Skip to content

Address code review feedback for build-and-summarize #775

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
jbachorik wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Address code review feedback for build-and-summarize #775

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
181 changes: 172 additions & 9 deletions .claude/commands/build-and-summarize
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,13 +67,176 @@ else
echo "✖ Gradle failed with status $status. Full log at: $LOG"
fi

# Hand over to your logs analyst agent — keep the main session output tiny.
# Generate the summary artifacts deterministically — no LLM, no claude spawn.
echo
echo "Delegating to gradle-logs-analyst agent…"
# If your CLI supports non-streaming, set it here to avoid verbose output.
# Example (uncomment if supported): export CLAUDE_NO_STREAM=1

# Sub-agents would inherit the full parent env, including CLAUDECODE, which
# apparently causes problems with some versions of Claude (e.g. 4.6).
unset CLAUDECODE
claude "Act as the gradle-logs-analyst agent to parse the build log at: $LOG. Generate the required Gradle summary artifacts as specified in the gradle-logs-analyst agent definition."
echo "Generating gradle summary…"
python3 - "$LOG" <<'PYEOF' || echo "⚠ gradle summary generation failed — full log at: $LOG"
import json, os, re, sys

log_path = sys.argv[1] if len(sys.argv) > 1 else ""
OUT_DIR = os.path.join("build", "reports", "claude")
MD = os.path.join(OUT_DIR, "gradle-summary.md")
JS = os.path.join(OUT_DIR, "gradle-summary.json")

status, total_time, cur_task, cur_test_task = "UNKNOWN", None, None, None
failed_tasks, headlines, dep_issues, test_failures = [], [], [], []
warnings, seen_warnings = [], set()
tests = {"total": 0, "failed": 0, "skipped": 0, "modules": {}}

RE_STATUS = re.compile(r"^BUILD (SUCCESSFUL|FAILED)(?: in (.+?))?\s*$")
RE_TASK = re.compile(r"^> Task (\S+)")
RE_TEST_TASK = re.compile(r"(?i)test|gtest")
RE_GSUM = re.compile(r"(\d+) tests? (successful|failed|skipped)")
RE_COMP = re.compile(r"(\d+) tests? completed(?:, (\d+) failed)?(?:, (\d+) skipped)?")
RE_GTEST_P = re.compile(r"\[ PASSED \] (\d+) tests?")
RE_GTEST_F = re.compile(r"\[ FAILED \] (\d+) tests?")
RE_DEP = re.compile(r"Could not (?:resolve|find|get)|timed out|status code: 40[13]|artifact .* not found", re.I)
RE_WARN = re.compile(r"\bw: |warning:|deprecat", re.I)
RE_FAILURE = re.compile(r"^FAILURE: Build (failed with an exception|completed with \d+ failures)")
RE_TASK_IN_MSG = re.compile(r"task '(:[^']+)'")

def mod(name):
return tests["modules"].setdefault(name, {"total": 0, "failed": 0, "skipped": 0})

def add_counts(name, ok, failed, skipped):
m = mod(name)
m["total"] += ok + failed + skipped
m["failed"] += failed
m["skipped"] += skipped
tests["total"] += ok + failed + skipped
tests["failed"] += failed
tests["skipped"] += skipped

if not log_path or not os.path.isfile(log_path) or os.path.getsize(log_path) == 0:
why = f"log not found: {log_path!r}" if not log_path or not os.path.isfile(log_path) else "log is empty"
os.makedirs(OUT_DIR, exist_ok=True)
open(MD, "w").write(f"# Gradle Summary\n\n- Status: UNKNOWN ({why})\n\nFull log unavailable or empty.\n")
json.dump({"status": "UNKNOWN", "totalTime": None, "failedTasks": [], "warnings": [],
"tests": tests, "slowTasks": [], "depIssues": [why], "actions": []}, open(JS, "w"), indent=1)
print(f"Gradle log unusable ({why}); wrote {MD} and {JS}")
sys.exit(0)

grab_headline = False
collecting_headline = False
with open(log_path, encoding="utf-8", errors="replace") as f:
for line in f:
line = line.rstrip("\n")
m = RE_STATUS.match(line)
if m:
status = m.group(1)
total_time = m.group(2)
continue
m = RE_TASK.match(line)
if m:
cur_task = m.group(1)
if RE_TEST_TASK.search(cur_task):
cur_test_task = cur_task
if line.endswith("FAILED") and m.group(1) not in failed_tasks:
failed_tasks.append(m.group(1))
continue
if RE_FAILURE.search(line):
grab_headline = True
continue
if grab_headline and line.strip().startswith("* What went wrong"):
headlines.append("")
collecting_headline = True
continue
if grab_headline and collecting_headline:
s = line.strip()
if s.startswith("*") or not s:
collecting_headline = False
continue
if headlines and len(headlines[-1]) < 200:
headlines[-1] += (" " if headlines[-1] else "") + s
continue
m = RE_COMP.search(line)
if m:
total = int(m.group(1))
failed = int(m.group(2) or 0)
skipped = int(m.group(3) or 0)
add_counts(cur_test_task or cur_task or "(unknown)", total - failed - skipped, failed, skipped)
continue
m = RE_GSUM.search(line)
if m:
n, verb = int(m.group(1)), m.group(2)
mm = mod(cur_test_task or cur_task or "(unknown)")
mm["total"] += n
tests["total"] += n
if verb == "failed":
mm["failed"] += n
tests["failed"] += n
elif verb == "skipped":
mm["skipped"] += n
tests["skipped"] += n
continue
m = RE_GTEST_P.search(line)
if m:
add_counts(cur_test_task or cur_task or "(gtest)", int(m.group(1)), 0, 0)
continue
m = RE_GTEST_F.search(line)
if m:
add_counts(cur_test_task or cur_task or "(gtest)", 0, int(m.group(1)), 0)
continue
if re.search(r" > \S+(?:\.\S+)+.* FAILED$", line) or re.search(r"\[ FAILED \] (\S+)", line):
test_failures.append(line.strip())
continue
if RE_DEP.search(line) and len(dep_issues) < 20:
if line not in dep_issues:
dep_issues.append(line.strip())
continue
wm = RE_WARN.search(line)
if wm and len(warnings) < 40:
key = line.strip()[:160]
if key not in seen_warnings:
seen_warnings.add(key)
warnings.append(key)

headline_by_task = {}
for h in headlines:
tm = RE_TASK_IN_MSG.search(h)
if tm and tm.group(1) in failed_tasks:
headline_by_task[tm.group(1)] = h
# Fallback for single-failure builds where the headline never names its task explicitly.
if not headline_by_task and len(failed_tasks) == 1 and headlines:
headline_by_task[failed_tasks[0]] = headlines[0]
failed = [t + (" — " + headline_by_task[t] if t in headline_by_task else "") for t in failed_tasks]
data = {"status": status, "totalTime": total_time, "failedTasks": failed, "warnings": warnings,
"tests": tests, "slowTasks": [], "depIssues": dep_issues, "actions": []}

os.makedirs(OUT_DIR, exist_ok=True)
with open(JS, "w") as f:
json.dump(data, f, indent=1)

L = ["# Gradle Summary\n", f"- Status: {status}", f"- Total time: {total_time or 'UNKNOWN'}",
f"- Log: {log_path}\n"]
if failed:
L.append("## Failing Tasks")
L += [f"- {t}" for t in failed]
L.append("")
if headlines:
L.append("## Primary Failure")
L += [f"```text\n{h}\n```" for h in headlines[:3] if h]
L.append("")
if tests["total"]:
L.append("## Tests")
L.append(f"- Total: {tests['total']}, failed: {tests['failed']}, skipped: {tests['skipped']}")
for name, m in tests["modules"].items():
L.append(f" - {name}: {m['total']} total, {m['failed']} failed, {m['skipped']} skipped")
if test_failures:
L.append("- Top failing tests:")
L += [f" - {t}" for t in test_failures[:10]]
L.append("")
if warnings:
L.append("## Warnings")
L += [f"- {w}" for w in warnings[:20]]
L.append("")
if dep_issues:
L.append("## Dependency / Network Issues")
L += [f"- {d}" for d in dep_issues[:10]]
L.append("")
L.append("- Per-task durations are not present in plain `-i` console logs; slowTasks omitted.")
open(MD, "w").write("\n".join(L) + "\n")

print(f"{status} (time: {total_time or 'n/a'}); {len(failed)} failing task(s), {tests['failed']} test failure(s)")
print(f"Wrote {MD} and {JS}")
PYEOF
Loading