feat(ai_review): render humanized token counts in usage + inline

pilot/ai_review.py

@@ -1033,7 +1033,7 @@ def inline_comment_body(f: dict) -> str:
     tok = f.get("_tok_attrib")
     if tok is not None:
         pct = (f.get("_tok_pct", 0.0) or 0.0) * 100
-        body += f"\n\n🪙 ~{tok} tok ({pct:.0f}% · attributed output)"
+        body += f"\n\n🪙 ~{fmt_tokens(tok)} tok ({pct:.0f}% · attributed output)"
     return body
 
 
@@ -1122,7 +1122,9 @@ def _render_collapsible_usage(usage: dict | None, model: str, config: dict | Non
         "<summary>🔋 AI Usage & Run Details</summary>",
         "",
         f"- **Model / Engine**: `{model}` · opencode · {usage.get('steps', 0)} steps · {dur_s}",
-        f"- **Total Tokens**: {in_tok} in / {out_tok} out ({reason_tok} reasoning, cache {cache_r} read / {cache_w} write, {total} total)",
+        f"- **Total Tokens**: {fmt_tokens(in_tok)} in / {fmt_tokens(out_tok)} out "
+        f"({fmt_tokens(reason_tok)} reasoning, cache {fmt_tokens(cache_r)} read / "
+        f"{fmt_tokens(cache_w)} write, {fmt_tokens(total)} total)",
         f"- **Est. cost on {eq_label}**: {eq_s}{eq_note}",
         f"- **Actual**: {actual_s}{actual_note}",
         f"- **Scope**: {scope}",

tests/pilot/test_ai_review.py

@@ -335,7 +335,7 @@ def test_inline_comment_body_with_token_attribution():
          "fix": "f", "suggestion": "", "reference": "",
          "_tok_attrib": 1234, "_tok_pct": 0.30}
     body = inline_comment_body(f)
-    assert "🪙 ~1234 tok" in body
+    assert "🪙 ~1,234 (1.2K) tok" in body
     assert "30%" in body
     assert "attributed output" in body
 
@@ -757,7 +757,7 @@ def test_render_collapsible_usage_renders_totals():
     assert "`glm-5.2:cloud`" in sec
     assert "7 steps" in sec
     assert "142.0s" in sec
-    assert "18420 in / 612 out" in sec and "19032 total" in sec
+    assert "18,420 (18.4K) in / 612 out" in sec and "19,032 (19.0K) total" in sec
     assert "$0.00" in sec
     assert "Whole-repo checkout" in sec
     assert "attributed" in sec
@@ -824,7 +824,7 @@ def test_render_collapsible_usage_contains_details():
     assert "<summary>🔋 AI Usage & Run Details</summary>" in block
     assert "</details>" in block
     assert "glm-5.2:cloud" in block
-    assert "1000 in / 200 out" in block
+    assert "1,000 (1.0K) in / 200 out" in block
 
 
 def test_render_collapsible_usage_empty_when_no_usage():
@@ -1668,3 +1668,27 @@ def test_fmt_tokens_none():
 def test_fmt_tokens_negative():
     assert fmt_tokens(-1) == "?"
 
+
+# ---------------------------------------------------------------------------
+# fmt_tokens — applied in usage + inline comment bodies (Task 3)
+# ---------------------------------------------------------------------------
+
+
+def test_collapsible_usage_renders_humanized_tokens():
+    usage = {"input": 2_071_025, "output": 17303, "reasoning": 0,
+             "cache_read": 0, "cache_write": 0, "total": 2_088_328,
+             "cost": 0.0, "steps": 1, "duration_s": 10.0}
+    block = _render_collapsible_usage(usage, "glm-5.2:cloud", config={})
+    assert "2,071,025 (2.1M) in" in block
+    assert "17,303 (17.3K) out" in block
+
+
+def test_inline_comment_body_humanized_tokens():
+    # Value chosen > 1000 so fmt_tokens actually adds the comma + short suffix;
+    # the plan's 362 would render identically with or without fmt_tokens.
+    f = {"severity": "medium", "path": "x.py", "line": 1,
+         "problem": "p", "fix": "", "suggestion": "", "reference": "",
+         "_tok_attrib": 17303, "_tok_pct": 0.11}
+    body = inline_comment_body(f)
+    assert "🪙 ~17,303 (17.3K) tok" in body
+