Grade 12-model backlog + fix native-API TTFT capture

Grading (12 new entries, 18→30 total in benchmark_history.json):
- KAT-Coder v2.5 Dev XL: lfu 49 / tts 52 / webhook 72 / rust 36 / automation 60
- Qwen3 Coder 30B: lfu 45 / tts 44 / webhook 62 / rust 54 / automation 58
- Qwen 3.6 35B-A3B uncensored (automation): 46
- Gemma 4 26B-A4B (data): 86 [tests pass]
All "coder" models scored Critical Bugs across prompts — plausible-looking
async code with fatal bugs (broken LFU eviction, in-flight cancel no-op,
submit() raising instead of backpressuring, un-awaited async read-through).

grade_run.py: switch from OpenAI-compat /v1/chat/completions (empty stats)
to native /api/v1/chat — returns full stats incl. time_to_first_token_seconds.
Verified on Gemma-26B (53.5 t/s, ttft 1.13). Two native-API gotchas handled:
input (string) not messages; max_output_tokens not max_tokens (that 400s).

New capture: outputs/gemma-4-26b-a4b-data.py (native-API run).

Co-Authored-By: Claude <noreply@anthropic.com>

outputs/.last_response_schema.json

@@ -1,12 +1,15 @@
 {
-  "usage": {
-    "prompt_tokens": 593,
-    "completion_tokens": 10029,
-    "total_tokens": 10622,
-    "completion_tokens_details": {
-      "reasoning_tokens": 7460
-    }
+  "model_instance_id": "google/gemma-4-26b-a4b",
+  "stats": {
+    "input_tokens": 718,
+    "total_output_tokens": 5153,
+    "reasoning_output_tokens": 1919,
+    "tokens_per_second": 53.47535329547263,
+    "time_to_first_token_seconds": 1.127
   },
-  "stats": {},
-  "system_fingerprint": "qwen3.6-35b-a3b-uncensored-hauhaucs-aggressive"
+  "response_id": "resp_d8fafc117fa4e51b927d8cd531ded49984ae59e49c39d3eb",
+  "_output_types": [
+    "reasoning",
+    "message"
+  ]
 }