java-codebase-rag 0.9.4__py3-none-any.whl → 0.9.5__py3-none-any.whl

java_codebase_rag/jrag.py

@@ -1163,6 +1163,20 @@ def build_parser() -> argparse.ArgumentParser:
     )
     search.set_defaults(handler=_cmd_search, auto_scope=True)
 
+    # ---- vocab-index subparser (PR-ABS-1) ----
+    vocab_index = subparsers.add_parser(
+        "vocab-index",
+        help="Rebuild the vocabulary index (absence diagnosis).",
+        parents=[_core_parser()],
+        description=(
+            "Rebuild the vocabulary index sidecar from the current Ladybug graph. "
+            "The index is a search-optimized projection of Symbol nodes used for "
+            "did-you-mean suggestions and external membership checks in absence "
+            "diagnosis. Printed on success: symbol count and sidecar path."
+        ),
+    )
+    vocab_index.set_defaults(handler=_cmd_vocab_index, detail="full")
+
     return parser
 
 
@@ -1217,6 +1231,40 @@ def _load_graph(cfg):  # type: ignore[no-untyped-def]
         raise _IndexStale(str(exc)) from exc
 
 
+def _cmd_vocab_index(args: argparse.Namespace) -> int:
+    """Rebuild the vocabulary index sidecar from the Ladybug graph."""
+    from ast_java import ONTOLOGY_VERSION
+    from absence_vocab import VocabularyIndex, VOCAB_INDEX_FILENAME
+
+    cfg = _resolve_cfg(args)
+    try:
+        graph = _load_graph(cfg)
+    except (_IndexNotFound, _IndexStale) as exc:
+        print(f"[error] {exc}", file=sys.stderr)
+        return 2
+
+    # Build vocabulary index
+    try:
+        index = VocabularyIndex.build(graph, q=cfg.absence_ngram_q)
+    except Exception as e:
+        print(f"[error] Vocabulary index build failed: {e}", file=sys.stderr)
+        return 1
+
+    # Save to sidecar
+    sidecar_path = cfg.ladybug_path.parent / VOCAB_INDEX_FILENAME
+    try:
+        index.save(sidecar_path, ontology_version=ONTOLOGY_VERSION)
+    except Exception as e:
+        print(f"[error] Failed to save vocabulary index: {e}", file=sys.stderr)
+        return 1
+
+    # Print success message (simple format for admin command)
+    print(f"Vocabulary index rebuilt successfully:")
+    print(f"  Symbol count: {index.symbol_count}")
+    print(f"  Sidecar path: {sidecar_path}")
+    return 0
+
+
 def _cmd_status(args: argparse.Namespace) -> int:
     from java_codebase_rag.jrag_envelope import Envelope
     from java_codebase_rag.jrag_render import render
@@ -4321,13 +4369,20 @@ def _cmd_search(args: argparse.Namespace) -> int:
             d["kind"] = "search_hit"
         # Add explain token when --explain is set
         if args.explain:
-            from search_lancedb import explain_score_components
+            # search_lancedb is unimportable on graph-only (macOS Intel) installs —
+            # lancedb/sentence-transformers are excluded by the PEP 508 markers in
+            # pyproject.toml, and this module imports them at module top. Importing the
+            # explain renderer from there would crash `jrag search ... --explain` on the
+            # exact Intel install that runs the lexical path. search_scoring is
+            # dependency-free and always installed, so the explain import works everywhere.
+            from search_scoring import explain_score_components
             comps = d.get("score_components")
             d["explain"] = explain_score_components(
                 comps,
                 role=d.get("role"),
                 hybrid=bool(args.hybrid),
                 graph_expanded=False,
+                lexical=bool(getattr(out, "lexical_mode", False)),
             )
         hit_dicts.append(d)
 

java_codebase_rag/jrag_envelope.py

@@ -18,6 +18,7 @@ import re
 from dataclasses import dataclass, field
 from typing import Any, Literal
 
+from absence_types import AbsenceDiagnosis
 from graph_types import NodeRef
 
 __all__ = [
@@ -118,6 +119,9 @@ class Envelope:
     # zero in-repo callers. Distinguishes the *correct* empty result ("external
     # entrypoint — no in-repo callers") from a bug-looking bare "0 callers".
     is_external_entrypoint: bool = False
+    # Absence diagnosis explaining why a result is empty (PR-ABS-4). Carried
+    # from MCP outputs and rendered in CLI text/JSON. None on ok/ambiguous.
+    absence: AbsenceDiagnosis | None = None
 
     def to_dict(self) -> dict[str, Any]:
         """Serialize to a JSON-ready dict, omitting empty optionals.
@@ -151,6 +155,8 @@ class Envelope:
             out["message"] = self.message
         if self.is_external_entrypoint:
             out["is_external_entrypoint"] = True
+        if self.absence is not None:
+            out["absence"] = self.absence.model_dump()
         return out
 
     def to_json(self) -> str:
@@ -237,6 +243,8 @@ class Envelope:
             out["message"] = self.message
         if self.is_external_entrypoint:
             out["is_external_entrypoint"] = True
+        if self.absence is not None:
+            out["absence"] = self.absence.model_dump()
         return out
 
     @staticmethod
@@ -610,7 +618,7 @@ def resolve_query(
     # the agent-facing CLI).
     if "jrag search" not in raw_msg:
         raw_msg = f"{raw_msg} Use `jrag search <query>` for ranked fuzzy lookup."
-    return None, Envelope(status="not_found", message=raw_msg)
+    return None, Envelope(status="not_found", message=raw_msg, absence=out.absence)
 
 
 # Listing breadcrumbs (root is None): 1–2 template hints pointing at the natural
@@ -1082,4 +1090,5 @@ def project_envelope(envelope: Envelope, detail: str) -> Envelope:
         file_location=envelope.file_location,
         message=envelope.message,
         is_external_entrypoint=envelope.is_external_entrypoint,
+        absence=envelope.absence,
     )

java_codebase_rag/jrag_render.py

@@ -12,6 +12,7 @@ from __future__ import annotations
 
 from typing import Any
 
+from absence_types import AbsenceDiagnosis
 from java_codebase_rag.jrag_envelope import Envelope, project_envelope, simple_name
 
 __all__ = ["render", "tiered_name", "display_name"]
@@ -32,6 +33,23 @@ _CALLS_FAMILY_EDGES = frozenset({"CALLS", "HTTP_CALLS", "ASYNC_CALLS"})
 # none) and are left untagged.
 _ROUTE_KIND_TAGS: dict[str, str] = {"kafka_topic": "kafka", "http_endpoint": "http"}
 
+# Absence verdict → human-readable label, shared by the not-found / listing /
+# traversal empty-result renderers. ``AbsenceVerdict`` is a closed Literal of
+# these four values.
+_ABSENCE_VERDICT_TEXT: dict[str, str] = {
+    "not_in_project": "not in project",
+    "external_dependency": "external dependency",
+    "refine_query": "refine your query",
+    "correct_empty": "correct empty",
+}
+
+
+def _verdict_line(absence: AbsenceDiagnosis) -> str | None:
+    """A ``Verdict: <label>`` line for an absence diagnosis, or ``None`` if the
+    verdict is not one of the known values."""
+    text = _ABSENCE_VERDICT_TEXT.get(absence.verdict)
+    return f"Verdict: {text}" if text else None
+
 # Identity keys already represented in a listing line (display_name + @service +
 # kind tag). At ``--detail full`` the per-row kv-block skips these (they are in
 # the header line) and renders every OTHER key, so full listing == per-row
@@ -226,7 +244,35 @@ def _render_error(envelope: Envelope) -> str:
 
 def _render_not_found(envelope: Envelope) -> str:
     msg = envelope.message or "not found"
-    return f"not found: {msg}"
+    base = f"not found: {msg}"
+
+    # If absence diagnosis is present, append verdict + message (+ did-you-mean)
+    if envelope.absence is not None:
+        lines = [base]
+        # Verdict line (human-readable label)
+        vline = _verdict_line(envelope.absence)
+        if vline:
+            lines.append(vline)
+
+        # Per-cause explanation message — surfaces the diagnosis's authored help
+        # (external-identity context, filter-relaxation suggestions, etc.).
+        if envelope.absence.message:
+            lines.append(envelope.absence.message)
+
+        # Add did-you-mean line if closest_symbols is non-empty
+        if envelope.absence.closest_symbols:
+            symbols = [s.fqn for s in envelope.absence.closest_symbols]
+            if len(symbols) == 1:
+                lines.append(f"Did you mean: {symbols[0]}?")
+            elif len(symbols) == 2:
+                lines.append(f"Did you mean: {symbols[0]} or {symbols[1]}?")
+            else:
+                joined = ", ".join(symbols[:-1]) + f", or {symbols[-1]}"
+                lines.append(f"Did you mean: {joined}?")
+
+        return "\n".join(lines)
+
+    return base
 
 
 def _render_listing(envelope: Envelope, *, noun: str, detail: str = "normal") -> str:
@@ -295,7 +341,12 @@ def _render_listing(envelope: Envelope, *, noun: str, detail: str = "normal") ->
             if rest:
                 lines.extend(_render_inspect_block(rest, 1))
     if not lines:
-        lines.append(f"0 {noun}".rstrip())
+        # Handle absence diagnosis (PR-ABS-4)
+        if envelope.absence is not None:
+            vline = _verdict_line(envelope.absence)
+            lines.append(vline if vline else f"0 {noun}".rstrip())
+        else:
+            lines.append(f"0 {noun}".rstrip())
     # Listing breadcrumbs (Phase 2): <=2 `next:` hint lines when the listing
     # command emitted agent_next_actions (routes/clients/producers/topics).
     lines.extend(_next_action_lines(envelope))
@@ -413,10 +464,23 @@ def _render_traversal(envelope: Envelope, *, noun: str, detail: str = "normal")
         root_node = envelope.nodes.get(root_id, {})
         root_fqn = str(root_node.get("fqn") or "").strip()
         root_svc = str(root_node.get("microservice") or "").strip()
-        if envelope.is_external_entrypoint:
+
+        # Handle absence diagnosis (PR-ABS-4)
+        if envelope.absence is not None:
+            absence = envelope.absence
+            if absence.verdict == "correct_empty":
+                # Same text as the is_external_entrypoint case.
+                parts = ["external entrypoint — no in-repo callers"]
+            else:
+                vline = _verdict_line(absence)
+                if vline:
+                    lines.append(vline)
+                parts = [f"0 {noun}".rstrip()]
+        elif envelope.is_external_entrypoint:
             parts = ["external entrypoint — no in-repo callers"]
         else:
             parts = [f"0 {noun}".rstrip()]
+
         if root_fqn:
             parts.append(root_fqn)
         if root_svc:

java_codebase_rag/pipeline.py

@@ -18,6 +18,16 @@ from java_codebase_rag.progress import ProgressEvent, ProgressRelay, make_relay
 
 COCOINDEX_TARGET = "java_index_flow_lancedb.py:JavaCodeIndexLance"
 
+# Operator-facing line printed when an indexing command skips the vectors phase
+# because the vector stack is absent (graph-only install, e.g. macOS Intel where
+# cocoindex[lancedb]/lancedb/sentence-transformers are gated off by PEP 508 markers).
+# Single source of truth — imported by cli.py (init/increment) and server.py
+# (reprocess) so the wording can't drift between the two paths.
+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 bundle_dir() -> Path:
     return Path(__file__).resolve().parent.parent

{java_codebase_rag-0.9.4.dist-info → java_codebase_rag-0.9.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: java-codebase-rag
-Version: 0.9.4
+Version: 0.9.5
 Summary: MCP server for semantic + structural search over Java codebases
 Author: HumanBean17
 License-Expression: MIT
@@ -86,7 +86,7 @@ The rest of this README is the install, the tool/command orientation, and the re
 pip install java-codebase-rag
 ```
 
-Python **3.11+** required, on **Linux, macOS, and Windows**. On Linux, Windows, and **Apple Silicon** Macs every native dependency (LanceDB, LadybugDB/kuzu, CocoIndex) ships a wheel and you get the full semantic + graph search. **Intel Macs (x86_64) install graph-only**: PyTorch ≥2.3 and LanceDB ≥0.26 dropped macOS Intel wheels, so the vector stack is auto-excluded via PEP 508 markers — `pip install java-codebase-rag` works out of the box, the graph layer (`find` / `describe` / `neighbors` / `resolve`) is fully usable, and the `search` (semantic) tool reports it is unavailable rather than failing. After install, `java-codebase-rag --help` should print the CLI groups.
+Python **3.11+** required, on **Linux, macOS, and Windows**. On Linux, Windows, and **Apple Silicon** Macs every native dependency (LanceDB, LadybugDB/kuzu, CocoIndex) ships a wheel and you get the full semantic + graph search. **Intel Macs (x86_64) install graph-only**: PyTorch ≥2.3 and LanceDB ≥0.26 dropped macOS Intel wheels, so the vector stack is auto-excluded via PEP 508 markers — `pip install java-codebase-rag` works out of the box, the graph layer (`find` / `describe` / `neighbors` / `resolve`) is fully usable, and the `search` tool falls back to **lexical (keyword) search** over the symbol graph (same tool contract, keyword-ranked instead of semantic; an advisory notes the mode). Semantic/vector search needs Apple Silicon, Linux, or Windows. After install, `java-codebase-rag --help` should print the CLI groups.
 The package includes the CocoIndex lifecycle dependency used by `init`, `increment`, `reprocess`, and `erase` on platforms that have it (it is absent on Intel Mac).
 
 ### Interactive setup (recommended)

{java_codebase_rag-0.9.4.dist-info → java_codebase_rag-0.9.5.dist-info}/RECORD

@@ -1,44 +1,49 @@
-ast_java.py,sha256=ZGykRdcVeLFBxTPFyUfUeAKXxlo6sf82GbyV4tuDuHg,99419
+absence_diagnosis.py,sha256=EorBpkVM5LRWxaTbmbQ3eo6Ew_V7r6enTgtXfcjqzfw,27533
+absence_types.py,sha256=ukDy1GKgebCYdM0OYJ7a5xoI82M2wd0i0KEJwxQFGlo,4220
+absence_vocab.py,sha256=yySRdonAR8hXv0YpTgvaUV0UzihvbvUuSoIXJa5WBiU,15897
+ast_java.py,sha256=1E5XU5lsc1Ltyv96kSv5VNhRl_KRTsYeHG_qDLgPMcc,99419
 brownfield_events.py,sha256=yxXkKDgMb3VPtaiakGzncHM_EGnda8xIue6w90yYp8s,2055
-build_ast_graph.py,sha256=wo5BwVf2JCwLEnZhMlpPPNozt59V1cVvsIhP9cuOFPs,172655
+build_ast_graph.py,sha256=scaC7TnmmmrjAv3R3qy_30kLb2DH4w7lznLxjDCntOs,176403
 chunk_heuristics.py,sha256=aQk2NOKxzUdqoUAJUO3G3LE0MN_bYZWNLQ0tkmj5uts,1813
-graph_enrich.py,sha256=Fxp7JurH9wWTOTX1nErjH4H6Jw5bB68YCqR17rsX6gw,62829
-graph_types.py,sha256=P6RVdEiqZlaSgTyXepnGbtMoZq0m_MaP2q6M6i7Uxlc,4539
+graph_enrich.py,sha256=CYc2K7Zw_CTefaJkL9h6nZmvw3uN8XbIkg4iYQ-ICY0,72528
+graph_types.py,sha256=bf8EEkvWSyRxFQgycTnxxZQwlikLZSU3B-U1Z1cFQtg,4789
 index_common.py,sha256=HT6FKHFJ084eFvd3fR1j8z8gf4eWoPHVW8GXLpw464I,285
-java_index_flow_lancedb.py,sha256=kDkhnRxl-Kz0YNMY27DTk3gwa8H2nWyGDCQC8hxx-jI,28970
+java_index_flow_lancedb.py,sha256=kZh8HgwtGV8Ul_pwdBS7g62hVvKkk8EXTk-qr6NNba8,29676
 java_index_v1_common.py,sha256=nF1KrSqboF_RRvWerG9knRRFmWwsrG_CvhgnsoZ8KqA,1154
 java_ontology.py,sha256=eUGFa96GV_09s2f2sWSMdqYmoxU3-1pyU2iipvcDjG0,17219
-ladybug_queries.py,sha256=rVnVEHwWwE4USeX7tICYEl1SSiSxJGnBNe1VX66R3Xk,100531
+ladybug_queries.py,sha256=SXXNcYxdXCHcQ6SBZdZyqAa-hv5_OFaKsfNx4zVtPgY,100688
 mcp_hints.py,sha256=zp-4cnOmbYD0YovmZiLS2oGcvWcWE7n8jKVz4_xifno,42512
-mcp_v2.py,sha256=ABNHiZEEwQ76uPF9E5fQWncJ4JmmgtG3vmt5TDxBGVo,68901
+mcp_v2.py,sha256=Q69-0IOna1XRG06RcEFEsS-YucuBh60sAVIIDKoOnBc,76688
 path_filtering.py,sha256=R--XzI51LXBu5IBKMCnJWbkNr6I5d-SDmltyQQnWco0,17674
 pr_analysis.py,sha256=zrmZZD5yotJtM02Kif6_jgI_oeformOao793akp0N6Y,18394
-resolve_service.py,sha256=lTHPSn5zgIFjNICiOZc6m_bBJShTn72kShhkofwZdoE,26364
-search_lancedb.py,sha256=1sGSZ6H8J9hGcKAwHpzB7F0_in3A_sEtOI5LvlZYIRI,43864
-server.py,sha256=nOK3DOr-i3PJnVmE7neye_tptJumgXfIXPlTIn01MPQ,37065
+resolve_service.py,sha256=EAfWlGQ4U1qKoPCfZ7BZUUy8pm0w9tldga3Krw0_GO4,28543
+search_lancedb.py,sha256=LmratGpyEKcCYohXVTapjGd-rk_kryS93oD43foGZeQ,34486
+search_lexical.py,sha256=6U0SgRH36Qmh3IIPzMi553ztW7MCnCvg5cSlMpxIdu8,14250
+search_scoring.py,sha256=SSs2GLvHCB_gsKPo0N-YPGeAVNWx-TsXXPJO2JPsOOY,12321
+server.py,sha256=SWh7hZshzVuhYqEm6Leq1GS2VP6olml4dz9nrGwf-KM,39889
 java_codebase_rag/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 java_codebase_rag/_fdlimit.py,sha256=vkwjsPbZfxzZ2DZTPWO5DxtuNlLzOADzIq07iYX7GCU,2465
 java_codebase_rag/_stdio.py,sha256=TDNbpt2EP0_Zd622ihdlKwlMfxkKHWOfgLVcU6TcNbo,1458
 java_codebase_rag/_version.py,sha256=Dnoh_a-c13fqPQ-HV9CsSPbFUkihUJl_z5CACW4qDyA,1365
-java_codebase_rag/cli.py,sha256=nI3eQ_21YDA80WbbYxKEVpIl9uA9tsf1szQhz_C-t9Q,45446
+java_codebase_rag/cli.py,sha256=LcNgfOS7r8_vTckuyUbUxI7bhUyYoU_iwzUb37nT5Ts,45296
 java_codebase_rag/cli_format.py,sha256=CT7-xdwZ0bMCdP68_UOwkvm-mnLluU3LutlM-mDNk60,1839
 java_codebase_rag/cli_progress.py,sha256=q6Wh97yzLGs1B8UFk_WAKivfQu7Y5RnUUE-T2YHWkIs,3237
-java_codebase_rag/config.py,sha256=1EAlKtQx7LUo-gPoE6BOVLz0YEl1OpWFRABkF06zjgk,26464
+java_codebase_rag/config.py,sha256=VPs69os_3co3UPSoBVhpfoVnqDaPJ6Ycbk8A4AyXZOo,30548
 java_codebase_rag/installer.py,sha256=c-_tR1Ct_O3yhmruFRnDoM1Wilz-igD9qdkDPsNqLMI,79934
-java_codebase_rag/jrag.py,sha256=odwSSxnWUOeyhx3O-C_q0y3D4KOVtqUqeDMyKgDVqNc,196991
-java_codebase_rag/jrag_envelope.py,sha256=5jD3p2O-p9acAKHqoif5FFoqgP7Q2ziCuKSiPCHoywc,47505
+java_codebase_rag/jrag.py,sha256=XJN1ejEwxLpTrDJW4lyPjdhP21m7ZRv-JZh73aQDc14,199393
+java_codebase_rag/jrag_envelope.py,sha256=cTe-2lk8-Fvmo9_Ps6rN0QtBSw4muSD_UXvm_rkUc48,47984
 java_codebase_rag/jrag_hints.py,sha256=k2PFE4s3lZgBYHMdZcTjx1-w28nfQcBtQEVsSxI_DvE,9262
-java_codebase_rag/jrag_render.py,sha256=WrBtVFvhpVlykHXg-uZtbdv2XsCw4KXNXVarE06pkLk,32350
+java_codebase_rag/jrag_render.py,sha256=MYPyiB7JiQrSw_KHMjCdWg9JuaxpO3Pv_FI4W7bG8sQ,34917
 java_codebase_rag/lance_optimize.py,sha256=HI3aFebP1fenLL6Cav1jMG5kLXSrHLndO_MIJY6qQVo,11977
-java_codebase_rag/pipeline.py,sha256=L65mjK-IxkVWazUNVyIvzfQNi24behQu-Kdc7o_HwEk,17754
+java_codebase_rag/pipeline.py,sha256=OCqBVjkGZOCvzmBElKMes6ynYn9dSN9J1bhRFyEceVE,18355
 java_codebase_rag/progress.py,sha256=2IxdMALDM0wAQCyJrrfZ975zM_85C-4BfHxf4AtYifE,23212
 java_codebase_rag/install_data/agents/explorer-rag-cli.md,sha256=bVmmzrBSSamMz7hDIKxL5alAZOXsJ_Km8TQnCcxDad0,10292
 java_codebase_rag/install_data/agents/explorer-rag-enhanced.md,sha256=gZsNFbuK0lSnOIlplbbS_muz2ozokJqvFUv65QM0NDM,10406
 java_codebase_rag/install_data/skills/explore-codebase/SKILL.md,sha256=A-v2dueVnxwBzBlxoRjZ2zOJk8DranLQ1TElwn94h0s,11529
 java_codebase_rag/install_data/skills/explore-codebase-cli/SKILL.md,sha256=K2qwZqk2xPxjPxXtUHvax1Ug2J7nBYeMTIjRznO100g,10059
-java_codebase_rag-0.9.4.dist-info/licenses/LICENSE,sha256=gxvtiHtuviR_q8ZAjWw-QTcF3DyPzg6ZY-lQrr8OPpw,1068
-java_codebase_rag-0.9.4.dist-info/METADATA,sha256=CEq0X_nWAQP89qo0VJgX5QR3Pf9NcsaRnk-AruJkL6k,20175
-java_codebase_rag-0.9.4.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
-java_codebase_rag-0.9.4.dist-info/entry_points.txt,sha256=cj3QTc11UYVQnj9T3orc4daiIGaCYrXP149vKbH2R4U,168
-java_codebase_rag-0.9.4.dist-info/top_level.txt,sha256=8vC-VN3cMwz5vhkSTaeJ1a1bDeqLWEfrTks1CvEvIg0,273
-java_codebase_rag-0.9.4.dist-info/RECORD,,
+java_codebase_rag-0.9.5.dist-info/licenses/LICENSE,sha256=gxvtiHtuviR_q8ZAjWw-QTcF3DyPzg6ZY-lQrr8OPpw,1068
+java_codebase_rag-0.9.5.dist-info/METADATA,sha256=cxCb0ljrq1h-E0nS7d7WI8t8LTQwUpIcYNwZXgUkMjM,20331
+java_codebase_rag-0.9.5.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
+java_codebase_rag-0.9.5.dist-info/entry_points.txt,sha256=cj3QTc11UYVQnj9T3orc4daiIGaCYrXP149vKbH2R4U,168
+java_codebase_rag-0.9.5.dist-info/top_level.txt,sha256=gYhQnlcJKpqwIOTwAneruJrkeBzIjoC71LeHMGMZLAY,349
+java_codebase_rag-0.9.5.dist-info/RECORD,,

{java_codebase_rag-0.9.4.dist-info → java_codebase_rag-0.9.5.dist-info}/top_level.txt

@@ -1,3 +1,6 @@
+absence_diagnosis
+absence_types
+absence_vocab
 ast_java
 brownfield_events
 build_ast_graph
@@ -16,4 +19,6 @@ path_filtering
 pr_analysis
 resolve_service
 search_lancedb
+search_lexical
+search_scoring
 server

java_index_flow_lancedb.py

@@ -51,7 +51,13 @@ from java_index_v1_common import (
 )
 from path_filtering import LayeredIgnore
 from ast_java import ONTOLOGY_VERSION, parse_java
-from graph_enrich import collect_annotation_meta_chain, enrich_chunk, load_brownfield_overrides
+from graph_enrich import (
+    classify_java_file,
+    collect_annotation_meta_chain,
+    enrich_chunk,
+    load_brownfield_overrides,
+    load_generated_detection,
+)
 
 # Older cocoindex (e.g. 1.0.0a43) uses ``tracked=False``; newer releases renamed
 # the flag to ``detect_change`` (default False) and reject ``tracked``.
@@ -280,6 +286,9 @@ class JavaLanceChunk:
     annotations_on_type: Annotated[list[str], LanceType(pa.list_(pa.string()))]
     symbols: Annotated[list[str], LanceType(pa.list_(pa.string()))]
     ontology_version: int
+    # Generated source detection: populated per-file, not per-chunk
+    generated: bool
+    generated_by: str | None
 
 
 @dataclass
@@ -364,12 +373,13 @@ def _parse_and_enrich_java(
     chunks: list[Any],
     rel: str,
     project_root: Path,
-) -> list[Any]:
+) -> tuple[list[Any], Any]:
     """Parse one Java file and enrich every chunk, off the event loop.
 
-    Returns a list of :class:`graph_enrich.ChunkEnrichment` aligned 1:1 with
-    ``chunks``. Intended to run via ``asyncio.to_thread`` from
-    ``process_java_file`` (vectors perf lever #2): while the worker thread
+    Returns a tuple of (enrichments, ast) where enrichments is a list of
+    :class:`graph_enrich.ChunkEnrichment` aligned 1:1 with ``chunks``, and ast
+    is the parsed :class:`JavaFileAst`. Intended to run via ``asyncio.to_thread``
+    from ``process_java_file`` (vectors perf lever #2): while the worker thread
     parses + enriches, the event loop is free to drive other files and keep the
     embedder's batching queue fed.
 
@@ -381,7 +391,7 @@ def _parse_and_enrich_java(
     ``lru_cache`` reads are thread-safe under the GIL.
     """
     ast = parse_java(content_bytes)
-    return [
+    enrichments = [
         enrich_chunk(
             ast,
             chunk_start_byte=ch.start.byte_offset,
@@ -391,6 +401,7 @@ def _parse_and_enrich_java(
         )
         for ch in chunks
     ]
+    return enrichments, ast
 
 
 @coco.fn(memo=True)
@@ -430,9 +441,16 @@ async def process_java_file(
     # (vectors perf lever #2) parse + enrich off the event loop so the loop can
     # keep the embedder's batching queue fed while this file is being parsed.
     # parse_java is thread-safe (per-thread tree-sitter Parser in ast_java).
-    enrichments = await asyncio.to_thread(
+    enrichments, ast = await asyncio.to_thread(
         _parse_and_enrich_java, content_bytes, chunks, rel, project_root
     )
+
+    # Compute generated source detection once per file (uses the AST and content_bytes)
+    generated_config = load_generated_detection(project_root)
+    generated, generated_by = classify_java_file(
+        content_bytes, ast, config=generated_config, project_root=project_root
+    )
+
     # (vectors perf lever #1) embed all chunks concurrently so the batched
     # embedder groups them into one ``model.encode(...)`` (max_batch_size=64)
     # instead of N serial batch-of-1 calls. Dominant win for ``increment``
@@ -462,6 +480,8 @@ async def process_java_file(
                 annotations_on_type=enrich.annotations_on_type,
                 symbols=enrich.symbols,
                 ontology_version=ONTOLOGY_VERSION,
+                generated=generated,
+                generated_by=generated_by,
             )
         )
 

ladybug_queries.py

@@ -207,7 +207,7 @@ def _symbol_return_for(alias: str) -> str:
         f"{alias}.modifiers AS modifiers, {alias}.annotations AS annotations, "
         f"{alias}.capabilities AS capabilities, "
         f"{alias}.role AS role, {alias}.signature AS signature, "
-        f"{alias}.parent_id AS parent_id, {alias}.resolved AS resolved"
+        f"{alias}.parent_id AS parent_id, {alias}.resolved AS resolved, {alias}.generated AS generated, {alias}.generated_by AS generated_by"
     )
 
 
@@ -296,7 +296,7 @@ def _row_to_symbol(row: dict[str, Any]) -> SymbolHit:
 _SYM_COLS = (
     "id", "kind", "name", "fqn", "package", "module", "microservice",
     "filename", "start_line", "end_line", "start_byte", "end_byte",
-    "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved",
+    "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved", "generated", "generated_by",
 )
 
 
@@ -1107,14 +1107,14 @@ class LadybugGraph:
             f"s.{c} AS s_{c}" for c in (
                 "id", "kind", "name", "fqn", "package", "module", "microservice",
                 "filename", "start_line", "end_line", "start_byte", "end_byte",
-                "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved",
+                "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved", "generated", "generated_by",
             )
         )
         t_proj = ", ".join(
             f"t.{c} AS t_{c}" for c in (
                 "id", "kind", "name", "fqn", "package", "module", "microservice",
                 "filename", "start_line", "end_line", "start_byte", "end_byte",
-                "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved",
+                "modifiers", "annotations", "capabilities", "role", "signature", "parent_id", "resolved", "generated", "generated_by",
             )
         )
         q = (