[fix] normalize provider-specific tool messages for cross-provider sessions

[hztBUAA]

Summary

Fixes cross-provider session incompatibility where tool messages saved by one provider (e.g., Gemini) fail when loaded by another provider (e.g., OpenAI). Providers serialize tool messages differently, causing deserialization errors when sessions are continued with a different model.

The fix adds a normalization layer that converts provider-specific tool message formats to a common intermediate format during session loading.

Fixes #5713

Type of change

• Bug fix (non-breaking change which fixes an issue)

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my code
• I have added tests that prove my fix is effective
• New and existing unit tests pass locally with my changes
• I have run ./scripts/format.sh and ./scripts/validate.sh

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[hztBUAA]

Thanks for the review and feedback. I am following up on this PR now and will either push the requested changes or reply point-by-point shortly.

[hztBUAA]

Quick follow-up: I am reviewing the feedback and will update this PR shortly.

[harshsinha03]

Hey! @hztBUAA Closing in favor of #6658 which provides a more comprehensive fix for the same issue, thank you for the contribution!

Thank you for using Agno!