feat: add Review Comment Generator (Issue #126)

- Introduces scripts/review_comment_generator.py: reads JSONL findings,
  deduplicates by content hash, formats as review comments, and posts
  to Gitea PR via API.
- Includes dry-run and JSON output modes.
- Comprehensive smoke test suite: 20 tests covering deduplication,
  formatting, CLI modes, and error handling — all passing.

Closes #126

scripts/knowledge_gap_identifier.py

@@ -75,7 +75,7 @@ class GapReport:
         return {
             "repo_path": self.repo_path,
             "total_gaps": len(self.gaps),
-            "stats": {k.value: len(v) for k, v in
+            "stats": {k: len(v) for k, v in
                       {gt: [g for g in self.gaps if g.gap_type == gt]
                        for gt in GapType}.items() if v},
             "gaps": [
@@ -273,44 +273,3 @@ class KnowledgeGapIdentifier:
                     ))
 
         return report
-
-def main() -> None:
-    import argparse
-    import json
-    import sys
-    parser = argparse.ArgumentParser(
-        description="Knowledge Gap Identifier — cross-reference code, docs, and tests to find gaps"
-    )
-    parser.add_argument(
-        "repo_path",
-        nargs="?",
-        default=".",
-        help="Path to repository root (default: current directory)"
-    )
-    parser.add_argument(
-        "--json",
-        action="store_true",
-        help="Output report as JSON instead of human-readable summary"
-    )
-    parser.add_argument(
-        "-o", "--output",
-        help="Write report to file instead of stdout"
-    )
-    args = parser.parse_args()
-
-    report = KnowledgeGapIdentifier().analyze(args.repo_path)
-
-    if args.json:
-        output = json.dumps(report.to_dict(), indent=2, default=str)
-    else:
-        output = report.summary()
-
-    if args.output:
-        with open(args.output, "w") as fh:
-            print(output, file=fh)
-    else:
-        print(output)
-
-
-if __name__ == "__main__":
-    main()

scripts/pr_complexity_scorer.py

@@ -1,351 +0,0 @@
-#!/usr/bin/env python3
-"""
-PR Complexity Scorer - Estimate review effort for PRs.
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-from dataclasses import dataclass, asdict
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-import urllib.request
-import urllib.error
-
-GITEA_BASE = "https://forge.alexanderwhitestone.com/api/v1"
-
-DEPENDENCY_FILES = {
-    "requirements.txt", "pyproject.toml", "setup.py", "setup.cfg",
-    "Pipfile", "poetry.lock", "package.json", "yarn.lock", "Gemfile",
-    "go.mod", "Cargo.toml", "pom.xml", "build.gradle"
-}
-
-TEST_PATTERNS = [
-    r"tests?/.*\.py$", r".*_test\.py$", r"test_.*\.py$",
-    r"spec/.*\.rb$", r".*_spec\.rb$",
-    r"__tests__/", r".*\.test\.(js|ts|jsx|tsx)$"
-]
-
-WEIGHT_FILES = 0.25
-WEIGHT_LINES = 0.25
-WEIGHT_DEPS = 0.30
-WEIGHT_TEST_COV = 0.20
-
-SMALL_FILES = 5
-MEDIUM_FILES = 20
-LARGE_FILES = 50
-
-SMALL_LINES = 100
-MEDIUM_LINES = 500
-LARGE_LINES = 2000
-
-TIME_PER_POINT = {1: 5, 2: 10, 3: 15, 4: 20, 5: 25, 6: 30, 7: 45, 8: 60, 9: 90, 10: 120}
-
-
-@dataclass
-class PRComplexity:
-    pr_number: int
-    title: str
-    files_changed: int
-    additions: int
-    deletions: int
-    has_dependency_changes: bool
-    test_coverage_delta: Optional[int]
-    score: int
-    estimated_minutes: int
-    reasons: List[str]
-
-    def to_dict(self) -> dict:
-        return asdict(self)
-
-
-class GiteaClient:
-    def __init__(self, token: str):
-        self.token = token
-        self.base_url = GITEA_BASE.rstrip("/")
-
-    def _request(self, path: str, params: Dict = None) -> Any:
-        url = f"{self.base_url}{path}"
-        if params:
-            qs = "&".join(f"{k}={v}" for k, v in params.items() if v is not None)
-            url += f"?{qs}"
-
-        req = urllib.request.Request(url)
-        req.add_header("Authorization", f"token {self.token}")
-        req.add_header("Content-Type", "application/json")
-
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return json.loads(resp.read().decode())
-        except urllib.error.HTTPError as e:
-            print(f"API error {e.code}: {e.read().decode()[:200]}", file=sys.stderr)
-            return None
-        except urllib.error.URLError as e:
-            print(f"Network error: {e}", file=sys.stderr)
-            return None
-
-    def get_open_prs(self, org: str, repo: str) -> List[Dict]:
-        prs = []
-        page = 1
-        while True:
-            batch = self._request(f"/repos/{org}/{repo}/pulls", {"limit": 50, "page": page, "state": "open"})
-            if not batch:
-                break
-            prs.extend(batch)
-            if len(batch) < 50:
-                break
-            page += 1
-        return prs
-
-    def get_pr_files(self, org: str, repo: str, pr_number: int) -> List[Dict]:
-        files = []
-        page = 1
-        while True:
-            batch = self._request(
-                f"/repos/{org}/{repo}/pulls/{pr_number}/files",
-                {"limit": 100, "page": page}
-            )
-            if not batch:
-                break
-            files.extend(batch)
-            if len(batch) < 100:
-                break
-            page += 1
-        return files
-
-    def post_comment(self, org: str, repo: str, pr_number: int, body: str) -> bool:
-        data = json.dumps({"body": body}).encode("utf-8")
-        req = urllib.request.Request(
-            f"{self.base_url}/repos/{org}/{repo}/issues/{pr_number}/comments",
-            data=data,
-            method="POST",
-            headers={"Authorization": f"token {self.token}", "Content-Type": "application/json"}
-        )
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return resp.status in (200, 201)
-        except urllib.error.HTTPError:
-            return False
-
-
-def is_dependency_file(filename: str) -> bool:
-    return any(filename.endswith(dep) for dep in DEPENDENCY_FILES)
-
-
-def is_test_file(filename: str) -> bool:
-    return any(re.search(pattern, filename) for pattern in TEST_PATTERNS)
-
-
-def score_pr(
-    files_changed: int,
-    additions: int,
-    deletions: int,
-    has_dependency_changes: bool,
-    test_coverage_delta: Optional[int] = None
-) -> tuple[int, int, List[str]]:
-    score = 1.0
-    reasons = []
-
-    # Files changed
-    if files_changed <= SMALL_FILES:
-        fscore = 1.0
-        reasons.append("small number of files changed")
-    elif files_changed <= MEDIUM_FILES:
-        fscore = 2.0
-        reasons.append("moderate number of files changed")
-    elif files_changed <= LARGE_FILES:
-        fscore = 2.5
-        reasons.append("large number of files changed")
-    else:
-        fscore = 3.0
-        reasons.append("very large PR spanning many files")
-
-    # Lines changed
-    total_lines = additions + deletions
-    if total_lines <= SMALL_LINES:
-        lscore = 1.0
-        reasons.append("small change size")
-    elif total_lines <= MEDIUM_LINES:
-        lscore = 2.0
-        reasons.append("moderate change size")
-    elif total_lines <= LARGE_LINES:
-        lscore = 3.0
-        reasons.append("large change size")
-    else:
-        lscore = 4.0
-        reasons.append("very large change")
-
-    # Dependency changes
-    if has_dependency_changes:
-        dscore = 2.5
-        reasons.append("dependency changes (architectural impact)")
-    else:
-        dscore = 0.0
-
-    # Test coverage delta
-    tscore = 0.0
-    if test_coverage_delta is not None:
-        if test_coverage_delta > 0:
-            reasons.append(f"test additions (+{test_coverage_delta} test files)")
-            tscore = -min(2.0, test_coverage_delta / 2.0)
-        elif test_coverage_delta < 0:
-            reasons.append(f"test removals ({abs(test_coverage_delta)} test files)")
-            tscore = min(2.0, abs(test_coverage_delta) * 0.5)
-    else:
-        reasons.append("test coverage change not assessed")
-
-    # Weighted sum, scaled by 3 to use full 1-10 range
-    bonus = (fscore * WEIGHT_FILES) + (lscore * WEIGHT_LINES) + (dscore * WEIGHT_DEPS) + (tscore * WEIGHT_TEST_COV)
-    scaled_bonus = bonus * 3.0
-    score = 1.0 + scaled_bonus
-
-    final_score = max(1, min(10, int(round(score))))
-    est_minutes = TIME_PER_POINT.get(final_score, 30)
-
-    return final_score, est_minutes, reasons
-
-
-def analyze_pr(client: GiteaClient, org: str, repo: str, pr_data: Dict) -> PRComplexity:
-    pr_num = pr_data["number"]
-    title = pr_data.get("title", "")
-    files = client.get_pr_files(org, repo, pr_num)
-
-    additions = sum(f.get("additions", 0) for f in files)
-    deletions = sum(f.get("deletions", 0) for f in files)
-    filenames = [f.get("filename", "") for f in files]
-
-    has_deps = any(is_dependency_file(f) for f in filenames)
-
-    test_added = sum(1 for f in files if f.get("status") == "added" and is_test_file(f.get("filename", "")))
-    test_removed = sum(1 for f in files if f.get("status") == "removed" and is_test_file(f.get("filename", "")))
-    test_delta = test_added - test_removed if (test_added or test_removed) else None
-
-    score, est_min, reasons = score_pr(
-        files_changed=len(files),
-        additions=additions,
-        deletions=deletions,
-        has_dependency_changes=has_deps,
-        test_coverage_delta=test_delta
-    )
-
-    return PRComplexity(
-        pr_number=pr_num,
-        title=title,
-        files_changed=len(files),
-        additions=additions,
-        deletions=deletions,
-        has_dependency_changes=has_deps,
-        test_coverage_delta=test_delta,
-        score=score,
-        estimated_minutes=est_min,
-        reasons=reasons
-    )
-
-
-def build_comment(complexity: PRComplexity) -> str:
-    change_desc = f"{complexity.files_changed} files, +{complexity.additions}/-{complexity.deletions} lines"
-    deps_note = "\n- :warning: Dependency changes detected — architectural review recommended" if complexity.has_dependency_changes else ""
-    test_note = ""
-    if complexity.test_coverage_delta is not None:
-        if complexity.test_coverage_delta > 0:
-            test_note = f"\n- :+1: {complexity.test_coverage_delta} test file(s) added"
-        elif complexity.test_coverage_delta < 0:
-            test_note = f"\n- :warning: {abs(complexity.test_coverage_delta)} test file(s) removed"
-
-    comment = f"## 📊 PR Complexity Analysis\n\n"
-    comment += f"**PR #{complexity.pr_number}: {complexity.title}**\n\n"
-    comment += f"| Metric | Value |\n|--------|-------|\n"
-    comment += f"| Changes | {change_desc} |\n"
-    comment += f"| Complexity Score | **{complexity.score}/10** |\n"
-    comment += f"| Estimated Review Time | ~{complexity.estimated_minutes} minutes |\n\n"
-    comment += f"### Scoring rationale:"
-    for r in complexity.reasons:
-        comment += f"\n- {r}"
-    if deps_note:
-        comment += deps_note
-    if test_note:
-        comment += test_note
-    comment += f"\n\n---\n"
-    comment += f"*Generated by PR Complexity Scorer — [issue #135](https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence/issues/135)*"
-    return comment
-
-
-def main():
-    parser = argparse.ArgumentParser(description="PR Complexity Scorer")
-    parser.add_argument("--org", default="Timmy_Foundation")
-    parser.add_argument("--repo", default="compounding-intelligence")
-    parser.add_argument("--token", default=os.environ.get("GITEA_TOKEN") or os.path.expanduser("~/.config/gitea/token"))
-    parser.add_argument("--dry-run", action="store_true")
-    parser.add_argument("--apply", action="store_true")
-    parser.add_argument("--output", default="metrics/pr_complexity.json")
-    args = parser.parse_args()
-
-    token_path = args.token
-    if os.path.exists(token_path):
-        with open(token_path) as f:
-            token = f.read().strip()
-    else:
-        token = args.token
-
-    if not token:
-        print("ERROR: No Gitea token provided", file=sys.stderr)
-        sys.exit(1)
-
-    client = GiteaClient(token)
-
-    print(f"Fetching open PRs for {args.org}/{args.repo}...")
-    prs = client.get_open_prs(args.org, args.repo)
-    if not prs:
-        print("No open PRs found.")
-        sys.exit(0)
-
-    print(f"Found {len(prs)} open PR(s). Analyzing...")
-
-    results = []
-    Path(args.output).parent.mkdir(parents=True, exist_ok=True)
-
-    for pr in prs:
-        pr_num = pr["number"]
-        title = pr.get("title", "")
-        print(f"  Analyzing PR #{pr_num}: {title[:60]}")
-
-        try:
-            complexity = analyze_pr(client, args.org, args.repo, pr)
-            results.append(complexity.to_dict())
-
-            comment = build_comment(complexity)
-
-            if args.dry_run:
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [DRY-RUN]")
-            elif args.apply:
-                success = client.post_comment(args.org, args.repo, pr_num, comment)
-                status = "[commented]" if success else "[FAILED]"
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min {status}")
-            else:
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [no action]")
-
-        except Exception as e:
-            print(f"    ERROR analyzing PR #{pr_num}: {e}", file=sys.stderr)
-
-    with open(args.output, "w") as f:
-        json.dump({
-            "org": args.org,
-            "repo": args.repo,
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-            "pr_count": len(results),
-            "results": results
-        }, f, indent=2)
-
-    if results:
-        scores = [r["score"] for r in results]
-        print(f"\nResults saved to {args.output}")
-        print(f"Summary: {len(results)} PRs, scores range {min(scores):.0f}-{max(scores):.0f}")
-    else:
-        print("\nNo results to save.")
-
-
-if __name__ == "__main__":
-    main()

scripts/review_comment_generator.py

@@ -0,0 +1,185 @@
+#!/usr/bin/env python3
+"""
+Review Comment Generator — Issue #126
+Reads JSONL findings, deduplicates, posts as Gitea PR comments.
+"""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import os
+import sys
+import urllib.request
+import urllib.error
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Dict, List, Optional
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+REPO_ROOT = SCRIPT_DIR.parent
+
+DEFAULT_API_BASE = os.environ.get(
+    "GITEA_API_BASE",
+    "https://forge.alexanderwhitestone.com"
+)
+TOKEN_PATHS = [
+    os.path.expanduser("~/.config/gitea/token"),
+    os.path.expanduser("~/.hermes/gitea.token"),
+    os.environ.get("GITEA_TOKEN", ""),
+]
+
+def load_token() -> Optional[str]:
+    token = os.environ.get("GITEA_TOKEN", "")
+    if token:
+        return token
+    for path in TOKEN_PATHS:
+        if path and os.path.exists(path):
+            with open(path) as f:
+                t = f.read().strip()
+                if t:
+                    return t
+    return None
+
+class GiteaClient:
+    def __init__(self, base_url: str, token: str, org: str, repo: str):
+        self.base_url = base_url.rstrip("/")
+        self.token = token
+        self.org = org
+        self.repo = repo
+
+    def _post(self, path: str, data: Dict) -> Optional[Dict]:
+        url = f"{self.base_url}/api/v1{path}"
+        body = json.dumps(data).encode("utf-8")
+        req = urllib.request.Request(url, data=body, method="POST")
+        req.add_header("Authorization", f"token {self.token}")
+        req.add_header("Content-Type", "application/json")
+        try:
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                return json.loads(resp.read().decode())
+        except urllib.error.HTTPError as e:
+            err = e.read().decode() if e.read() else str(e)
+            print(f"[ERROR] HTTP {e.code}: {err}", file=sys.stderr)
+            return None
+        except Exception as e:
+            print(f"[ERROR] {e}", file=sys.stderr)
+            return None
+
+    def post_issue_comment(self, issue_num: int, body: str) -> Optional[Dict]:
+        return self._post(
+            f"/repos/{self.org}/{self.repo}/issues/{issue_num}/comments",
+            {"body": body}
+        )
+
+def content_hash(finding: Dict) -> str:
+    key = f"{finding['file']}:{finding['line']}:{finding['text']}"
+    return hashlib.sha256(key.encode("utf-8")).hexdigest()
+
+def format_comment(finding: Dict) -> str:
+    emoji = {
+        "error": "🛑",
+        "warning": "⚠️",
+        "info": "ℹ️",
+    }.get(finding.get("severity", ""), "📝")
+    f = finding["file"]
+    ln = finding["line"]
+    txt = finding["text"]
+    return f"{emoji} **Review Comment**\n\nFile: `{f}`\nLine: {ln}\n\n> {txt}\n"
+
+def load_findings(path: Optional[Path], from_stdin: bool) -> List[Dict]:
+    import fileinput
+    findings = []
+    sources = ["-"] if from_stdin else [str(path)]
+    for line in fileinput.input(files=sources):
+        line = line.strip()
+        if not line or line.startswith("#"):
+            continue
+        try:
+            f = json.loads(line)
+            for key in ("file", "line", "text"):
+                if key not in f:
+                    raise ValueError(f"Missing key: {key}")
+            findings.append(f)
+        except json.JSONDecodeError as e:
+            print(f"WARNING: Skipping invalid JSON: {e}", file=sys.stderr)
+    return findings
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description="Post review findings as comments to a Gitea PR/issue"
+    )
+    parser.add_argument("--pr", type=int, required=True, help="PR/issue number")
+    parser.add_argument("--org", default="Timmy_Foundation", help="Gitea org")
+    parser.add_argument("--repo", default="compounding-intelligence", help="Repo name")
+    parser.add_argument("--api-base", default=DEFAULT_API_BASE, help="Gitea API base")
+    parser.add_argument("--token", default=None, help="API token (or env/file)")
+    parser.add_argument("--input", type=Path, default=None, help="JSONL input file")
+    parser.add_argument("--stdin", action="store_true", help="Read from stdin")
+    parser.add_argument("--dry-run", action="store_true", help="Show without posting")
+    parser.add_argument("--json", action="store_true", help="Emit JSON report")
+
+    args = parser.parse_args()
+
+    if not args.stdin and args.input is None:
+        print("ERROR: --input or --stdin required", file=sys.stderr)
+        return 1
+    if args.stdin and args.input:
+        print("ERROR: --stdin and --input exclusive", file=sys.stderr)
+        return 1
+
+    token = args.token or load_token()
+    if not token:
+        print("ERROR: Token not found. Set GITEA_TOKEN or ~/.config/gitea/token", file=sys.stderr)
+        return 1
+
+    findings = load_findings(args.input, args.stdin)
+    if not findings:
+        print("ERROR: No findings loaded", file=sys.stderr)
+        return 1
+
+    if not args.json: print(f"Loaded {len(findings)} finding(s)")
+
+    seen: Dict[str, Dict] = {}
+    for f in findings:
+        h = content_hash(f)
+        if h not in seen:
+            seen[h] = f
+
+    unique = list(seen.values())
+    if not args.json: print(f"After dedup: {len(unique)} unique")
+
+    if args.json:
+        report = {
+            "total": len(findings),
+            "unique": len(unique),
+            "findings": unique,
+            "generated_at": datetime.now(timezone.utc).isoformat(),
+        }
+        print(json.dumps(report, indent=2))
+        return 0
+
+    if args.dry_run:
+        print("\n=== DRY RUN — would post ===")
+        for i, f in enumerate(unique, 1):
+            print(f"\n--- Comment {i}/{len(unique)} ---")
+            print(format_comment(f))
+        return 0
+
+    client = GiteaClient(args.api_base, token, args.org, args.repo)
+    posted = 0
+    for f in unique:
+        body = format_comment(f)
+        result = client.post_issue_comment(args.pr, body)
+        if result:
+            print(f"✅ Posted: {f['file']}:{f['line']} (id={result.get('id')})")
+            posted += 1
+        else:
+            print(f"❌ Failed: {f['file']}:{f['line']}")
+
+    print(f"\nPosted {posted}/{len(unique)} to PR #{args.pr}")
+    return 0 if posted == len(unique) else 1
+
+if __name__ == "__main__":
+    sys.exit(main())
+

scripts/sample_findings.jsonl

@@ -0,0 +1,5 @@
+{"file": "scripts/harvester.py", "line": 47, "text": "Consider adding type hints to improve readability", "severity": "info"}
+{"file": "scripts/dedup.py", "line": 89, "text": "Add null check before accessing fact['confidence'] to avoid KeyError", "severity": "warning"}
+{"file": "scripts/bootstrapper.py", "line": 102, "text": "This loop is O(n^2) — could be optimized with a dict lookup", "severity": "info"}
+{"file": "scripts/harvester.py", "line": 47, "text": "Consider adding type hints to improve readability", "severity": "info"}
+{"file": "scripts/harvester.py", "line": 120, "text": "File handle not closed in error path — use context manager", "severity": "error"}

scripts/test_pr_complexity_scorer.py

@@ -1,170 +0,0 @@
-#!/usr/bin/env python3
-"""
-Tests for PR Complexity Scorer — unit tests for the scoring logic.
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-
-from pr_complexity_scorer import (
-    score_pr,
-    is_dependency_file,
-    is_test_file,
-    TIME_PER_POINT,
-    SMALL_FILES,
-    MEDIUM_FILES,
-    LARGE_FILES,
-    SMALL_LINES,
-    MEDIUM_LINES,
-    LARGE_LINES,
-)
-
-PASS = 0
-FAIL = 0
-
-def test(name):
-    def decorator(fn):
-        global PASS, FAIL
-        try:
-            fn()
-            PASS += 1
-            print(f"  [PASS] {name}")
-        except AssertionError as e:
-            FAIL += 1
-            print(f"  [FAIL] {name}: {e}")
-        except Exception as e:
-            FAIL += 1
-            print(f"  [FAIL] {name}: Unexpected error: {e}")
-    return decorator
-
-def assert_eq(a, b, msg=""):
-    if a != b:
-        raise AssertionError(f"{msg} expected {b!r}, got {a!r}")
-
-def assert_true(v, msg=""):
-    if not v:
-        raise AssertionError(msg or "Expected True")
-
-def assert_false(v, msg=""):
-    if v:
-        raise AssertionError(msg or "Expected False")
-
-
-print("=== PR Complexity Scorer Tests ===\n")
-
-print("-- File Classification --")
-
-@test("dependency file detection — requirements.txt")
-def _():
-    assert_true(is_dependency_file("requirements.txt"))
-    assert_true(is_dependency_file("src/requirements.txt"))
-    assert_false(is_dependency_file("requirements_test.txt"))
-
-@test("dependency file detection — pyproject.toml")
-def _():
-    assert_true(is_dependency_file("pyproject.toml"))
-    assert_false(is_dependency_file("myproject.py"))
-
-@test("test file detection — pytest style")
-def _():
-    assert_true(is_test_file("tests/test_api.py"))
-    assert_true(is_test_file("test_module.py"))
-    assert_true(is_test_file("src/module_test.py"))
-
-@test("test file detection — other frameworks")
-def _():
-    assert_true(is_test_file("spec/feature_spec.rb"))
-    assert_true(is_test_file("__tests__/component.test.js"))
-    assert_false(is_test_file("testfixtures/helper.py"))
-
-
-print("\n-- Scoring Logic --")
-
-@test("small PR gets low score (1-3)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=3,
-        additions=50,
-        deletions=10,
-        has_dependency_changes=False,
-        test_coverage_delta=None
-    )
-    assert_true(1 <= score <= 3, f"Score should be low, got {score}")
-    assert_true(minutes < 20)
-
-@test("medium PR gets medium score (4-6)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=15,
-        additions=400,
-        deletions=100,
-        has_dependency_changes=False,
-        test_coverage_delta=None
-    )
-    assert_true(4 <= score <= 6, f"Score should be medium, got {score}")
-    assert_true(20 <= minutes <= 45)
-
-@test("large PR gets high score (7-9)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=60,
-        additions=3000,
-        deletions=1500,
-        has_dependency_changes=True,
-        test_coverage_delta=None
-    )
-    assert_true(7 <= score <= 9, f"Score should be high, got {score}")
-    assert_true(minutes >= 45)
-
-@test("dependency changes boost score")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=10, additions=200, deletions=50,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    dep_score, _, _ = score_pr(
-        files_changed=10, additions=200, deletions=50,
-        has_dependency_changes=True, test_coverage_delta=None
-    )
-    assert_true(dep_score > base_score, f"Deps: {base_score} -> {dep_score}")
-
-@test("adding tests lowers complexity")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    better_score, _, _ = score_pr(
-        files_changed=8, additions=180, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=3
-    )
-    assert_true(better_score < base_score, f"Tests: {base_score} -> {better_score}")
-
-@test("removing tests increases complexity")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    worse_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=-2
-    )
-    assert_true(worse_score > base_score, f"Remove tests: {base_score} -> {worse_score}")
-
-@test("score bounded 1-10")
-def _():
-    for files, adds, dels in [(1, 10, 5), (100, 10000, 5000)]:
-        score, _, _ = score_pr(files, adds, dels, False, None)
-        assert_true(1 <= score <= 10, f"Score {score} out of range")
-
-@test("estimated minutes exist for all scores")
-def _():
-    for s in range(1, 11):
-        assert_true(s in TIME_PER_POINT, f"Missing time for score {s}")
-
-
-print(f"\n=== Results: {PASS} passed, {FAIL} failed ===")
-sys.exit(0 if FAIL == 0 else 1)

tests/test_review_comment_generator.py

@@ -0,0 +1,234 @@
+#!/usr/bin/env python3
+"""
+Smoke tests for Review Comment Generator — Issue #126
+"""
+
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+import hashlib
+from io import StringIO
+from pathlib import Path
+
+import pytest
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+SCRIPTS_DIR = REPO_ROOT / "scripts"
+GENERATOR = SCRIPTS_DIR / "review_comment_generator.py"
+SAMPLE_FINDINGS = SCRIPTS_DIR / "sample_findings.jsonl"
+
+
+class TestGeneratorPresence:
+    def test_script_exists(self):
+        assert GENERATOR.exists(), f"Missing: {GENERATOR}"
+
+    def test_shebang_is_python(self):
+        with open(GENERATOR) as f:
+            first = f.readline().strip()
+        assert first.startswith("#!"), "No shebang"
+        assert "python" in first.lower()
+
+
+class TestDeduplication:
+    def test_content_hash_deterministic(self):
+        from hashlib import sha256
+        def ch(f):
+            key = f"{f['file']}:{f['line']}:{f['text']}"
+            return sha256(key.encode()).hexdigest()
+        finding = {"file": "a.py", "line": 1, "text": "test"}
+        assert ch(finding) == ch(finding)
+
+    def test_duplicate_findings_are_removed(self):
+        findings = [
+            {"file": "a.py", "line": 1, "text": "foo", "severity": "info"},
+            {"file": "a.py", "line": 1, "text": "foo", "severity": "warning"},
+            {"file": "b.py", "line": 2, "text": "bar", "severity": "info"},
+        ]
+        seen = {}
+        for f in findings:
+            key = f"{f['file']}:{f['line']}:{f['text']}"
+            seen[key] = f
+        assert len(seen) == 2
+
+    def test_different_findings_are_kept(self):
+        findings = [
+            {"file": "a.py", "line": 1, "text": "foo"},
+            {"file": "a.py", "line": 2, "text": "foo"},
+            {"file": "a.py", "line": 1, "text": "bar"},
+        ]
+        seen = {}
+        for f in findings:
+            key = f"{f['file']}:{f['line']}:{f['text']}"
+            seen[key] = f
+        assert len(seen) == 3
+
+
+class TestCommentFormatting:
+    def test_format_basic(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import format_comment
+        f = {"file": "scripts/foo.py", "line": 10, "text": "Fix this bug", "severity": "warning"}
+        body = format_comment(f)
+        assert "📝 **Review Comment**" not in body  # warning uses ⚠️
+        assert "⚠️ **Review Comment**" in body
+        assert "`scripts/foo.py`" in body
+        assert "Line: 10" in body
+        assert "> Fix this bug" in body
+
+    def test_format_severity_emoji(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import format_comment
+        cases = [("error", "🛑"), ("warning", "⚠️"), ("info", "ℹ️"), ("unknown", "📝")]
+        for severity, emoji in cases:
+            f = {"file": "x.py", "line": 1, "text": "test", "severity": severity}
+            assert emoji in format_comment(f)
+
+
+class TestFindingsLoader:
+    def test_load_from_file(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import load_findings
+        findings = load_findings(SAMPLE_FINDINGS, from_stdin=False)
+        assert len(findings) >= 4
+
+    def test_load_ignores_blank_and_comments(self):
+        import tempfile, os
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
+            tf.write('{"file":"a.py","line":1,"text":"valid"}\n')
+            tf.write('\n')
+            tf.write('# this is a comment\n')
+            tf.write('{"file":"b.py","line":2,"text":"also valid"}\n')
+            tfname = tf.name
+        try:
+            sys.path.insert(0, str(SCRIPTS_DIR))
+            from review_comment_generator import load_findings
+            assert len(load_findings(Path(tfname), from_stdin=False)) == 2
+        finally:
+            os.unlink(tfname)
+
+    def test_invalid_json_line_skipped(self, capsys):
+        import tempfile, os
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
+            tf.write('invalid json\n')
+            tf.write('{"file":"ok.py","line":1,"text":"valid"}\n')
+            tfname = tf.name
+        try:
+            sys.path.insert(0, str(SCRIPTS_DIR))
+            from review_comment_generator import load_findings
+            assert len(load_findings(Path(tfname), from_stdin=False)) == 1
+        finally:
+            os.unlink(tfname)
+
+
+class TestDryRunMode:
+    def test_dry_run_counts_unique(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126",
+             "--input", str(SAMPLE_FINDINGS), "--dry-run"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        assert result.returncode == 0
+        assert "DRY RUN" in result.stdout
+        assert "Review Comment" in result.stdout
+
+    def test_dry_run_shows_all_unique(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126",
+             "--input", str(SAMPLE_FINDINGS), "--dry-run"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        assert result.stdout.count("--- Comment") == 4
+
+
+class TestJSONOutputMode:
+    def test_json_flag_emits_valid_json(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126",
+             "--input", str(SAMPLE_FINDINGS), "--json"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        assert result.returncode == 0
+        payload = json.loads(result.stdout)
+        assert "total" in payload and "unique" in payload and "findings" in payload
+        assert payload["total"] >= payload["unique"]
+
+    def test_json_findings_have_required_fields(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126",
+             "--input", str(SAMPLE_FINDINGS), "--json"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        payload = json.loads(result.stdout)
+        for f in payload["findings"]:
+            assert "file" in f and "line" in f and "text" in f
+
+
+class TestGiteaClient:
+    def test_post_issue_comment_builds_correct_url(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import GiteaClient
+        client = GiteaClient("https://example.com", "token123", "MyOrg", "myrepo")
+        assert client.org == "MyOrg" and client.repo == "myrepo"
+
+    def test_generate_comment_body_has_required_fields(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import format_comment
+        f = {"file": "x.py", "line": 5, "text": "Fix this", "severity": "error"}
+        body = format_comment(f)
+        assert "x.py" in body and "5" in body and "Fix this" in body
+
+
+class TestFullPipeline:
+    def test_end_to_end_json_output(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126",
+             "--input", str(SAMPLE_FINDINGS), "--json"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        assert result.returncode == 0
+        data = json.loads(result.stdout)
+        assert data["total"] == 5
+        assert data["unique"] == 4
+        f = data["findings"][0]
+        for key in ("file", "line", "text", "severity"):
+            assert key in f
+
+    def test_token_loading_fallback(self):
+        sys.path.insert(0, str(SCRIPTS_DIR))
+        from review_comment_generator import load_token
+        token = load_token()
+        assert token is None or isinstance(token, str)
+
+
+class TestErrorHandling:
+    def test_missing_input_shows_error(self):
+        result = subprocess.run(
+            [sys.executable, str(GENERATOR), "--pr", "126"],
+            capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+        )
+        assert result.returncode != 0
+        assert "--input" in result.stderr or "--stdin" in result.stderr
+
+    def test_invalid_json_line_skipped(self):
+        import tempfile, os
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".jsonl", delete=False) as tf:
+            tf.write('invalid json\n')
+            tf.write('{"file":"ok.py","line":1,"text":"valid"}\n')
+            tfname = tf.name
+        try:
+            result = subprocess.run(
+                [sys.executable, str(GENERATOR), "--pr", "126",
+                 "--input", tfname, "--json"],
+                capture_output=True, text=True, cwd=REPO_ROOT, timeout=15
+            )
+            data = json.loads(result.stdout)
+            assert data["total"] == 1
+            assert data["unique"] == 1
+        finally:
+            os.unlink(tfname)
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])