sourcecode 1.30.7__tar.gz → 1.30.9__tar.gz

{sourcecode-1.30.7 → sourcecode-1.30.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.30.7
+Version: 1.30.9
 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
 
 **Deterministic, behavior-aware codebase context for AI agents and PR review.**
 
-![Version](https://img.shields.io/badge/version-1.30.7-blue)
+![Version](https://img.shields.io/badge/version-1.30.9-blue)
 ![Python](https://img.shields.io/badge/python-3.10%2B-green)
 
 ---
@@ -257,7 +257,7 @@ pipx install sourcecode
 
 ```bash
 sourcecode version
-# sourcecode 1.30.7
+# sourcecode 1.30.9
 ```
 
 ---

{sourcecode-1.30.7 → sourcecode-1.30.9}/README.md

@@ -2,7 +2,7 @@
 
 **Deterministic, behavior-aware codebase context for AI agents and PR review.**
 
-![Version](https://img.shields.io/badge/version-1.30.7-blue)
+![Version](https://img.shields.io/badge/version-1.30.9-blue)
 ![Python](https://img.shields.io/badge/python-3.10%2B-green)
 
 ---
@@ -38,7 +38,7 @@ pipx install sourcecode
 
 ```bash
 sourcecode version
-# sourcecode 1.30.7
+# sourcecode 1.30.9
 ```
 
 ---

{sourcecode-1.30.7 → sourcecode-1.30.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sourcecode"
-version = "1.30.7"
+version = "1.30.9"
 description = "Deterministic codebase context for AI coding agents"
 readme = "README.md"
 requires-python = ">=3.9"

{sourcecode-1.30.7 → sourcecode-1.30.9}/src/sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.30.7"
+__version__ = "1.30.9"

{sourcecode-1.30.7 → sourcecode-1.30.9}/src/sourcecode/flow_analyzer.py

@@ -364,7 +364,8 @@ def _domain_from_class(class_name: str) -> str:
 
 
 def _impact_item(statement: str, support: str, certainty: str) -> dict:
-    return {"statement": statement, "support": support, "certainty": certainty}
+    truth_level = "observed" if certainty == "high" else "inferred"
+    return {"statement": statement, "support": support, "certainty": certainty, "truth_level": truth_level}
 
 
 def _impact_descriptions(
@@ -380,14 +381,14 @@ def _impact_descriptions(
 
     if changed_type in _REPO_ARTIFACT_TYPES:
         items.append(_impact_item(
-            f"{domain} persistence affected" if domain else "persistence affected",
-            f"{changed_class} is a repository in path",
+            f"{domain} persistence may be affected (inferred from path)" if domain else "persistence may be affected (inferred from path)",
+            f"{changed_class} classified as repository from path",
             certainty,
         ))
     elif changed_type in _SERVICE_ARTIFACT_TYPES:
         if end_state == "DB write":
             items.append(_impact_item(
-                f"{domain} persistence affected" if domain else "persistence affected",
+                f"{domain} persistence may be affected (repository with DB write in path)" if domain else "persistence may be affected (repository with DB write in path)",
                 f"{changed_class} delegates to repository with DB write",
                 certainty,
             ))
@@ -439,7 +440,7 @@ def _impact_descriptions_for_controller(
                 domain = d
                 break
         items.append(_impact_item(
-            f"{domain} persistence affected" if domain else "data persistence affected",
+            f"{domain} persistence may be affected (repository with DB write in path)" if domain else "data persistence may be affected (repository with DB write in path)",
             "repository with DB write detected in path",
             certainty,
         ))

{sourcecode-1.30.7 → sourcecode-1.30.9}/src/sourcecode/prepare_context.py

@@ -419,20 +419,122 @@ _ALL_EXTENSIONS: frozenset[str] = _SOURCE_EXTENSIONS | frozenset({
     ".md", ".toml", ".yaml", ".yml", ".json", ".xml",
 })
 
+# ── Evidence admission helpers (valid types: git_diff, annotation, import, symbol, config) ──
+
+_CLASS_SUFFIX_EVIDENCE: list[tuple[tuple[str, ...], str, str]] = [
+    (("Repository", "Dao", "DAO"),                  "repository pattern",   "medium"),
+    (("Mapper",),                                   "mapper pattern",       "medium"),
+    (("Service", "Manager", "Handler", "Facade"),   "service pattern",      "medium"),
+    (("Controller", "Resource", "Endpoint"),        "controller pattern",   "medium"),
+    (("Config", "Configuration"),                   "config class",         "medium"),
+    (("Test", "Tests", "IT", "Spec"),               "test class",           "strong"),
+    (("DTO", "Dto"),                                "DTO pattern",          "medium"),
+    (("Entity",),                                   "entity pattern",       "medium"),
+]
+
+
+def _symbol_evidence_from_class(class_name: str) -> "dict | None":
+    for suffixes, label, strength in _CLASS_SUFFIX_EVIDENCE:
+        for suffix in suffixes:
+            if class_name.endswith(suffix) and class_name != suffix:
+                return {
+                    "type": "symbol",
+                    "strength": strength,
+                    "signal": f"class name suffix '{suffix}' — {label}",
+                }
+    return None
+
+
+_PERSISTENCE_ANNOTATION_SIGNALS = frozenset({
+    "@Repository", "@Entity", "@Table", "@MappedSuperclass",
+    "@NamedQuery", "@SqlResultSetMapping", "@Embeddable",
+})
+_PERSISTENCE_IMPORT_PREFIXES = (
+    "javax.persistence", "jakarta.persistence",
+    "org.hibernate", "org.springframework.data.jpa",
+)
+_PERSISTENCE_ORM_SYMBOLS = ("EntityManager", "JpaRepository", "CrudRepository", "HibernateTemplate", "SessionFactory")
+
+
+def _read_persistence_evidence(root: Path, file_path: str) -> "list[dict]":
+    evidence: list[dict] = []
+    try:
+        with open(root / file_path, encoding="utf-8", errors="replace") as _fp:
+            content = _fp.read(8000)
+    except OSError:
+        return evidence
+    for ann in _PERSISTENCE_ANNOTATION_SIGNALS:
+        if ann in content:
+            evidence.append({"type": "annotation", "strength": "strong", "signal": f"{ann} found in file content"})
+            break
+    for imp in _PERSISTENCE_IMPORT_PREFIXES:
+        if imp in content:
+            evidence.append({"type": "import", "strength": "strong", "signal": f"import {imp}.* found in file content"})
+            break
+    for sym in _PERSISTENCE_ORM_SYMBOLS:
+        if sym in content:
+            evidence.append({"type": "symbol", "strength": "medium", "signal": f"{sym} usage found in file content"})
+            break
+    return evidence
+
+
+# Code signal rules for non-persistence classifiable types.
+# Path/module/suffix are explicitly excluded — only code-grounded signals.
+_CODE_SIGNAL_RULES: dict[str, list[str]] = {
+    "service":        ["@Service", "@Component(", "@Transactional\n", "@Transactional("],
+    "controller":     ["@RestController", "@Controller", "@RequestMapping",
+                       "@GetMapping", "@PostMapping", "@PutMapping", "@DeleteMapping", "@PatchMapping"],
+    "entrypoint":     ["@SpringBootApplication", "public static void main", "if __name__ == '__main__'"],
+    "security":       ["@EnableWebSecurity", "SecurityFilterChain", "WebSecurityConfigurerAdapter",
+                       "extends OncePerRequestFilter"],
+    "spring_config":  ["@Configuration", "@Bean\n", "@Bean("],
+    "spring_profile": ["@Profile(", "@ConditionalOnProperty"],
+    "dto":            ["@Data\n", "@Data(", "@Value\n", "@JsonProperty", "@Schema(", "@XmlRootElement",
+                       "@Builder\n", "@Builder(", "@Getter", "@Setter"],
+    "test":           ["@Test\n", "@Test(", "import org.junit", "import org.testng",
+                       "import org.mockito", "import org.springframework.boot.test",
+                       "@BeforeEach", "@BeforeAll", "@Before\n", "@Before("],
+}
+
+
+def _read_code_signal_evidence(root: Path, file_path: str, artifact_type: str) -> "list[dict]":
+    """Verify artifact_type with code signals from file content (first 8KB).
+    Returns single-item list on first match, empty list if no signal found.
+    Path segments, module names, and class suffixes are excluded — per evidence firewall rules.
+    """
+    signals = _CODE_SIGNAL_RULES.get(artifact_type, [])
+    if not signals:
+        return []
+    try:
+        with open(root / file_path, encoding="utf-8", errors="replace") as _fp:
+            content = _fp.read(8000)
+    except OSError:
+        return []
+    for signal in signals:
+        if signal in content:
+            ev_type = (
+                "annotation" if signal.startswith("@")
+                else "import" if signal.startswith("import ")
+                else "symbol"
+            )
+            return [{"type": ev_type, "strength": "strong", "signal": f"{signal.strip()} found in file content"}]
+    return []
+
+
 _ARTIFACT_CHANGE_EFFECT: dict[str, str] = {
-    "entrypoint":     "modifies application startup, CLI entry, or framework bootstrap — all request flows may be affected",
-    "controller":     "alters HTTP routing, API contract, or response shape — API consumers are affected",
-    "service":        "changes business rules, transaction scope, or orchestration logic — callers and dependents affected",
-    "repository":     "modifies persistence queries or data access patterns — data consistency and service layer affected",
-    "mapper":         "alters SQL-to-object binding or query templates — data shape and repositories affected",
-    "security":       "changes authentication flow, access control rules, or session handling — all secured endpoints affected",
-    "spring_config":  "modifies bean wiring, datasource, or framework-wide settings — all wired beans potentially affected",
-    "spring_profile": "changes environment-specific overrides — behavior differs per active profile",
-    "config":         "adjusts configuration values — all modules reading this config are affected",
+    "entrypoint":     "may affect application startup, CLI entry, or framework bootstrap — all request flows may be affected (inferred from role)",
+    "controller":     "may alter HTTP routing, API contract, or response shape — API consumers may be affected (inferred from role)",
+    "service":        "may change business rules, transaction scope, or orchestration logic — callers and dependents may be affected (inferred from role)",
+    "repository":     "may modify persistence queries or data access patterns — verify data consistency and service layer (inferred from role)",
+    "mapper":         "may alter SQL-to-object binding or query templates — data shape and repositories may be affected (inferred from role)",
+    "security":       "may change authentication flow, access control rules, or session handling — all secured endpoints may be affected (inferred from role)",
+    "spring_config":  "may modify bean wiring, datasource, or framework-wide settings — wired beans potentially affected (inferred from role)",
+    "spring_profile": "may change environment-specific overrides — behavior may differ per active profile (inferred from role)",
+    "config":         "may adjust configuration values — all modules reading this config may be affected (inferred from role)",
     "build_manifest": "changes dependencies, plugins, or project structure — compile-time and runtime classpath affected",
     "db_migration":   "modifies database schema — existing queries, mappings, and constraints may break",
-    "domain_model":   "alters entity structure — cascades to repositories, DTOs, serializers, and mappers",
-    "dto":            "changes data transfer contract — serialization and API consumers may break",
+    "domain_model":   "may alter entity structure — may cascade to repositories, DTOs, serializers, and mappers (inferred from role)",
+    "dto":            "may change data transfer contract — serialization and API consumers may break (inferred from role)",
     "test":           "modifies test coverage or test behavior — no production code affected",
     "documentation":  "updates documentation only — no runtime impact",
     "ide_noise":      "IDE/tooling artifact — no application impact",
@@ -953,21 +1055,55 @@ class TaskContextBuilder:
                 if _f_atype == "build_manifest":
                     _build_artifact_files.append(_f)
                     continue
-                # role: always "inferred" — no runtime evidence for role classification
-                _cls_conf = _f_cls["confidence"]  # "high"|"medium"|"low" from _classify_changed_file
-                _role_basis = "naming" if _cls_conf == "high" else ("path" if _cls_conf == "medium" else "extension")
+                # ── Evidence: only admitted types [git_diff, annotation, import, symbol, config] ──
+                _evidence: list[dict] = [
+                    {"type": "git_diff", "strength": "weak", "signal": "file present in commit diff"}
+                ]
+                # Symbol evidence from class name (path segments are rejected — not a valid type)
+                _class_name = Path(_f).stem
+                _sym_ev = _symbol_evidence_from_class(_class_name)
+                if _sym_ev:
+                    _evidence.append(_sym_ev)
+
+                # All classifiable types require at least one code signal from content.
+                # Path segments and module names are rejected evidence — not a valid type.
+                _PERSISTENCE_SENSITIVE = frozenset({"repository", "mapper", "domain_model"})
+                _CONTENT_VERIFIABLE = frozenset({
+                    "service", "controller", "entrypoint", "security",
+                    "spring_config", "spring_profile", "dto",
+                })
+                if _f_atype in _PERSISTENCE_SENSITIVE:
+                    _content_ev = _read_persistence_evidence(self.root, _f)
+                    if _content_ev:
+                        _evidence.extend(_content_ev)
+                    else:
+                        _f_atype = "source"
+                elif _f_atype in _CONTENT_VERIFIABLE:
+                    _content_ev = _read_code_signal_evidence(self.root, _f, _f_atype)
+                    if _content_ev:
+                        _evidence.extend(_content_ev)
+                    else:
+                        _f_atype = "source"
+                elif _f_atype == "test":
+                    # test: class name suffix is valid per gate (naming rule)
+                    # additionally verify with test framework signals for stronger evidence
+                    _test_ev = _read_code_signal_evidence(self.root, _f, "test")
+                    if _test_ev:
+                        _evidence.extend(_test_ev)
+                    # no downgrade — naming is a valid gate signal for test
+
+                # Role basis: derived from strongest admitted evidence
+                _has_code_ev = any(e["type"] in ("annotation", "import") for e in _evidence)
+                _has_symbol_ev = any(e["type"] == "symbol" for e in _evidence)
+                _role_basis = "annotation" if _has_code_ev else ("symbol" if _has_symbol_ev else "git_diff_only")
+                _cls_conf = _f_cls["confidence"]
                 _role_obj = {
                     "type": "inferred",
-                    "confidence": "medium" if _cls_conf == "high" else "low",
+                    "confidence": "medium" if (_has_code_ev or (_has_symbol_ev and _cls_conf == "high")) else "low",
                     "basis": _role_basis,
                 }
-                # evidence: list what we actually know
-                _evidence: list[str] = ["changed in git diff"]
-                _f_module = _f_cls.get("module", "")
-                if _f_module:
-                    _evidence.append(f"matched module path: {_f_module}")
-                _evidence.append("NO call graph evidence")
-                # file confidence: replaces numeric score
+
+                # File confidence: replaces numeric score
                 _impact_s = _delta_impact_score_per_file.get(_f, 0.45)
                 _f_conf = "high" if _impact_s >= 0.60 else ("medium" if _impact_s >= 0.40 else "low")
                 _pr_runtime_changes.append({
@@ -976,7 +1112,11 @@ class TaskContextBuilder:
                     "confidence": _f_conf,
                     "artifact_type": _f_atype,
                     "evidence": _evidence,
-                    "change_effect": _ARTIFACT_CHANGE_EFFECT.get(_f_atype, "modifies application logic"),
+                    "change_effect": {
+                        "statement": _ARTIFACT_CHANGE_EFFECT.get(_f_atype, "may modify application logic (role inferred from path)"),
+                        "truth_level": "inferred",
+                        "confidence": _role_obj["confidence"],
+                    },
                 })
 
             if _build_artifact_files:
@@ -2521,19 +2661,19 @@ class TaskContextBuilder:
         def _runtime_impact(tc: dict[str, int]) -> list[str]:
             _ri: list[str] = []
             if "entrypoint" in tc:
-                _ri.append("Application bootstrap modified — full context restart required before deploy")
+                _ri.append("Entrypoint-classified file modified — may require full context restart before deploy (role inferred from path)")
             if "spring_config" in tc:
-                _ri.append("Spring ApplicationContext bean wiring modified — dependent beans rewired on restart")
+                _ri.append("Spring config-classified file modified — wired beans may be rewired on restart (role inferred from path)")
             if "security" in tc:
-                _ri.append("Security filter chain modified — all secured endpoints affected after restart")
+                _ri.append("Security-classified file modified — secured endpoints may be affected after restart (role inferred from path)")
             if "db_migration" in tc:
                 _ri.append("Database schema migration pending — execute before deploying application")
             _svc = tc.get("service", 0)
             if _svc >= 2:
-                _ri.append(f"{_svc} service(s) modified — verify transaction scope and data consistency")
+                _ri.append(f"{_svc} service-classified file(s) modified — verify transaction scope and data consistency (role inferred from path)")
             _repo = tc.get("repository", 0) + tc.get("mapper", 0)
             if _repo > 0:
-                _ri.append(f"{_repo} persistence component(s) modified — verify data access queries")
+                _ri.append(f"{_repo} persistence-classified component(s) modified — verify data access queries (role inferred from path)")
             if "build_manifest" in tc:
                 _ri.append("Build manifest modified — dependency resolution required before compile")
             return _ri