feat: visualization of conversation affinity in dashboard

router.py

@@ -445,10 +445,12 @@ token_usage_counts: Dict[str, Dict[str, int]] = defaultdict(lambda: defaultdict(
 usage_lock = asyncio.Lock()  # protects access to usage_counts
 token_usage_lock = asyncio.Lock()
 
-# Conversation affinity map: fingerprint -> (endpoint, expires_at_monotonic).
+# Conversation affinity map: fingerprint -> (endpoint, model, expires_at_monotonic).
 # Keeps the same conversation pinned to the endpoint that already has its
-# KV-cache prefix warm. Never held together with usage_lock.
-_affinity_map: Dict[str, tuple[str, float]] = {}
+# KV-cache prefix warm. Model is stored so the dashboard can aggregate live
+# entries per (endpoint, model) without recomputing fingerprints.
+# Never held together with usage_lock.
+_affinity_map: Dict[str, tuple[str, str, float]] = {}
 _affinity_lock = asyncio.Lock()
 _AFFINITY_MAX_ENTRIES = 10000
 
@@ -1859,7 +1861,7 @@ async def choose_endpoint(model: str, reserve: bool = True,
         async with _affinity_lock:
             entry = _affinity_map.get(affinity_key)
             if entry is not None:
-                ep, expires_at = entry
+                ep, _stored_model, expires_at = entry
                 if expires_at < time.monotonic():
                     _affinity_map.pop(affinity_key, None)
                 else:
@@ -1961,10 +1963,10 @@ async def choose_endpoint(model: str, reserve: bool = True,
     if reserve and config.conversation_affinity and affinity_key:
         expires_at = time.monotonic() + config.conversation_affinity_ttl
         async with _affinity_lock:
-            _affinity_map[affinity_key] = (selected, expires_at)
+            _affinity_map[affinity_key] = (selected, model, expires_at)
             if len(_affinity_map) > _AFFINITY_MAX_ENTRIES:
                 now = time.monotonic()
-                for k in [k for k, v in _affinity_map.items() if v[1] < now]:
+                for k in [k for k, v in _affinity_map.items() if v[2] < now]:
                     _affinity_map.pop(k, None)
     return selected, tracking_model
 
@@ -3103,6 +3105,39 @@ async def ps_details_proxy(request: Request):
 
     return JSONResponse(content={"models": models}, status_code=200)
 
+# -------------------------------------------------------------
+# 18b. Conversation-affinity stats – feeds the PS-table dot matrix
+# -------------------------------------------------------------
+@app.get("/api/affinity_stats")
+async def affinity_stats(request: Request):
+    """
+    Aggregate live conversation-affinity pins, one entry per pinned conversation.
+    Each entry exposes only the endpoint, model, and remaining TTL in seconds —
+    no fingerprints or content. When conversation_affinity is disabled the
+    `entries` list is always empty.
+    """
+    if not config.conversation_affinity:
+        return {"enabled": False, "ttl": config.conversation_affinity_ttl, "entries": []}
+
+    now = time.monotonic()
+    entries: list[dict] = []
+    async with _affinity_lock:
+        for fp, (ep, mdl, expires_at) in list(_affinity_map.items()):
+            remaining = expires_at - now
+            if remaining <= 0:
+                _affinity_map.pop(fp, None)
+                continue
+            entries.append({
+                "endpoint": ep,
+                "model": mdl,
+                "remaining": round(remaining, 2),
+            })
+    return {
+        "enabled": True,
+        "ttl": config.conversation_affinity_ttl,
+        "entries": entries,
+    }
+
 # -------------------------------------------------------------
 # 19. Proxy usage route – for monitoring
 # -------------------------------------------------------------