feat: Add Agent QA Pipeline template

[Samir-atra]

Description

This PR implements the Agent QA Pipeline template as proposed in Issue #4286 - a goal-driven agent that performs quality assessment on other Hive agents.

What it does

The Agent QA Pipeline performs comprehensive quality assessment on other Hive agents through:

• Static Analysis: Topology, patterns, edge consistency, node quality
• Functional Testing: Spec-level correctness validation
• Resilience Testing: Error handling and recovery patterns
• Security Auditing: OWASP LLM Top 10 checks

The pipeline produces a PASS / CONDITIONAL / FAIL verdict with a score (0-100) and letter grade (A-F), along with actionable fix suggestions and iterative re-test cycles.

Graph Architecture

intake → load-agent → static-analysis → generate-test-plan → review-test-plan (HITL pause)
  → [fan-out: run-functional | run-resilience | run-security]
  → [fan-in: aggregate-results]
  → judge-quality
    → PASS/FAIL → generate-report → deliver-report
    → CONDITIONAL → request-fixes → load-agent (feedback cycle, max 3x)

Framework Features Demonstrated

This template is the first to demonstrate these features (all at 0% template coverage before this PR):

Feature	Implementation	Notes
Fan-out / fan-in	3 parallel test runners → aggregate-results	Demonstrates parallel execution
on_failure edge	load-agent → generate-report	Graceful error handling
HITL pause_nodes	review-test-plan	User approves test plan
Conditional routing	judge-quality → PASS/FAIL vs CONDITIONAL	Multi-path routing
Feedback loop with max_node_visits	request-fixes → load-agent (max 3)	Prevents infinite loops
nullable_output_keys	load_errors, test_preferences, fix_suggestions	Optional outputs

Type of Change

• New feature (non-breaking change that adds functionality)

Related Issues

Resolves #4286

Changes Made

• examples/templates/agent_qa_pipeline/agent.py: Main agent class with 13 nodes, 17 edges
• examples/templates/agent_qa_pipeline/agent.json: Declarative agent spec
• examples/templates/agent_qa_pipeline/config.py: Configuration class
• examples/templates/agent_qa_pipeline/init.py: Module exports
• examples/templates/agent_qa_pipeline/main.py: Entry point
• examples/templates/agent_qa_pipeline/nodes/init.py: All 13 node definitions
• examples/templates/agent_qa_pipeline/tests/test_structure.py: 27 comprehensive tests
• examples/templates/agent_qa_pipeline/tests/conftest.py: Pytest configuration

Testing

All 27 tests pass:

cd core && uv run pytest ../examples/templates/agent_qa_pipeline/tests/ -v
# Output: 27 passed in 4.31s

• Unit tests pass
• Graph validation passes (0 errors, 0 warnings)
• Manual testing performed

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• My changes generate no new warnings
• I have added tests that prove my feature works
• New and existing unit tests pass locally with my changes

Implementation Notes

Phase 1 (Works Today)

• Static analysis + spec-level LLM reasoning for all 3 test categories
• All graph patterns work with current framework
• Useful as-is for structural validation

Future Enhancements (Framework Proposals)

• Proposal 1: Sub-Graph Execution Node - for actual runtime testing
• Proposal 2: Tool Interception/Mocking - for resilience testing
• Proposal 3: Execution Snapshot & Comparison - for regression testing

Each phase is independently valuable and can be implemented incrementally.

[github-actions]

PR Requirements Warning

This PR does not meet the contribution requirements.
If the issue is not fixed within ~24 hours, it may be automatically closed.

PR Author: @Samir-atra
Found issues: #4286 (assignees: none)
Problem: The PR author must be assigned to the linked issue.

To fix:

1. Assign yourself (@Samir-atra) to one of the linked issues
2. Re-open this PR

Exception: To bypass this requirement, you can:

• Add the micro-fix label or include micro-fix in your PR title for trivial fixes
• Add the documentation label or include doc/docs in your PR title for documentation changes

Micro-fix requirements (must meet ALL):

Qualifies	Disqualifies
< 20 lines changed	Any functional bug fix
Typos & Documentation & Linting	Refactoring for "clean code"
No logic/API/DB changes	New features (even tiny ones)

Why is this required? See #472 for details.