fix(model): normalize native provider-prefixed model ids

[bobashopcashier]

What does this PR do?

Normalizes native provider-prefixed model IDs only when the prefix matches the active Hermes provider, and applies that same rule everywhere Hermes can send a direct-provider model unchanged: CLI startup, AIAgent runtime initialization, fallback activation, and auxiliary routing (including vision/main-provider resolution).

Related Issue

Fixes #6211
Supersedes the narrower direct-provider overlap in #6224 by covering both main runtime and auxiliary routing with the same active-provider-only rule
Related: #6242
Context: #5910 is already fixed separately in the current codebase
Separate env/pairing hardening is tracked in PR #6956

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

• kept hermes_cli/model_normalize.py as the shared normalization source for active-provider-only prefix stripping
• applied the same normalization outcome in direct auxiliary provider routing so resolve_provider_client() returns the provider-native model slug it will actually send
• updated fallback activation in run_agent.py to consume the resolved normalized model instead of keeping the raw prefixed config value
• added focused regression coverage for matching-provider stripping, non-matching prefix passthrough, aggregator preservation, vision/main-provider routing, and fallback activation

How to Test

1. Run /Users/kennyxie/Documents/Code/clawspace/hermes-agent/.venv/bin/python -m pytest tests/hermes_cli/test_model_normalize.py -q
2. Run /Users/kennyxie/Documents/Code/clawspace/hermes-agent/.venv/bin/python -m pytest tests/agent/test_auxiliary_named_custom_providers.py -q
3. Run /Users/kennyxie/Documents/Code/clawspace/hermes-agent/.venv/bin/python -m pytest tests/run_agent/test_run_agent.py::TestProviderModelNormalization tests/run_agent/test_fallback_model.py::TestTryActivateFallback -q
4. Configure a direct provider with a matching prefixed model like zai/glm-5.1 and verify Hermes sends the native slug glm-5.1
5. Verify unrelated slash-bearing IDs such as aggregator slugs or non-matching prefixes remain unchanged

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 26.4

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 — or N/A

Screenshots / Logs

• /Users/kennyxie/Documents/Code/clawspace/hermes-agent/.venv/bin/python -m pytest tests/hermes_cli/test_model_normalize.py tests/agent/test_auxiliary_named_custom_providers.py tests/run_agent/test_run_agent.py::TestProviderModelNormalization tests/run_agent/test_fallback_model.py::TestTryActivateFallback -q → 67 passed

[teknium1]

Merged via PR #7187. All 3 commits cherry-picked with your authorship preserved. Thorough fix for the prefix normalization — thanks!