[FEATURE]: integrate DeBERTa-base LocalLLMClient for EDIS fallacy detection

## Summary
Proposes integrating a fine-tuned DeBERTa-base model as the
LocalLLMClient fallback implementation for EDIS signal extraction.

## Why DeBERTa over DistilBERT
DeBERTa-base significantly outperforms DistilBERT on multi-label
fallacy classification due to its disentangled attention mechanism
which handles nuanced reasoning language better.

## Model Details
- Base model: microsoft/deberta-base
- Training data: 9,400 debate-style examples
- Fallacy classes: 8
- Validation F1-macro: 1.0
- Hard OOD test: 13/15
- Model: https://huggingface.co/RowdyI7er/DebateLLM

## Integration
The model implements the LocalLLMClient interface described
in the EDIS architecture — providing a zero-API-cost fallback
for fallacy detection without any changes to the existing
debate flow or Elo pipeline.

### Additional Context

_No response_

### Code of Conduct

- [x] I have joined the [Discord server](https://discord.gg/hjUhu33uAn) and will post updates there
- [x] I have searched existing issues to avoid duplicates

Start by locating the LocalLLMClient interface and the EDIS signal-extraction path described in the issue. Check how the fallback is selected and verify that DeBERTa-based fallacy detection works without changing the existing debate flow or Elo pipeline, covering all 8 fallacy classes.

Written by the indexing model from the issue text.