live: heartbeat sync 2026-10-21T02:32:51-07:00 (Refs #11)

agent/models.yml

@@ -96,19 +96,20 @@ providers:
         # halogen flash-server on the Strix Halo iGPU. Payload, shape, eras,
         # laws, rollback: serverAppConfigs-docs/LLM/frank-dragoon.md — and
         # scripts/frank-dragoon.env is the authority for every number there.
-        # contextWindow sits deliberately BELOW the engine ceiling
-        # (HALOGEN_CTX): the clamp below leaves the gap that absorbs the
-        # harness's chars/4 under-count, so a window equal to the ceiling
-        # would make every long request a guaranteed 400.
-        contextWindow: 155648
+        # contextWindow: 200,000 under the native 262,144 engine ceiling
+        # (HALOGEN_CTX, 2026-10-21) — the 400-zone law: the window MUST sit
+        # ~45k under the ceiling, never at it.
+        contextWindow: 200000
         # The clamp is max_tokens = min(maxTokens, contextWindow − est −
         # 4096); the chars/4 est UNDER-counts the rendered prompt by ~3 %
         # on code/agent traffic (measured 2026-10-07: est 152,938 ->
-        # server 157,388). Worst-case request = window − 4096 + 3 % est
-        # error ≈ 156.2k, inside the engine ceiling with ~44k of margin
-        # (robust to a ~25 % under-count). Compaction fires at 85 % of the
-        # window and rides on frank-zealot: input ≈ threshold −
-        # keepRecent(20k), comfortably inside its per-slot window.
+        # server 157,388). Worst-case request = (200,000 − 4,096) × 1.03
+        # ≈ 201.8k; the compaction trigger fires at 95 % (config.yml
+        # thresholdPercent): 190,000 × 1.03 + 45,056 ≈ 240.8k — both inside
+        # 262,144 (margin 60k / 21k). Compaction rides frank-zealot:
+        # input ≈ 190,000 − keepRecent(20k) ≈ 175k ≤ its 200,704 slot.
+        # Recompute all of it after ANY window or threshold change; tests/
+        # frank_dragoon_unit.bats pins this arithmetic at 95 %.
         # HALOGEN_MAX_TOKENS_CAP in frank-dragoon.env must stay >= this.
         maxTokens: 45056
         reasoning: true