feat(agent): tighten prompt to bound beyond-diff reads + de-generalize cost-model labels

Three changes from operator feedback:

1. Per-comment � attribution restored on inline comments (operator wants
   it back — the PR-level collapsible is collapsed by default, so the
   attribution is the visible signal of per-finding cost share).
   Hidden only when no _tok_attrib was computed (legacy callers / ollama
   path without usage metering).

2. Agent prompt now bounds reads beyond the diff — the single biggest
   driver of input-token bloat on long agent loops:
     * ≤ 5 file reads beyond the diff for the entire review
     * ≤ 80 lines per read (use --offset + --limit)
     * ≤ 3 grep calls beyond the diff (prefer rtk grep)
     * no re-reads of files already seen
     * no directory walks (ls -R, find .)
     * honor .pr-review.json:exclude_paths

3. De-generalize cost_model calibration labels. The OBSERVED_RUNS list
   referred to `gitea_admin/pragent#7` — a real internal repo path that
   blocks commercialization. Replaced with `internal/hardening-PR (16
   files, 1020 insertions / 91 deletions)`. The numbers (input/output
   tokens, steps, duration) are unchanged — only the labels are
   generic.

Tests:
  * test_inline_comment_body_with_attribution_line — asserts 🪙 line
    shows when _tok_attrib is set
  * test_inline_comment_body_no_attribution_no_coin_line — still
    verifies the line is hidden when no attribution data
  * test_observed_report_prices_every_model — asserts no internal
    repo name appears in the rendered report
Co-Authored-By: Claude <noreply@anthropic.com>

tests/pilot/test_ai_review.py

@@ -326,15 +326,18 @@ def test_inline_comment_body_severity_emoji_mapping():
         assert badge in inline_comment_body(f), f"{sev} → {badge}"
 
 
-def test_inline_comment_body_no_token_attribution():
-    # Per spec: no per-comment 🪙 token attribution line.
+def test_inline_comment_body_with_token_attribution():
+    # Operator wants per-comment attribution back: every inline comment shows
+    # the attributed output tokens + share of total. Hidden only when no
+    # attribution data was computed (legacy callers / ollama path without
+    # usage metering).
     f = {"severity": "high", "path": "a", "line": 1, "problem": "p",
          "fix": "f", "suggestion": "", "reference": "",
-         "_tok_attrib": 1234, "_tok_pct": 0.3}
+         "_tok_attrib": 1234, "_tok_pct": 0.30}
     body = inline_comment_body(f)
-    assert "🪙" not in body
-    assert "tok" not in body.lower().split("fix")[0]  # only in fix is OK
-    assert "attributed" not in body
+    assert "🪙 ~1234 tok" in body
+    assert "30%" in body
+    assert "attributed output" in body
 
 
 def test_summary_bullets_format():
@@ -673,15 +676,17 @@ def test_compute_attribution_noop_on_empty_or_zero_budget():
     assert "_tok_attrib" not in fs[0]
 
 
-def test_inline_comment_body_no_attribution_line():
-    # Per spec: NO per-comment token attribution — that telemetry lives in the
-    # collapsible block on the PR-level comment.
+def test_inline_comment_body_with_attribution_line():
+    # Operator wants per-comment attribution back: every inline comment shows
+    # the attributed output tokens + share of total. Hidden only when no
+    # attribution data was computed (legacy callers / ollama path without
+    # usage metering).
     f = {"severity": "high", "path": "a", "line": 1, "problem": "bad", "fix": "swap",
          "suggestion": "", "_tok_attrib": 180, "_tok_pct": 0.29}
     body = inline_comment_body(f)
-    assert "🪙" not in body
-    assert "tok" not in body
-    assert "attributed" not in body
+    assert "🪙 ~180 tok" in body
+    assert "29%" in body
+    assert "attributed output" in body
 
 
 def test_inline_comment_body_no_attribution_no_coin_line():

tests/pilot/test_cost_model.py

@@ -226,7 +226,9 @@ def test_observed_report_prices_every_model():
     text = cm.observed_report(["claude-opus-5", "gpt-5.6-luna"])
     assert "Claude Opus 5" in text
     assert "GPT-5.6 Luna" in text
-    assert "pragent#7" in text
+    # Labels are generic (no internal repo names) for commercialization.
+    assert "gitea_admin" not in text
+    assert "internal/hardening-PR" in text
 
 
 def test_model_is_within_an_order_of_magnitude_of_the_measurement():