What does this PR do?

Fixes a provider-selection persistence bug in hermes setup model.

Problem:

• If a user had custom selected and then changed models/providers in setup, Hermes could keep
  HERMES_INFERENCE_PROVIDER=custom, causing runtime/provider mismatch.

What this changes:

• Normalizes Keep current to an explicit provider before model selection.
• Persists HERMES_INFERENCE_PROVIDER in provider/model flows (including OpenAI Codex and custom endpoint flows).
• Prevents setup from silently falling through to the wrong provider behavior.

Why this approach:

• Fixes the issue at the source (setup model flow) instead of requiring manual .env edits.

Related Issue

N/A (no issue opened)

Fixes #

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 provider persistence and selection logic in:
  • hermes_cli/setup.py
  • hermes_cli/main.py
• Added regression tests:
  • tests/test_setup_model_provider.py
    • test_setup_keep_current_custom_does_not_fall_through
    • test_setup_switch_custom_to_codex_updates_provider

How to Test

1. Start from a custom endpoint setup (HERMES_INFERENCE_PROVIDER=custom, OPENAI_BASE_URL set).
2. Run hermes setup model, select Login with OpenAI Codex, choose a Codex model.
3. Verify:
   • HERMES_INFERENCE_PROVIDER=openai-codex
   • OPENAI_BASE_URL is cleared
   • Hermes runs using Codex provider without custom-provider mismatch.

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: Windows 11 (WSL2 Ubuntu)

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A (N/A)
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A (N/A)
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A (N/A)
• I've considered cross-platform impact (Windows, macOS) per the [compatibility guide](https://github.com/
  NousResearch/hermes-agent/blob/main/CONTRIBUTING.md#cross-platform-compatibility) — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A (N/A)

Screenshots / Logs

Targeted regression tests:

• pytest -q tests/test_setup_model_provider.py
• Result: 2 passed