@oh-my-pi/pi-ai 8.2.0 → 8.2.2

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "8.2.0",
+	"version": "8.2.2",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./src/index.ts",
@@ -56,7 +56,7 @@
 		"test": "bun test"
 	},
 	"dependencies": {
-		"@oh-my-pi/pi-utils": "8.2.0",
+		"@oh-my-pi/pi-utils": "8.2.2",
 		"@anthropic-ai/sdk": "^0.71.2",
 		"@aws-sdk/client-bedrock-runtime": "^3.975.0",
 		"@bufbuild/protobuf": "^2.10.2",

package/src/models.generated.ts

@@ -4614,7 +4614,7 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.09,
-				output: 0.44999999999999996,
+				output: 0.39999999999999997,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -5296,7 +5296,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.024999999999999998,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 8192,
@@ -5313,7 +5313,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.024999999999999998,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 8192,
@@ -5347,7 +5347,7 @@ export const MODELS = {
 				input: 0.3,
 				output: 2.5,
 				cacheRead: 0.03,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5364,7 +5364,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.01,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5381,7 +5381,7 @@ export const MODELS = {
 				input: 0.09999999999999999,
 				output: 0.39999999999999997,
 				cacheRead: 0.01,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5398,7 +5398,7 @@ export const MODELS = {
 				input: 0.3,
 				output: 2.5,
 				cacheRead: 0.03,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -5466,7 +5466,7 @@ export const MODELS = {
 				input: 0.5,
 				output: 3,
 				cacheRead: 0.049999999999999996,
-				cacheWrite: 0.08333333333333333,
+				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
@@ -10927,9 +10927,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -10945,9 +10945,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.2,
-				output: 1.1,
-				cacheRead: 0.03,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -10981,8 +10981,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.6,
-				output: 1.8,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -10999,9 +10999,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 204800,
@@ -11017,8 +11017,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.3,
-				output: 0.9,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -11035,13 +11035,31 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0.11,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-4.7-flash": {
+			id: "glm-4.7-flash",
+			name: "GLM-4.7-Flash",
+			api: "openai-completions",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 } as const;

package/src/providers/openai-responses.ts

@@ -240,6 +240,13 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 						});
 					}
 				}
+				// Handle function call arguments done (some providers send this instead of deltas)
+				else if (event.type === "response.function_call_arguments.done") {
+					if (currentItem?.type === "function_call" && currentBlock?.type === "toolCall") {
+						currentBlock.partialJson = event.arguments;
+						currentBlock.arguments = parseStreamingJson(currentBlock.partialJson);
+					}
+				}
 				// Handle output item completion
 				else if (event.type === "response.output_item.done") {
 					const item = event.item;
@@ -265,13 +272,17 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 						});
 						currentBlock = null;
 					} else if (item.type === "function_call") {
+						const args =
+							currentBlock?.type === "toolCall" && currentBlock.partialJson
+								? JSON.parse(currentBlock.partialJson)
+								: JSON.parse(item.arguments);
 						const toolCall: ToolCall = {
 							type: "toolCall",
 							id: `${item.call_id}|${item.id}`,
 							name: item.name,
-							arguments: JSON.parse(item.arguments),
+							arguments: args,
 						};
-
+						currentBlock = null;
 						stream.push({ type: "toolcall_end", contentIndex: blockIndex(), toolCall, partial: output });
 					}
 				}