Classify a request before you route it

#!/usr/bin/env bash
# Requires bash, curl, jq, S1M_API_KEY and TENSORX_API_KEY.
set -euo pipefail
: "${S1M_API_KEY:?Set S1M_API_KEY}" "${TENSORX_API_KEY:?Set TENSORX_API_KEY}"
request='Write a Python function that returns the square of a number.'
fast='deepseek/deepseek-v3.2'
strong='deepseek/deepseek-v4.1-flash'
# Edit this category x difficulty table and fallback for your own catalog.
routes=$(jq -n --arg fast "$fast" --arg strong "$strong"   '{coding:{easy:$fast,hard:$strong},general:{easy:$fast,hard:$strong}}')
classifier_payload=$(jq --arg request "$request" '.state.request = $request' <<'CLASSIFIER_JSON'
{"model":"s1-llm-auto-router","state":{"request":"Write a Python function that returns the square of a number.","context":"(new conversation)"},"questions":{"category":{"type":"choice","criteria":{"coding":"","agentic":"","math":"","knowledge":"","long_context":"","tool_use":"","design":"","summarisation":"","general":""}},"difficulty":{"type":"score","criteria":["trivial","easy","moderate","hard","frontier"]},"stakes":{"type":"score","criteria":["negligible","low","medium","high"]},"needs_tools":{"type":"noul"},"needs_vision":{"type":"noul"},"needs_long_context":{"type":"noul"},"follow_up":{"type":"noul"}}}
CLASSIFIER_JSON
)
result=$(curl --fail-with-body --silent --show-error --max-time 60 \
  https://api.system1models.ai/v1/systemone \
  -H "Authorization: Bearer $S1M_API_KEY" -H 'Content-Type: application/json' \
  --data-binary "$classifier_payload")
decision=$(jq --argjson routes "$routes" --arg fallback "$strong" '
  .answers as $a | (if $a.difficulty.score >= 2 then "hard" else "easy" end) as $level |
  ([$a | to_entries[] | select(.key == "needs_tools" or .key == "needs_vision" or
     .key == "needs_long_context" or .key == "follow_up") | select(.value.noul >= 0.5) | .key]) as $unsupported |
  {request_id:.id, signals:$a, unsupported:$unsupported,
   model:(if $a.category.confidence < 0.6 or $a.stakes.score >= 2 then $fallback
          else ($routes[$a.category.choice][$level] // $fallback) end),
   reason:(if $a.category.confidence < 0.6 or $a.stakes.score >= 2 then
           "low confidence or high stakes" else "category/difficulty table" end)}' <<<"$result")
printf '%s\n' "$decision"  # distributions + flag probabilities; no prompts/keys
if [ "$(jq '.unsupported | length' <<<"$decision")" != 0 ]; then
  echo 'Configure capability support / conversation history before forwarding' >&2; exit 1
fi
model=$(jq -r '.model' <<<"$decision")
payload=$(jq -n --arg model "$model" --arg request "$request"   '{model:$model,messages:[{role:"user",content:$request}],max_tokens:80,temperature:0}')
curl --fail-with-body --silent --show-error --max-time 60   https://api.tensorx.ai/v1/chat/completions   -H "Authorization: Bearer $TENSORX_API_KEY" -H 'Content-Type: application/json'   --data-binary "$payload" | jq -r '.choices[0].message.content'

import json, os, urllib.request

# Requires S1M_API_KEY and TENSORX_API_KEY; Python 3.10+ (standard library only).
REQUEST = "Write a Python function that returns the square of a number."
QUESTIONS = {'category': {'type': 'choice', 'criteria': {'coding': '', 'agentic': '', 'math': '', 'knowledge': '', 'long_context': '', 'tool_use': '', 'design': '', 'summarisation': '', 'general': ''}}, 'difficulty': {'type': 'score', 'criteria': ['trivial', 'easy', 'moderate', 'hard', 'frontier']}, 'stakes': {'type': 'score', 'criteria': ['negligible', 'low', 'medium', 'high']}, 'needs_tools': {'type': 'noul'}, 'needs_vision': {'type': 'noul'}, 'needs_long_context': {'type': 'noul'}, 'follow_up': {'type': 'noul'}}
FAST = "deepseek/deepseek-v3.2"
STRONG = "deepseek/deepseek-v4.1-flash"
ROUTES = {"coding": {"easy": FAST, "hard": STRONG},
          "general": {"easy": FAST, "hard": STRONG}}
FALLBACK = STRONG

def post(url, key, body):
    req = urllib.request.Request(url, data=json.dumps(body).encode(), headers={
        "Authorization": "Bearer " + key, "Content-Type": "application/json"})
    with urllib.request.urlopen(req, timeout=60) as response:
        return json.load(response)

result = post("https://api.system1models.ai/v1/systemone", os.environ["S1M_API_KEY"],
              {"model": "s1-llm-auto-router", "state": {"request": REQUEST,
               "context": "(new conversation)"}, "questions": QUESTIONS})
a = result["answers"]
# score is an expected LEVEL (0..4 / 0..3), not a probability.
difficulty = "hard" if a["difficulty"]["score"] >= 2 else "easy"
model = ROUTES.get(a["category"]["choice"], {}).get(difficulty, FALLBACK)
reason = "category/difficulty table"
if a["category"]["confidence"] < 0.6 or a["stakes"]["score"] >= 2:
    model, reason = FALLBACK, "low confidence or high stakes"
# This demo handles a new text turn. Never silently lose required capabilities/context.
unsupported = [f for f in ("needs_tools", "needs_vision", "needs_long_context", "follow_up")
               if a[f]["noul"] >= 0.5]
decision = {"request_id": result["id"], "model": model, "reason": reason,
            "signals": a, "unsupported": unsupported}
print(json.dumps(decision))  # All distributions and flag probabilities; no prompts or keys.
if unsupported:
    raise SystemExit("Configure capability support / conversation history before forwarding")
completion = post("https://api.tensorx.ai/v1/chat/completions", os.environ["TENSORX_API_KEY"],
                  {"model": model, "messages": [{"role": "user", "content": REQUEST}],
                   "max_tokens": 80, "temperature": 0})
print(completion["choices"][0]["message"]["content"])

// Node 22.18+ supports: node route.ts (no dependencies).
const REQUEST = "Write a Python function that returns the square of a number.";
const QUESTIONS = {"category": {"type": "choice", "criteria": {"coding": "", "agentic": "", "math": "", "knowledge": "", "long_context": "", "tool_use": "", "design": "", "summarisation": "", "general": ""}}, "difficulty": {"type": "score", "criteria": ["trivial", "easy", "moderate", "hard", "frontier"]}, "stakes": {"type": "score", "criteria": ["negligible", "low", "medium", "high"]}, "needs_tools": {"type": "noul"}, "needs_vision": {"type": "noul"}, "needs_long_context": {"type": "noul"}, "follow_up": {"type": "noul"}};
const FAST = "deepseek/deepseek-v3.2";
const STRONG = "deepseek/deepseek-v4.1-flash";
const ROUTES: Record<string, Record<string, string>> = {
  coding: {easy: FAST, hard: STRONG}, general: {easy: FAST, hard: STRONG}
};
const FALLBACK = STRONG;
function key(name: string): string {
  const value = process.env[name]; if (!value) throw new Error(`Set ${name}`); return value;
}
async function post(url: string, token: string, body: unknown): Promise<any> {
  const response = await fetch(url, {method: "POST", headers: {
    Authorization: `Bearer ${token}`, "Content-Type": "application/json"},
    body: JSON.stringify(body), signal: AbortSignal.timeout(60000)});
  if (!response.ok) throw new Error(`API returned HTTP ${response.status}`);
  return response.json();
}
const result = await post("https://api.system1models.ai/v1/systemone", key("S1M_API_KEY"),
  {model: "s1-llm-auto-router", state: {request: REQUEST, context: "(new conversation)"},
   questions: QUESTIONS});
const a = result.answers;
// score is an expected LEVEL (0..4 / 0..3), not a probability.
const difficulty = a.difficulty.score >= 2 ? "hard" : "easy";
let model = ROUTES[a.category.choice]?.[difficulty] ?? FALLBACK;
let reason = "category/difficulty table";
if (a.category.confidence < 0.6 || a.stakes.score >= 2) {
  model = FALLBACK; reason = "low confidence or high stakes";
}
const unsupported = ["needs_tools", "needs_vision", "needs_long_context", "follow_up"]
  .filter(f => a[f].noul >= 0.5);
console.log(JSON.stringify({request_id: result.id, model, reason, signals: a, unsupported}));
if (unsupported.length) throw new Error("Configure capability support / conversation history before forwarding");
const completion = await post("https://api.tensorx.ai/v1/chat/completions", key("TENSORX_API_KEY"),
  {model, messages: [{role: "user", content: REQUEST}], max_tokens: 80, temperature: 0});
console.log(completion.choices[0].message.content);
export {};

git clone https://github.com/fstandhartinger/auto-model-router.git
cd auto-model-router
git fetch origin pull/5/head
git checkout a92814ecd17cb98f3f04c1f866bde8f3592f0b9c
python3 -m venv .venv
. .venv/bin/activate
pip install -e .
cp examples/models.yaml router.local.yaml
# Edit providers/models in router.local.yaml for your own catalog and keys.
# Set S1M_API_KEY in the environment, then put the YAML below under policy.
export AUTO_ROUTER_CONFIG="$PWD/router.local.yaml"
uvicorn auto_router.server:app --host 127.0.0.1 --port 8787

policy:
  name: F_expected
  classifier:
    backend: s1-llm-auto-router-api
    api_key_env: S1M_API_KEY
  verify:
    enabled: false  # start with selection only; configure an answer judge separately
# Keep the providers/models blocks from your own edited examples/models.yaml.

curl --fail-with-body http://127.0.0.1:8787/v1/chat/completions   -H 'Content-Type: application/json'   -d '{"model":"auto","messages":[{"role":"user","content":"Write a Python function that returns the square of a number."}],"max_tokens":80}'
curl --fail-with-body http://127.0.0.1:8787/v1/router/decisions