PR #13317: fix(model_metadata): use /props endpoint at server root for llama.cpp

• Repository: NousResearch/hermes-agent
• Author: Linux2010
• State: open | merged: False
• Link: https://github.com/NousResearch/hermes-agent/pull/13317

Description (problem / solution / changelog)

What broke

When using llama.cpp as a provider, Hermes requested /v1/props endpoint which returned 404 because llama.cpp exposes /props at server root (not under /v1 prefix per httplib routes). Users saw 404 errors in llama-server logs.

Root cause

The comment incorrectly stated "llama.cpp exposes /v1/props (older builds used /props)". Actually, per llama.cpp's httplib routes (server.cpp line 174: ctx_http.get("/props", ...)), /props is at server root. The endpoint order was reversed: /v1/props was tried before /props.

Why this fix is minimal

• Only changes endpoint order: try /props first (server root), then /v1/props as fallback
• Strips /v1 prefix from base_url to get server root for /props request
• Preserves fallback for alternative builds/configs that might use /v1 path
• No changes to response body parsing or other server type detection

What I tested

• Added regression tests for /props endpoint detection
• Tests verify correct URL construction with /v1 prefix stripping
• Tests cover fallback to /v1/props when /props returns 404

What I intentionally did not change

• Response body parsing (default_generation_settings check unchanged)
• Other server type detection (LM Studio, Ollama, vLLM unchanged)
• Error handling and fallback logic structure

Fixes #13091

Changed files

• agent/model_metadata.py (modified, +9/-6)
• tests/agent/test_model_metadata_local_ctx.py (modified, +84/-0)