fix(nemo-relay): align adaptive config with tool_parallelism mode

[mnajafian-nv]

What does this PR do?

Aligns the bundled observability/nemo_relay plugin with the current NeMo Relay adaptive config shape.

Before this change, Hermes adaptive examples and tests still used a legacy top-level adaptive mode field. NeMo Relay's current adaptive config contract, including the 0.4 runtime line, nests that setting under tool_parallelism.mode.

This change makes Hermes prefer tool_parallelism.mode when reading adaptive config, keeps the older top-level mode as a compatibility fallback, and updates the README/tests to use the current config shape.

Execution control flow is unchanged. This PR aligns adaptive config parsing, docs, tests, and the default emitted mode metadata with the current NeMo Relay adaptive config vocabulary.

Related Issue

No GitHub issue filed.

Type of Change

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

Changes Made

• Updated plugins/observability/nemo_relay/__init__.py to prefer components.config.tool_parallelism.mode, while preserving legacy top-level components.config.mode as a fallback.
• Updated plugins/observability/nemo_relay/README.md adaptive examples from top-level mode = "route" to [components.config.tool_parallelism] mode = "observe_only".
• Clarified that the adaptive example requires a NeMo Relay runtime that supports [components.config.tool_parallelism].
• Updated tests/plugins/test_nemo_relay_plugin.py coverage for the current nested config shape, unset-mode default, legacy fallback, and nested-over-legacy precedence.

How to Test

1. Run the focused plugin test:

   scripts/run_tests.sh tests/plugins/test_nemo_relay_plugin.py -- -q

2. Run the broader plugin suite:

   scripts/run_tests.sh tests/plugins -- -q

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: macOS

Documentation & Housekeeping

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

Screenshots / Logs

$ scripts/run_tests.sh tests/plugins -- -q

=== Summary: 36 files, 1084 tests passed, 0 failed in 23.8s ===