feat(ai): add partial JSON parsing for streaming tool calls

- Added partial-json package for parsing incomplete JSON during streaming
- Tool call arguments now contain partially parsed JSON during toolcall_delta events
- Enables progressive UI updates (e.g., showing file paths before content is complete)
- Arguments are always valid objects (minimum empty {}), never undefined
- Full validation still occurs at toolcall_end when arguments are complete
- Updated all providers (Anthropic, OpenAI Completions/Responses) to use parseStreamingJson
- Added comprehensive documentation and examples in README
- Added test to verify arguments are always defined during streaming

packages/ai/src/providers/openai-responses.ts

@@ -11,6 +11,7 @@ import type {
 	ResponseReasoningItem,
 } from "openai/resources/responses/responses.js";
 import { AssistantMessageEventStream } from "../event-stream.js";
+import { parseStreamingJson } from "../json-parse.js";
 import { calculateCost } from "../models.js";
 import type {
 	Api,
@@ -194,12 +195,7 @@ export const streamOpenAIResponses: StreamFunction<"openai-responses"> = (
 						currentBlock.type === "toolCall"
 					) {
 						currentBlock.partialJson += event.delta;
-						try {
-							const args = JSON.parse(currentBlock.partialJson);
-							currentBlock.arguments = args;
-						} catch {
-							// Ignore JSON parse errors - the JSON might be incomplete
-						}
+						currentBlock.arguments = parseStreamingJson(currentBlock.partialJson);
 						stream.push({
 							type: "toolcall_delta",
 							contentIndex: blockIndex(),