fix: Preserve tool calls for LLMRails tool rails

[JashG]

Description

This PR enables tool call guardrails to work when checking a tool-call message directly (as opposed to when the library itself generates the tool call).

Desired use case:
Supporting tool call guardrails from agentic workflows where we don't rely on generate_async to orchestrate the LLMCalls end-to-end. Example flow:

• An assistant response generates tool_calls
• Before executing the tools, use the library to inspect the tool call name/args
• After the agent executes the tools out-of-band, use the library to inspect the results

Current issue:
In LLMRails, assistant messages were treated as plain text output and removed from the message history. If that assistant message contained tool_calls, the tool calls never became BotToolCalls events, so tool output rails could be skipped.

This change preserves assistant tool_calls long enough for the existing tool-rail pipeline to see them, and updates logging so tool input/output rails appear correctly in the generation log.

Related Issue(s)

Verification

AI Assistance

• No AI tools were used.
• AI tools were used; a human reviewed and can explain every change (tool: GPT 5.5 via Cursor).

Checklist

• I've read the CONTRIBUTING guidelines.
• This PR links to a triaged issue assigned to me.
• My PR title follows the project commit convention.
• I've updated the documentation if applicable.
• I've added tests if applicable.
• I've noted any verification beyond CI and any checks I couldn't run.
• I did not update generated changelog files manually.
• I addressed all CodeRabbit, Greptile, and other review comments, or replied with why no change is needed.
• @mentions of the person or team responsible for reviewing proposed changes.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!