feat: add context_length to /v1/models response

- Add get_jean_context_lengths() to fetch n_ctx from Jean /v1/models
- Add preset_ctx_map with known CTX values for each preset
- Add context_length to Jean model metadata in /v1/models
- Add context_length to Ollama model metadata from details.context_length
- This allows OpenFox to know the max tokens each model can handle

jean-router/app.py

@@ -38,6 +38,7 @@ app = Flask(__name__)
 
 presets_cache = {"data": [], "timestamp": 0}
 ollama_cache = {"data": [], "timestamp": 0}
+jean_ctx_cache = {}
 CACHE_TTL = 30
 switch_lock = threading.Lock()
 vram_lock = threading.Lock()
@@ -73,6 +74,38 @@ def get_ollama_models(force_refresh=False):
     if not force_refresh and ollama_cache["data"] and (now - ollama_cache["timestamp"]) < CACHE_TTL:
         return ollama_cache["data"]
 
+
+def get_jean_context_lengths():
+    """Récupère les context_length depuis Jean /v1/models (avec cache)"""
+    preset_ctx_map = {
+        "ornith-35b-q6": 64000,
+        "qwen3.6-27b-mtp": 55000,
+        "qwen3.6-35b-moe-compact": 131072,
+        "qwen3.6-35b-moe-compact-reason": 131072,
+        "qwen3.6-35b-moe-nano": 100000,
+    }
+
+    try:
+        url = f"http://{JEAN_PROXY_HOST}:{JEAN_PROXY_PORT}/v1/models"
+        r = requests.get(url, timeout=2)
+        if r.ok:
+            models = r.json().get("data", [])
+            for m in models:
+                meta = m.get("meta", {})
+                n_ctx = meta.get("n_ctx")
+                if n_ctx:
+                    alias = m.get("id", "")
+                    jean_ctx_cache[alias] = n_ctx
+                    log.debug(f"[Jean] Context length pour {alias}: {n_ctx}")
+    except Exception as e:
+        log.debug(f"[Jean] Impossible de récupérer context_length: {e}")
+
+    for preset_id, ctx in preset_ctx_map.items():
+        if preset_id not in jean_ctx_cache:
+            jean_ctx_cache[preset_id] = ctx
+
+    return jean_ctx_cache
+
     try:
         url = f"http://{OLLAMA_PROXY_HOST}:{OLLAMA_PROXY_PORT}/api/tags"
         r = requests.get(url, timeout=3)
@@ -316,6 +349,7 @@ def ensure_vram_for_backend(target_backend: str) -> bool:
 def list_models():
     """Expose tous les presets Jean + modèles Ollama comme modèles OpenAI"""
     presets = get_presets()
+    jean_ctx = get_jean_context_lengths()
     models = []
 
     for p in presets:
@@ -342,6 +376,10 @@ def list_models():
         if p.get("bench"):
             meta["bench"] = p["bench"]
 
+        ctx_len = jean_ctx.get(model_id)
+        if ctx_len:
+            meta["context_length"] = ctx_len
+
         if meta:
             model_info["meta"] = meta
 
@@ -372,6 +410,8 @@ def list_models():
                 meta["quantization"] = details["quantization_level"]
             if details.get("family"):
                 meta["family"] = details["family"]
+            if details.get("context_length"):
+                meta["context_length"] = details["context_length"]
             if m.get("capabilities"):
                 meta["capabilities"] = m["capabilities"]