sourcecode 1.28.0__py3-none-any.whl → 1.30.0__py3-none-any.whl

sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.28.0"
+__version__ = "1.30.0"

sourcecode/cli.py

@@ -1633,7 +1633,7 @@ def prepare_context_cmd(
       refactor       Structural issues, improvement opportunities
       generate-tests Untested source files, test gap analysis
       onboard        Full project context for new agents/developers
-      review-pr      Changed files + architectural impact
+      review-pr      PR diff: changed files, security/transactional impact, test gaps (requires git diff or --since)
       delta          Incremental context: git-changed files only
 
     \b
@@ -1642,6 +1642,8 @@ def prepare_context_cmd(
       sourcecode prepare-context explain /path/to/repo
       sourcecode prepare-context fix-bug
       sourcecode prepare-context delta --since main
+      sourcecode prepare-context review-pr --since origin/main
+      sourcecode prepare-context review-pr . --since main --output review.json
       sourcecode prepare-context onboard --llm-prompt
       sourcecode prepare-context --task-help
     """
@@ -1734,6 +1736,14 @@ def prepare_context_cmd(
             "test_gaps": False, "code_notes_summary": False,
             "changed_files": True, "affected_entry_points": True,
         },
+        "review-pr": {
+            "project_summary": False, "architecture_summary": False,
+            "relevant_files": True, "key_dependencies": False,
+            "gaps": True, "confidence": False,
+            "suspected_areas": False, "improvement_opportunities": False,
+            "test_gaps": False, "code_notes_summary": False,
+            "changed_files": True, "affected_entry_points": True,
+        },
     }
     _content_filter = _TASK_CONTENT_MAP.get(task, {})
 
@@ -1813,6 +1823,53 @@ def prepare_context_cmd(
             out["dependency_graph_summary"] = output.dependency_graph_summary
         if output.impact_score_per_file:
             out["impact_score_per_file"] = output.impact_score_per_file
+    # review-pr specific fields
+    if task == "review-pr":
+        if output.error_code:
+            _err_out: dict[str, Any] = {
+                "task": output.task,
+                "ci_decision": output.ci_decision or "error",
+                "error": output.error_code,
+                "message": output.error_message,
+            }
+            if output.since:
+                _err_out["since"] = output.since
+            if output.error_hints:
+                _err_out["hint"] = output.error_hints
+            _err_json = json.dumps(_err_out, indent=2, ensure_ascii=False)
+            if output_path is not None:
+                output_path.write_text(_err_json, encoding="utf-8")
+            else:
+                import sys as _sys
+                _sys.stdout.buffer.write(_err_json.encode("utf-8"))
+                _sys.stdout.buffer.write(b"\n")
+                _sys.stdout.buffer.flush()
+            raise typer.Exit(code=1)
+        out["review_type"] = "pull_request"
+        if output.ci_decision:
+            out["ci_decision"] = output.ci_decision
+        if output.base_ref:
+            out["base_ref"] = output.base_ref
+        if output.since:
+            out["since"] = output.since
+        if output.affected_modules:
+            out["affected_modules"] = output.affected_modules
+        if output.security_impact:
+            out["security_impact"] = output.security_impact
+        if output.transactional_impact:
+            out["transactional_impact"] = output.transactional_impact
+        if output.configuration_impact:
+            out["configuration_impact"] = output.configuration_impact
+        if output.test_coverage_risk:
+            out["test_coverage_risk"] = output.test_coverage_risk
+        if output.review_hotspots:
+            out["review_hotspots"] = output.review_hotspots
+        if output.suggested_review_order:
+            out["suggested_review_order"] = output.suggested_review_order
+        if output.impact_summary:
+            out["impact_summary"] = output.impact_summary
+        if output.why_these_files:
+            out["reasoning"] = output.why_these_files
     if output.limitations:
         out["limitations"] = output.limitations
     if output.symptom:

sourcecode/prepare_context.py

@@ -338,11 +338,19 @@ class TaskOutput:
     error_message: Optional[str] = None
     error_hints: list[str] = field(default_factory=list)
     # CI decision state machine — machine-decidable signal
-    ci_decision: Optional[str] = None  # "no_changes" | "analysis_success" | "git_ref_error"
+    ci_decision: Optional[str] = None  # "no_changes" | "analysis_success" | "git_ref_error" | "no_git_repo"
     # git baseline resolution metadata
     resolved_since_ref: Optional[str] = None   # actual ref/hash used for the diff
     resolution_path: Optional[str] = None      # "exact_local_ref"|"remote_tracking_ref"|"symbolic_ref"|"head_minus_1_fallback"|"uncommitted_changes"|"unresolvable"
     diff_validation_status: Optional[str] = None  # "valid_non_empty"|"valid_empty"|"invalid_ref"
+    # review-pr specific impact sections
+    base_ref: Optional[str] = None
+    security_impact: dict = field(default_factory=dict)
+    transactional_impact: dict = field(default_factory=dict)
+    configuration_impact: dict = field(default_factory=dict)
+    test_coverage_risk: dict = field(default_factory=dict)
+    review_hotspots: list[str] = field(default_factory=list)
+    suggested_review_order: list[str] = field(default_factory=list)
 
 
 # ─────────────────────────────────────────────────────────────────────────────
@@ -659,6 +667,64 @@ class TaskContextBuilder:
             elif _delta_raw:
                 _delta_files = set(_delta_raw)
 
+        # ── 5d. review-pr: git-first gate ──────────────────────────────────────
+        if task_name == "review-pr":
+            if not self._is_git_repo():
+                return TaskOutput(
+                    task="review-pr", goal=spec.goal,
+                    project_summary=None, architecture_summary=None,
+                    relevant_files=[], suspected_areas=[],
+                    improvement_opportunities=[], test_gaps=[],
+                    key_dependencies=[], code_notes_summary=None,
+                    limitations=[], confidence="low",
+                    error_code="no_git_repo",
+                    error_message="review-pr requires a git repository.",
+                    ci_decision="no_git_repo",
+                )
+            if since is None:
+                # review-pr with no --since: check only uncommitted changes.
+                # _get_git_changed_files(since=None) defaults to HEAD~1 which
+                # returns the last *committed* diff — a false positive here.
+                _pr_raw: Optional[list[str]] = self._get_uncommitted_changed_files()
+            else:
+                _pr_raw = self._get_git_changed_files(since=since)
+            if _pr_raw is None:
+                _avail_pr, _sug_pr = self._get_available_refs(since or "")
+                _pr_hints: list[str] = []
+                if _sug_pr:
+                    _pr_hints.append(f"Did you mean '{_sug_pr}'?")
+                if _avail_pr:
+                    _pr_hints.append(f"Available refs: {', '.join(_avail_pr[:8])}")
+                return TaskOutput(
+                    task="review-pr", goal=spec.goal,
+                    project_summary=None, architecture_summary=None,
+                    relevant_files=[], suspected_areas=[],
+                    improvement_opportunities=[], test_gaps=[],
+                    key_dependencies=[], code_notes_summary=None,
+                    limitations=[], confidence="low",
+                    since=since,
+                    error_code="git_ref_not_found",
+                    error_message=f"Base ref '{since}' not found in this repository.",
+                    error_hints=_pr_hints,
+                    gaps=[f"Cannot compute PR diff: git ref '{since}' not found."] + _pr_hints,
+                    ci_decision="git_ref_error",
+                )
+            if not _pr_raw:
+                _no_diff_hint = "review-pr requires changed files or --since <ref>."
+                return TaskOutput(
+                    task="review-pr", goal=spec.goal,
+                    project_summary=None, architecture_summary=None,
+                    relevant_files=[], suspected_areas=[],
+                    improvement_opportunities=[], test_gaps=[],
+                    key_dependencies=[], code_notes_summary=None,
+                    limitations=[], confidence="low",
+                    error_code="no_diff",
+                    error_message=f"No PR diff detected. {_no_diff_hint}",
+                    gaps=[f"No PR diff detected. {_no_diff_hint}"],
+                    ci_decision="no_changes",
+                )
+            _delta_files = set(_pr_raw)
+
         # ── 5c. review-pr suspected_areas (needs git uncommitted_files) ──────
         if task_name == "review-pr" and spec.enable_code_notes:
             pr_areas: dict[str, int] = {}
@@ -698,7 +764,7 @@ class TaskContextBuilder:
         _delta_dep_graph_summary: dict = {}
         _delta_impact_score_per_file: dict = {}
 
-        if task_name == "delta":
+        if task_name in ("delta", "review-pr"):
             _delta_changed_list: list[str] = sorted(_delta_files) if _delta_files else []
             (
                 relevant_files,
@@ -727,7 +793,88 @@ class TaskContextBuilder:
                 delta_files=None,
             )
 
-        # ── 6b. Symptom keyword boost + related notes (fix-bug + --symptom) ──
+        # ── 6b. review-pr: derive PR-specific impact sections from delta analysis ──
+        _pr_security_impact: dict = {}
+        _pr_transactional_impact: dict = {}
+        _pr_configuration_impact: dict = {}
+        _pr_test_coverage_risk: dict = {}
+        _pr_review_hotspots: list[str] = []
+        _pr_suggested_review_order: list[str] = []
+        _pr_base_ref: Optional[str] = None
+
+        if task_name == "review-pr":
+            _pr_base_ref = since or "HEAD"
+            _sys_risk_areas = _delta_system_impact.get("risk_areas", [])
+
+            _security_files = [
+                f for ra in _sys_risk_areas if ra["area"] == "security"
+                for f in ra["affected_files"]
+            ]
+            _transaction_files = [
+                f for ra in _sys_risk_areas if ra["area"] in ("transactions", "business_logic")
+                for f in ra["affected_files"]
+            ]
+            _config_files = [
+                f for ra in _sys_risk_areas if ra["area"] in ("api", "config")
+                for f in ra["affected_files"]
+                if any(kw in f.lower() for kw in ("config", "properties", "yml", "yaml", "xml", "spring"))
+            ]
+
+            if _security_files:
+                _pr_security_impact = {
+                    "affected_resources": _security_files,
+                    "risk_level": "high",
+                }
+            if _transaction_files:
+                _pr_transactional_impact = {
+                    "affected_transactions": _transaction_files,
+                    "risk": "possible transaction boundary change",
+                }
+            if _config_files:
+                _pr_configuration_impact = {"changed_configs": _config_files}
+
+            # Test coverage risk scoped to changed source files only
+            _changed_src = [
+                f for f in sorted(_delta_files or set())
+                if not self._is_test(f) and self._is_source(f)
+            ]
+            _test_stems = {Path(p).stem for p in test_set}
+            _untested_changed = [f for f in _changed_src if Path(f).stem not in _test_stems]
+            _test_risk_level = (
+                "high" if len(_untested_changed) > 3
+                else "medium" if _untested_changed
+                else "low"
+            )
+            _pr_test_coverage_risk = {
+                "changed_files_without_tests": _untested_changed[:10],
+                "risk_level": _test_risk_level,
+            }
+
+            # Review hotspots: top changed files ranked by impact score
+            _pr_review_hotspots = sorted(
+                _delta_files or set(),
+                key=lambda f: _delta_impact_score_per_file.get(f, 0.0),
+                reverse=True,
+            )[:8]
+
+            # Suggested review order: security first, then api → service → persistence → config
+            _ORDER_TYPES = ["security", "controller", "service", "repository", "mapper",
+                            "spring_config", "config", "domain_model", "dto"]
+            _seen_order: set[str] = set()
+            for _otype in _ORDER_TYPES:
+                for _ra in _delta_risk_areas:
+                    for _f in _ra.get("affected_files", []):
+                        if _f not in _seen_order:
+                            _cls = self._classify_changed_file(_f)
+                            if _cls["artifact_type"] == _otype:
+                                _pr_suggested_review_order.append(_f)
+                                _seen_order.add(_f)
+            for _f in _pr_review_hotspots:
+                if _f not in _seen_order:
+                    _pr_suggested_review_order.append(_f)
+                    _seen_order.add(_f)
+
+        # ── 6c. Symptom keyword boost + related notes (fix-bug + --symptom) ──
         symptom_keywords: list[str] = []
         related_notes: list[dict] = []
         symptom_note: Optional[str] = None
@@ -883,7 +1030,7 @@ class TaskContextBuilder:
 
         conf_summary, analysis_gaps = ConfidenceAnalyzer().analyze(sm_for_conf)
         confidence = conf_summary.overall
-        if task_name == "delta":
+        if task_name in ("delta", "review-pr"):
             # Use delta-specific gaps; ConfidenceAnalyzer gaps are about full-repo
             # detection quality and are not meaningful for an incremental diff.
             gaps = _delta_analysis_gaps
@@ -895,16 +1042,16 @@ class TaskContextBuilder:
                 gaps.append(_mybatis_warning["reason"])
 
         # ── 9. why_these_files ────────────────────────────────────────────────
-        if task_name == "delta":
+        if task_name in ("delta", "review-pr"):
             why_these_files = _delta_why
         else:
             why_these_files = {rf.path: rf.reason for rf in relevant_files}
 
-        # ── 10. Delta: git changed files + entry points ───────────────────────
+        # ── 10. Delta / review-pr: git changed files + entry points ──────────
         changed_files: list[str] = []
         affected_entry_points: list[str] = []
-        if task_name == "delta":
-            changed_files = sorted(_delta_files) if _delta_files else self._get_git_changed_files(since=since)
+        if task_name in ("delta", "review-pr"):
+            changed_files = sorted(_delta_files) if _delta_files else (self._get_git_changed_files(since=since) or [])
             _ep_set = {ep.path for ep in entry_points}
             # include framework-detected entry points AND files classified as
             # entrypoint/controller/security by artifact taxonomy
@@ -939,16 +1086,24 @@ class TaskContextBuilder:
             impact_summary=_delta_impact_summary,
             affected_modules=_delta_affected_modules,
             risk_areas=_delta_risk_areas,
-            since=since if task_name == "delta" else None,
+            since=since if task_name in ("delta", "review-pr") else None,
             system_impact=_delta_system_impact,
             change_type=_delta_change_type,
             dependency_graph_summary=_delta_dep_graph_summary,
             impact_score_per_file=_delta_impact_score_per_file,
             ci_decision=(
                 "no_changes" if task_name == "delta" and not changed_files
-                else "analysis_success" if task_name == "delta"
+                else "analysis_success" if task_name in ("delta", "review-pr")
                 else None
             ),
+            # review-pr specific
+            base_ref=_pr_base_ref,
+            security_impact=_pr_security_impact,
+            transactional_impact=_pr_transactional_impact,
+            configuration_impact=_pr_configuration_impact,
+            test_coverage_risk=_pr_test_coverage_risk,
+            review_hotspots=_pr_review_hotspots,
+            suggested_review_order=_pr_suggested_review_order,
         )
 
     def render_prompt(self, output: TaskOutput) -> str:
@@ -1240,6 +1395,19 @@ class TaskContextBuilder:
     def _is_source(self, path: str) -> bool:
         return Path(path).suffix.lower() in _SOURCE_EXTENSIONS
 
+    def _is_git_repo(self) -> bool:
+        import subprocess
+        try:
+            r = subprocess.run(
+                ["git", "rev-parse", "--git-dir"],
+                cwd=str(self.root),
+                capture_output=True, text=True,
+                encoding="utf-8", errors="replace", timeout=5,
+            )
+            return r.returncode == 0
+        except (subprocess.TimeoutExpired, FileNotFoundError):
+            return False
+
     # ── Delta impact analysis ─────────────────────────────────────────────────
 
     @staticmethod
@@ -2248,6 +2416,25 @@ class TaskContextBuilder:
                 "error": True,
             }
 
+    def _get_uncommitted_changed_files(self) -> list[str]:
+        """Return files with uncommitted working-tree changes (unstaged only).
+
+        Used by review-pr when no --since ref is given, so we don't confuse
+        the last *committed* diff (HEAD~1 vs HEAD) with an actual PR diff.
+        """
+        import subprocess
+        try:
+            result = subprocess.run(
+                ["git", "diff", "--name-only", "--relative"],
+                cwd=str(self.root), capture_output=True, text=True,
+                encoding="utf-8", errors="replace", timeout=10,
+            )
+            if result.returncode == 0:
+                return [l.strip() for l in (result.stdout or "").splitlines() if l.strip()]
+        except (subprocess.TimeoutExpired, FileNotFoundError):
+            pass
+        return []
+
     def _get_git_changed_files(self, since: Optional[str] = None) -> Optional[list[str]]:
         """Get files changed since a git ref (default: HEAD~1) relative to self.root.
 

{sourcecode-1.28.0.dist-info → sourcecode-1.30.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.28.0
+Version: 1.30.0
 Summary: Deterministic codebase context for AI coding agents
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -221,7 +221,7 @@ Description-Content-Type: text/markdown
 
 **Compressed AI-ready context for Java/Spring enterprise codebases.**
 
-![Version](https://img.shields.io/badge/version-1.28.0-blue)
+![Version](https://img.shields.io/badge/version-1.30.0-blue)
 ![Python](https://img.shields.io/badge/python-3.10%2B-green)
 
 ---
@@ -255,7 +255,7 @@ pipx install sourcecode
 
 ```bash
 sourcecode version
-# sourcecode 1.28.0
+# sourcecode 1.30.0
 ```
 
 ---

{sourcecode-1.28.0.dist-info → sourcecode-1.30.0.dist-info}/RECORD

@@ -1,10 +1,10 @@
-sourcecode/__init__.py,sha256=3x3ggja8yI1ruQ2kQv4TUDWkkzQNoGoAeTJj9npxRRk,103
+sourcecode/__init__.py,sha256=Bqhw95H9r5IFRlnJFDRt1uCsK_ahVHjggAAWdJ3d-5c,103
 sourcecode/adaptive_scanner.py,sha256=RTNExwWPXzjgLaRueT7UuxkPj5ZEToWjGbx1j0LSZ9E,10250
 sourcecode/architecture_analyzer.py,sha256=MyBa0Hf5HmkudZQDLKrjcWDKETXETXl0mQX1swtTwAA,39091
 sourcecode/architecture_summary.py,sha256=z34_6v7cSwy98cof2UVciGho7SCrZ93tiqMmq5WNzRQ,20405
 sourcecode/ast_extractor.py,sha256=XgrZg2DcWcUm9r87cRG3KGO7IK2TIL_N-CvhSbUmmh4,49901
 sourcecode/classifier.py,sha256=pYve2J1LqtYssU3lYLMDz18PT-CjN5c18QYE7R_IG1Q,7507
-sourcecode/cli.py,sha256=RrJiXz6C8ESZ8Q_jATbWFlko6TdPWxpsoSEm9Gk3SLM,77863
+sourcecode/cli.py,sha256=iWzo7u-wmWjj0GYAF54UpbicfpXt2OUxPRy44h2VaCI,80646
 sourcecode/code_notes_analyzer.py,sha256=y1MJBnPZHYp4i6cQCXUb9ATIyifS_qMQWjw_8lPkpsU,9215
 sourcecode/confidence_analyzer.py,sha256=xw_Jv8pAd0wd8t2vvQlorw8Ih0rSF3YCoFS8K-_4aXg,15762
 sourcecode/context_scorer.py,sha256=QpChSpsmaAYz91rXA4Ue5xzQmNz_ZboZN09YOHScq1U,14679
@@ -20,7 +20,7 @@ sourcecode/file_classifier.py,sha256=48ly5Z6exkzBy8lNy1AkdP4-oJqIA1zT3LZfffuTyDo
 sourcecode/git_analyzer.py,sha256=_pCg2V4d2aa17k9hayTzpexAj8syvyk4y9NYNvvgOAI,12802
 sourcecode/graph_analyzer.py,sha256=iUK-7pSV-cvGqqD2hENdYmhnm0wcXFEyK-xnu5ul8OU,62515
 sourcecode/metrics_analyzer.py,sha256=m0ENgtqKeBL17kUIK3fmGkgo7UfXBNHxCMj0H_Y5K7c,22750
-sourcecode/prepare_context.py,sha256=5iwOsq6H4WtyTeRmzlkNZup-8R2I1wc396afjuh0HxI,111997
+sourcecode/prepare_context.py,sha256=UxAwXHLZC61WFmYWwp-LWRUXnH6CbaX_lsyn6W7ok4o,121062
 sourcecode/progress.py,sha256=qn30sWaHOkjTgXsSBmiPkz7Rsbwc5oSlIe6JNEMYp_k,3149
 sourcecode/ranking_engine.py,sha256=virVglafZufioHpZpwktjMvUiL0TZELWQCQnQNV8dFo,9360
 sourcecode/redactor.py,sha256=xuGcadGEHaPw4qZXlMDvzMCsr4VOkdp3oBQptHyJk8c,2884
@@ -61,8 +61,8 @@ sourcecode/telemetry/consent.py,sha256=wLMvGNJeSSyZoNkQXpoUioY6mMv4Qdvuw7S9jAEWn
 sourcecode/telemetry/events.py,sha256=oEvvulfsv5GIDWG2174gSS6tNB95w38AIYiYeifGKlE,2294
 sourcecode/telemetry/filters.py,sha256=Asa71oRl7q3Wt_FMwuufIZJFzSYdgRNKS8LHCIyFeYE,4805
 sourcecode/telemetry/transport.py,sha256=KJeIPCPWMdmbCP3ySGs2iUlia34U6vWne2dZsUezesw,1560
-sourcecode-1.28.0.dist-info/METADATA,sha256=6U_sJqilesXL6hWI7OSWgzJAkFWWxL3vwUUhTFzaQ0k,23417
-sourcecode-1.28.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-sourcecode-1.28.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
-sourcecode-1.28.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
-sourcecode-1.28.0.dist-info/RECORD,,
+sourcecode-1.30.0.dist-info/METADATA,sha256=RDWe-iF73ttF7ZeXsUoUp2kQQUGB8lnxCWHI7dZQroM,23417
+sourcecode-1.30.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+sourcecode-1.30.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
+sourcecode-1.30.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
+sourcecode-1.30.0.dist-info/RECORD,,