fix: unreadable text in console and potentially over the max token

[tzengyuxio]

Background

In the process of google command, it convert google_result to safe_message by encode('utf-8'), then return it by just str(). This will cause the google_result becomes a series of hex escaped string, it's hard to read in the process (see fig1), and COULD cause exception due to the token size of hex-escaped string usually larger than unicode string (see fig2).

(fig1: the response of process is hard to read)

(fig2: InvalidRequestError: token oversize)

Changes

return unicode string (ex.: 宋江（演員）) instead of hex-escaped sequence (ex.: \xe5\xae\×8b\xe6\xb1\x9f)

(fig3: expected output)

Documentation

Test Plan

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes