peregrine/config/llm.yaml
pyr0ball 84eb647348 feat: LGBTQIA+ focus + Phase 2/3 audit fixes
LGBTQIA+ inclusion section in research briefs:
- user_profile.py: add candidate_lgbtq_focus bool accessor
- user.yaml.example: add candidate_lgbtq_focus flag (default false)
- company_research.py: gate new LGBTQIA+ section behind flag; section
  count now dynamic (7 base + 1 per opt-in section, max 9)
- 2_Settings.py: add "Research Brief Preferences" expander with
  checkboxes for both accessibility and LGBTQIA+ focus flags;
  mission_preferences now round-trips through save (no silent drop)

Phase 2 fixes:
- manage-vllm.sh: MODEL_DIR and VLLM_BIN now read from env vars
  (VLLM_MODELS_DIR, VLLM_BIN) with portable defaults
- search_profiles.yaml: replace personal CS/TAM/Bay Area profiles
  with a documented generic starter profile

Phase 3 fix:
- llm.yaml: rename alex-cover-writer:latest → llama3.2:3b with
  inline comment for users to substitute their fine-tuned model;
  fix model-exclusion comment

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-24 20:02:03 -08:00

66 lines
1.6 KiB
YAML

backends:
anthropic:
api_key_env: ANTHROPIC_API_KEY
enabled: false
model: claude-sonnet-4-6
type: anthropic
supports_images: true
claude_code:
api_key: any
base_url: http://localhost:3009/v1
enabled: false
model: claude-code-terminal
type: openai_compat
supports_images: true
github_copilot:
api_key: any
base_url: http://localhost:3010/v1
enabled: false
model: gpt-4o
type: openai_compat
supports_images: false
ollama:
api_key: ollama
base_url: http://localhost:11434/v1
enabled: true
model: llama3.2:3b # replace with your fine-tuned cover letter model if you have one
type: openai_compat
supports_images: false
ollama_research:
api_key: ollama
base_url: http://localhost:11434/v1
enabled: true
model: llama3.1:8b
type: openai_compat
supports_images: false
vllm:
api_key: ''
base_url: http://localhost:8000/v1
enabled: true
model: __auto__
type: openai_compat
supports_images: false
vision_service:
base_url: http://localhost:8002
enabled: false
type: vision_service
supports_images: true
fallback_order:
- ollama
- claude_code
- vllm
- github_copilot
- anthropic
research_fallback_order:
- claude_code
- vllm
- ollama_research
- github_copilot
- anthropic
vision_fallback_order:
- vision_service
- claude_code
- anthropic
# Note: 'ollama' intentionally excluded from research order — research
# must never use the cover letter model, and this also avoids evicting
# the writer from GPU memory while a cover letter task is in flight.