79 lines
2.9 KiB
YAML
79 lines
2.9 KiB
YAML
# Konfiguration für die Agent-Modell-Auswahl
|
|
|
|
global:
|
|
min_context_tokens: 64000
|
|
max_auto_escalation_factor: 5 # ab diesem Faktor gilt ein Wechsel als "Ferrari-Sprung" -> braucht manual_override
|
|
min_distinct_model_families: 3 # Mindest-Diversität über alle Agents hinweg
|
|
max_retries_per_task: 3 # danach Task pausieren, nicht weiter eskalieren
|
|
default_hard_stop_eur_per_day: 1.0 # 1€/Tag/Agent als hartes Maximum
|
|
on_budget_exceeded: postpone_to_next_day # Arbeit verschieben statt Agent komplett zu blockieren
|
|
basic_questions_fallback: vps_ollama # einfache/Grundfragen weiter über lokales VPS-Ollama, wenn kontextuell sinnvoll
|
|
|
|
agents:
|
|
agent_a:
|
|
role: master
|
|
description: "Master-Agent, Allround, Linux-System-Support"
|
|
hard_stop_eur_per_day: 1.0
|
|
capability_tags: [linux_system, allround, orchestration]
|
|
escalation_ladder:
|
|
- model: "nvidia/nemotron-3-super" # Stufe 0, Standard
|
|
cost_factor: 1
|
|
- model: "nvidia/nemotron-3-ultra" # Stufe 1, Eskalation
|
|
cost_factor: 3
|
|
manual_override_allowed: false
|
|
|
|
agent_b:
|
|
role: worker
|
|
description: "DeepSeek Flash/Pro Eskalationsleiter"
|
|
hard_stop_eur_per_day: 1.0
|
|
capability_tags: [code, logic, database]
|
|
escalation_ladder:
|
|
- model: "deepseek/deepseek-flash"
|
|
cost_factor: 1
|
|
- model: "deepseek/deepseek-pro"
|
|
cost_factor: 3
|
|
manual_override_allowed: false
|
|
|
|
switch_hermes:
|
|
role: cockpit
|
|
description: "Nur Prompt/Code-Generierung, kein lokales Ausführen"
|
|
hard_stop_eur_per_day: 1.0
|
|
capability_tags: [homebrew_code, prompt_generation]
|
|
escalation_ladder:
|
|
- model: "openrouter/free" # OpenRouter Auto-Router, Free-Tier
|
|
cost_factor: 0
|
|
- model: "qwen/qwen3-coder:free"
|
|
cost_factor: 0
|
|
manual_override_allowed: false
|
|
|
|
laptop_hermes:
|
|
role: worker
|
|
description: "PDF/PowerPoint/HTML-Kompilation, gelegentlich High-End auf Wunsch"
|
|
hard_stop_eur_per_day: 1.0
|
|
capability_tags: [document_generation, html_css_js]
|
|
escalation_ladder:
|
|
- model: "google/gemini-flash"
|
|
cost_factor: 1
|
|
- model: "anthropic/claude-sonnet"
|
|
cost_factor: 4
|
|
manual_override_allowed: true # Opus/GPT-5.5/Fable nur per bewusstem manuellen Opt-in
|
|
|
|
agent_xyz:
|
|
role: worker
|
|
description: "Saubere JavaScript-Datenbank-Abfragen"
|
|
hard_stop_eur_per_day: 1.0
|
|
capability_tags: [javascript, database_query]
|
|
escalation_ladder:
|
|
- model: "qwen/qwen2.5-7b"
|
|
cost_factor: 1
|
|
- model: "deepseek/deepseek-flash"
|
|
cost_factor: 2
|
|
manual_override_allowed: false
|
|
|
|
local_fallback:
|
|
description: "Kostenfreier lokaler Fallback auf dem VPS via Ollama"
|
|
model: "deepseek-r1:7b"
|
|
min_context_tokens: 64000
|
|
allowed_for_task_tags: [document_generation, javascript, database_query, linux_system]
|
|
# Bewusst NICHT erlaubt für: homebrew_code (zu fehleranfällig bei 7B-Klasse)
|