fix(cli): raise model picker cap from 50 to 200 to surface all provider models

[liuhao1024]

What does this PR do?

Raises the model picker cap from 50 to 200 across all picker entry points, so providers with 100+ models (like NVIDIA NIM) surface all available models instead of only the first 50 alphabetically.

Related Issue

Fixes #42270

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)

Changes Made

• hermes_cli/model_switch.py: Raised max_models default from 8 to 200 in list_authenticated_providers() and list_picker_providers(); updated prewarm caller from 50 to 200
• hermes_cli/inventory.py: Raised build_models_payload() default from 50 to 200
• hermes_cli/web_server.py: Updated both /api/model/options callers from 50 to 200

How to Test

1. Authenticate with a provider that has 100+ models (e.g., NVIDIA NIM, OpenRouter)
2. Run hermes --tui and type /model to open the picker
3. Select the provider — verify all models are listed (not just 50)
4. Check the Desktop model picker — same behavior
5. Verify total_models count in the API response matches the actual model count

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, 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

Code Intelligence

• Analyzed: model_switch.py::list_authenticated_providers, inventory.py::build_models_payload
• Blast radius: LOW — numeric constant change only, no control flow changes
• Related patterns: cached_provider_model_ids() provides the full model list; total_models field already reports real count

[tonydwb]

Code Review Summary

Verdict: Approved

Configuration

• Raises the model picker cap from 50 to 200 across all call sites: build_models_payload(), list_authenticated_providers(), list_picker_providers(), and get_recommended_default_model().

Reason

• Some providers now offer 100+ models. A cap of 50 was too restrictive and was preventing all available models from appearing in the picker.

Looks Good

• Simple config change, no risk.

---

Reviewed by Hermes Agent

[teknium1]

Fixed on main via PR #48611 — the interactive model pickers no longer cap at 50 models; large provider catalogs are fully searchable.

This was one of several PRs targeting the same picker cap. We merged @islam666's #48297 as the implementation (cleanest scope — it correctly keeps the Telegram/Discord inline-keyboard cap, which genuinely needs a bound) plus a follow-up tightening max_models=0 semantics and a regression test. Closing this as a duplicate — thanks for the contribution and for flagging the issue.

#48611