feat(cross-cutting): added multi-syntax in-band tool-call support for runtime tool conversion

- Added optional Agent and SDK tool-call syntax controls (`toolCallSyntax`, `PI_OWNED_TOOLS`) for owned calls. - Added in-band grammar scanners and renderers for Anthropic, DeepSeek, GLM, Hermes, Kimi, PI, and Qwen3. - Added supportsTools propagation and model schema updates to route unsupported models to fallback syntax. - Replaced stream-markup parsing with syntax-specific in-band scanners and event conversion.
2026-06-15 06:44:54 +02:00
parent 907bc9979e
commit fbba331f8a
66 changed files with 7528 additions and 543 deletions
@@ -130,11 +130,13 @@ export function mergeDiscoveredModel<TApi extends Api>(
 	providerOverride?: Pick<ProviderOverride, "baseUrl" | "headers" | "transport">,
 ): Model<TApi> {
 	if (existing) {
+		const supportsTools = model.supportsTools ?? existing.supportsTools;
 		return buildModel({
 			...model,
 			baseUrl: providerOverride?.baseUrl ?? model.baseUrl ?? existing.baseUrl,
 			headers: existing.headers ? { ...existing.headers, ...model.headers } : model.headers,
 			transport: providerOverride?.transport ?? existing.transport ?? model.transport,
+			...(supportsTools !== undefined ? { supportsTools } : {}),
 			compat: model.compatConfig,
 		} as ModelSpec<TApi>);
 	}
@@ -370,6 +372,7 @@ interface ModelPatch {
 	reasoning?: boolean;
 	thinking?: ThinkingConfig;
 	input?: ("text" | "image")[];
+	supportsTools?: boolean;
 	cost?: Partial<Model<Api>["cost"]>;
 	contextWindow?: number;
 	maxTokens?: number;
@@ -395,6 +398,7 @@ function applyModelPatch(base: Model<Api>, patch: ModelPatch, transport: ModelTr
 	if (patch.reasoning !== undefined) result.reasoning = patch.reasoning;
 	if (patch.thinking !== undefined) result.thinking = patch.thinking;
 	if (patch.input !== undefined) result.input = patch.input;
+	if (patch.supportsTools !== undefined) result.supportsTools = patch.supportsTools;
 	if (patch.contextWindow !== undefined) result.contextWindow = patch.contextWindow;
 	if (patch.maxTokens !== undefined) result.maxTokens = patch.maxTokens;
 	if (patch.omitMaxOutputTokens !== undefined) result.omitMaxOutputTokens = patch.omitMaxOutputTokens;
@@ -506,6 +510,7 @@ function buildCustomModelOverlay(
 		reasoning: modelDef.reasoning,
 		thinking: modelDef.thinking,
 		input: modelDef.input,
+		supportsTools: modelDef.supportsTools,
 		cost: modelDef.cost,
 		contextWindow: modelDef.contextWindow,
 		maxTokens: modelDef.maxTokens,
@@ -535,6 +540,7 @@ function finalizeCustomModel(model: CustomModelOverlay, options: CustomModelBuil
 		reference?.cost ??
 		(options.useDefaults ? { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 } : undefined);
 	const input = resolvedModel.input ?? reference?.input ?? (options.useDefaults ? ["text"] : undefined);
+	const supportsTools = resolvedModel.supportsTools ?? reference?.supportsTools;
 	return buildModel({
 		id: resolvedModel.id,
 		name: resolvedModel.name ?? (options.useDefaults ? resolvedModel.id : undefined),
@@ -544,6 +550,7 @@ function finalizeCustomModel(model: CustomModelOverlay, options: CustomModelBuil
 		reasoning: resolvedModel.reasoning ?? reference?.reasoning ?? (options.useDefaults ? false : undefined),
 		thinking: resolvedModel.thinking ?? reference?.thinking,
 		input: input as ("text" | "image")[],
+		...(supportsTools !== undefined ? { supportsTools } : {}),
 		cost,
 		contextWindow: resolvedModel.contextWindow ?? reference?.contextWindow ?? (options.useDefaults ? 128000 : null),
 		maxTokens: resolvedModel.maxTokens ?? reference?.maxTokens ?? (options.useDefaults ? 16384 : null),
@@ -878,10 +885,12 @@ export class ModelRegistry {
 	#mergeResolvedModels(baseModels: Model<Api>[], replacementModels: Model<Api>[]): Model<Api>[] {
 		return mergeByModelKey(baseModels, replacementModels, (existing, replacementModel) => {
 			if (!existing) return replacementModel;
+			const supportsTools = replacementModel.supportsTools ?? existing.supportsTools;
 			return {
 				...replacementModel,
 				contextWindow: replacementModel.contextWindow ?? existing.contextWindow,
 				maxTokens: replacementModel.maxTokens ?? existing.maxTokens,
+				...(supportsTools !== undefined ? { supportsTools } : {}),
 			};
 		});
 	}
@@ -2205,6 +2214,7 @@ export interface ProviderConfigInput {
 		reasoning: boolean;
 		thinking?: ThinkingConfig;
 		input: ("text" | "image")[];
+		supportsTools?: boolean;
 		cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
 		contextWindow: number;
 		maxTokens: number;
@@ -133,6 +133,7 @@ const ModelDefinitionSchema = z.object({
 	reasoning: z.boolean().optional(),
 	thinking: ModelThinkingSchema.optional(),
 	input: z.array(z.enum(["text", "image"])).optional(),
+	supportsTools: z.boolean().optional(),
 	cost: z
 		.object({
 			input: z.number(),
@@ -155,6 +156,7 @@ export const ModelOverrideSchema = z.object({
 	reasoning: z.boolean().optional(),
 	thinking: ModelThinkingSchema.optional(),
 	input: z.array(z.enum(["text", "image"])).optional(),
+	supportsTools: z.boolean().optional(),
 	cost: z
 		.object({
 			input: z.number().optional(),
@@ -17,6 +17,7 @@ export interface ProviderValidationModel {
 	id: string;
 	api?: Api;
 	contextWindow?: number;
+	supportsTools?: boolean;
 	maxTokens?: number;
 }

@@ -1719,6 +1719,48 @@ export const SETTINGS_SCHEMA = {
 		},
 	},

+	"tools.format": {
+		type: "enum",
+		values: [
+			"auto",
+			"native",
+			"glm",
+			"hermes",
+			"kimi",
+			"xml",
+			"anthropic",
+			"deepseek",
+			"harmony",
+			"pi",
+			"qwen3",
+		] as const,
+		default: "auto",
+		ui: {
+			tab: "context",
+			group: "Experimental",
+			label: "Tool Call Format",
+			description:
+				"Controls how tools are exposed to the model. Auto uses native tool calls unless the selected model is marked as not supporting tools, then falls back to GLM-style in-band tool calls. Native forces provider-native tools; the other values force the named in-band syntax. Applies on session start.",
+			options: [
+				{
+					value: "auto",
+					label: "Auto",
+					description: "Use native tool calls unless the model is known not to support them.",
+				},
+				{ value: "native", label: "Native", description: "Use provider-native tool calls." },
+				{ value: "glm", label: "GLM", description: "Use GLM-style in-band tool calls." },
+				{ value: "hermes", label: "Hermes", description: "Use Hermes-style in-band tool calls." },
+				{ value: "kimi", label: "Kimi", description: "Use Kimi-style in-band tool calls." },
+				{ value: "xml", label: "XML", description: "Use generic XML in-band tool calls." },
+				{ value: "anthropic", label: "Anthropic", description: "Use Anthropic-style in-band tool calls." },
+				{ value: "deepseek", label: "DeepSeek", description: "Use DeepSeek-style in-band tool calls." },
+				{ value: "harmony", label: "Harmony", description: "Use Harmony-style in-band tool calls." },
+				{ value: "pi", label: "Pi", description: "Use Pi-style in-band tool calls." },
+				{ value: "qwen3", label: "Qwen3", description: "Use Qwen3-style in-band tool calls." },
+			],
+		},
+	},
+
 	"snapcompact.shape": {
 		type: "enum",
 		values: ["auto", ...SHAPE_VARIANT_NAMES] as const,
@@ -16,6 +16,7 @@ import {
 	type SimpleStreamOptions,
 	streamSimple,
 } from "@oh-my-pi/pi-ai";
+import type { ToolCallSyntax } from "@oh-my-pi/pi-ai/grammar";
 import {
 	getOpenAICodexTransportDetails,
 	prewarmOpenAICodexResponses,
@@ -550,6 +551,17 @@ export interface CreateAgentSessionResult {
 	eventBus: EventBus;
 }

+export type ToolCallFormat = "auto" | "native" | ToolCallSyntax;
+
+export function resolveToolCallSyntax(
+	format: ToolCallFormat,
+	model: Pick<Model, "supportsTools"> | undefined,
+): ToolCallSyntax | undefined {
+	if (format === "native") return undefined;
+	if (format === "auto") return model?.supportsTools === false ? "glm" : undefined;
+	return format;
+}
+
 // Re-exports

 export type { PromptTemplate } from "./config/prompt-templates";
@@ -2489,6 +2501,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 				return result;
 			},
 			intentTracing: !!intentField,
+			toolCallSyntax: resolveToolCallSyntax(settings.get("tools.format"), model),
 			getToolChoice: () => session?.nextToolChoice(),
 			telemetry: options.telemetry,
 			appendOnlyContext: model