More complete DMR support

[krissetto]

With this PR the dmr provider can now support:

• Proper context length setup using max_tokens
• temperature, top_p, frequency_penalty, presence_penalty all get mapped into the proper runtime flags based on the engine in use (for now only llama.cpp mappings);
• Raw runtime flags to pass to the inference engine in use, via provider_opts:runtime_flags

Configuration example supported with these changes:

models:
  root:
    provider: dmr
    model: ai/qwen3:14B-Q6_K
    max_tokens: 32768
    temperature: 0.7
    top_p: 0.95
    frequency_penalty: 0.2
    presence_penalty: 0.1
    provider_opts:
      runtime_flags: |
        --batch-size 1024
        --ubatch-size 512

closes #71