diff --git a/README.md b/README.md
index b81f9d2..2caa290 100644
--- a/README.md
+++ b/README.md
@@ -150,10 +150,21 @@ rates, calibrated against runs measured through the usage telemetry
 (`OBSERVED_RUNS` in that file — append to it, don't guess). Tokens are summed
 from opencode `step_finish` events per review.
 
+Each review is governed by hard limits: 20 completed steps, 120,000 total
+tokens, 20,000 output tokens, and 480 seconds by default. Limits can be
+overridden deployment-wide with `PRAGENT_MAX_REVIEW_STEPS`,
+`PRAGENT_MAX_REVIEW_TOKENS`, `PRAGENT_MAX_REVIEW_OUTPUT_TOKENS`, and
+`PRAGENT_REVIEW_TIMEOUT`, or per repository in the trusted base-branch
+`.pr-review.json`; repository values win.
+
 Two measured reviews of a ~1100-line PR in this repo: 28 and 31 agent steps,
 ~2.1M input tokens each, **zero cache reads or writes**. The demo repo's PR, same
 tier: 126K tokens.
 
+The measurements above are historical uncapped runs. A capped run preserves
+completed output, reports the cap reason in the review, and records it in
+Langfuse.
+
 | Model | this repo, ~1100-line PR | demo repo PR |
 |---|---:|---:|
 | Claude Opus 5 | ~$10.79 | ~$0.71 |