#3915 This submission may cause a MCP tool execution exception, resulting in the abandonment of all tool results.

Bug description
In Spring AI 1.0.2 (with submission #3915), when the LLM attempts to call multiple tools simultaneously, if any one of the tools throws an exception (such as response too large, timeout, etc.), the entire executeToolCalls method fails to handle the exception on a per-tool basis. As a result, all tool responses — including those from successfully completed tools — are discarded.

Environment
Spring AI version: 1.0.2
Java version: 21
Additional Context

Expected behavior
Each tool call should be executed and handled independently. Even if one or more tool calls fail, the results of successfully completed tool calls should be returned to the LLM for further processing.

Related code

    public ToolExecutionResult executeToolCalls(Prompt prompt, ChatResponse chatResponse) {
        Assert.notNull(prompt, "prompt cannot be null");
        Assert.notNull(chatResponse, "chatResponse cannot be null");
        Optional<Generation> toolCallGeneration = chatResponse.getResults().stream().filter((g) -> !CollectionUtils.isEmpty(g.getOutput().getToolCalls())).findFirst();
        if (toolCallGeneration.isEmpty()) {
            throw new IllegalStateException("No tool call requested by the chat model");
        } else {
            AssistantMessage assistantMessage = ((Generation)toolCallGeneration.get()).getOutput();
            ToolContext toolContext = buildToolContext(prompt, assistantMessage);
            InternalToolExecutionResult internalToolExecutionResult = this.executeToolCall(prompt, assistantMessage, toolContext);
            List<Message> conversationHistory = this.buildConversationHistoryAfterToolExecution(prompt.getInstructions(), assistantMessage, internalToolExecutionResult.toolResponseMessage());
            return ToolExecutionResult.builder().conversationHistory(conversationHistory).returnDirect(internalToolExecutionResult.returnDirect()).build();
        }

Start at executeToolCalls and trace its call to executeToolCall, using the issue's example as the reproduction scenario. Inspect how multiple tool calls and exceptions are handled, then verify that a failing call does not discard responses from successful calls and that those responses are returned to the LLM.