fix(DATAGO-134114): replace hardcoded max_llm_calls_per_task with constant and increase value to 30

[cyrus2281]

What is the purpose of this change?

Replace hardcoded max LLM calls per task value with a constant to improve code consistency and maintainability.

How was this change implemented?

- Added a new constant DEFAULT_MAX_LLM_CALLS_PER_TASK in the common/constants.py file
- Replaced all hardcoded instances of the value "20" with the new constant across multiple files:
  - fix: replace hardcoded max_llm_calls_per_task with constant DEFAULT_MAX_LLM_CALLS_PER_TASK

Key Design Decisions (optional - delete if not applicable)

Using a constant makes the code more maintainable by centralizing the configuration value in one place, making future changes easier and reducing the risk of inconsistency.

How was this change tested?

• Manual testing: Verified agent behavior remains unchanged with the constant
• Unit tests: Not applicable - constant replacement only
• Integration tests: Not applicable
• Known limitations: None - direct value replacement with no functional changes

Is there anything the reviewers should focus on/be aware of?

Ensure all instances of the hardcoded value have been replaced correctly.

[github-actions]

✅ FOSSA Guard: Licensing (SolaceLabs_solace-agent-mesh) • PASSED

Compared against main (1.22.0) • 0 new, 9 total (9 in base)

Scan Report | View Details in FOSSA

[github-actions]

✅ FOSSA Guard: Vulnerability (SolaceLabs_solace-agent-mesh) • PASSED

Compared against main (1.22.0) • 0 new, 8 total (8 in base)

Scan Report | View Details in FOSSA

[Copilot]

Pull request overview

This PR aims to improve maintainability by centralizing the default “max LLM calls per task” value into a shared constant and using it as the fallback where the runtime config is read.

Changes:

• Added DEFAULT_MAX_LLM_CALLS_PER_TASK = 20 to common/constants.py.
• Replaced hardcoded 20 fallbacks for max_llm_calls_per_task with DEFAULT_MAX_LLM_CALLS_PER_TASK in agent execution paths (SAC component, structured invocation handler, and A2A request handling).

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
src/solace_agent_mesh/common/constants.py	Introduces the centralized default constant for max LLM calls per task.
src/solace_agent_mesh/agent/sac/structured_invocation/handler.py	Uses the shared constant as the get_config fallback when building RunConfig.
src/solace_agent_mesh/agent/sac/component.py	Uses the shared constant as the get_config fallback when re-triggering runs.
src/solace_agent_mesh/agent/protocol/event_handlers.py	Uses the shared constant as the get_config fallback for A2A task execution.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[sonarqube-solacecloud]

Quality Gate passed

Issues
0 New issues
0 Fixed issues
0 Accepted issues

Measures
0 Security Hotspots
100.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube

[enavitan]

looks good, wonder if we log the failures and at least try to understand where things went south, and perhaps have a follow up task to tweak prompts to reduce these failures case per case basis