java-codebase-rag 0.6.3__tar.gz → 0.6.4__tar.gz

{java_codebase_rag-0.6.3/java_codebase_rag.egg-info → java_codebase_rag-0.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: java-codebase-rag
-Version: 0.6.3
+Version: 0.6.4
 Summary: MCP server for semantic + structural search over Java codebases
 Author: HumanBean17
 License-Expression: MIT
@@ -44,7 +44,7 @@ Dynamic: license-file
 
 A graph-native code intelligence layer for Java microservice estates, exposed to LLM agents via the **Model Context Protocol (MCP)**.
 
-The system extracts a deterministic property graph from Java source (tree-sitter), stores it in **Kuzu** (graph) alongside a **LanceDB** vector index (chunks), and exposes a deliberately small MCP surface — **five tools**: `search`, `find`, `describe`, `neighbors`, `resolve` — that collapse onto three primitive agent operations: **locate**, **inspect**, **walk**.
+The system extracts a deterministic property graph from Java source (tree-sitter), stores it in **LadybugDB** (graph) alongside a **LanceDB** vector index (chunks), and exposes a deliberately small MCP surface — **five tools**: `search`, `find`, `describe`, `neighbors`, `resolve` — that collapse onto three primitive agent operations: **locate**, **inspect**, **walk**.
 
 > **What this MCP is:** a **GPS for code navigation**, not a reasoning engine.
 > Agents use a simple loop:
@@ -63,9 +63,9 @@ For the design rationale, the GPS metaphor, and the full ontology, see [`docs/pa
 
 Generic code-search tools (grep, ctags, vector-only RAG) hit a ceiling on real Java microservice estates: they find files but lose the structure that makes a Spring/JAX-RS system navigable. This project is built around five choices that target that gap.
 
-- **Hybrid RAG + GraphRAG, not either-or.** Semantic recall (LanceDB chunk vectors) and structural navigation (Kuzu property graph) are composed in one surface. `search` finds candidate nodes by meaning; `neighbors` walks the exact edge you care about (`CALLS`, `IMPLEMENTS`, `INJECTS`, `DECLARES_ROUTE`, …). The agent picks the right primitive per step instead of being forced into pure-vector or pure-symbol search.
+- **Hybrid RAG + GraphRAG, not either-or.** Semantic recall (LanceDB chunk vectors) and structural navigation (LadybugDB property graph) are composed in one surface. `search` finds candidate nodes by meaning; `neighbors` walks the exact edge you care about (`CALLS`, `IMPLEMENTS`, `INJECTS`, `EXPOSES`, …). The agent picks the right primitive per step instead of being forced into pure-vector or pure-symbol search.
 
-- **A Java-tuned role model.** Symbols are labelled with stereotypes inferred from Spring and JAX-RS conventions — `CONTROLLER`, `SERVICE`, `REPOSITORY`, `CLIENT`, `PRODUCER`, `MAPPER`, `DTO`. Agents can ask "list controllers" or "who injects this repository" directly, instead of grep-ing for `@RestController` and hoping for the best. Roles drive both filtering (`find` with a `NodeFilter`) and ranking.
+- **A Java-tuned role model.** Symbols are labelled with stereotypes inferred from Spring and JAX-RS conventions — `CONTROLLER`, `SERVICE`, `REPOSITORY`, `COMPONENT`, `CONFIG`, `ENTITY`, `CLIENT`, `MAPPER`, `DTO`. Agents can ask "list controllers" or "who injects this repository" directly, instead of grep-ing for `@RestController` and hoping for the best. Roles drive both filtering (`find` with a `NodeFilter`) and ranking.
 
 - **Ranking specialized for Java codebases.** The composite ranker is aware of role, microservice, and FQN structure — not a generic BM25. A search for `"chat ingress"` surfaces controllers before utility classes; a search scoped to one microservice doesn't drown in matches from the other 19. Defaults are tuned on the bank-chat fixture and exposed in `docs/CONFIGURATION.md` for per-repo overrides.
 
@@ -113,7 +113,7 @@ All indexing lifecycle commands (`init`, `increment`, `reprocess`, `install`, `u
 
 If you prefer manual configuration, see [`docs/JAVA-CODEBASE-RAG-CLI.md`](./docs/JAVA-CODEBASE-RAG-CLI.md) for the full CLI reference.
 
-> **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/Kuzu schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
+> **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/LadybugDB schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
 
 ---
 
@@ -126,7 +126,7 @@ This repo ships a small multi-module Spring fixture under [`tests/bank-chat-syst
 git clone https://github.com/HumanBean17/java-codebase-rag
 cd java-codebase-rag
 
-# 2. Build the index (Lance vectors + Kuzu graph). First run downloads the
+# 2. Build the index (Lance vectors + LadybugDB graph). First run downloads the
 #    embedding model (~90 MB) and takes ~30-60s on the fixture.
 java-codebase-rag init --source-root tests/bank-chat-system --index-dir /tmp/bank-chat-index
 
@@ -141,7 +141,7 @@ Smoke-test the index with two checks (`search_lancedb` ships with the package):
 JAVA_CODEBASE_RAG_INDEX_DIR=/tmp/bank-chat-index \
   python -m search_lancedb "chat ingress controller" --table java --limit 3
 
-# Vector + graph expansion — proves Kuzu is wired in
+# Vector + graph expansion — proves LadybugDB is wired in
 JAVA_CODEBASE_RAG_INDEX_DIR=/tmp/bank-chat-index \
   python -m search_lancedb "chat ingress controller" --table java --limit 3 \
     --graph-expand --expand-depth 2
@@ -241,8 +241,8 @@ Run `java-codebase-rag --help` to list grouped subcommands. Operator playbook wi
 | Setup | `install` | Interactive setup wizard: config, MCP registration, skill/agent deployment, indexing. |
 | Setup | `update` | Refresh shipped artifacts (skill, agent, MCP entry) + incremental Lance/graph catch-up after pip upgrade. |
 | Lifecycle | `init` | First-time index. Refuses if artifacts already exist. |
-| Lifecycle | `increment` | CocoIndex catch-up + incremental Kuzu update. `--vectors-only` for Lance only. |
-| Lifecycle | `reprocess` | Full Lance + Kuzu rebuild. `--vectors-only` / `--graph-only` for a single phase. |
+| Lifecycle | `increment` | CocoIndex catch-up + incremental LadybugDB update. `--vectors-only` for Lance only. |
+| Lifecycle | `reprocess` | Full Lance + LadybugDB rebuild. `--vectors-only` / `--graph-only` for a single phase. |
 | Lifecycle | `erase` | Delete index artifacts. Requires `--yes` or TTY confirm. |
 | Introspection | `meta`, `tables`, `diagnose-ignore`, `unresolved-calls` | Health, table listing, ignore-layer diagnostics, receiver-failure call sites. |
 | Analysis | `analyze-pr` | Blast-radius / risk from a unified diff. |
@@ -277,7 +277,7 @@ python3 -m venv .venv
 
 The `cocoindex` package powers lifecycle commands that run the indexer (`init`, `increment`, `reprocess`, `erase`). Search and MCP navigation do not invoke it directly.
 
-The default embedding model is `sentence-transformers/all-MiniLM-L6-v2` (downloaded on first `init`). Override via the `EMBEDDING_MODEL` env var — see [`docs/CONFIGURATION.md` §1](./docs/CONFIGURATION.md#1-environment-variables).
+The default embedding model is `sentence-transformers/all-MiniLM-L6-v2` (downloaded on first `init`). Override via the `SBERT_MODEL` env var — see [`docs/CONFIGURATION.md` §1](./docs/CONFIGURATION.md#1-environment-variables).
 
 ---
 

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/README.md

@@ -2,7 +2,7 @@
 
 A graph-native code intelligence layer for Java microservice estates, exposed to LLM agents via the **Model Context Protocol (MCP)**.
 
-The system extracts a deterministic property graph from Java source (tree-sitter), stores it in **Kuzu** (graph) alongside a **LanceDB** vector index (chunks), and exposes a deliberately small MCP surface — **five tools**: `search`, `find`, `describe`, `neighbors`, `resolve` — that collapse onto three primitive agent operations: **locate**, **inspect**, **walk**.
+The system extracts a deterministic property graph from Java source (tree-sitter), stores it in **LadybugDB** (graph) alongside a **LanceDB** vector index (chunks), and exposes a deliberately small MCP surface — **five tools**: `search`, `find`, `describe`, `neighbors`, `resolve` — that collapse onto three primitive agent operations: **locate**, **inspect**, **walk**.
 
 > **What this MCP is:** a **GPS for code navigation**, not a reasoning engine.
 > Agents use a simple loop:
@@ -21,9 +21,9 @@ For the design rationale, the GPS metaphor, and the full ontology, see [`docs/pa
 
 Generic code-search tools (grep, ctags, vector-only RAG) hit a ceiling on real Java microservice estates: they find files but lose the structure that makes a Spring/JAX-RS system navigable. This project is built around five choices that target that gap.
 
-- **Hybrid RAG + GraphRAG, not either-or.** Semantic recall (LanceDB chunk vectors) and structural navigation (Kuzu property graph) are composed in one surface. `search` finds candidate nodes by meaning; `neighbors` walks the exact edge you care about (`CALLS`, `IMPLEMENTS`, `INJECTS`, `DECLARES_ROUTE`, …). The agent picks the right primitive per step instead of being forced into pure-vector or pure-symbol search.
+- **Hybrid RAG + GraphRAG, not either-or.** Semantic recall (LanceDB chunk vectors) and structural navigation (LadybugDB property graph) are composed in one surface. `search` finds candidate nodes by meaning; `neighbors` walks the exact edge you care about (`CALLS`, `IMPLEMENTS`, `INJECTS`, `EXPOSES`, …). The agent picks the right primitive per step instead of being forced into pure-vector or pure-symbol search.
 
-- **A Java-tuned role model.** Symbols are labelled with stereotypes inferred from Spring and JAX-RS conventions — `CONTROLLER`, `SERVICE`, `REPOSITORY`, `CLIENT`, `PRODUCER`, `MAPPER`, `DTO`. Agents can ask "list controllers" or "who injects this repository" directly, instead of grep-ing for `@RestController` and hoping for the best. Roles drive both filtering (`find` with a `NodeFilter`) and ranking.
+- **A Java-tuned role model.** Symbols are labelled with stereotypes inferred from Spring and JAX-RS conventions — `CONTROLLER`, `SERVICE`, `REPOSITORY`, `COMPONENT`, `CONFIG`, `ENTITY`, `CLIENT`, `MAPPER`, `DTO`. Agents can ask "list controllers" or "who injects this repository" directly, instead of grep-ing for `@RestController` and hoping for the best. Roles drive both filtering (`find` with a `NodeFilter`) and ranking.
 
 - **Ranking specialized for Java codebases.** The composite ranker is aware of role, microservice, and FQN structure — not a generic BM25. A search for `"chat ingress"` surfaces controllers before utility classes; a search scoped to one microservice doesn't drown in matches from the other 19. Defaults are tuned on the bank-chat fixture and exposed in `docs/CONFIGURATION.md` for per-repo overrides.
 
@@ -71,7 +71,7 @@ All indexing lifecycle commands (`init`, `increment`, `reprocess`, `install`, `u
 
 If you prefer manual configuration, see [`docs/JAVA-CODEBASE-RAG-CLI.md`](./docs/JAVA-CODEBASE-RAG-CLI.md) for the full CLI reference.
 
-> **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/Kuzu schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
+> **Stability disclaimer.** This package does **not** promise backward compatibility. MCP tool contracts, env vars, Lance/LadybugDB schemas, config files, and Python APIs may change without a deprecation period. Track `main` and rebuild indexes when ontology or embedding settings change.
 
 ---
 
@@ -84,7 +84,7 @@ This repo ships a small multi-module Spring fixture under [`tests/bank-chat-syst
 git clone https://github.com/HumanBean17/java-codebase-rag
 cd java-codebase-rag
 
-# 2. Build the index (Lance vectors + Kuzu graph). First run downloads the
+# 2. Build the index (Lance vectors + LadybugDB graph). First run downloads the
 #    embedding model (~90 MB) and takes ~30-60s on the fixture.
 java-codebase-rag init --source-root tests/bank-chat-system --index-dir /tmp/bank-chat-index
 
@@ -99,7 +99,7 @@ Smoke-test the index with two checks (`search_lancedb` ships with the package):
 JAVA_CODEBASE_RAG_INDEX_DIR=/tmp/bank-chat-index \
   python -m search_lancedb "chat ingress controller" --table java --limit 3
 
-# Vector + graph expansion — proves Kuzu is wired in
+# Vector + graph expansion — proves LadybugDB is wired in
 JAVA_CODEBASE_RAG_INDEX_DIR=/tmp/bank-chat-index \
   python -m search_lancedb "chat ingress controller" --table java --limit 3 \
     --graph-expand --expand-depth 2
@@ -199,8 +199,8 @@ Run `java-codebase-rag --help` to list grouped subcommands. Operator playbook wi
 | Setup | `install` | Interactive setup wizard: config, MCP registration, skill/agent deployment, indexing. |
 | Setup | `update` | Refresh shipped artifacts (skill, agent, MCP entry) + incremental Lance/graph catch-up after pip upgrade. |
 | Lifecycle | `init` | First-time index. Refuses if artifacts already exist. |
-| Lifecycle | `increment` | CocoIndex catch-up + incremental Kuzu update. `--vectors-only` for Lance only. |
-| Lifecycle | `reprocess` | Full Lance + Kuzu rebuild. `--vectors-only` / `--graph-only` for a single phase. |
+| Lifecycle | `increment` | CocoIndex catch-up + incremental LadybugDB update. `--vectors-only` for Lance only. |
+| Lifecycle | `reprocess` | Full Lance + LadybugDB rebuild. `--vectors-only` / `--graph-only` for a single phase. |
 | Lifecycle | `erase` | Delete index artifacts. Requires `--yes` or TTY confirm. |
 | Introspection | `meta`, `tables`, `diagnose-ignore`, `unresolved-calls` | Health, table listing, ignore-layer diagnostics, receiver-failure call sites. |
 | Analysis | `analyze-pr` | Blast-radius / risk from a unified diff. |
@@ -235,7 +235,7 @@ python3 -m venv .venv
 
 The `cocoindex` package powers lifecycle commands that run the indexer (`init`, `increment`, `reprocess`, `erase`). Search and MCP navigation do not invoke it directly.
 
-The default embedding model is `sentence-transformers/all-MiniLM-L6-v2` (downloaded on first `init`). Override via the `EMBEDDING_MODEL` env var — see [`docs/CONFIGURATION.md` §1](./docs/CONFIGURATION.md#1-environment-variables).
+The default embedding model is `sentence-transformers/all-MiniLM-L6-v2` (downloaded on first `init`). Override via the `SBERT_MODEL` env var — see [`docs/CONFIGURATION.md` §1](./docs/CONFIGURATION.md#1-environment-variables).
 
 ---
 

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/ast_java.py

@@ -14,8 +14,8 @@ from __future__ import annotations
 
 import posixpath
 import sys
+import threading
 from dataclasses import dataclass, field
-from functools import lru_cache
 from typing import Iterable
 
 import tree_sitter_java as _ts_java
@@ -215,10 +215,23 @@ _ANON_SUPER_AS_INTERFACE: frozenset[str] = frozenset({
 })
 
 
-@lru_cache(maxsize=1)
+# tree-sitter's ``Parser`` mutates internal state during ``parse()`` and is NOT
+# thread-safe, so each OS thread gets its own instance. ``parse_java`` is called
+# concurrently from worker threads when indexing runs with cocoindex's inflight
+# parallelism — both directly (java_index_flow_lancedb.py: process_java_file
+# offloads parse+enrich to asyncio.to_thread) and transitively
+# (graph_enrich.collect_annotation_meta_chain -> _collect_annotation_decl_index
+# -> parse_java, reached from enrich_chunk). The ``Language`` is immutable and
+# shared; per-thread ``Parser`` construction is lazy and cheap (once per thread),
+# which also preserves parse parallelism instead of serializing it.
+_parser_tls = threading.local()
+
+
 def _parser() -> Parser:
-    lang = Language(_ts_java.language())
-    return Parser(lang)
+    p = getattr(_parser_tls, "parser", None)
+    if p is None:
+        _parser_tls.parser = p = Parser(Language(_ts_java.language()))
+    return p
 
 
 # ---------- dataclasses ----------
@@ -1565,62 +1578,20 @@ def _parse_codebase_http_route_inner_annotation(
     return out
 
 
-def _codebase_route_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseHttpRoute":
-                found.append(n)
-        for c in n.children:
-            visit(c)
+def _inner_annotation_nodes(container_ann: Node, src: bytes, target_simple: str) -> list[Node]:
+    """Collect nested ``@<target_simple>`` annotations anywhere under ``container_ann``.
 
-    visit(container_ann)
-    return found
-
-
-def _codebase_async_route_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseAsyncRoute":
-                found.append(n)
-        for c in n.children:
-            visit(c)
-
-    visit(container_ann)
-    return found
-
-
-def _codebase_http_client_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
-    found: list[Node] = []
-
-    def visit(n: Node) -> None:
-        if n.type == "annotation":
-            name_node = n.child_by_field_name("name")
-            n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseHttpClient":
-                found.append(n)
-        for c in n.children:
-            visit(c)
-
-    visit(container_ann)
-    return found
-
-
-def _codebase_producer_inner_annotation_nodes(container_ann: Node, src: bytes) -> list[Node]:
+    Shared by the four brownfield container walkers — ``CodebaseHttpRoute``,
+    ``CodebaseAsyncRoute``, ``CodebaseHttpClient``, ``CodebaseProducer`` — which
+    differ only by the target annotation simple name.
+    """
     found: list[Node] = []
 
     def visit(n: Node) -> None:
         if n.type == "annotation":
             name_node = n.child_by_field_name("name")
             n_simple = _txt(name_node, src).rsplit(".", 1)[-1] if name_node is not None else ""
-            if n_simple == "CodebaseProducer":
+            if n_simple == target_simple:
                 found.append(n)
         for c in n.children:
             visit(c)
@@ -1842,7 +1813,7 @@ def _outgoing_calls_from_codebase_http_client_producer_annotations(
                 ),
             )
         elif simple == "CodebaseHttpClients":
-            for inner in _codebase_http_client_inner_annotation_nodes(ann, src):
+            for inner in _inner_annotation_nodes(ann, src, "CodebaseHttpClient"):
                 out.append(
                     _parse_codebase_http_client_annotation(
                         inner,
@@ -1869,7 +1840,7 @@ def _outgoing_calls_from_codebase_http_client_producer_annotations(
                 ),
             )
         elif simple == "CodebaseProducers":
-            for inner in _codebase_producer_inner_annotation_nodes(ann, src):
+            for inner in _inner_annotation_nodes(ann, src, "CodebaseProducer"):
                 out.append(
                     _parse_codebase_producer_annotation(
                         inner,
@@ -2343,7 +2314,7 @@ def _collect_routes(
                 ),
             )
         elif simple == "CodebaseHttpRoutes":
-            for inner in _codebase_route_inner_annotation_nodes(node, src):
+            for inner in _inner_annotation_nodes(node, src, "CodebaseHttpRoute"):
                 routes.extend(
                     _parse_codebase_http_route_inner_annotation(
                         inner,
@@ -2359,7 +2330,7 @@ def _collect_routes(
         elif simple in ("CodebaseAsyncRoute", "CodebaseAsyncRoutes"):
             nodes = [node]
             if simple == "CodebaseAsyncRoutes":
-                nodes = list(_codebase_async_route_inner_annotation_nodes(node, src))
+                nodes = list(_inner_annotation_nodes(node, src, "CodebaseAsyncRoute"))
             for ann in nodes:
                 pairs, _ = _annotation_kv_nodes(ann, src)
                 topic_node = pairs.get("topic")

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/build_ast_graph.py

@@ -2010,8 +2010,21 @@ def _producer_id(
     return f"p:{hashlib.sha1(key.encode()).hexdigest()[:16]}"
 
 
+# The four brownfield source layers — single source of truth. Consumed by the
+# client/producer source-layer classifiers, the *_from_brownfield_pct stats
+# (via brownfield_strategies), and the brownfield_only authoritativeness gate in
+# _is_brownfield_sourced. codebase_client/codebase_producer are caller-side
+# declaration strategies, not layers — they extend brownfield_strategies only.
+_BROWNFIELD_LAYERS = frozenset({
+    "layer_a_meta",
+    "layer_b_ann",
+    "layer_b_fqn",
+    "layer_c_source",
+})
+
+
 def _client_source_layer(strategy: str) -> str:
-    if strategy in {"layer_a_meta", "layer_b_ann", "layer_b_fqn", "layer_c_source"}:
+    if strategy in _BROWNFIELD_LAYERS:
         return strategy
     # Some caller extraction paths emit client kind as strategy; treat those
     # as builtin-source declarations instead of warning on every row.
@@ -2023,7 +2036,7 @@ def _client_source_layer(strategy: str) -> str:
 
 
 def _producer_source_layer(strategy: str) -> str:
-    if strategy in {"layer_a_meta", "layer_b_ann", "layer_b_fqn", "layer_c_source"}:
+    if strategy in _BROWNFIELD_LAYERS:
         return strategy
     if strategy in VALID_PRODUCER_KINDS:
         return "builtin"
@@ -2458,15 +2471,14 @@ def pass5_imperative_edges(
         tables.producer_stats.producers_by_kind = defaultdict(int)
         for row in tables.producer_rows:
             tables.producer_stats.producers_by_kind[row.producer_kind] += 1
-        brownfield_strategies = frozenset(
-            (
-                "layer_b_ann",
-                "layer_a_meta",
-                "layer_c_source",
-                "layer_b_fqn",
-                "codebase_client",
-                "codebase_producer",
-            ),
+        # brownfield_strategies = the four brownfield layers plus the two
+        # caller-side declaration strategies (@CodebaseHttpClient /
+        # @CodebaseProducer). These extend _BROWNFIELD_LAYERS deliberately:
+        # the *_from_brownfield_pct stats count annotation-declared callers as
+        # brownfield-sourced even though they are not "layers" and so do not
+        # gate brownfield_only authoritativeness in _is_brownfield_sourced.
+        brownfield_strategies = _BROWNFIELD_LAYERS | frozenset(
+            {"codebase_client", "codebase_producer"},
         )
         if tables.call_edge_stats.http_calls_total:
             n_http = sum(
@@ -2568,14 +2580,6 @@ def _match_call_edge(
     return "cross_service", candidates
 
 
-_BROWNFIELD_LAYERS = frozenset({
-    "layer_c_source",
-    "layer_b_ann",
-    "layer_b_fqn",
-    "layer_a_meta",
-})
-
-
 def _is_brownfield_sourced(
     call_strategy: str,
     candidates: list[RouteRow],

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/graph_enrich.py

@@ -23,7 +23,7 @@ import sys
 from dataclasses import dataclass, field, replace
 from functools import lru_cache
 from pathlib import Path
-from typing import Any
+from typing import Any, TypeVar
 from ast_java import (
     AnnotationRef,
     JavaFileAst,
@@ -820,7 +820,15 @@ def _route_path_atom(raw_value: str, value_kind: str | None) -> tuple[str, str,
     return "", "constant_ref", 0.7, False
 
 
-def _route_hint_lookup(ann: AnnotationRef, hints: dict[str, RouteHint]) -> RouteHint | None:
+_HINT = TypeVar("_HINT")
+
+
+def _hint_lookup(ann: AnnotationRef, hints: dict[str, _HINT]) -> _HINT | None:
+    """Resolve a brownfield hint by qualified name, then simple name, then suffix.
+
+    Shared by route / http-client / async-producer hint resolution; the three
+    former copies differed only in the hint value type.
+    """
     q = ann.qualified.strip()
     if q in hints:
         return hints[q]
@@ -1118,7 +1126,7 @@ def resolve_routes_for_method(
 
     # ----- Step 2: Layer B — annotation route hints -----
     for _is_m, ann in combined_anns:
-        hint = _route_hint_lookup(ann, overrides.annotation_to_route_hint)
+        hint = _hint_lookup(ann, overrides.annotation_to_route_hint)
         if hint is None:
             continue
         working.append(
@@ -1172,36 +1180,6 @@ def resolve_routes_for_method(
     return working
 
 
-def _client_hint_lookup(
-    ann: AnnotationRef,
-    hints: dict[str, HttpClientHint],
-) -> HttpClientHint | None:
-    q = ann.qualified.strip()
-    if q in hints:
-        return hints[q]
-    if ann.name in hints:
-        return hints[ann.name]
-    for k, h in sorted(hints.items(), key=lambda kv: kv[0]):
-        if k.endswith("." + ann.name):
-            return h
-    return None
-
-
-def _async_hint_lookup(
-    ann: AnnotationRef,
-    hints: dict[str, AsyncProducerHint],
-) -> AsyncProducerHint | None:
-    q = ann.qualified.strip()
-    if q in hints:
-        return hints[q]
-    if ann.name in hints:
-        return hints[ann.name]
-    for k, h in sorted(hints.items(), key=lambda kv: kv[0]):
-        if k.endswith("." + ann.name):
-            return h
-    return None
-
-
 def _call_from_http_hint(
     *,
     hint: HttpClientHint,
@@ -1296,7 +1274,7 @@ def resolve_http_client_for_method(
     anchor = builtin_http[0] if builtin_http else (layer_c_src[0] if layer_c_src else None)
 
     for _is_m, ann in combined_anns:
-        hint = _client_hint_lookup(ann, overrides.annotation_to_http_client_hint)
+        hint = _hint_lookup(ann, overrides.annotation_to_http_client_hint)
         if hint is None:
             continue
         brownfield_calls.append(
@@ -1388,7 +1366,7 @@ def resolve_async_producer_for_method(
     anchor = builtin_async[0] if builtin_async else (layer_c_src[0] if layer_c_src else None)
 
     for _is_m, ann in combined_anns:
-        hint = _async_hint_lookup(ann, overrides.annotation_to_async_producer_hint)
+        hint = _hint_lookup(ann, overrides.annotation_to_async_producer_hint)
         if hint is None:
             continue
         brownfield_calls.append(

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/java_codebase_rag/cli.py

@@ -251,7 +251,7 @@ def _startup_hints(cfg: ResolvedOperatorConfig) -> None:
 
 def _add_index_embedding_flags(p: argparse.ArgumentParser) -> None:
     p.add_argument("--source-root", type=str, default=None, help="Java repository root (default: cwd)")
-    p.add_argument("--index-dir", type=str, default=None, help="Index directory (Lance + Kuzu + cocoindex state)")
+    p.add_argument("--index-dir", type=str, default=None, help="Index directory (Lance + LadybugDB + cocoindex state)")
     p.add_argument("--embedding-model", type=str, default=None, help="Override SBERT_MODEL / YAML embedding.model")
     p.add_argument("--embedding-device", type=str, default=None, help="Override SBERT_DEVICE / YAML embedding.device")
 
@@ -536,7 +536,7 @@ 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/kuzu
+        import server  # lazy: pulls sentence_transformers/torch/lancedb/ladybug
 
         result = asyncio.run(
             server.run_refresh_pipeline(
@@ -715,7 +715,7 @@ def _cmd_unresolved_calls_list(args: argparse.Namespace) -> int:
     from ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
-        _emit({"success": False, "message": "Kuzu graph not found"})
+        _emit({"success": False, "message": "LadybugDB graph not found"})
         return 1
     graph = LadybugGraph.get()
     rows = graph.list_unresolved_call_sites(
@@ -736,7 +736,7 @@ def _cmd_unresolved_calls_stats(args: argparse.Namespace) -> int:
     from ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
-        _emit({"success": False, "message": "Kuzu graph not found"})
+        _emit({"success": False, "message": "LadybugDB graph not found"})
         return 1
     graph = LadybugGraph.get()
     buckets = graph.stats_unresolved_call_sites(by=args.by)
@@ -761,7 +761,7 @@ def _cmd_analyze_pr(args: argparse.Namespace) -> int:
     from ladybug_queries import LadybugGraph  # lazy
 
     if not LadybugGraph.exists():
-        _emit({"success": False, "message": "Kuzu graph not found"})
+        _emit({"success": False, "message": "LadybugDB graph not found"})
         return 1
     graph = LadybugGraph.get()
     report = pr_analysis.analyze_pr_pipeline(graph, diff_text)
@@ -801,7 +801,7 @@ def build_parser() -> argparse.ArgumentParser:
         help="Create a fresh index from a Java repository.",
         description=(
             "First-time index creation. Refuses if the resolved index directory "
-            "already contains a Kuzu graph or Lance tables. Exit 2 on refusal."
+            "already contains a LadybugDB graph or Lance tables. Exit 2 on refusal."
         ),
     )
     _add_index_embedding_flags(init)
@@ -870,7 +870,7 @@ def build_parser() -> argparse.ArgumentParser:
     increment = subparsers.add_parser(
         "increment",
         help="Pick up changes since the last index update.",
-        description="Runs cocoindex catch-up and incremental Kuzu graph update. Use --vectors-only to skip graph update.",
+        description="Runs cocoindex catch-up and incremental LadybugDB graph update. Use --vectors-only to skip graph update.",
     )
     _add_index_embedding_flags(increment)
     _add_verbosity_flags(increment)
@@ -883,9 +883,9 @@ def build_parser() -> argparse.ArgumentParser:
 
     reprocess = subparsers.add_parser(
         "reprocess",
-        help="Rebuild vectors and/or Kuzu (default: both full phases).",
+        help="Rebuild vectors and/or LadybugDB (default: both full phases).",
         description=(
-            "Default: full Lance reprocess (cocoindex --full-reprocess) then full Kuzu graph rebuild. "
+            "Default: full Lance reprocess (cocoindex --full-reprocess) then full LadybugDB graph rebuild. "
             "Use --vectors-only or --graph-only to run a single phase (mutually exclusive)."
         ),
     )
@@ -907,7 +907,7 @@ def build_parser() -> argparse.ArgumentParser:
     erase = subparsers.add_parser(
         "erase",
         help="Delete the index from disk.",
-        description="Runs cocoindex drop, removes Kuzu, and drops Lance tables. Requires --yes or TTY confirmation.",
+        description="Runs cocoindex drop, removes LadybugDB, and drops Lance tables. Requires --yes or TTY confirmation.",
     )
     _add_index_embedding_flags(erase)
     erase.add_argument("--yes", action="store_true", help="Confirm destructive deletion (required in CI)")

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/java_codebase_rag/install_data/agents/explorer-rag-enhanced.md

@@ -151,15 +151,15 @@ Simple types in parentheses; generics erased. No spaces after commas. No-arg: `(
 
 ### Shared NodeFilter
 
-For `find`, `filter` is required — `{}` means no predicates. **Strict frame:** unknown keys or inapplicable populated fields → `success=false`.
+For `find`, `filter` is required — `{}` means no predicates. **Strict frame:** unknown keys or inapplicable populated fields → `success=false`; invalid enum values (e.g. wrong case) are rejected earlier at the schema layer with the valid set listed.
 
 | Keys | Applies to |
 | ---- | ---------- |
 | `microservice`, `module` | All kinds |
 | `role`, `exclude_roles`, `annotation`, `capability`, `fqn_prefix`, `symbol_kind`, `symbol_kinds` | **symbol** |
 | `http_method`, `path_prefix`, `framework` | **route** |
-| `client_kind`, `target_service`, `target_path_prefix`, `http_method` | **client** |
-| `producer_kind`, `topic_prefix` | **producer** |
+| `source_layer`, `client_kind`, `target_service`, `target_path_prefix`, `http_method` | **client** |
+| `source_layer`, `producer_kind`, `topic_prefix` | **producer** |
 
 No wildcards in prefix fields — use `search(query=…)` for fuzzy text.
 

{java_codebase_rag-0.6.3 → java_codebase_rag-0.6.4}/java_codebase_rag/install_data/skills/explore-codebase/SKILL.md

@@ -125,15 +125,15 @@ Use these strings **verbatim** in `neighbors(..., edge_types=[...])`.
 
 ### NodeFilter (`find`, `search.filter`, `neighbors.filter`)
 
-For `find`, `filter` is required — `{}` means no predicates. **Strict frame:** unknown keys or inapplicable populated fields → `success=false`.
+For `find`, `filter` is required — `{}` means no predicates. **Strict frame:** unknown keys or inapplicable populated fields → `success=false`; invalid enum values (e.g. wrong case) are rejected earlier at the schema layer with the valid set listed.
 
 | Applicable to | Keys |
 | ------------- | ---- |
 | All kinds | `microservice`, `module` |
 | **symbol** only | `role`, `exclude_roles`, `annotation`, `capability`, `fqn_prefix`, `symbol_kind`, `symbol_kinds` |
 | **route** only | `http_method`, `path_prefix`, `framework` |
-| **client** only | `client_kind`, `target_service`, `target_path_prefix`, `http_method` |
-| **producer** only | `producer_kind`, `topic_prefix` |
+| **client** only | `source_layer`, `client_kind`, `target_service`, `target_path_prefix`, `http_method` |
+| **producer** only | `source_layer`, `producer_kind`, `topic_prefix` |
 
 No wildcards in prefix fields — use `search(query=…)` for ranked text.
 
@@ -166,8 +166,8 @@ Exclude `DTO`, `OTHER`, `MAPPER` with `exclude_roles` when tracing business logi
 
 **Symbol kinds:** `class`, `interface`, `enum`, `record`, `annotation`, `method`, `constructor`.
 
-**Route frameworks:** `spring_mvc`, `webflux`, `kafka`, `rabbitmq`, `jms`, `stream`, `codebase_async_route`, …
-**Client kinds:** `feign_method`, `rest_template`, `web_client`. **Producer kinds:** `kafka_send`, `stream_bridge_send`.
+**Route frameworks:** `spring_mvc`, `webflux`. (Route *kinds* are `http_endpoint`, `http_consumer`, `kafka_topic`, `rabbit_queue`, `jms_destination`, `stream_binding`.)
+**Client kinds:** `feign_method`, `rest_template`, `web_client`. **Producer kinds:** `kafka_send`, `stream_bridge_send`. **Source layers (client/producer):** `builtin`, `layer_a_meta`, `layer_b_ann`, `layer_b_fqn`, `layer_c_source`.
 **Match types:** `cross_service`, `intra_service`, `ambiguous`, `phantom`, `unresolved`.
 
 ---