feat(proxy): T-X6 模型池能力位过滤——vision/tools/context 硬过滤（采纳 cortiq capabilities）

- model_pool：条目新增 capabilities{vision,tools,context_window}，
  归一化缺省全兼容（老条目行为零变化；非法形态回落缺省）；
  filter_by_capabilities 硬过滤（context_window=0 视为不限）
- proxy routes：_request_needs 从请求体推断需求（多模态 image_url → vision、
  tools 非空 → tools、上下文需求 = 字符/3 + min(max_tokens,4096) 与预扣同口径）；
  条目不满足时在池内重定向到首个合格条目
- 与 T-X1/T-X2 组合语义：能力重定向 → 预算降档 → 降级链，逐级独立不互扰

pytest 461 passed（T-X3 后 455 + 6）

gateway/proxy/routes.py

@@ -274,6 +274,41 @@ def _budget_headers(budget_mode: str) -> Dict[str, str]:
     return {"X-Budget-Mode": budget_mode} if budget_mode and budget_mode != "normal" else {}
 
 
+def _request_needs(body: dict) -> Dict[str, Any]:
+    """从请求体推断能力需求（T-X6）：多模态图片 -> vision；带 tools -> tools；
+    上下文需求 = 提示字符/3 + min(max_tokens, 4096)（与预扣估算同口径）。"""
+    vision = False
+    for m in body.get("messages") or []:
+        content = m.get("content")
+        if isinstance(content, list):
+            for part in content:
+                if isinstance(part, dict) and ("image_url" in part
+                                               or part.get("type") == "image_url"):
+                    vision = True
+    prompt_chars = sum(len(str(m.get("content") or ""))
+                       if not isinstance(m.get("content"), list)
+                       else sum(len(str(p.get("text") or "")) for p in m["content"]
+                                if isinstance(p, dict))
+                       for m in (body.get("messages") or []))
+    est_out = min(int(body.get("max_tokens") or 1024), 4096)
+    return {"vision": vision,
+            "tools": bool(body.get("tools")),
+            "min_context_tokens": prompt_chars // 3 + est_out}
+
+
+def _entry_meets(entry: Dict[str, Any], needs: Dict[str, Any]) -> bool:
+    """条目能力位是否满足请求需求（capabilities 缺省全兼容）。"""
+    cap = entry.get("capabilities") or {}
+    if needs["vision"] and not cap.get("vision", True):
+        return False
+    if needs["tools"] and not cap.get("tools", True):
+        return False
+    ctx = int(cap.get("context_window") or 0)
+    if needs["min_context_tokens"] > 0 and 0 < ctx < needs["min_context_tokens"]:
+        return False
+    return True
+
+
 def _fallback_chain(pool, entry: Dict[str, Any], max_total: int = 3) -> List[Dict[str, Any]]:
     """上游有序降级链（T-X2，采纳 cortiq tier 链思路）。
 
@@ -367,6 +402,21 @@ async def _run_chat(body: dict, headers: Dict[str, str], ctx: Dict[str, Any],
         if isinstance(body.get("stream_options"), dict) else False
     is_stream = bool(body.get("stream"))
 
+    # ---- 能力位硬过滤（T-X6）：请求需要 vision/tools/上下文而条目不满足时重定向 ----
+    needs = _request_needs(body)
+    if not _entry_meets(entry, needs):
+        from gateway.model_pool import filter_by_capabilities
+        cap_entries = filter_by_capabilities(
+            [e for e in pool.list().get("entries", [])
+             if e.get("enabled") and e.get("backend") not in ("mock",)
+             and e.get("base_url")],
+            need_vision=needs["vision"], need_tools=needs["tools"],
+            min_context_tokens=needs["min_context_tokens"])
+        if cap_entries:
+            entry = cap_entries[0]
+            model = str(entry.get("model") or model)
+            body = {**body, "model": model}
+
     # ---- 预算四档（T-X1）：接近日上限渐进降档；>100% 仍由 try_hold 硬拒 ----
     budget_mode = "normal"
     try: