java-codebase-rag 0.9.4__py3-none-any.whl → 0.9.6__py3-none-any.whl

resolve_service.py → java_codebase_rag/analysis/resolve_service.py

@@ -6,11 +6,14 @@ by the CLI layer. Provides resolve_v2(identifier, hint_kind, graph) -> ResolveOu
 
 from __future__ import annotations
 
-from typing import Literal
+from typing import Any, Literal
 
 from pydantic import BaseModel, ConfigDict, Field
 
-from graph_types import (
+from java_codebase_rag.absence.absence_types import AbsenceDiagnosis
+from java_codebase_rag.absence.absence_diagnosis import diagnose
+from java_codebase_rag.absence.absence_vocab import get_vocabulary_index
+from java_codebase_rag.graph.graph_types import (
     NodeRef,
     StructuredHint,
     _hints_or_skip,
@@ -18,9 +21,9 @@ from graph_types import (
     _to_structured_hints,
     set_hints_enabled,
 )
-from java_ontology import ResolveReason
-from ladybug_queries import LadybugGraph
-from mcp_hints import MCP_HINTS_STRUCTURED_FIELD_DESCRIPTION
+from java_codebase_rag.graph.java_ontology import ResolveReason
+from java_codebase_rag.graph.ladybug_queries import LadybugGraph
+from java_codebase_rag.mcp.mcp_hints import MCP_HINTS_STRUCTURED_FIELD_DESCRIPTION
 
 __all__ = [
     "resolve_v2",
@@ -28,6 +31,7 @@ __all__ = [
     "ResolveCandidate",
     "ResolveStatus",
     "set_hints_enabled",
+    "set_absence_config",
 ]
 
 
@@ -35,6 +39,35 @@ ResolveStatus = Literal["one", "many", "none"]
 
 _RESOLVE_CANDIDATE_CAP = 10
 
+# Module-level holder for absence diagnosis config (set by server.py)
+_absence_config: Any = None
+
+
+def set_absence_config(cfg: Any) -> None:
+    """Set the global absence diagnosis config for resolve service.
+
+    Mirrors set_hints_enabled: called from server.py to make cfg reachable
+    in resolve functions without threading it through every signature.
+    """
+    global _absence_config
+    _absence_config = cfg
+
+
+def _get_absence_config() -> Any:
+    """Get the absence diagnosis config, with safe fallback.
+
+    Returns the module-level config if set; otherwise falls back to a
+    default config (for direct tool calls in tests without server init).
+    """
+    if _absence_config is not None:
+        return _absence_config
+
+    # Fallback: resolve from cwd for direct test calls
+    from java_codebase_rag.config import resolve_operator_config
+    from pathlib import Path
+
+    return resolve_operator_config(source_root=Path.cwd())
+
 _RESOLVE_REASON_PRIORITY: dict[ResolveReason, int] = {
     "exact_id": 0,
     "exact_fqn": 1,
@@ -129,6 +162,7 @@ class ResolveOutput(BaseModel):
     resolved_identifier: str | None = None
     advisories: list[str] = Field(default_factory=list, description="Pure informational text with no tool call suggestion")
     hints_structured: list[StructuredHint] = Field(default_factory=list, description=MCP_HINTS_STRUCTURED_FIELD_DESCRIPTION)
+    absence: AbsenceDiagnosis | None = None
 
 
 def _resolve_validate_identifier(raw: str) -> tuple[str | None, str | None]:
@@ -566,6 +600,9 @@ def _resolve_finalize_success(
     trimmed: str,
     hint_kind: Literal["symbol", "route", "client", "producer"] | None,
     matches: list[ResolveCandidate],
+    graph: LadybugGraph | None = None,
+    microservice: str = "",
+    module: str = "",
 ) -> ResolveOutput:
     if not matches:
         out = ResolveOutput(
@@ -591,6 +628,28 @@ def _resolve_finalize_success(
             resolved_identifier=trimmed,
         )
 
+    # Absence diagnosis for empty results (status="none")
+    cfg = _get_absence_config()
+    diag: AbsenceDiagnosis | None = None
+    if not matches:
+        g = graph
+        vocab = get_vocabulary_index(g, cfg)
+        # Map hint_kind to filter_kind (symbol -> "symbol", etc.)
+        filter_kind = hint_kind if hint_kind in ("symbol", "route", "client", "producer") else None
+        # Build scope from microservice/module params
+        scope = {"microservice": microservice or "", "module": module or ""}
+        diag = diagnose(
+            tool="resolve",
+            query=trimmed,
+            filt=None,
+            filter_kind=filter_kind,
+            root_node=None,
+            scope=scope,
+            vocab=vocab,
+            graph=g,
+            cfg=cfg,
+        )
+
     path_prefix_seed, target_service_seed = _resolve_seeds_for_hints(trimmed)
     hint_payload = {
         "status": out.status,
@@ -604,6 +663,7 @@ def _resolve_finalize_success(
     out = out.model_copy(update={
         "advisories": raw_advisories,
         "hints_structured": _to_structured_hints(raw_struct),
+        "absence": diag,
     })
     _resolve_assert_invariants(out)
     return out
@@ -660,7 +720,14 @@ def resolve_v2(
         deduped = _resolve_dedupe_candidates(raw)
         ranked = _resolve_rank_candidates(deduped)
         capped = ranked[:_RESOLVE_CANDIDATE_CAP]
-        return _resolve_finalize_success(trimmed, hint_kind, capped)
+        return _resolve_finalize_success(
+            trimmed,
+            hint_kind,
+            capped,
+            graph=g,
+            microservice=microservice,
+            module=module,
+        )
     except Exception as exc:
         out = ResolveOutput(
             success=False,

ast_java.py → java_codebase_rag/ast/ast_java.py

@@ -20,7 +20,7 @@ from typing import Iterable
 
 import tree_sitter_java as _ts_java
 
-from brownfield_events import (
+from java_codebase_rag.ast.brownfield_events import (
     emit_brownfield_exclusivity_shadowing,
     emit_brownfield_method_string_literal,
 )
@@ -84,7 +84,7 @@ _DTO_LOMBOK_ANNOTATIONS: frozenset[str] = frozenset({
 # Phase 11: `EDGE_SCHEMA` in `java_ontology.py` (canonical edge navigation schema; v14 re-index).
 # Phase 12: CALLS `callee_declaring_role`, supertype-walk dedup, pass3 unresolved counters (v15 re-index).
 # Bumps whenever extraction / enrichment semantics change.
-ONTOLOGY_VERSION = 17
+ONTOLOGY_VERSION = 18
 
 ROLE_ANNOTATIONS: dict[str, str] = {
     # Spring Web
@@ -1617,7 +1617,7 @@ def _parse_codebase_http_client_annotation(
         val, vkind = _annotation_value(pairs["clientKind"], src)
         if val and vkind == "enum":
             kind_val = str(val)
-            from java_ontology import VALID_CLIENT_KINDS  # deferred: java_ontology imports ast_java
+            from java_codebase_rag.graph.java_ontology import VALID_CLIENT_KINDS  # deferred: java_ontology imports ast_java
             if kind_val in VALID_CLIENT_KINDS:
                 client_kind = kind_val
             else:
@@ -1697,7 +1697,7 @@ def _parse_codebase_producer_annotation(
         val, vkind = _annotation_value(kind_node, src)
         if val and vkind == "enum":
             kind_val = str(val)
-            from java_ontology import VALID_PRODUCER_KINDS  # deferred: java_ontology imports ast_java
+            from java_codebase_rag.graph.java_ontology import VALID_PRODUCER_KINDS  # deferred: java_ontology imports ast_java
             if kind_val in VALID_PRODUCER_KINDS:
                 client_kind = kind_val
             else:
@@ -1868,7 +1868,7 @@ def _collect_outgoing_calls(
     file_rel: str,
 ) -> list[OutgoingCallDecl]:
     del project_root
-    from java_ontology import (  # deferred: java_ontology imports ast_java
+    from java_codebase_rag.graph.java_ontology import (  # deferred: java_ontology imports ast_java
         CLIENT_KIND_FEIGN_METHOD,
         CLIENT_KIND_REST_TEMPLATE,
         CLIENT_KIND_WEB_CLIENT,

java_codebase_rag/cli.py

@@ -27,6 +27,7 @@ from java_codebase_rag.config import (
 from java_codebase_rag._fdlimit import raise_fd_limit
 from java_codebase_rag._version import version_string
 from java_codebase_rag.pipeline import (
+    VECTORS_SKIPPED_GRAPH_ONLY as _VECTORS_SKIPPED_GRAPH_ONLY,
     clip,
     is_cocoindex_preflight_blocker,
     is_graph_preflight_blocker,
@@ -35,7 +36,7 @@ from java_codebase_rag.pipeline import (
     run_cocoindex_update,
     run_incremental_graph,
 )
-from java_ontology import VALID_UNRESOLVED_CALL_REASONS
+from java_codebase_rag.graph.java_ontology import VALID_UNRESOLVED_CALL_REASONS
 
 LADYBUG_INCREMENTAL_TRACKING_ISSUE_URL = "https://github.com/HumanBean17/java-codebase-rag/issues/73"
 
@@ -72,12 +73,6 @@ def _reprocess_drift_graph_only_line(index_dir: Path) -> str:
     )
 
 
-_VECTORS_SKIPPED_GRAPH_ONLY = (
-    "java-codebase-rag: vectors skipped — vector stack not installed on this platform "
-    "(graph-only mode). The graph is built/refreshed; semantic search is unavailable."
-)
-
-
 def _reprocess_exit_code(payload: dict[str, Any]) -> int:
     if payload.get("success"):
         return 0
@@ -607,7 +602,7 @@ def _cmd_reprocess(args: argparse.Namespace) -> int:
             _emit_reprocess_outcome(payload, selective_tty_mode="graph" if ok else None)
             return _reprocess_exit_code(payload)
 
-        import server  # lazy: pulls sentence_transformers/torch/lancedb/ladybug
+        from java_codebase_rag.mcp import server  # lazy: pulls sentence_transformers/torch/lancedb/ladybug
 
         result = asyncio.run(
             server.run_refresh_pipeline(
@@ -682,7 +677,7 @@ def _cmd_erase(args: argparse.Namespace) -> int:
     # tree_sitter (~54ms), and these filenames are only needed on the erase path.
     # Keeping it out of the top-level import lets `java-codebase-rag --help` (and
     # every other command) stay fast -- see the lazy-import invariant atop this file.
-    from build_ast_graph import BUILDER_OWNED_INDEX_FILES
+    from java_codebase_rag.graph.build_ast_graph import BUILDER_OWNED_INDEX_FILES
     builder_paths = [cfg.ladybug_path.parent / name for name in BUILDER_OWNED_INDEX_FILES]
     operator_paths = [cfg.index_dir / name for name in OPERATOR_OWNED_INDEX_FILES]
     to_describe: list[Path] = [
@@ -773,12 +768,12 @@ def _cmd_erase(args: argparse.Namespace) -> int:
 
 
 def _cmd_meta(args: argparse.Namespace) -> int:
-    import server  # lazy
+    from java_codebase_rag.mcp import server  # lazy
 
     cfg = _resolved_from_ns(args)
     _startup_hints(cfg)
     cfg.apply_to_os_environ()
-    from ladybug_queries import LadybugGraph  # lazy
+    from java_codebase_rag.graph.ladybug_queries import LadybugGraph  # lazy
 
     LadybugGraph._instance = None
     LadybugGraph._instance_path = None
@@ -797,7 +792,7 @@ def _cmd_meta(args: argparse.Namespace) -> int:
 
 
 def _cmd_tables(args: argparse.Namespace) -> int:
-    import server  # lazy
+    from java_codebase_rag.mcp import server  # lazy
 
     cfg = _resolved_from_ns(args)
     _startup_hints(cfg)
@@ -808,8 +803,8 @@ def _cmd_tables(args: argparse.Namespace) -> int:
 
 
 def _cmd_diagnose_ignore(args: argparse.Namespace) -> int:
-    import server  # lazy
-    from path_filtering import LayeredIgnore  # lazy
+    from java_codebase_rag.mcp import server  # lazy
+    from java_codebase_rag.graph.path_filtering import LayeredIgnore  # lazy
 
     cfg = _resolved_from_ns(args)
     _startup_hints(cfg)
@@ -838,7 +833,7 @@ def _cmd_unresolved_calls_list(args: argparse.Namespace) -> int:
     cfg = _resolved_from_ns(args)
     _startup_hints(cfg)
     cfg.apply_to_os_environ()
-    from ladybug_queries import LadybugGraph  # lazy
+    from java_codebase_rag.graph.ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
         _emit({"success": False, "message": "LadybugDB graph not found"})
@@ -859,7 +854,7 @@ def _cmd_unresolved_calls_stats(args: argparse.Namespace) -> int:
     cfg = _resolved_from_ns(args)
     _startup_hints(cfg)
     cfg.apply_to_os_environ()
-    from ladybug_queries import LadybugGraph  # lazy
+    from java_codebase_rag.graph.ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
         _emit({"success": False, "message": "LadybugDB graph not found"})
@@ -883,8 +878,8 @@ def _cmd_analyze_pr(args: argparse.Namespace) -> int:
     if not diff_text.strip():
         _emit({"success": False, "message": "Diff is empty"})
         return 1
-    import pr_analysis  # lazy
-    from ladybug_queries import LadybugGraph  # lazy
+    from java_codebase_rag.analysis import pr_analysis  # lazy
+    from java_codebase_rag.graph.ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
         _emit({"success": False, "message": "LadybugDB graph not found"})

java_codebase_rag/config.py

@@ -363,6 +363,17 @@ class ResolvedOperatorConfig:
     embedding_model_source: SettingSource
     embedding_device_source: SettingSource
     hints_enabled_source: SettingSource
+    # Absence diagnosis config knobs (PR-ABS-0)
+    absence_close_threshold: float
+    absence_absent_floor: float
+    absence_candidate_count: int
+    absence_ngram_q: int
+    absence_diag_enabled: bool
+    absence_close_threshold_source: SettingSource
+    absence_absent_floor_source: SettingSource
+    absence_candidate_count_source: SettingSource
+    absence_ngram_q_source: SettingSource
+    absence_diag_enabled_source: SettingSource
     # Absolute path of the YAML actually loaded (None when built-in defaults were
     # used with no config file). Recorded into the index dir at index time so a
     # later discovery run from a sibling/cwd can relocate this config.
@@ -380,6 +391,8 @@ class ResolvedOperatorConfig:
         os.environ["SBERT_MODEL"] = self.embedding_model
         if self.embedding_device is not None:
             os.environ["SBERT_DEVICE"] = self.embedding_device
+        # Publish absence diagnosis knobs for subprocess builds (PR-ABS-1)
+        os.environ["JAVA_CODEBASE_RAG_ABSENCE_NGRAM_Q"] = str(self.absence_ngram_q)
 
     def subprocess_env(self, base: dict[str, str] | None = None) -> dict[str, str]:
         out = dict(base or os.environ)
@@ -390,6 +403,8 @@ class ResolvedOperatorConfig:
             out["SBERT_DEVICE"] = self.embedding_device
         else:
             out.pop("SBERT_DEVICE", None)
+        # Publish absence diagnosis knobs for subprocess builds (PR-ABS-1)
+        out["JAVA_CODEBASE_RAG_ABSENCE_NGRAM_Q"] = str(self.absence_ngram_q)
         return out
 
 
@@ -459,6 +474,66 @@ def _pick_bool(
     return default, "default"
 
 
+def _pick_float(
+    *,
+    env_key: str,
+    yaml_dict: dict[str, Any],
+    yaml_path: tuple[str, ...],
+    default: float,
+) -> tuple[float, SettingSource]:
+    """Pick a float setting from env (parsed via float(...)), YAML, or default.
+
+    Precedence: CLI > env > YAML > default. Env values that fail to parse as float
+    fall back to the default (matching the brief's requirement for graceful degradation).
+    """
+    env_raw = os.environ.get(env_key, "").strip()
+    if env_raw:
+        try:
+            return float(env_raw), "env"
+        except ValueError:
+            # Invalid env value falls back to default (per brief)
+            pass
+    cur: Any = yaml_dict
+    for part in yaml_path:
+        if not isinstance(cur, dict) or part not in cur:
+            cur = None
+            break
+        cur = cur.get(part)
+    if isinstance(cur, (int, float)):
+        return float(cur), "yaml"
+    return default, "default"
+
+
+def _pick_int(
+    *,
+    env_key: str,
+    yaml_dict: dict[str, Any],
+    yaml_path: tuple[str, ...],
+    default: int,
+) -> tuple[int, SettingSource]:
+    """Pick an int setting from env (parsed via int(...)), YAML, or default.
+
+    Precedence: CLI > env > YAML > default. Env values that fail to parse as int
+    fall back to the default (matching the brief's requirement for graceful degradation).
+    """
+    env_raw = os.environ.get(env_key, "").strip()
+    if env_raw:
+        try:
+            return int(env_raw), "env"
+        except ValueError:
+            # Invalid env value falls back to default (per brief)
+            pass
+    cur: Any = yaml_dict
+    for part in yaml_path:
+        if not isinstance(cur, dict) or part not in cur:
+            cur = None
+            break
+        cur = cur.get(part)
+    if isinstance(cur, int):
+        return cur, "yaml"
+    return default, "default"
+
+
 def _resolve_index_dir_path(
     *,
     source_root: Path,
@@ -565,6 +640,37 @@ def resolve_operator_config(
         yaml_path=("hints", "enabled"),
         default=True,
     )
+    # Absence diagnosis config (PR-ABS-0)
+    abs_close, abs_close_src = _pick_float(
+        env_key="JAVA_CODEBASE_RAG_ABSENCE_CLOSE_THRESHOLD",
+        yaml_dict=yaml_dict,
+        yaml_path=("absence", "close_threshold"),
+        default=0.85,
+    )
+    abs_floor, abs_floor_src = _pick_float(
+        env_key="JAVA_CODEBASE_RAG_ABSENCE_ABSENT_FLOOR",
+        yaml_dict=yaml_dict,
+        yaml_path=("absence", "absent_floor"),
+        default=0.40,
+    )
+    abs_cand, abs_cand_src = _pick_int(
+        env_key="JAVA_CODEBASE_RAG_ABSENCE_CANDIDATE_COUNT",
+        yaml_dict=yaml_dict,
+        yaml_path=("absence", "candidate_count"),
+        default=5,
+    )
+    abs_q, abs_q_src = _pick_int(
+        env_key="JAVA_CODEBASE_RAG_ABSENCE_NGRAM_Q",
+        yaml_dict=yaml_dict,
+        yaml_path=("absence", "ngram_q"),
+        default=3,
+    )
+    abs_diag, abs_diag_src = _pick_bool(
+        env_key="JAVA_CODEBASE_RAG_ABSENCE_DIAG_ENABLED",
+        yaml_dict=yaml_dict,
+        yaml_path=("absence", "diag_enabled"),
+        default=True,
+    )
     ku = index_dir / "code_graph.lbug"
     coco = index_dir / "cocoindex.db"
     return ResolvedOperatorConfig(
@@ -579,6 +685,16 @@ def resolve_operator_config(
         embedding_model_source=model_src,
         embedding_device_source=device_src,
         hints_enabled_source=hints_src,
+        absence_close_threshold=abs_close,
+        absence_absent_floor=abs_floor,
+        absence_candidate_count=abs_cand,
+        absence_ngram_q=abs_q,
+        absence_diag_enabled=abs_diag,
+        absence_close_threshold_source=abs_close_src,
+        absence_absent_floor_source=abs_floor_src,
+        absence_candidate_count_source=abs_cand_src,
+        absence_ngram_q_source=abs_q_src,
+        absence_diag_enabled_source=abs_diag_src,
         yaml_config_path=find_yaml_config_file(config_dir),
     )