sourcecode 1.46.0__py3-none-any.whl → 1.51.0__py3-none-any.whl

sourcecode/__init__.py

@@ -1,3 +1,3 @@
 """sourcecode — Deterministic codebase context maps for AI coding agents."""
 
-__version__ = "1.46.0"
+__version__ = "1.51.0"

sourcecode/migrate_check.py

@@ -536,6 +536,11 @@ _ALL_RULES: list[_Rule] = (
 
 SEVERITY_ORDER: dict[str, int] = {"critical": 0, "high": 1, "medium": 2, "low": 3}
 
+# G-1: cap on total readiness deduction from low-severity (advisory, non-blocking)
+# findings, so optional modernization cleanups cannot collapse the migration-readiness
+# headline on a repo with zero blockers. See MigrationReport.finalize.
+_LOW_SEVERITY_DEDUCTION_CAP: int = 15
+
 
 # ---------------------------------------------------------------------------
 # XML config rules (applied to Spring XML config files)
@@ -1022,11 +1027,17 @@ class MigrationReport:
             else:
                 low_files.add(f.source_file)
 
+        # G-1: low-severity findings are advisory (e.g. java.time modernization),
+        # not Boot-2→3 blockers. Cap their total contribution so a repo with zero
+        # blockers cannot score near zero on optional cleanups alone (mall: 96 low
+        # findings dragged readiness to 4/100 despite 0 blocking, already on Boot 3).
+        # Blockers (critical/high) stay uncapped — a genuinely blocked repo still
+        # floors at 0 (shopizer: 301 blocking → 0/100, unchanged).
         deduction = (
             len(critical_files) * 15
             + len(high_files) * 8
             + len(medium_files) * 3
-            + len(low_files) * 1
+            + min(len(low_files) * 1, _LOW_SEVERITY_DEDUCTION_CAP)
         )
         self.readiness_score = max(0, 100 - deduction)
 

sourcecode/repository_ir.py

@@ -3829,6 +3829,18 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
     all_symbols: list[SymbolRecord] = []
     extends_map: dict[str, str] = {}
 
+    # F-2: detect WebFlux / functional (RouterFunction) routing. Such routes register
+    # via a fluent DSL (route().GET("/path", handler)) instead of @RequestMapping
+    # annotations, so the annotation-based surface built below does not see them. We
+    # deliberately do NOT synthesize endpoint entries: the literal paths here are
+    # relative (the real path includes nest()/group-version prefixes that cannot be
+    # resolved statically), and emitting partial paths would mislead more than an empty
+    # surface. Instead we count them and surface an honest limitation so a zero/partial
+    # annotation surface is never read as "this app exposes no endpoints".
+    _FN_ROUTE_RE = _re.compile(r'\.(?:GET|POST|PUT|DELETE|PATCH|HEAD|OPTIONS)\s*\(\s*"')
+    _fn_route_files: set[str] = set()
+    _fn_route_count = 0
+
     for jf in java_files:
         try:
             source = jf.read_text(encoding="utf-8", errors="replace")
@@ -3838,6 +3850,11 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
             rel = str(jf.relative_to(root)).replace("\\", "/")
         except ValueError:
             rel = str(jf).replace("\\", "/")
+        if "RouterFunction" in source or "RequestPredicates" in source:
+            _fn_hits = len(_FN_ROUTE_RE.findall(source))
+            if _fn_hits:
+                _fn_route_files.add(rel)
+                _fn_route_count += _fn_hits
         _, symbols, _ = _extract_symbols(source, rel, extra_capture=_extra_capture)
         for sym in symbols:
             all_symbols.append(sym)
@@ -4045,6 +4062,26 @@ def extract_java_endpoints(root: Path) -> "dict[str, Any]":
         result["spec_sourced_endpoints"] = len(_spec_endpoints)
         if _openapi_spec_path:
             result["openapi_spec"] = _openapi_spec_path
+    # F-2: surface functional/RouterFunction routing as an honest limitation. Not modeled
+    # in the surface above; counted so an empty/partial annotation surface is not misread.
+    if _fn_route_count:
+        result["functional_routing"] = {
+            "files": len(_fn_route_files),
+            "route_registrations": _fn_route_count,
+            "modeled": False,
+        }
+        _fr_msg = (
+            f"{_fn_route_count} functional route registration(s) across "
+            f"{len(_fn_route_files)} file(s) use WebFlux/RouterFunction routing "
+            f'(route().GET("/path", handler)), which is NOT modeled here — this surface '
+            f"covers annotation-based (@RequestMapping/@GetMapping) endpoints only."
+        )
+        if not endpoints:
+            _fr_msg += (
+                " This surface is EMPTY despite functional routes being present — "
+                "do NOT read it as 'no endpoints'; the app's HTTP surface is unmodeled."
+            )
+        result.setdefault("warnings", []).append(_fr_msg)
     return result
 
 

sourcecode/spring_impact.py

@@ -44,7 +44,18 @@ _SCHEMA_VERSION = "1.0"
 #                Only appears on class nodes, never method nodes. Including it
 #                chains through DTOs and entities that merely reference the service
 #                type, inflating caller counts without semantic value.
-_SKIP_EDGE_TYPES: frozenset[str] = frozenset({"contained_in", "imports"})
+# implements /  — CH-006: structural type declarations, NOT calls. The reverse edge
+# extends        on an interface/base lists its implementors/subclasses; an
+#                implementor does not *call* the interface by virtue of implementing
+#                it. Traversing these attributes every SIBLING implementor of a shared
+#                interface as a "caller". On a high-fanout in-repo hub interface (e.g.
+#                halo's CustomEndpoint, 43 implementors) this turned a leaf endpoint
+#                into 42 false direct callers / risk:high. Interface→impl expansion that
+#                IS wanted (CH-001a/b) flows through ImplementationGraph indices, not
+#                through these reverse-graph edges, so excluding them here is loss-free.
+_SKIP_EDGE_TYPES: frozenset[str] = frozenset(
+    {"contained_in", "imports", "implements", "extends"}
+)
 
 # Max BFS depth guard — caller growth is bounded per _bfs_callers
 _BFS_DEFAULT_DEPTH = 4
@@ -148,6 +159,68 @@ _STEREOTYPE_ANNOTATIONS = frozenset({
 _VALUE_TYPE_KINDS = frozenset({"class", "enum", "record"})
 
 
+# ---------------------------------------------------------------------------
+# CH-005 — framework/external-interface DI blind-spot detection
+# ---------------------------------------------------------------------------
+# When a class implements/extends a type that is NOT an in-repo symbol (a
+# framework or library supertype — e.g. Spring Security's RedirectStrategy, a
+# servlet Filter, a JPA base), the class is typically invoked polymorphically
+# *through that external type* and wired by framework DI/config. No in-repo call
+# edge ever names the impl's own method, and ImplementationGraph.build()
+# deliberately drops external supertypes (cir_graphs: `to_fqn not in
+# known_symbols` → skipped), so CH-001b cannot expand to the interface. Result:
+# impact-chain reports 0 callers / risk:low at confidence=high — a dangerous
+# false negative, since the real blast radius flows through framework wiring the
+# static call-graph never traverses. Detect the external supertype positively,
+# warn, and downgrade confidence (parallel to the CH-003 value-type guard).
+#
+# Inert marker interfaces carry no methods → no polymorphic dispatch → no hidden
+# blast radius, so they are excluded to avoid firing on plain Serializable DTOs.
+_INERT_MARKER_SUPERTYPES = frozenset({
+    "Serializable", "java.io.Serializable",
+    "Cloneable", "java.lang.Cloneable",
+    "Externalizable", "java.io.Externalizable",
+})
+
+
+def _external_supertypes(cir, class_fqn: str) -> list[str]:
+    """Return supertypes of class_fqn that are NOT in-repo symbols.
+
+    Reads raw implements/extends edges from cir.dependencies and keeps only those
+    whose target cannot be resolved to a single in-repo class (i.e. framework /
+    library types). Mirrors ImplementationGraph's resolution rules (exact FQN
+    match, then unambiguous simple-name match) so the internal/external split is
+    identical. Inert marker interfaces are dropped. Order-preserving, deduped.
+    """
+    deps = getattr(cir, "dependencies", None) or []
+    known: set[str] = set(getattr(cir, "symbols", None) or [])
+    simple_to_fqn: dict[str, list[str]] = {}
+    for sym in known:
+        if "#" not in sym and "." in sym:
+            simple_to_fqn.setdefault(sym.rsplit(".", 1)[1], []).append(sym)
+
+    external: list[str] = []
+    for edge in deps:
+        if edge.get("type") not in ("implements", "extends"):
+            continue
+        frm = normalize_owner_fqn((edge.get("from") or "").strip())
+        if frm != class_fqn:
+            continue
+        to = (edge.get("to") or "").strip()
+        if not to or ">" in to or "<" in to:
+            continue
+        simple = to.rsplit(".", 1)[1] if "." in to else to
+        if simple in _INERT_MARKER_SUPERTYPES or to in _INERT_MARKER_SUPERTYPES:
+            continue
+        # Internal if it resolves to exactly one in-repo class (exact or simple-name).
+        if to in known:
+            continue
+        if len(simple_to_fqn.get(simple, [])) == 1:
+            continue
+        external.append(to)
+    return list(dict.fromkeys(external))
+
+
 def _is_unmodeled_value_type(cir, class_fqn: str, model) -> bool:
     """True iff class_fqn is positively a plain value/DTO type whose blast radius
     flows only through type-usage edges the impact graph does not model.
@@ -605,6 +678,12 @@ class ImpactOrchestrator:
         t0 = time.monotonic()
         depth = max(1, min(depth, _BFS_HARD_LIMIT))
         warnings: list[str] = []
+        # F-1: not every warning degrades confidence. The CH-001a/b interface↔impl
+        # expansion notices are INFORMATIONAL (they describe normal, correct operation)
+        # and previously forced every Spring interface/impl query — the common case — down
+        # to confidence=medium permanently. Only genuinely degrading conditions (capped
+        # traversal) set this flag; resolution=="partial" is handled separately below.
+        confidence_reducing = False
 
         # ── 1. Resolve symbol ─────────────────────────────────────────────
         resolution, seed_fqns, sym_warnings = _resolve_symbol(symbol, cir.symbols)
@@ -702,6 +781,7 @@ class ImpactOrchestrator:
                 "Hub-class guard active: symbol has > 500 direct callers — "
                 "indirect caller traversal capped at depth=1."
             )
+            confidence_reducing = True  # capped traversal → result is incomplete
 
         # ── 3. Endpoints affected ─────────────────────────────────────────
         all_callers = direct_callers + indirect_callers
@@ -750,16 +830,38 @@ class ImpactOrchestrator:
             impact_findings_raw,
         )
 
-        # CH-003: empty blast radius on a positively-identified value/DTO type is a
-        # type-usage blind spot, not proof of dead code — warn + drop confidence.
+        # Empty blast radius is ambiguous: genuinely-unused code OR an unmodeled-edge
+        # blind spot. Two positively-detected blind spots reclassify it from a
+        # high-confidence "safe to change" into a low-confidence "look further".
         empty_blast = (
             not direct_callers and not indirect_callers
             and not endpoints_affected and not subtype_classes_added
         )
+        class_level_seed = "#" not in resolved_symbol and resolution != "not_found"
+
+        # CH-005: framework/external-interface DI blind spot. Checked first because
+        # its diagnosis (polymorphic invocation via an external supertype + framework
+        # wiring) is more specific than the value-type fallback for the same symbol.
+        external_supertypes: list[str] = []
+        if empty_blast and class_level_seed:
+            external_supertypes = _external_supertypes(cir, resolved_symbol)
+        framework_di_blind_spot = bool(external_supertypes)
+        if framework_di_blind_spot:
+            warnings.append(
+                "Framework/external-interface DI blind spot (CH-005): this class "
+                "implements/extends external type(s) [" + ", ".join(external_supertypes)
+                + "] and is likely invoked polymorphically through them and wired by "
+                "framework DI/config. The static call-graph has no in-repo edge naming "
+                "this class's methods, so 0 callers is NOT proof it is unused — search "
+                "DI/security/config wiring for the supertype to find the real callers."
+            )
+
+        # CH-003: empty blast radius on a positively-identified value/DTO type is a
+        # type-usage blind spot, not proof of dead code — warn + drop confidence.
         value_type_blind_spot = (
             empty_blast
-            and "#" not in resolved_symbol
-            and resolution != "not_found"
+            and class_level_seed
+            and not framework_di_blind_spot
             and _is_unmodeled_value_type(cir, resolved_symbol, model)
         )
         if value_type_blind_spot:
@@ -773,9 +875,9 @@ class ImpactOrchestrator:
         confidence: str
         if resolution == "not_found":
             confidence = "low"
-        elif value_type_blind_spot:
+        elif framework_di_blind_spot or value_type_blind_spot:
             confidence = "low"
-        elif resolution == "partial" or warnings:
+        elif resolution == "partial" or confidence_reducing:
             confidence = "medium"
         else:
             confidence = "high"
@@ -803,6 +905,11 @@ class ImpactOrchestrator:
                 "risk_score": risk_score,
                 "model_build_time_ms": model.build_time_ms,
                 "query_time_ms": elapsed_ms,
+                "blind_spots": (
+                    (["framework_di"] if framework_di_blind_spot else [])
+                    + (["value_type"] if value_type_blind_spot else [])
+                ),
+                "external_supertypes": external_supertypes,
             },
         )
 

{sourcecode-1.46.0.dist-info → sourcecode-1.51.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sourcecode
-Version: 1.46.0
+Version: 1.51.0
 Summary: Persistent structural context and ultra-fast repeated analysis for AI coding agents
 License-File: LICENSE
 Keywords: agents,ai,codebase,context,developer-tools,llm
@@ -40,7 +40,7 @@ Description-Content-Type: text/markdown
 
 **Persistent structural context and ultra-fast repeated analysis for AI coding agents.**
 
-![Version](https://img.shields.io/badge/version-1.46.0-blue)
+![Version](https://img.shields.io/badge/version-1.50.0-blue)
 ![Python](https://img.shields.io/badge/python-3.9%2B-green)
 
 ---
@@ -368,6 +368,8 @@ sourcecode endpoints /path/to/repo --output endpoints.json
 
 Extracts all Spring MVC (`@GetMapping`, `@PostMapping`, `@RequestMapping`, etc.) and JAX-RS (`@GET`, `@POST`, `@Path`) endpoint methods. Returns HTTP method, path, controller class, and handler method.
 
+**Functional / WebFlux routing (honest limitation).** Routes registered via the functional DSL — `route().GET("/path", handler)` / `RouterFunction` / `CustomEndpoint`, common in reactive Spring apps — are **not** modeled (their real paths depend on `nest()`/group-version prefixes that can't be resolved statically). Rather than emit partial paths that would mislead, the output reports a `functional_routing` block (`files`, `route_registrations`, `modeled: false`) plus a warning. When the annotation surface is empty but functional routes exist, the warning explicitly tells you not to read it as "no endpoints". Annotation-based (MVC/JAX-RS) repos are unaffected.
+
 **Custom security annotations.** Enterprise repos often guard endpoints with a bespoke annotation instead of `@PreAuthorize`/`@Secured`. Drop a `sourcecode.config.json` at the repo root to teach the scanner about it — otherwise those endpoints report `policy: "none_detected"`:
 
 ```json
@@ -435,6 +437,12 @@ Unlike `impact` (which traces the caller graph), `impact-chain` builds on the Sp
 | `security_surfaces` | Per-endpoint security policy + SEC finding IDs |
 | `impact_findings` | TX-001..005 and SEC-001..003 findings that touch the call chain |
 | `risk_level` | `critical` \| `high` \| `medium` \| `low` |
+| `confidence` | `high` \| `medium` \| `low` — `low` on a detected blind spot, `medium` on partial resolution or capped traversal. Informational interface↔impl expansion notices do **not** lower it, so a clean resolved query stays `high`. |
+| `metadata.blind_spots` | `framework_di` and/or `value_type` when an empty result is unmodeled-edge driven, not real dead code |
+
+**Framework/DI blind spot (CH-005).** An empty blast radius is ambiguous: genuinely unused, or invoked through an edge the static graph does not model. When the target class implements/extends an **external** framework type (e.g. Spring Security's `RedirectStrategy`, a servlet `Filter`) it is typically wired by framework DI/config and invoked polymorphically — no in-repo edge names its methods, so `direct_callers` is `0`. Rather than report that as `risk:low` at high confidence (a dangerous false negative that reads as "safe to change"), `impact-chain` detects the external supertype, drops `confidence` to `low`, lists it in `metadata.external_supertypes`, and emits a `CH-005` warning telling you to search the DI/security/config wiring for the supertype. Inert markers (`Serializable`, `Cloneable`) are excluded.
+
+**Caller precision (CH-006).** `implements`/`extends` are structural type declarations, not calls — so they are excluded from the caller graph. Querying a class that implements a high-fanout interface (e.g. a 40-implementor `CustomEndpoint` or a shared `Mapper<E,D>` base) does **not** report its sibling implementors as callers; only real `injects`/`calls` edges count. This prevents a leaf class from being inflated to a large false blast radius.
 
 **Event topology** — query the publisher/consumer graph for a Spring event class:
 

{sourcecode-1.46.0.dist-info → sourcecode-1.51.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sourcecode/__init__.py,sha256=wdCd8tksQK-HjW2hTdGl_yIjBeUdzZy-xU36D1PCWmo,103
+sourcecode/__init__.py,sha256=_wGmSIirvZbvcf9uQNlNJs_jaX8mbucBaAgRR5jo_YA,103
 sourcecode/adaptive_scanner.py,sha256=XffluXKzJUXrMtjEiAOnSNPZnztdIcts17T9ouHeID0,10521
 sourcecode/architecture_analyzer.py,sha256=liCwQmLgb5vplohy8arjYxs_HOIv5C9MjLh_gY6bc5Q,44115
 sourcecode/architecture_summary.py,sha256=z34_6v7cSwy98cof2UVciGho7SCrZ93tiqMmq5WNzRQ,20405
@@ -31,7 +31,7 @@ sourcecode/graph_analyzer.py,sha256=DHR8fY69oU_Pi4SYaWboX6EoEFrctQKB9dsjpqwGMzw,
 sourcecode/license.py,sha256=i_X1bYdobL_z9OVuLiycnWEFSaaNhcKKuTd6G55U3_k,20747
 sourcecode/mcp_nudge.py,sha256=5ELU_ixzh6uA83NXLOZT8h00OhL53okfQdji3jyKOjg,2917
 sourcecode/metrics_analyzer.py,sha256=m0ENgtqKeBL17kUIK3fmGkgo7UfXBNHxCMj0H_Y5K7c,22750
-sourcecode/migrate_check.py,sha256=vowVIAxVaHU8vhZUEt-HrWrWM38m6a5INHJQGjEg5E0,55390
+sourcecode/migrate_check.py,sha256=H8iy7Vk8cGL0dnR3ZkFPS20CtfF5LJWuzQVQE4awQ9s,56192
 sourcecode/openapi_surface.py,sha256=BTt0K-woZbkbWTN77IkqeBm_Okag9owR0848fmot8sk,16207
 sourcecode/output_budget.py,sha256=Js9yUlfQtPhqBl9R6wn_9UHVjjJc3GtLcqyfjf5t50Q,9869
 sourcecode/path_filters.py,sha256=EN1RGZRvLq5EcPgpjYV_IyCKVlAQQn2bbpEisQ5LpGg,3780
@@ -44,7 +44,7 @@ sourcecode/redactor.py,sha256=SB4hwIvg8h-hvcqKcDWaZvA-aSyn-at-BIRwa0tUv5E,3227
 sourcecode/relevance_scorer.py,sha256=0AgEt4KrV73nioMqBgjhGjtY7L2C7L7cSyKtj3IKcrw,9408
 sourcecode/rename_refactor.py,sha256=h6dNFlB9aZ_3q6heeHBkgXQeXaT03nvPSsYH6P8qxFg,12965
 sourcecode/repo_classifier.py,sha256=FG1vaWKdWXsWdl-S8hjVMiTqcwgaRXkDyvK4rPcOGtQ,22681
-sourcecode/repository_ir.py,sha256=WjDYwbBm-eWp-k6aSdBrgO_XcRGuP-Llp0TZHBhq8bY,208237
+sourcecode/repository_ir.py,sha256=eBC8Jh1rBH8xE46atHmdGNQxcjuROyUCr0iCuhqviUc,210340
 sourcecode/ris.py,sha256=RcqLVwC-doFcKKViYDkCjZLBqf_wzLES7-F6vHEeWzE,20419
 sourcecode/runtime_classifier.py,sha256=uTAD6BDCiBLUZEDRfqk718kM4RTT_vAbfkcOI2_Xx58,18432
 sourcecode/scanner.py,sha256=WdOQ78mMzjR1NjmKTlbxdgwinnCTfAhxCVLBEFQiFHU,8899
@@ -54,7 +54,7 @@ sourcecode/semantic_analyzer.py,sha256=4OdG6tTSnTvq3_dSWMbQu8Ad1ndSCKeG-b9qM4hIx
 sourcecode/serializer.py,sha256=TGzftrSKitZrtl6Hh-R05s4KdTOxwTmph_lGDbo2Wzg,125015
 sourcecode/spring_event_topology.py,sha256=5_ON_21Le5zbG-1GRc5GLIi5HJfy_QjcXLVPC5WeUGQ,18055
 sourcecode/spring_findings.py,sha256=G7Or2lKBUQbcTDqudLvSs9XvNg_YoAa-_lBOG_ULs8E,5457
-sourcecode/spring_impact.py,sha256=rUKSiCfXh9NpC9a97KvjCu6Kn8bYezTnMDY3F7sgtCI,38737
+sourcecode/spring_impact.py,sha256=WUbBw6Ne9esN_KczIs9BCJdRAmjDKtU6E2_auo-771s,44865
 sourcecode/spring_model.py,sha256=zOAgFmrRbG4a6KLm1TJl55aWMyPNsz3OS3FSczqPG6A,16594
 sourcecode/spring_security_audit.py,sha256=XtPJ1SXlZJ8k6VYmaWuAp7Bbir4UmreAL7doIGQ5I7o,20595
 sourcecode/spring_semantic.py,sha256=O1nKSGVzlukuxLHQVuCPxc-XrcrMFxwlHA20_dmEGgM,13307
@@ -101,8 +101,8 @@ sourcecode/telemetry/consent.py,sha256=wLMvGNJeSSyZoNkQXpoUioY6mMv4Qdvuw7S9jAEWn
 sourcecode/telemetry/events.py,sha256=LtzYfaX9Ilckj5PTvAcTpDa9mLqDsYPDUiDkRa58piY,2580
 sourcecode/telemetry/filters.py,sha256=NHa5T-6DaZduQPFuC34jOqHWQgSizM-Ygq8aZ4j19ng,5834
 sourcecode/telemetry/transport.py,sha256=4gGHsq0WeY9VywEZXA3vUxykfiYnw9uuqfjAAec7F8o,1681
-sourcecode-1.46.0.dist-info/METADATA,sha256=EVvziqzOlPxygHshUqVQ3DYrYPRDKzQwLf0ewY9twKY,32359
-sourcecode-1.46.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
-sourcecode-1.46.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
-sourcecode-1.46.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
-sourcecode-1.46.0.dist-info/RECORD,,
+sourcecode-1.51.0.dist-info/METADATA,sha256=v-FRo1rN-BioZGvKK-WIC7mT3R-q3lQvXqyBXYj0s4U,34684
+sourcecode-1.51.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+sourcecode-1.51.0.dist-info/entry_points.txt,sha256=ex3F9rmbXeyDIoFQHtkEqTsKSaJow8F0LrVu8XfIktQ,57
+sourcecode-1.51.0.dist-info/licenses/LICENSE,sha256=7DdHrU9Z_3e7dSvq4ISijZNjnuHo5NIHNiHDouMQ9JU,10491
+sourcecode-1.51.0.dist-info/RECORD,,