@oh-my-pi/pi-catalog 15.13.1 → 15.13.2

package/CHANGELOG.md

@@ -2,6 +2,25 @@
 
 ## [Unreleased]
 
+## [15.13.2] - 2026-06-15
+
+### Added
+
+- Added the `ToolCallSyntax` union and `FALLBACK_TOOL_SYNTAX` constant to `@oh-my-pi/pi-catalog/identity` (re-exported from `@oh-my-pi/pi-ai/grammar`).
+- Added `preferredToolSyntax(modelId)` to `@oh-my-pi/pi-catalog/identity`, resolving a model's native tool-call syntax affinity from its family token (Claude→`anthropic`, GLM→`glm`, Kimi→`kimi`, Qwen→`qwen3`, DeepSeek→`deepseek`, OpenAI/gpt-oss→`harmony`, else the `xml` fallback).
+- Added `flux-1-schnell-fp8` to the Fireworks serverless model catalog
+- Added `gpt-oss-20b` to the Fireworks model catalog
+- Added `qwen3-embedding-8b` to the Fireworks model catalog
+- Added `qwen3-reranker-8b` to the Fireworks model catalog
+- Added `Gemma 4 E2B IT` and `Gemma 4 E4B IT` to the Google model catalog
+- Added `qwen/qwen3-asr-flash` to the Zenmux model catalog
+- Added sparse `supportsTools` model metadata so providers can mark models that require in-band tool-call formatting.
+
+### Changed
+
+- Kept non-tool-capable Fireworks serverless models in discovery results and marked them with `supportsTools: false` for fallback-aware handling
+- Extended `modelFamilyToken(modelId)` to classify Claude/OpenAI ids the structured parser misses (older dated forms such as `claude-3-5-sonnet-20241022` and `gpt-4o`), returning `anthropic`/`openai` instead of an empty token.
+
 ## [15.13.1] - 2026-06-15
 
 ### Added

package/dist/types/identity/family.d.ts

@@ -37,6 +37,8 @@ export declare function isMinimaxM2FamilyModelId(modelId: string): boolean;
  * and `none`.
  */
 export declare function isOpenAIGptOssModelId(modelId: string): boolean;
+/** OpenAI model ids (gpt-*, o1-*, o3-*, o4-*, or prefixed with openai/). */
+export declare function isOpenAIModelId(modelId: string): boolean;
 /**
  * Reasoning-capable GLM coding SKUs: glm-4.5 and up on the base / `-air` /
  * `-turbo` lines. Excludes the vision (`…v`) shape, the non-reasoning

package/dist/types/identity/index.d.ts

@@ -7,3 +7,4 @@ export * from "./markers";
 export * from "./priority";
 export * from "./reference";
 export * from "./selection";
+export * from "./tool-syntax";

package/dist/types/identity/tool-syntax.d.ts

@@ -0,0 +1,3 @@
+export type ToolCallSyntax = "glm" | "hermes" | "kimi" | "xml" | "anthropic" | "deepseek" | "harmony" | "pi" | "qwen3";
+export declare const FALLBACK_TOOL_SYNTAX: ToolCallSyntax;
+export declare function preferredToolSyntax(modelId: string): ToolCallSyntax;

package/dist/types/types.d.ts

@@ -371,6 +371,13 @@ export interface Model<TApi extends Api = Api> {
     baseUrl: string;
     reasoning: boolean;
     input: ("text" | "image")[];
+    /**
+     * Native provider tool-call support. `false` is the only unsupported signal:
+     * `true` and `undefined` both mean callers may use native tools. Catalog and
+     * discovery sources should set this sparsely when an upstream explicitly
+     * reports that native tool calling is unsupported.
+     */
+    supportsTools?: boolean;
     cost: {
         input: number;
         output: number;

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "15.13.1",
+	"version": "15.13.2",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -34,11 +34,11 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-utils": "15.13.1",
+		"@oh-my-pi/pi-utils": "15.13.2",
 		"zod": "^4"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "15.13.1",
+		"@oh-my-pi/pi-ai": "15.13.2",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/identity/family.ts

@@ -78,6 +78,11 @@ export function isOpenAIGptOssModelId(modelId: string): boolean {
 	return /(^|\/)gpt-oss[-:]/i.test(modelId);
 }
 
+/** OpenAI model ids (gpt-*, o1-*, o3-*, o4-*, or prefixed with openai/). */
+export function isOpenAIModelId(modelId: string): boolean {
+	return /(^|\/)(gpt|o1|o3|o4)[-.]/i.test(modelId) || modelId.toLowerCase().includes("openai/");
+}
+
 /**
  * Reasoning-capable GLM coding SKUs: glm-4.5 and up on the base / `-air` /
  * `-turbo` lines. Excludes the vision (`…v`) shape, the non-reasoning
@@ -114,6 +119,8 @@ export function isGlmVisionModelId(modelId: string): boolean {
 export function modelFamilyToken(modelId: string): string {
 	const parsed = parseKnownModel(modelId);
 	if (parsed.family !== "unknown") return parsed.family;
+	if (isClaudeModelId(modelId) || isAnthropicNamespacedModelId(modelId)) return "anthropic";
+	if (isOpenAIModelId(modelId)) return "openai";
 	if (isKimiModelId(modelId)) return "kimi";
 	if (isQwenModelId(modelId)) return "qwen";
 	if (isMinimaxM2FamilyModelId(modelId)) return "minimax";

package/src/identity/index.ts

@@ -7,3 +7,4 @@ export * from "./markers";
 export * from "./priority";
 export * from "./reference";
 export * from "./selection";
+export * from "./tool-syntax";

package/src/identity/tool-syntax.ts

@@ -0,0 +1,25 @@
+import { modelFamilyToken } from "./family";
+
+export type ToolCallSyntax = "glm" | "hermes" | "kimi" | "xml" | "anthropic" | "deepseek" | "harmony" | "pi" | "qwen3";
+
+export const FALLBACK_TOOL_SYNTAX: ToolCallSyntax = "xml";
+
+export function preferredToolSyntax(modelId: string): ToolCallSyntax {
+	switch (modelFamilyToken(modelId)) {
+		case "anthropic":
+			return "anthropic";
+		case "glm":
+			return "glm";
+		case "kimi":
+			return "kimi";
+		case "qwen":
+			return "qwen3";
+		case "deepseek":
+			return "deepseek";
+		case "openai":
+		case "gpt-oss":
+			return "harmony";
+		default:
+			return FALLBACK_TOOL_SYNTAX;
+	}
+}

package/src/models.json

@@ -13692,6 +13692,39 @@
 				"requiresAssistantContentForToolCalls": true
 			}
 		},
+		"flux-1-schnell-fp8": {
+			"id": "flux-1-schnell-fp8",
+			"name": "FLUX.1 [schnell] FP8",
+			"api": "openai-completions",
+			"provider": "fireworks",
+			"baseUrl": "https://api.fireworks.ai/inference/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": null,
+			"maxTokens": null,
+			"supportsTools": false,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				],
+				"effortMap": {
+					"minimal": "none"
+				}
+			}
+		},
 		"glm-5": {
 			"id": "glm-5",
 			"name": "GLM-5",
@@ -13783,6 +13816,26 @@
 				]
 			}
 		},
+		"gpt-oss-20b": {
+			"id": "gpt-oss-20b",
+			"name": "OpenAI gpt-oss-20b",
+			"api": "openai-completions",
+			"provider": "fireworks",
+			"baseUrl": "https://api.fireworks.ai/inference/v1",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 65536,
+			"supportsTools": false
+		},
 		"kimi-k2.5": {
 			"id": "kimi-k2.5",
 			"name": "Kimi K2.5",
@@ -14003,6 +14056,70 @@
 				}
 			}
 		},
+		"qwen3-embedding-8b": {
+			"id": "qwen3-embedding-8b",
+			"name": "Qwen3 Embedding 8B",
+			"api": "openai-completions",
+			"provider": "fireworks",
+			"baseUrl": "https://api.fireworks.ai/inference/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 40960,
+			"maxTokens": null,
+			"supportsTools": false,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				],
+				"effortMap": {
+					"minimal": "none"
+				}
+			}
+		},
+		"qwen3-reranker-8b": {
+			"id": "qwen3-reranker-8b",
+			"name": "Qwen3 Reranker 8B",
+			"api": "openai-completions",
+			"provider": "fireworks",
+			"baseUrl": "https://api.fireworks.ai/inference/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 40960,
+			"maxTokens": null,
+			"supportsTools": false,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				],
+				"effortMap": {
+					"minimal": "none"
+				}
+			}
+		},
 		"qwen3.6-plus": {
 			"id": "qwen3.6-plus",
 			"name": "Qwen3.6 Plus",
@@ -16509,6 +16626,64 @@
 					"high"
 				]
 			}
+		},
+		"gemma-4-E2B-it": {
+			"id": "gemma-4-E2B-it",
+			"name": "Gemma 4 E2B IT",
+			"api": "google-generative-ai",
+			"provider": "google",
+			"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 8192,
+			"thinking": {
+				"mode": "budget",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"gemma-4-E4B-it": {
+			"id": "gemma-4-E4B-it",
+			"name": "Gemma 4 E4B IT",
+			"api": "google-generative-ai",
+			"provider": "google",
+			"baseUrl": "https://generativelanguage.googleapis.com/v1beta",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 131072,
+			"maxTokens": 8192,
+			"thinking": {
+				"mode": "budget",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
 		}
 	},
 	"google-antigravity": {
@@ -75419,6 +75594,34 @@
 				"requiresEffort": true
 			}
 		},
+		"qwen/qwen3-asr-flash": {
+			"id": "qwen/qwen3-asr-flash",
+			"name": "Qwen3-ASR-Flash",
+			"api": "openai-completions",
+			"provider": "zenmux",
+			"baseUrl": "https://zenmux.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": null,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
 		"qwen/qwen3-coder": {
 			"id": "qwen/qwen3-coder",
 			"name": "Qwen3-Coder",

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

@@ -1160,6 +1160,7 @@ function mapFireworksControlPlaneModel(
 ): ModelSpec<"openai-completions"> {
 	const name = toModelName(record.displayName, reference?.name ?? publicModelId);
 	const supportsImage = toBoolean(record.supportsImageInput) === true;
+	const supportsTools = toBoolean(record.supportsTools);
 	const contextWindow = toPositiveNumber(record.contextLength, reference?.contextWindow ?? null);
 	// The control plane reports no max-output budget; default the Kimi family to
 	// its published cap, everyone else to the discovery fallback, then clamp.
@@ -1192,6 +1193,7 @@ function mapFireworksControlPlaneModel(
 		input: supportsImage ? ["text", "image"] : (reference?.input ?? ["text"]),
 		contextWindow,
 		maxTokens,
+		...(supportsTools === false ? { supportsTools: false } : {}),
 	};
 	return stripFireworksDeepSeekThinkingToggle(model, publicModelId);
 }
@@ -1240,7 +1242,6 @@ async function fetchFireworksServerlessModels(options: {
 			if (!isRecord(entry)) continue;
 			const record = entry as FireworksControlPlaneModel;
 			if (toBoolean(record.supportsServerless) !== true) continue;
-			if (toBoolean(record.supportsTools) !== true) continue;
 			if (typeof record.state === "string" && record.state !== "READY") continue;
 			const wireName = typeof record.name === "string" ? record.name : "";
 			if (!wireName) continue;
@@ -1396,6 +1397,7 @@ function mapWaferModel(
 	const capabilities = wafer?.capabilities ?? {};
 	const reasoning = capabilities.reasoning === true;
 	const vision = capabilities.vision === true;
+	const supportsTools = toBoolean(capabilities.tools) === false ? false : undefined;
 	const contextWindow = toPositiveNumber(
 		wafer?.context_length,
 		toPositiveNumber((entry as { max_model_len?: unknown }).max_model_len, defaults.contextWindow),
@@ -1434,6 +1436,7 @@ function mapWaferModel(
 		cost,
 		contextWindow,
 		maxTokens,
+		...(supportsTools === false ? { supportsTools } : {}),
 	};
 	if (reasoning) {
 		// Wafer's `wafer.provider` envelope tells us which upstream backend serves
@@ -2928,6 +2931,7 @@ export function mapModelsDevToModels(
 				},
 				contextWindow: toPositiveNumber(m.limit?.context, desc.defaultContextWindow ?? null),
 				maxTokens: toPositiveNumber(m.limit?.output, desc.defaultMaxTokens ?? null),
+				...(m.tool_call === false ? { supportsTools: false } : {}),
 				...(desc.compat && { compat: desc.compat }),
 				...(desc.headers && { headers: { ...desc.headers } }),
 			};

package/src/types.ts

@@ -436,6 +436,13 @@ export interface Model<TApi extends Api = Api> {
 	baseUrl: string;
 	reasoning: boolean;
 	input: ("text" | "image")[];
+	/**
+	 * Native provider tool-call support. `false` is the only unsupported signal:
+	 * `true` and `undefined` both mean callers may use native tools. Catalog and
+	 * discovery sources should set this sparsely when an upstream explicitly
+	 * reports that native tool calling is unsupported.
+	 */
+	supportsTools?: boolean;
 	cost: {
 		input: number; // $/million tokens
 		output: number; // $/million tokens