feat: LiteLLM multi-backends + jean-proxy avec WoL

Architecture (voir docs/ARCHITECTURE-LITELLM.md): open-webui -> LiteLLM:4000 |- qwen3.6-27b -> jean-proxy:3012 -> Jean (.11:8080) |- llama3.1-8b -> wol-proxy:3011 -> Ollama (.11:11434) Nouveaux fichiers: - wol-proxy/ (versionne l'app.py de prod deja en place) - jean-proxy/ (clone du wol-proxy avec HEALTH_PATH=/health + retry post-WoL pour services qui mettent du temps a demarrer apres WoL, ex: Jean qui charge 14 Go en VRAM) - litellm/config.yaml (routing par nom de modele, drop_params=true) - docker-compose.litellm.yml (override ADDITIF: ajoute uniquement jean-proxy et litellm, ne redemarre PAS open-webui/wol-proxy/hermes) Teste en prod sur .27: Jean + Ollama repondent via LiteLLM:4000 avec path-through de chat_template_kwargs.enable_thinking (raisonnement Qwen3.6 desactivable par requete). Zero impact hermes-webui/wol-proxy. Basculer open-webui reste une etape manuelle (step 3 de la doc).
2026-06-27 16:19:08 +02:00
parent 2f270aeca8
commit 2a9f721c4e
8 changed files with 526 additions and 1 deletions
@@ -0,0 +1,14 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# dépendances
+RUN pip install --no-cache-dir flask requests
+
+COPY app.py .
+
+ENV LISTEN_PORT=3010
+EXPOSE 3010
+
+CMD ["python", "app.py"]
+
@@ -0,0 +1,123 @@
+import os
+import time
+import socket
+import logging
+from urllib.parse import urljoin
+
+import requests
+from flask import Flask, request, Response
+
+TARGET_HOST = os.getenv("TARGET_HOST", "192.168.1.11")
+TARGET_PORT = int(os.getenv("TARGET_PORT", "8080"))
+TARGET_MAC = os.getenv("TARGET_MAC", "")
+LISTEN_PORT = int(os.getenv("LISTEN_PORT", "3012"))
+WAKE_TIMEOUT = int(os.getenv("WAKE_TIMEOUT", "60"))
+CHECK_INTERVAL = int(os.getenv("CHECK_INTERVAL", "5"))
+BROADCAST_IP = os.getenv("BROADCAST_IP", "192.168.1.255")
+# Endpoint de sante de la cible : Ollama = /api/version, Jean = /health
+HEALTH_PATH = os.getenv("HEALTH_PATH", "/health")
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+log = logging.getLogger(__name__)
+
+app = Flask(__name__)
+
+def send_wol(mac_address: str):
+    mac = mac_address.replace(":", "").replace("-", "")
+    if len(mac) != 12:
+        raise ValueError("MAC invalide: %s" % mac_address)
+    data = bytes.fromhex("FF" * 6 + mac * 16)
+    with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as s:
+        s.setsockopt(socket.SOL_SOCKET, socket.SO_BROADCAST, 1)
+        for i in range(3):
+            s.sendto(data, (BROADCAST_IP, 9))
+            log.info(f"[WoL] Paquet magic #{i+1} envoye -> MAC={mac_address} via {BROADCAST_IP}:9")
+
+def target_alive() -> bool:
+    try:
+        url = f"http://{TARGET_HOST}:{TARGET_PORT}{HEALTH_PATH}"
+        r = requests.get(url, timeout=2)
+        return r.ok
+    except Exception:
+        return False
+
+def wait_for_target():
+    if target_alive():
+        log.info(f"[WoL] Cible deja UP ({TARGET_HOST}:{TARGET_PORT}{HEALTH_PATH})")
+        return
+    if not TARGET_MAC:
+        log.warning("[WoL] Pas de TARGET_MAC, skip WoL, attente directe")
+    else:
+        log.info(f"[WoL] Cible DOWN -> envoi WoL vers {TARGET_MAC}")
+        send_wol(TARGET_MAC)
+    deadline = time.time() + WAKE_TIMEOUT
+    while time.time() < deadline:
+        remaining = int(deadline - time.time())
+        if target_alive():
+            log.info(f"[WoL] Cible UP apres reveil (reste {remaining}s)")
+            return
+        log.info(f"[WoL] En attente de la cible... ({remaining}s restantes)")
+        time.sleep(CHECK_INTERVAL)
+    raise RuntimeError(f"Cible ne repond pas apres {WAKE_TIMEOUT}s")
+
+def proxy_request(path: str):
+    wait_for_target()
+    base = f"http://{TARGET_HOST}:{TARGET_PORT}"
+    upstream_url = urljoin(base + "/", path)
+    headers = dict(request.headers)
+    headers.pop("Host", None)
+    refused_msg = None
+    try:
+        resp = requests.request(
+            method=request.method,
+            url=upstream_url,
+            headers=headers,
+            data=request.get_data(),
+            cookies=request.cookies,
+            params=request.args,
+            allow_redirects=False,
+            stream=True,
+            timeout=None,
+        )
+    except Exception as e:
+        refused_msg = str(e)
+        if "Connection refused" in refused_msg and not refused_msg.endswith(" apres WoL"):
+            # Le service n est pas encore pret (ex: Jean qui charge son modele) -> attendre + retry
+            log.warning(f"[Proxy] connexion refusee, attente {WAKE_TIMEOUT}s puis retry")
+            deadline = time.time() + WAKE_TIMEOUT
+            while time.time() < deadline:
+                time.sleep(CHECK_INTERVAL)
+                try:
+                    resp = requests.request(
+                        method=request.method, url=upstream_url, headers=headers,
+                        data=request.get_data(), params=request.args,
+                        allow_redirects=False, stream=True, timeout=None,
+                    )
+                    break
+                except Exception as e2:
+                    log.info(f"[Proxy] retry en cours... ({int(deadline-time.time())}s)")
+            else:
+                return Response(refused_msg, status=502)
+        else:
+            return Response(refused_msg, status=502)
+
+    excluded = {"content-encoding", "content-length", "transfer-encoding", "connection"}
+    response_headers = [
+        (name, value)
+        for name, value in resp.headers.items()
+        if name.lower() not in excluded
+    ]
+    return Response(
+        resp.raw,
+        status=resp.status_code,
+        headers=response_headers,
+        direct_passthrough=True,
+    )
+
+@app.route("/", defaults={"path": ""}, methods=["GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS"])
+@app.route("/<path:path>", methods=["GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS"])
+def handle(path):
+    return proxy_request(path)
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=LISTEN_PORT, threaded=True)