pr-context-engine 0.1.3__tar.gz → 0.1.4__tar.gz

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/CHANGELOG.md

@@ -6,6 +6,18 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). Thi
 
 ## Unreleased
 
+## 0.1.4 — 2026-05-23
+
+### Fixed
+
+- **Risk scorer false positives** — Comment lines (including `#no-space` Python comments) and bare type/struct/class declarations are now skipped before the auth-keyword check, eliminating spurious `modifies_auth` flags on struct definitions and comment blocks.
+- **Auth flag noise** — `modifies_auth` is now deduplicated to one hit per file; large new store files no longer flood the briefing with dozens of identical flags.
+
+### Added
+
+- **`large_new_file` flag** — New files with 300+ added lines are flagged for explicit review.
+- **Briefing prompt improvements** — LLM is instructed to cover all change threads (not just the largest file), name changed type signatures explicitly, and avoid asking questions whose answers are already visible in the diff.
+
 ## 0.1.3 — 2026-05-23
 
 ### Fixed

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pr-context-engine
-Version: 0.1.3
+Version: 0.1.4
 Summary: An AI tool that reads every PR and posts a senior-engineer-style briefing.
 Project-URL: Homepage, https://github.com/paramahastha/pr-context-engine
 Project-URL: Repository, https://github.com/paramahastha/pr-context-engine

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pr-context-engine"
-version = "0.1.3"
+version = "0.1.4"
 description = "An AI tool that reads every PR and posts a senior-engineer-style briefing."
 readme = "README.md"
 requires-python = ">=3.12"

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/src/analyzers/risk_scorer.py

@@ -27,6 +27,18 @@ _FUNC_DEF_RE = re.compile(
 
 _MIGRATION_MARKERS = ("migrations/", "alembic/", "alembic_migrations/")
 
+# Lines that look auth-related by keyword but carry no real risk:
+# - comment lines (//  #  /*  *  <!--)
+# - bare type/struct/class/interface declarations
+_COMMENT_LINE_RE = re.compile(r"^\s*(?://|/\*|\*+/?\s|#|<!--)")
+_TYPE_DECL_RE = re.compile(
+    r"^\s*type\s+\w+\s+(?:struct|interface)\b"  # Go struct/interface
+    r"|^\s*type\s+\w+\s*(?:=|\b(?:int|string|float|bool)\b)"  # Go type alias/definition
+    r"|^\s*(?:class|interface)\s+\w+"  # Python / JS / TS
+)
+
+_LARGE_NEW_FILE_THRESHOLD = 300  # added lines; new files above this warrant explicit review
+
 
 @dataclass
 class RiskFlag:
@@ -64,6 +76,26 @@ def _is_config(path: str) -> bool:
     return False
 
 
+def _dedup_flags(flags: list[RiskFlag]) -> list[RiskFlag]:
+    """Deduplicate flags where one occurrence per file is enough.
+
+    modifies_auth fires once per matching line and can produce dozens of hits
+    in a large file (e.g. a new store implementation).  Keeping only the first
+    match per file preserves the signal while eliminating fix-suggestion spam.
+    Other flag types are kept as-is because each occurrence is independently
+    meaningful (e.g. multiple deletes_public_api deletions).
+    """
+    seen_auth_files: set[str] = set()
+    result: list[RiskFlag] = []
+    for flag in flags:
+        if flag.flag == "modifies_auth":
+            if flag.file in seen_auth_files:
+                continue
+            seen_auth_files.add(flag.file)
+        result.append(flag)
+    return result
+
+
 def score(changes: list[FileChange]) -> list[RiskFlag]:
     """Return all risk flags detected across the list of file changes."""
     flags: list[RiskFlag] = []
@@ -79,6 +111,16 @@ def score(changes: list[FileChange]) -> list[RiskFlag]:
                 RiskFlag(flag="changes_config", file=change.path, line=None, snippet=change.path)
             )
 
+        if change.is_new_file and len(change.added_lines) >= _LARGE_NEW_FILE_THRESHOLD:
+            flags.append(
+                RiskFlag(
+                    flag="large_new_file",
+                    file=change.path,
+                    line=None,
+                    snippet=f"{len(change.added_lines)} lines added — review for correctness and completeness",
+                )
+            )
+
         for hunk in change.hunks:
             new_lineno = hunk.new_start
             old_lineno = hunk.old_start
@@ -86,6 +128,10 @@ def score(changes: list[FileChange]) -> list[RiskFlag]:
             for raw in hunk.lines:
                 if raw.startswith("+") and not raw.startswith("+++"):
                     content = raw[1:]
+                    stripped = content.strip()
+                    if _COMMENT_LINE_RE.match(stripped) or _TYPE_DECL_RE.match(stripped):
+                        new_lineno += 1
+                        continue
                     if _AUTH_RE.search(content):
                         flags.append(
                             RiskFlag(
@@ -118,4 +164,4 @@ def score(changes: list[FileChange]) -> list[RiskFlag]:
                     new_lineno += 1
                     old_lineno += 1
 
-    return flags
+    return _dedup_flags(flags)

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/src/briefing/prompt_templates.py

@@ -18,9 +18,13 @@ Produce a briefing with exactly four sections:
 
 1. WHAT CHANGED — 2-3 sentences. Describe the *intent* of the change, not the
    lines. Do not list files. If you can't tell the intent, say so.
+   If the PR has multiple distinct threads (e.g. both new infrastructure and
+   model/API changes), cover all threads — do not describe only the largest file.
 
 2. BLAST RADIUS — Which callers, services, contracts, or data could break?
    Be specific. If the change is internal and self-contained, write "Self-contained."
+   If any public-facing struct field or type signature changed, name it explicitly
+   (e.g. "Snapshot.Configs changed from map[string]Config to map[string]ConfigEntry").
 
 3. RISK FLAGS — Bullet list. Only include flags that are actually present.
    If none, write "None."
@@ -29,6 +33,8 @@ Produce a briefing with exactly four sections:
    approving. Questions must be answerable and specific. Bad question:
    "Did you test this?" Good question: "The new retry loop in fetch_user
    has no backoff — is that intentional given this is called per-request?"
+   Do NOT ask questions whose answer is already visible in the diff (e.g. do
+   not ask about WAL mode if the schema already sets PRAGMA journal_mode=WAL).
 
 Rules:
 - Be terse. Aim for under 200 words total.

{pr_context_engine-0.1.3 → pr_context_engine-0.1.4}/tests/unit/test_risk_scorer.py

@@ -4,6 +4,20 @@ from src.analyzers.diff_parser import FileChange, Hunk
 from src.analyzers.risk_scorer import score
 
 
+def _new_file_change(path: str, num_lines: int) -> FileChange:
+    lines = [f"+    x_{i} = {i}" for i in range(num_lines)]
+    h = Hunk(old_start=0, old_count=0, new_start=1, new_count=num_lines, lines=lines)
+    added = [ln[1:] for ln in lines]
+    return FileChange(
+        path=path,
+        language="python",
+        added_lines=added,
+        removed_lines=[],
+        hunks=[h],
+        is_new_file=True,
+    )
+
+
 def _hunk(old_start: int, new_start: int, lines: list[str]) -> Hunk:
     added = sum(1 for ln in lines if ln.startswith("+") and not ln.startswith("+++"))
     removed = sum(1 for ln in lines if ln.startswith("-") and not ln.startswith("---"))
@@ -176,3 +190,92 @@ def test_no_flags_for_plain_change():
     c = _change("src/constants.py", [h])
     flags = score([c])
     assert flags == []
+
+
+# ── comment and type-decl false-positive suppression ─────────────────────────
+
+def test_python_comment_without_space_not_flagged():
+    # Previously `#\s` required a space, so `#token` slipped through.
+    h = _hunk(1, 1, ['+#auth_token = request.headers.get("X-Token")'])
+    c = _change("src/auth.py", [h])
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+def test_python_comment_with_space_not_flagged():
+    h = _hunk(1, 1, ['+# store the auth token here'])
+    c = _change("src/auth.py", [h])
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+def test_go_line_comment_not_flagged():
+    h = _hunk(1, 1, ['+// token is validated upstream'])
+    c = _change("pkg/handler.go", [h], language="go")
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+def test_go_struct_decl_not_flagged():
+    h = _hunk(1, 1, ['+type AuthStore struct {'])
+    c = _change("pkg/store.go", [h], language="go")
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+def test_python_class_decl_not_flagged():
+    h = _hunk(1, 1, ['+class AuthManager:'])
+    c = _change("src/auth.py", [h])
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+def test_python_class_with_base_not_flagged():
+    h = _hunk(1, 1, ['+class AuthManager(BaseManager):'])
+    c = _change("src/auth.py", [h])
+    assert not any(f.flag == "modifies_auth" for f in score([c]))
+
+
+# ── modifies_auth deduplication ───────────────────────────────────────────────
+
+def test_auth_deduped_within_file():
+    lines = ['+    token_a = get_token()', '+    token_b = get_token()', '+    password = "secret"']
+    h = _hunk(1, 1, lines)
+    c = _change("src/auth.py", [h])
+    auth_flags = [f for f in score([c]) if f.flag == "modifies_auth"]
+    assert len(auth_flags) == 1
+
+
+def test_auth_not_deduped_across_files():
+    h = _hunk(1, 1, ['+    token = get_token()'])
+    c1 = _change("src/auth.py", [h])
+    c2 = _change("src/user.py", [h])
+    auth_flags = [f for f in score([c1, c2]) if f.flag == "modifies_auth"]
+    assert len(auth_flags) == 2
+
+
+def test_auth_dedup_preserves_first_match_line():
+    lines = ['+    password_a = "x"', '+    password_b = "y"']
+    h = _hunk(10, 10, lines)
+    c = _change("src/auth.py", [h])
+    auth_flags = [f for f in score([c]) if f.flag == "modifies_auth"]
+    assert auth_flags[0].line == 10
+
+
+# ── large_new_file ────────────────────────────────────────────────────────────
+
+def test_large_new_file_flagged():
+    c = _new_file_change("src/new_store.py", 300)
+    assert any(f.flag == "large_new_file" for f in score([c]))
+
+
+def test_boundary_new_file_flagged():
+    c = _new_file_change("src/new_store.py", 301)
+    assert any(f.flag == "large_new_file" for f in score([c]))
+
+
+def test_small_new_file_not_flagged():
+    c = _new_file_change("src/tiny.py", 50)
+    assert not any(f.flag == "large_new_file" for f in score([c]))
+
+
+def test_large_existing_file_not_flagged():
+    lines = [f"+    x_{i} = {i}" for i in range(300)]
+    h = _hunk(1, 1, lines)
+    c = _change("src/existing.py", [h])
+    assert not any(f.flag == "large_new_file" for f in score([c]))