-k2.7-code", name: "Kimi K2.7 Code Fast", cost: { input: 1.9, output: 8, cacheRead: 0.38 } },
 	{ base: "kimi-k2.6", name: "Kimi K2.6 Fast", cost: { input: 2, output: 8, cacheRead: 0.3 } },
 	{ base: "glm-5.1", name: "GLM-5.1 Fast", cost: { input: 2.8, output: 8.8, cacheRead: 0.52 } },
+	{ base: "glm-5.2", name: "GLM-5.2 Fast", cost: { input: 2.1, output: 6.6, cacheRead: 0.21 } },
 ];
 
 /**
@@ -3549,10 +3550,13 @@ export function basetenModelManagerOptions(
 			const features = Array.isArray(raw.supported_features) ? raw.supported_features : [];
 			const modalities = Array.isArray(raw.input_modalities) ? raw.input_modalities : [];
 
-			const isBasetenNativeReasoning =
+			// Baseten's reasoning router accepts only the high/max
+			// effort tiers for its GLM-5.2 and gpt-oss routes.
+			const isEffortReasoning =
 				defaults.id === "openai/gpt-oss-120b" ||
-				defaults.id === "deepseek-ai/DeepSeek-V4-Pro" ||
-				defaults.id === "zai-org/GLM-5.2";
+				defaults.id === "zai-org/GLM-5.2" ||
+				defaults.id === "zai-org/GLM-5.2-Fast";
+			const isBasetenNativeReasoning = isEffortReasoning || defaults.id === "deepseek-ai/DeepSeek-V4-Pro";
 			const reasoning =
 				isBasetenNativeReasoning && (features.includes("reasoning") || features.includes("reasoning_effort"));
 			const supportsTools = features.includes("tools") ? undefined : false;
@@ -3570,10 +3574,6 @@ export function basetenModelManagerOptions(
 			const maxTokens = toPositiveNumber(raw.max_completion_tokens, reference?.maxTokens ?? defaults.maxTokens);
 
 			const baseModel = mapWithBundledReference(entry, defaults, reference);
-
-			// Baseten's reasoning router accepts only the high/max
-			// effort tiers for its GLM-5.2 and gpt-oss routes.
-			const isEffortReasoning = defaults.id === "openai/gpt-oss-120b" || defaults.id === "zai-org/GLM-5.2";
 			const thinking = isEffortReasoning
 				? {
 						mode: "effort" as const,
@@ -3659,6 +3659,40 @@ export const META_MUSE_STATIC_MODELS: readonly ModelSpec<"openai-responses">[] =
 			includeEncryptedReasoning: true,
 		},
 	},
+	{
+		id: "muse-spark-1.2",
+		name: "Muse Spark 1.2",
+		api: "openai-responses",
+		provider: "meta",
+		baseUrl: META_MODEL_API_BASE_URL,
+		reasoning: true,
+		input: ["text", "image"],
+		cost: META_MUSE_SPARK_COST,
+		contextWindow: 1_048_576,
+		maxTokens: 131_072,
+		thinking: META_MUSE_SPARK_THINKING,
+		compat: {
+			supportsReasoningEffort: true,
+			includeEncryptedReasoning: true,
+		},
+	},
+	{
+		id: "muse-spark-1.2-contributor",
+		name: "Muse Spark 1.2 Contributor (Data Used for Training)",
+		api: "openai-responses",
+		provider: "meta",
+		baseUrl: META_MODEL_API_BASE_URL,
+		reasoning: true,
+		input: ["text", "image"],
+		cost: { input: 0.1, output: 0.2, cacheRead: 0.002, cacheWrite: 0 },
+		contextWindow: 1_048_576,
+		maxTokens: 131_072,
+		thinking: META_MUSE_SPARK_THINKING,
+		compat: {
+			supportsReasoningEffort: true,
+			includeEncryptedReasoning: true,
+		},
+	},
 ];
 
 // ---------------------------------------------------------------------------