Merge PR #10: read the AI-USAGE opt-in at render time

Late AI-USAGE labels now reach the review body. Verified live on this PR: AI-REVIEW then AI-USAGE six seconds later, usage block present in review #131.

pilot/ai_review.py

@@ -66,6 +66,8 @@ SHA_MARKER = "<!-- pragent:sha={sha} -->"
 _SHA_MARKER_RE = re.compile(r"<!-- pragent:sha=([0-9a-f]{7,40}) -->")
 
 AI_REVIEW_LABEL = "AI-REVIEW"
+# Opt-in label for the token-usage block. Read at render time — see pr_has_label.
+AI_USAGE_LABEL = "AI-USAGE"
 SEVERITIES = ("critical", "high", "medium", "low")
 # Severity rank — higher = more severe. Used by `apply_repo_config` to drop
 # findings below `severity_threshold`. Critical=3, high=2, medium=1, low=0.
@@ -156,6 +158,33 @@ def parse_text_blocks(content: list) -> str:
     return "\n".join(out).strip()
 
 
+def pr_has_label(api: str, repo: str, index: str, token: str, label: str) -> bool:
+    """True if the PR currently carries `label`. False on any failure.
+
+    Read at RENDER time, not at review start. A reviewer labels AI-REVIEW and
+    AI-USAGE seconds apart; the review claims on the first event and the
+    second is dropped by the in-flight dedupe, so the trigger payload never
+    sees the opt-in. Re-reading when the review begins is no better — that is
+    still milliseconds after the first click. Only a read taken once the
+    review has finished (a minute or more later) reliably sees the label.
+    """
+    try:
+        code, raw = gitea_get(api, repo, f"issues/{index}/labels", token)
+        if code >= 300:
+            return False
+        data = json.loads(raw.decode() or "[]")
+    except Exception as e:
+        print(f"pragent: could not re-read labels for {repo}#{index}: {e}",
+              file=sys.stderr, flush=True)
+        return False
+    if not isinstance(data, list):
+        return False
+    return any(
+        (isinstance(x, dict) and x.get("name") == label) or x == label
+        for x in data
+    )
+
+
 def _int_env(name: str, default: int) -> int:
     """Read an int from the environment, falling back on anything unparseable.
 
@@ -1896,6 +1925,13 @@ def review_pr(
                     file=sys.stderr, flush=True,
                 )
                 salvaged = salvage_summary(stdout)
+                # The AI-USAGE opt-in is re-checked HERE, at render time: the label
+                # is usually applied moments after AI-REVIEW, long after this
+                # review was claimed and its trigger payload frozen.
+                if not report_usage:
+                    report_usage = pr_has_label(api, repo, index, token, AI_USAGE_LABEL)
+                    if report_usage and usage and usage.get('output'):
+                        compute_attribution(findings, usage['output'])
                 usage_section = _render_collapsible_usage(usage, model, config=config) if report_usage else ""
                 post_review(api, repo, index, token, format_review_body(
                     salvaged or "AI review produced no parseable output.",
@@ -1936,6 +1972,13 @@ def review_pr(
         # for it.
         if report_usage and usage and usage.get("output"):
             compute_attribution(findings, usage["output"])
+        # The AI-USAGE opt-in is re-checked HERE, at render time: the label
+        # is usually applied moments after AI-REVIEW, long after this
+        # review was claimed and its trigger payload frozen.
+        if not report_usage:
+            report_usage = pr_has_label(api, repo, index, token, AI_USAGE_LABEL)
+            if report_usage and usage and usage.get('output'):
+                compute_attribution(findings, usage['output'])
         usage_section = _render_collapsible_usage(usage, model, config=config) if report_usage else ""
 
         # Anchor against the RAW diff, never the compressed one. Compression

tests/pilot/test_ai_review.py

@@ -616,6 +616,35 @@ def test_reference_non_url_renders_as_plain_text():
     assert "](CVE-" not in body
 
 
+def test_pr_has_label_reads_the_live_labels(monkeypatch):
+    # The AI-USAGE opt-in is read at render time, not from the trigger
+    # payload: labelling AI-REVIEW then AI-USAGE is two events, the review
+    # claims on the first, and the second is dropped by the in-flight dedupe.
+    seen = {}
+
+    def _get(api, repo, path, token, accept="application/json"):
+        seen["path"] = path
+        return 200, b'[{"name": "AI-REVIEW"}, {"name": "AI-USAGE"}]'
+
+    monkeypatch.setattr(ai_review, "gitea_get", _get)
+    assert ai_review.pr_has_label("http://api", "o/r", "9", "t", "AI-USAGE") is True
+    assert seen["path"] == "issues/9/labels"
+    assert ai_review.pr_has_label("http://api", "o/r", "9", "t", "NOPE") is False
+
+
+def test_pr_has_label_survives_a_broken_api(monkeypatch):
+    def _boom(*a, **k):
+        raise RuntimeError("gitea down")
+    monkeypatch.setattr(ai_review, "gitea_get", _boom)
+    assert ai_review.pr_has_label("http://api", "o/r", "9", "t", "AI-USAGE") is False
+
+    monkeypatch.setattr(ai_review, "gitea_get", lambda *a, **k: (404, b"nope"))
+    assert ai_review.pr_has_label("http://api", "o/r", "9", "t", "AI-USAGE") is False
+
+    monkeypatch.setattr(ai_review, "gitea_get", lambda *a, **k: (200, b'{"not": "a list"}'))
+    assert ai_review.pr_has_label("http://api", "o/r", "9", "t", "AI-USAGE") is False
+
+
 def test_int_env_falls_back_on_garbage(monkeypatch, capsys):
     monkeypatch.setenv("PRAGENT_DIFF_CONTEXT", "two")
     assert ai_review._int_env("PRAGENT_DIFF_CONTEXT", 1) == 1