diff --git a/README.md b/README.md
index 2caa290..6dded1b 100644
--- a/README.md
+++ b/README.md
@@ -157,6 +157,11 @@ overridden deployment-wide with `PRAGENT_MAX_REVIEW_STEPS`,
 `PRAGENT_REVIEW_TIMEOUT`, or per repository in the trusted base-branch
 `.pr-review.json`; repository values win.
 
+For repositories with broad diffs, the pilot automatically raises headroom to
+40/400K, 60/800K, or 80/1.2M steps/tokens as changed lines cross 200, 800, or
+2,000. Explicit repository budgets always take precedence, and the global
+hard ceilings remain in force.
+
 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.
diff --git a/pilot/README-webhook.md b/pilot/README-webhook.md
index 2e946af..9749fe1 100644
--- a/pilot/README-webhook.md
+++ b/pilot/README-webhook.md
@@ -306,6 +306,11 @@ limit, preserves any output already emitted, and records the cap reason in the
 review body and Langfuse metadata. Environment variables provide deployment-wide
 defaults; repository budget values override them.
 
+Without an explicit repository budget, changed diffs receive adaptive headroom:
+the default 20-step/120K-token budget grows to 40/400K, 60/800K, or 80/1.2M for
+diffs over 200, 800, or 2,000 changed lines. This keeps focused PRs inexpensive
+while allowing broad TypeScript/Go reviews to finish. Hard ceilings still apply.
+
 **Cross-lens dedup:** synthesiser drops duplicates by
 `sha256[:16](path|line|severity|problem[:80])` (matches the feedback DB's
 `posthash`), then promotes multi-lens agreement by one severity step
diff --git a/pilot/review/budget.py b/pilot/review/budget.py
index 709e93e..59b1f82 100644
--- a/pilot/review/budget.py
+++ b/pilot/review/budget.py
@@ -15,6 +15,13 @@ DEFAULTS = {
     "max_duration_seconds": 480,
 }
 
+PROFILES = (
+    # (changed lines threshold, steps, total tokens, output tokens, seconds)
+    (2_000, 80, 1_200_000, 80_000, 1_800),
+    (800, 60, 800_000, 60_000, 1_200),
+    (200, 40, 400_000, 40_000, 900),
+)
+
 
 @dataclass(frozen=True)
 class Budget:
@@ -63,6 +70,34 @@ class Budget:
             price_target=price_target,
         )
 
+    @classmethod
+    def for_review(cls, config: dict | None, diff: str) -> "Budget":
+        """Choose safe headroom from diff size, unless config is explicit."""
+        if isinstance((config or {}).get("budget"), dict):
+            return cls.from_config(config)
+        changed_lines = _changed_line_count(diff)
+        for threshold, steps, tokens, output, seconds in PROFILES:
+            if changed_lines >= threshold:
+                return cls.from_config({
+                    **(config or {}),
+                    "budget": {
+                        "max_steps": steps,
+                        "max_total_tokens": tokens,
+                        "max_output_tokens": output,
+                        "max_duration_seconds": seconds,
+                    },
+                })
+        return cls.from_config(config)
+
+
+def _changed_line_count(diff: str) -> int:
+    """Count changed lines without treating hunk headers as additions."""
+    return sum(
+        1 for line in diff.splitlines()
+        if (line.startswith("+") and not line.startswith("+++"))
+        or (line.startswith("-") and not line.startswith("---"))
+    )
+
 
 def _env_int(name: str, default: int) -> int:
     try:
diff --git a/pilot/review/opencode.py b/pilot/review/opencode.py
index 7c54dce..ce6f5cf 100644
--- a/pilot/review/opencode.py
+++ b/pilot/review/opencode.py
@@ -440,7 +440,7 @@ def run_lenses_review(
     always has: prose + a final ```json fence with the legacy schema).
     """
     os.makedirs(WORK_ROOT, exist_ok=True)
-    budget = budget or Budget.from_config(config)
+    budget = budget or Budget.for_review(config, diff)
     budget_state = budget_state or BudgetState(budget)
     workdir = tempfile.mkdtemp(prefix=f"{repo.replace('/', '_')}-{sha[:8]}-", dir=WORK_ROOT)
     keep = bool(os.environ.get("PRAGENT_KEEP_WORK"))
@@ -687,7 +687,7 @@ def run(
             additional_context=additional_context,
         )
 
-    budget = Budget.from_config(config)
+    budget = Budget.for_review(config, diff)
     budget_state = BudgetState(budget)
     os.makedirs(WORK_ROOT, exist_ok=True)
     workdir = tempfile.mkdtemp(prefix=f"{repo.replace('/', '_')}-{sha[:8]}-", dir=WORK_ROOT)
diff --git a/tests/pilot/review_tests/budget_test.py b/tests/pilot/review_tests/budget_test.py
index 58bb5d1..bb5e6da 100644
--- a/tests/pilot/review_tests/budget_test.py
+++ b/tests/pilot/review_tests/budget_test.py
@@ -18,6 +18,19 @@ def test_budget_reads_config_over_environment(monkeypatch):
     assert budget.max_steps == 7
 
 
+def test_budget_scales_for_broad_diff():
+    diff = "".join("+changed\n" for _ in range(850))
+    budget = Budget.for_review({}, diff)
+    assert budget.max_steps == 60
+    assert budget.max_total_tokens == 800_000
+
+
+def test_explicit_budget_wins_over_diff_profile():
+    diff = "".join("+changed\n" for _ in range(2_100))
+    budget = Budget.for_review({"budget": {"max_steps": 9}}, diff)
+    assert budget.max_steps == 9
+
+
 def test_budget_state_stops_at_token_limit():
     state = BudgetState(Budget(max_steps=20, max_total_tokens=100))
     assert state.record({"steps": 1, "total": 60, "output": 10}) == ""