add action input as parameters for tool execution in conversational agent

[jngz-es]

Description

Related Issues

Resolves #[Issue number to be closed when this PR is merged]
#3134

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.

[pyek-bot]

can actionInput be null here?

[jngz-es]

Yes.

[pyek-bot]

will it be a problem if we put actionInput as null within the params? I can see that isJson will check for null, but wondering if line 475 can cause issue

[dbwiddis]

Good catch, @pyek-bot looking at MLToolSpec we'd get here:

ml-commons/common/src/main/java/org/opensearch/ml/common/utils/StringUtils.java

Lines 109 to 118 in 5cfdc3c

	Object value = parameterObjs.get(key);
	try {
	AccessController.doPrivileged((PrivilegedExceptionAction<Void>) () -> {
	if (value instanceof String) {
	parameters.put(key, (String) value);
	} else {
	parameters.put(key, gson.toJson(value));
	}
	return null;
	});

and Gson.toJson internally uses Object.getClass() which may throw NPE...

which looks like it handles null.

[pyek-bot]

looks good, thanks for validating!

[ylwu-amzn]

@jngz-es Can you add a test case for null value ? From code https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/utils/StringUtils.java#L69, it will throw null pointer exception

[mingshl]

tests passed but failed in upload, not related to this code change. Approved.

Run actions/upload-artifact@v4
/usr/bin/docker exec  a6c6ef6ad38d2e9993d03ba2bdc50f2146f892a4a109fc9fecaf2c66802943f0 sh -c "cat /etc/*release | grep ^ID"
/__e/node[20](https://github.com/opensearch-project/ml-commons/actions/runs/11670434010/job/32954019963?pr=3200#step:8:21)/bin/node: /lib64/libm.so.6: version `GLIBC_2.27' not found (required by /__e/node20/bin/node)
/__e/node20/bin/node: /lib64/libc.so.6: version `GLIBC_2.28' not found (required by /__e/node20/bin/node)
``'

[ylwu-amzn]

action_input looks like coupled with code logic. Change to more readable name ?

[reuschling]

The changes for AgentUtils look fine, but is AgentUtils used for conversational agents? The tool parameters are build inside MLConversationalFlowAgentRunner.getToolExecuteParams(MLToolSpec toolSpec, Map<String, String> params), i.e. here. There is no AgentUtils invocation. The only invocation of AgentUtils.‎‎constructToolParams I found is inside MLChatAgentRunner.

I showed a code proposal for getToolExecuteParams at #2977 (comment), the only difference is that there is no dedicated actionInput parameter, the actionInput is the "input" entry so far, which has to be temporarily stored inside a local variable.

I would also highly recommend to add the new "action_input" parameter to flow agents (i.e. MLFlowAgentRunner.getToolExecuteParams) also. There is no use of AgentUtils too. Of course there is the possibility with parameters.previous_tool_name.output, but tool specifications should act the same independent where they should be used, whether inside flow or conversational agents.