Agent/Tool Parsing Fixes

[pyek-bot]

Description

Fixes the following issues:

1. When the LLM responds with empty content, then there is no actual string to be processed. This by default falls back to tool use, however in tool use block we do a .getFirst().get() assuming there is a tool use block in the response. This PR adds a simple check to avoid such NPEs. Look at [BUG] ChatAgent fails while parsing LLMOutput #4136 for more details. There is another issue where the LLM responds with tool_use but no tool use block, for this we need to raise a ticket to the bedrock team.
2. When steps returned by LLM contains a , the parsing breaks. This is due to a double conversion of json array to string and string to array. This has been fixed in this PR by directly returning the original json.
3. When tool parameters contain nested json, the extractInputParameters method fails due to expecting a Map<String, String> . This has been fixed and the exception made clearer as we fall back to string by default.

For more details look at the issues mentioned below

Related Issues

Resolves #4135
Resolves #4137
Partially resolves #4136

Check List

• New functionality includes testing.
• New functionality has been documented.
• API changes companion pull request created.
• Commits are signed per the DCO using --signoff.
• Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[codecov]

Codecov Report

❌ Patch coverage is 94.11765% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 81.85%. Comparing base (45002a7) to head (117806f).
⚠️ Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
...nsearch/ml/engine/algorithms/agent/AgentUtils.java	87.50%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@             Coverage Diff              @@
##               main    #4138      +/-   ##
============================================
+ Coverage     81.81%   81.85%   +0.03%     
- Complexity     8866     8870       +4     
============================================
  Files           762      762              
  Lines         38167    38169       +2     
  Branches       4264     4266       +2     
============================================
+ Hits          31228    31243      +15     
+ Misses         5111     5098      -13     
  Partials       1828     1828              

Flag	Coverage Δ
ml-commons	81.85% <94.11%> (+0.03%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[akolarkunnu]

LGTM