chore(cost-model): record the second measured review

31 steps, 190s, 2,213,077 in / 9,058 out, cache 0/0 — within 7% of the first
run's input on the same tier, which is the first evidence the recalibrated tier
defaults hold rather than fitting a single point.

Also weakens the step-cap hypothesis from the previous commit: this run used 31
steps (more than the 28 that succeeded, and more than the run that failed) and
parsed fine, so hitting `steps: 40` is not on its own what breaks the output
format. Leaving the cap alone until the stderr logging catches a real failure.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01B11e8TZZxJyzHW7jj7KWUN

pilot/cost_model.py

@@ -188,6 +188,22 @@ OBSERVED_RUNS: list[dict] = [
         "cache_write": 0,
         "subagents": 0,
     },
+    {
+        "label": "gitea_admin/pragent#7 (+ cost-model calibration + salvage fix)",
+        "date": "2026-08-18",
+        "tier": "full",
+        "diff_tokens": 21_000,     # same PR, two commits later
+        "steps": 31,
+        "duration_s": 189.8,
+        "input": 2_213_077,
+        "output": 9_058,
+        "cache_read": 0,
+        "cache_write": 0,
+        "subagents": 0,
+    },
+    # A third run of the same PR (sha 2613b3e, 31 steps' worth of work in 330s)
+    # ended without a parseable findings block and so reported no usage at all —
+    # the reason `salvage_summary` now keeps the usage section on that path.
 ]