aleksey
6fd2f0e689
LLM classify via LiteLLM gigachat-classifier when heuristic confidence is low. CLASSIFIER_MODE=heuristic|hybrid|llm. Metrics classifier_source.
41 lines
635 B
YAML
41 lines
635 B
YAML
default_quality_mode: auto
|
|
|
|
start_lanes:
|
|
SIMPLE: A
|
|
MEDIUM_OPS: A
|
|
MEDIUM_CODE: A
|
|
COMPLEX: B
|
|
REASONING: B
|
|
VISION_OCR: A
|
|
VISION_UI: A
|
|
|
|
quality_mode_map:
|
|
economy: A
|
|
balanced: B
|
|
max: C
|
|
|
|
lane_order: [A, B, C]
|
|
|
|
budget_caps:
|
|
warn_pct: 80
|
|
hard_pct: 95
|
|
warn_max_lane: B
|
|
hard_max_lane: A
|
|
|
|
escalation:
|
|
repeat_prompt_window_sec: 300
|
|
context_tokens_min_lane_b: 32000
|
|
session_ttl_sec: 1800
|
|
|
|
redis:
|
|
key_prefix: "ai-router:session:"
|
|
ttl_sec: 1800
|
|
|
|
classifier:
|
|
# heuristic | hybrid (default) | llm
|
|
mode: hybrid
|
|
llm_model: gigachat-classifier
|
|
low_confidence_threshold: 0.6
|
|
timeout_sec: 15
|
|
max_tokens: 64
|