aleksey
83d516afa1
FastAPI gateway with A/B/C lane orchestration, LiteLLM proxy config, Swarm stack (postgres, redis, VPN off-by-default), deploy/smoke/audit scripts.
79 lines
2.4 KiB
Bash
79 lines
2.4 KiB
Bash
#!/usr/bin/env bash
|
|
# Sync model_list fragment from config/*.yaml
|
|
set -euo pipefail
|
|
|
|
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
|
export ROOT
|
|
|
|
python3 <<'PY'
|
|
import os
|
|
import yaml
|
|
from pathlib import Path
|
|
|
|
root = Path(os.environ["ROOT"])
|
|
rules = yaml.safe_load((root / "config/routing_rules.yaml").read_text(encoding="utf-8"))
|
|
matrix = yaml.safe_load((root / "config/model_matrix.yaml").read_text(encoding="utf-8"))
|
|
|
|
entries = []
|
|
for name, cfg in matrix.get("models", {}).items():
|
|
novita = cfg.get("novita")
|
|
if not novita:
|
|
continue
|
|
entry = {
|
|
"model_name": name,
|
|
"litellm_params": {
|
|
"model": novita,
|
|
"api_key": "os.environ/NOVITA_API_KEY",
|
|
},
|
|
}
|
|
if cfg.get("rpm"):
|
|
entry["litellm_params"]["rpm"] = cfg["rpm"]
|
|
entries.append(entry)
|
|
|
|
for name, cfg in matrix.get("optional_providers", {}).items():
|
|
entries.append({
|
|
"model_name": name,
|
|
"litellm_params": {
|
|
"model": cfg["model"],
|
|
"api_key": cfg.get("api_key", "os.environ/GROQ_API_KEY"),
|
|
},
|
|
})
|
|
|
|
litellm_rules = rules.get("litellm", {})
|
|
entries.append({
|
|
"model_name": "smart-router-internal",
|
|
"litellm_params": {
|
|
"model": "auto_router/complexity_router",
|
|
"drop_params": True,
|
|
"complexity_router_default_model": "a-medium-ops",
|
|
"complexity_router_config": {
|
|
"tiers": {
|
|
"SIMPLE": "a-simple",
|
|
"MEDIUM": "a-medium-ops",
|
|
"MEDIUM_CODE": "a-medium-code",
|
|
"COMPLEX": "a-complex",
|
|
"REASONING": "a-reasoning",
|
|
},
|
|
"classifier_fallback": "heuristic",
|
|
"keyword_tier_rules": litellm_rules.get("keyword_tier_rules", []),
|
|
"custom_technical_keywords": litellm_rules.get("custom_technical_keywords", []),
|
|
"token_thresholds": {"simple": 20, "complex": 500},
|
|
"tier_boundaries": {
|
|
"simple_medium": 0.18,
|
|
"medium_complex": 0.38,
|
|
"complex_reasoning": 0.62,
|
|
},
|
|
"session_affinity": True,
|
|
"session_affinity_ttl_seconds": 1800,
|
|
},
|
|
},
|
|
})
|
|
|
|
out = root / "litellm_config.generated.yaml"
|
|
out.write_text(
|
|
yaml.dump({"model_list": entries}, allow_unicode=True, sort_keys=False),
|
|
encoding="utf-8",
|
|
)
|
|
print(f"Wrote {out} ({len(entries)} models)")
|
|
PY
|