live: heartbeat sync 2026-10-19T04:06:41-07:00 (Refs #11)

agent/models.yml

@@ -158,13 +158,13 @@ providers:
         # contextWindow is the PER-SLOT window: llama.cpp divides --ctx-size
         # across slots and answers a longer prompt with a 400, never a
         # truncation, so this value must follow every reslice (live now:
-        # 2 x 262,144 over exact f16 KV, 68afc6d).
-        contextWindow: 262144
+        # 3 x 200,704 over f16 K + q8_0 V with the MTP drafter armed, ba69ea5).
+        contextWindow: 200704
         # Prompt + budget must fit inside the slot window; thinking counts
         # against the budget. Compaction fires at 85 % of the window =
-        # 222,822 est; worst-case prompt + budget ≈ 222,822 × 1.03 +
-        # 16,384 ≈ 245,891 ≤ 262,144. This endpoint is the fleet's
-        # compaction hub: the widest window in the fleet.
+        # 170,598 est; worst-case prompt + budget ≈ 170,598 × 1.03 +
+        # 16,384 ≈ 192,100 ≤ 200,704. This endpoint stays the fleet's
+        # compaction hub: still the widest window in this file.
         maxTokens: 16384
         reasoning: true
         input: [text, image]