router: v3 — 5-tier routing with vision guard, MoE spillover, code hint

GUARD: multimodal -> VLM only TIER 1 Tiny: VLM->Dense->MoE TIER 2 Light: VLM->Dense->MoE TIER 3 Medium: MoE<->Dense (40% spill)->VLM TIER 4 Heavy: Dense->MoE->VLM (quality first) TIER 5 Default: MoE<->Dense (40% spill)->VLM HINTS: speed->VLM, quality->MoE, code->Dense + moe_spillover(): 60/40 MoE/Dense load distribution
2026-06-05 23:48:45 +00:00
parent c0be4c1699
commit e6a6c30211
1 changed files with 92 additions and 0 deletions
@@ -0,0 +1,92 @@
+def route(rd, tier, agent=""):
+    msgs = rd.get("messages",[]); t = estimate_tokens(msgs)
+    sys = any(m.get("role")=="system" for m in msgs)
+    turns = len([m for m in msgs if m.get("role") in ("user","assistant")])
+    hints = rd.get("routing_hints",{})
+    allowed = TIER_MODELS.get(tier, ["gemma-4-12b"])
+    avail = [m for m in available_models() if m in allowed]
+    if not avail: return {"model": allowed[0], "reason": "all_saturated", "saturated": True}
+    if all(is_gpu_busy(m) for m in avail):
+        return {"model": avail[0], "reason": "all_saturated", "saturated": True}
+
+    # GUARD: multimodal -> VLM only (sole vision model)
+    has_image = any(
+        isinstance(m.get("content"), list) and
+        any(p.get("type") == "image_url" for p in m["content"] if isinstance(p, dict))
+        for m in msgs
+    )
+    if has_image:
+        if "gemma-4-12b" in avail and not is_gpu_busy("gemma-4-12b"):
+            return {"model": "gemma-4-12b", "reason": "vision"}
+        elif "gemma-4-12b" in avail:
+            return {"model": "gemma-4-12b", "reason": "vision_saturated", "saturated": True}
+        else:
+            return {"model": allowed[0], "reason": "vision_unavailable"}
+
+    req = rd.get("model","auto")
+    if req != "auto":
+        target = req if req in avail else avail[0]
+        if is_gpu_busy(target) and req in allowed:
+            alts = [m for m in avail if m != target and m in allowed]
+            if alts:
+                alt = select_best_gpu(alts, "explicit", agent)
+                if alt: return alt
+        return {"model": target, "reason": "explicit"}
+
+    if hints:
+        if hints.get("priority")=="speed" and "gemma-4-12b" in avail:
+            return select_best_gpu(["gemma-4-12b"], "hint_speed", agent) or {"model":"gemma-4-12b","reason":"hint_speed"}
+        if hints.get("priority")=="quality" and "qwen3.6-35B-A3B" in avail:
+            return select_best_gpu(["qwen3.6-35B-A3B"], "hint_quality", agent) or {"model":"qwen3.6-35B-A3B","reason":"hint_quality"}
+        if hints.get("priority")=="code" and "qwen3.6-27B-code" in avail:
+            return select_best_gpu(["qwen3.6-27B-code"], "hint_code", agent) or {"model":"qwen3.6-27B-code","reason":"hint_code"}
+
+    first_msg = msgs[0].get("content","") if msgs else ""
+    words = len(first_msg.split()) if isinstance(first_msg, str) else 99
+
+    # TIER 1: Tiny - single-turn micro queries -> VLM (fastest)
+    if not sys and turns <= 1 and t <= 300 and words <= 100 and "gemma-4-12b" in avail:
+        if not is_gpu_busy("gemma-4-12b"):
+            return {"model":"gemma-4-12b","reason":"tiny"}
+        fallback = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B"] if m in avail]
+        result = select_best_gpu(fallback, "tiny_fallback", agent)
+        if result: return result
+
+    # TIER 2: Light - moderate chat -> Dense primary, saves VLM for vision/speed
+    if t <= 5000 and turns <= 4:
+        candidates = [m for m in ["qwen3.6-27B-code","gemma-4-12b","qwen3.6-35B-A3B"] if m in avail]
+        result = select_best_gpu(candidates, "light", agent)
+        if result: return result
+
+    # TIER 3: Medium - quality matters -> MoE primary (60%), Dense spillover (40%)
+    if t <= 30000:
+        candidates = moe_spillover(avail, ["qwen3.6-35B-A3B","qwen3.6-27B-code","gemma-4-12b"])
+        result = select_best_gpu(candidates, "medium", agent)
+        if result: return result
+
+    # TIER 4: Heavy - big context -> MoE primary (60%), Dense spillover (40%)
+    if t > 30000:
+        candidates = moe_spillover(avail, ["qwen3.6-35B-A3B","qwen3.6-27B-code","gemma-4-12b"])
+        result = select_best_gpu(candidates, "heavy", agent)
+        if result: return result
+
+    # TIER 5: Default - MoE primary (60%), Dense spillover (40%)
+    candidates = moe_spillover(avail, ["qwen3.6-35B-A3B","qwen3.6-27B-code","gemma-4-12b"])
+    result = select_best_gpu(candidates, "default", agent)
+    if result: return result
+    return {"model":avail[0],"reason":"last_resort"}
+
+
+def moe_spillover(avail, default_order):
+    """Spill 40% of MoE-first traffic to Dense to prevent Strix Halo overheating.
+    Only applies when MoE is first candidate, available, and not busy."""
+    import random
+    if (default_order[0] == "qwen3.6-35B-A3B" 
+        and "qwen3.6-35B-A3B" in avail 
+        and not is_gpu_busy("qwen3.6-35B-A3B")
+        and "qwen3.6-27B-code" in avail
+        and not is_gpu_busy("qwen3.6-27B-code")
+        and random.random() < 0.4):
+        # Swap: Dense first, MoE second
+        return ["qwen3.6-27B-code","qwen3.6-35B-A3B"] + [m for m in default_order[2:] if m in avail and m not in ("qwen3.6-27B-code","qwen3.6-35B-A3B")]
+    return [m for m in default_order if m in avail]