What does this PR do?

Fix delegation so delegate_task consistently applies model/provider override precedence across top-level and per-task configuration, and forwards the resolved credentials to child agents. This resolves cases where users pass model/provider but child tasks still use unintended defaults.

Also updates the tool schema and tests to document and verify the new behavior.

Related Issue

Fixes #10995

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✅ Tests (adding or improving test coverage)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

• Added optional top-level model and provider args to delegate_task in tools/delegate_tool.py.
• Applied precedence handling so delegation credentials resolve in this order:
  • task-level model/provider
  • top-level model/provider
  • delegation.model/delegation.provider from config
  • parent agent fallback
• Passed resolved per-task credentials into child construction (model, override_provider, override_base_url, override_api_key, override_api_mode) in tools/delegate_tool.py.
• Extended DELEGATE_TASK_SCHEMA with:
  • top-level model, provider
  • per-task tasks[].model, tasks[].provider
  • precedence descriptions for both levels.
• Added regression/integration coverage in tests/tools/test_delegate.py:
  • TestDelegateRequirements.test_schema_valid now checks new schema fields.
  • test_top_level_model_provider_overrides validates top-level propagation.
  • test_per_task_model_provider_override validates per-task precedence over top-level values.

How to Test

1. Run focused tests:
   • scripts/run_tests.sh tests/tools/test_delegate.py
2. Run the targeted new tests:
   • scripts/run_tests.sh -k "model_provider_override"
3. Optional: execute a delegation call manually with mixed config and task-level values and verify child creation uses task-level values where provided, then top-level values, then config fallback.

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform:

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior