feat(ai): support message-anchored tool loading (#6474)

This adds cache-friendly dynamic tool loading anchored to tool results. Purely additive active-tool changes are recorded with `addedToolNames`, allowing supported Anthropic and OpenAI Responses models to load tool definitions at the point they become available instead of placing them in the cached prompt prefix.

It retains safe fallback behavior for unsupported models and non-additive changes but it will wipe caches.

packages/agent/src/agent-loop.ts

@@ -734,6 +734,7 @@ async function finalizeExecutedToolCall(
 			);
 			if (afterResult) {
 				result = {
+					...result,
 					content: afterResult.content ?? result.content,
 					details: afterResult.details ?? result.details,
 					terminate: afterResult.terminate ?? result.terminate,
@@ -779,6 +780,7 @@ function createToolResultMessage(finalized: FinalizedToolCallOutcome): ToolResul
 		// so the null never enters session history or provider payloads.
 		content: finalized.result.content ?? [],
 		details: finalized.result.details,
+		...(finalized.result.addedToolNames?.length ? { addedToolNames: finalized.result.addedToolNames } : {}),
 		isError: finalized.isError,
 		timestamp: Date.now(),
 	};

packages/agent/src/types.ts

@@ -352,6 +352,8 @@ export interface AgentToolResult<T> {
 	content: (TextContent | ImageContent)[];
 	/** Arbitrary structured details for logs or UI rendering. */
 	details: T;
+	/** Names of tools introduced by this result and available from this transcript point onward. */
+	addedToolNames?: string[];
 	/**
 	 * Hint that the agent should stop after the current tool batch.
 	 * Early termination only happens when every finalized tool result in the batch sets this to true.