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-completions.ts

@@ -8,6 +8,7 @@ import type {
 	ChatCompletionMessageParam,
 } from "openai/resources/chat/completions.js";
 import { AssistantMessageEventStream } from "../event-stream.js";
+import { parseStreamingJson } from "../json-parse.js";
 import { calculateCost } from "../models.js";
 import type {
 	AssistantMessage,
@@ -210,6 +211,7 @@ export const streamOpenAICompletions: StreamFunction<"openai-completions"> = (
 								if (toolCall.function?.arguments) {
 									delta = toolCall.function.arguments;
 									currentBlock.partialArgs += toolCall.function.arguments;
+									currentBlock.arguments = parseStreamingJson(currentBlock.partialArgs);
 								}
 								stream.push({
 									type: "toolcall_delta",