gitnexus 1.6.9-rc.31 → 1.6.9-rc.33

package/dist/cli/i18n/en.d.ts

@@ -234,5 +234,5 @@ export declare const en: {
     readonly 'help.option.group.contracts.type': "Filter by contract type";
     readonly 'help.option.group.contracts.repo': "Filter by repo";
     readonly 'help.option.group.contracts.unmatched': "Show only unmatched contracts";
-    readonly 'help.analyze.environment': "\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).";
+    readonly 'help.analyze.environment': "\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n  GITNEXUS_VECTOR_MAX_DISTANCE=N  Max accepted semantic/vector cosine distance (0 < N <= 2; higher values clamp to 2). Default 0.6 for MCP, 0.5 elsewhere.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).";
 };

package/dist/cli/i18n/en.js

@@ -234,5 +234,5 @@ export const en = {
     'help.option.group.contracts.type': 'Filter by contract type',
     'help.option.group.contracts.repo': 'Filter by repo',
     'help.option.group.contracts.unmatched': 'Show only unmatched contracts',
-    'help.analyze.environment': '\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).',
+    'help.analyze.environment': '\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n  GITNEXUS_VECTOR_MAX_DISTANCE=N  Max accepted semantic/vector cosine distance (0 < N <= 2; higher values clamp to 2). Default 0.6 for MCP, 0.5 elsewhere.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).',
 };

package/dist/cli/i18n/resources.d.ts

@@ -235,7 +235,7 @@ export declare const cliResources: {
         readonly 'help.option.group.contracts.type': "Filter by contract type";
         readonly 'help.option.group.contracts.repo': "Filter by repo";
         readonly 'help.option.group.contracts.unmatched': "Show only unmatched contracts";
-        readonly 'help.analyze.environment': "\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).";
+        readonly 'help.analyze.environment': "\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1   Skip .gitignore parsing (still reads .gitnexusignore)\n  GITNEXUS_MAX_FILE_SIZE=N  Override large-file skip threshold (KB). Default 512, max 32768.\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker idle timeout in milliseconds. Default 30000.\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL auto-checkpoint threshold in bytes (default 67108864 = 64 MiB; -1 keeps Ladybug stock ~16 MiB).\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker job byte budget. Default 8388608.\n  GITNEXUS_WORKER_POOL_SIZE=N  Parse worker count override. Default cores-1 capped at 16.\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  Concurrent in-flight parse chunks. Default 2.\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  Max replacement spawns per slot before drop. Default 3.\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  Total retry wall-time per job. Default 5x sub-batch timeout.\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  Per-slot deaths to trip circuit breaker. Default max(3, poolSize).\n  GITNEXUS_EMBEDDING_THREADS=N  Limit local ONNX CPU threads for --embeddings.\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  Max embedding chunks for exact-scan fallback. Default 10000.\n  GITNEXUS_VECTOR_MAX_DISTANCE=N  Max accepted semantic/vector cosine distance (0 < N <= 2; higher values clamp to 2). Default 0.6 for MCP, 0.5 elsewhere.\n\nFlags override the corresponding env vars when both are provided.\n\nTip: `.gitnexusignore` supports `.gitignore`-style negation. Add e.g.\n     `!__tests__/` to index a directory that is auto-filtered by default (#771).";
     };
     readonly 'zh-CN': {
         'common.notIndexed': string;

package/dist/cli/i18n/zh-CN.js

@@ -234,5 +234,5 @@ export const zhCN = {
     'help.option.group.contracts.type': '按契约类型过滤',
     'help.option.group.contracts.repo': '按仓库过滤',
     'help.option.group.contracts.unmatched': '仅显示未匹配契约',
-    'help.analyze.environment': '\n环境变量：\n  GITNEXUS_NO_GITIGNORE=1   跳过 .gitignore 解析（仍读取 .gitnexusignore）\n  GITNEXUS_MAX_FILE_SIZE=N  覆盖大文件跳过阈值（KB）。默认 512，最大 32768。\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker 空闲超时（毫秒）。默认 30000。\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL 自动 checkpoint 阈值（字节，默认 67108864 = 64 MiB；-1 保持 Ladybug 默认约 16 MiB）。\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker 作业字节预算。默认 8388608。\n  GITNEXUS_WORKER_POOL_SIZE=N  解析 worker 数量覆盖值。默认 cores-1，最多 16。\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  并发进行中的解析分块数。默认 2。\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  每个 slot 丢弃前允许的最大替换进程数。默认 3。\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  每个作业的总重试墙钟时间。默认 5 倍子批次超时。\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  每个 slot 触发熔断的死亡次数。默认 max(3, poolSize)。\n  GITNEXUS_EMBEDDING_THREADS=N  限制 --embeddings 的本地 ONNX CPU 线程数。\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  exact-scan 回退的最大嵌入分块数。默认 10000。\n\n当参数和对应环境变量同时提供时，参数优先。\n\n提示：`.gitnexusignore` 支持 `.gitignore` 风格的取反。比如添加\n     `!__tests__/` 可以索引默认自动过滤的目录（#771）。',
+    'help.analyze.environment': '\n环境变量：\n  GITNEXUS_NO_GITIGNORE=1   跳过 .gitignore 解析（仍读取 .gitnexusignore）\n  GITNEXUS_MAX_FILE_SIZE=N  覆盖大文件跳过阈值（KB）。默认 512，最大 32768。\n  GITNEXUS_WORKER_SUB_BATCH_TIMEOUT_MS=N  Worker 空闲超时（毫秒）。默认 30000。\n  GITNEXUS_WAL_CHECKPOINT_THRESHOLD=N  LadybugDB WAL 自动 checkpoint 阈值（字节，默认 67108864 = 64 MiB；-1 保持 Ladybug 默认约 16 MiB）。\n  GITNEXUS_WORKER_SUB_BATCH_MAX_BYTES=N  Worker 作业字节预算。默认 8388608。\n  GITNEXUS_WORKER_POOL_SIZE=N  解析 worker 数量覆盖值。默认 cores-1，最多 16。\n  GITNEXUS_PARSE_CHUNK_CONCURRENCY=N  并发进行中的解析分块数。默认 2。\n  GITNEXUS_WORKER_MAX_RESPAWNS_PER_SLOT=N  每个 slot 丢弃前允许的最大替换进程数。默认 3。\n  GITNEXUS_WORKER_MAX_CUMULATIVE_TIMEOUT_MS=N  每个作业的总重试墙钟时间。默认 5 倍子批次超时。\n  GITNEXUS_WORKER_CONSECUTIVE_FAILURE_THRESHOLD=N  每个 slot 触发熔断的死亡次数。默认 max(3, poolSize)。\n  GITNEXUS_EMBEDDING_THREADS=N  限制 --embeddings 的本地 ONNX CPU 线程数。\n  GITNEXUS_SEMANTIC_EXACT_SCAN_LIMIT=N  exact-scan 回退的最大嵌入分块数。默认 10000。\n  GITNEXUS_VECTOR_MAX_DISTANCE=N  语义/向量搜索接受的最大余弦距离（0 < N <= 2；超出则钳制为 2）。MCP 默认 0.6，其他路径默认 0.5。\n\n当参数和对应环境变量同时提供时，参数优先。\n\n提示：`.gitnexusignore` 支持 `.gitignore` 风格的取反。比如添加\n     `!__tests__/` 可以索引默认自动过滤的目录（#771）。',
 };

package/dist/core/embeddings/config.d.ts

@@ -1,2 +1,17 @@
 import { type EmbeddingConfig } from './types.js';
+export declare const DEFAULT_VECTOR_MAX_DISTANCE = 0.5;
+export declare const DEFAULT_MCP_VECTOR_MAX_DISTANCE = 0.6;
+/**
+ * Cosine distance over normalized embeddings is bounded to [0, 2], so any threshold
+ * above this accepts every row and silently disables the relevance filter. Values
+ * over the ceiling are clamped to it rather than passed through.
+ */
+export declare const VECTOR_MAX_DISTANCE_CEILING = 2;
+/**
+ * Resolve the effective max accepted vector/semantic cosine distance.
+ * Reads `GITNEXUS_VECTOR_MAX_DISTANCE`. Unset/empty/whitespace → silent fallback.
+ * Invalid (non-numeric, <= 0, non-finite) → fallback plus a one-time warning.
+ * Values above the cosine ceiling (2) are clamped to it with a one-time warning.
+ */
+export declare const getVectorMaxDistance: (fallback?: number) => number;
 export declare const resolveEmbeddingConfig: (overrides?: Partial<EmbeddingConfig>) => EmbeddingConfig;

package/dist/core/embeddings/config.js

@@ -1,5 +1,42 @@
 import { defaultEmbeddingThreads } from '../platform/capabilities.js';
+import { logger } from '../logger.js';
 import { DEFAULT_EMBEDDING_CONFIG } from './types.js';
+export const DEFAULT_VECTOR_MAX_DISTANCE = 0.5;
+export const DEFAULT_MCP_VECTOR_MAX_DISTANCE = 0.6;
+/**
+ * Cosine distance over normalized embeddings is bounded to [0, 2], so any threshold
+ * above this accepts every row and silently disables the relevance filter. Values
+ * over the ceiling are clamped to it rather than passed through.
+ */
+export const VECTOR_MAX_DISTANCE_CEILING = 2;
+const warned = new Set();
+const warnOnce = (key, message) => {
+    if (warned.has(key))
+        return;
+    warned.add(key);
+    logger.warn(message);
+};
+/**
+ * Resolve the effective max accepted vector/semantic cosine distance.
+ * Reads `GITNEXUS_VECTOR_MAX_DISTANCE`. Unset/empty/whitespace → silent fallback.
+ * Invalid (non-numeric, <= 0, non-finite) → fallback plus a one-time warning.
+ * Values above the cosine ceiling (2) are clamped to it with a one-time warning.
+ */
+export const getVectorMaxDistance = (fallback = DEFAULT_VECTOR_MAX_DISTANCE) => {
+    const raw = process.env.GITNEXUS_VECTOR_MAX_DISTANCE;
+    if (raw === undefined || raw.trim() === '')
+        return fallback;
+    const parsed = Number(raw);
+    if (!Number.isFinite(parsed) || parsed <= 0) {
+        warnOnce(`invalid:${raw}`, `  GITNEXUS_VECTOR_MAX_DISTANCE must be a positive number in (0, ${VECTOR_MAX_DISTANCE_CEILING}], got "${raw}" — using default ${fallback}`);
+        return fallback;
+    }
+    if (parsed > VECTOR_MAX_DISTANCE_CEILING) {
+        warnOnce(`clamp:${raw}`, `  GITNEXUS_VECTOR_MAX_DISTANCE=${parsed} exceeds the cosine-distance ceiling (${VECTOR_MAX_DISTANCE_CEILING}) — clamping`);
+        return VECTOR_MAX_DISTANCE_CEILING;
+    }
+    return parsed;
+};
 const parsePositiveInt = (name, value, fallback) => {
     if (value === undefined)
         return fallback;

package/dist/core/embeddings/embedding-pipeline.js

@@ -14,7 +14,7 @@ import { generateEmbeddingText } from './text-generator.js';
 import { chunkNode, characterChunk } from './chunker.js';
 import { extractStructuralNames } from './structural-extractor.js';
 import { EMBEDDABLE_LABELS, isShortLabel, LABEL_METHOD, LABELS_WITH_EXPORTED, STRUCTURAL_LABELS, collectBestChunks, } from './types.js';
-import { resolveEmbeddingConfig } from './config.js';
+import { DEFAULT_VECTOR_MAX_DISTANCE, getVectorMaxDistance, resolveEmbeddingConfig, } from './config.js';
 import { rankExactEmbeddingRows } from './exact-search.js';
 import { EMBEDDING_TABLE_NAME, EMBEDDING_INDEX_NAME, STALE_HASH_SENTINEL } from '../lbug/schema.js';
 import { loadVectorExtension, createVectorIndex } from '../lbug/lbug-adapter.js';
@@ -447,7 +447,7 @@ export const runEmbeddingPipeline = async (executeQuery, executeWithReusedStatem
 /**
  * Perform semantic search using the vector index with chunk deduplication
  */
-export const semanticSearch = async (executeQuery, query, k = 10, maxDistance = 0.5) => {
+export const semanticSearch = async (executeQuery, query, k = 10, maxDistance = getVectorMaxDistance(DEFAULT_VECTOR_MAX_DISTANCE)) => {
     if (!isEmbedderReady()) {
         throw new Error('Embedding model not initialized. Run embedding pipeline first.');
     }
@@ -569,7 +569,7 @@ export const semanticSearch = async (executeQuery, query, k = 10, maxDistance =
  * Semantic search with graph expansion (flattened results)
  */
 export const semanticSearchWithContext = async (executeQuery, query, k = 5, _hops = 1) => {
-    const results = await semanticSearch(executeQuery, query, k, 0.5);
+    const results = await semanticSearch(executeQuery, query, k);
     return results.map((r) => ({
         matchId: r.nodeId,
         matchName: r.name,

package/dist/core/group/extractors/http-route-extractor.d.ts

@@ -24,6 +24,8 @@ import type { ExtractedContract, RepoHandle } from '../types.js';
  * widen `HTTP_SCAN_GLOB` if needed.
  */
 export declare const HANDLES_ROUTE_QUERY = "\nMATCH (handlerFile:File)-[r:CodeRelation {type: 'HANDLES_ROUTE'}]->(route:Route)\nRETURN handlerFile.id AS fileId, handlerFile.filePath AS filePath,\n       route.name AS routePath, route.id AS routeId,\n       route.method AS routeMethod,\n       route.handlerSymbolId AS handlerSymbolId,\n       route.responseKeys AS responseKeys,\n       r.reason AS routeSource";
+export declare const RESOLVE_BY_NAME_QUERY = "\nMATCH (n) WHERE labels(n) IN ['Function','Method','CodeElement']\n  AND n.name = $name AND n.filePath <> ''\nRETURN n.id AS uid, n.name AS name, n.filePath AS filePath\nLIMIT 2";
+export declare const RESOLVE_IN_MODULE_QUERY = "\nMATCH (n) WHERE labels(n) IN ['Function','Method','CodeElement']\n  AND n.name = $name AND (n.filePath STARTS WITH $fileDot OR n.filePath STARTS WITH $fileSlash)\nRETURN n.id AS uid, n.name AS name, n.filePath AS filePath\nLIMIT 2";
 /**
  * Canonicalize a provider-side HTTP path for contract-id generation:
  *   - strip query string

package/dist/core/group/extractors/http-route-extractor.js

@@ -67,10 +67,21 @@ MATCH (sym:CodeElement)
 WHERE sym.filePath = $filePath AND sym.startLine IS NOT NULL AND sym.endLine IS NOT NULL
 RETURN sym.id AS uid, sym.name AS name, sym.filePath AS filePath,
        sym.startLine AS startLine, sym.endLine AS endLine, labels(sym) AS labels`;
-// Repo-wide lookup of a symbol by exact name (label-union, as in
-// manifest-extractor.ts). Used to resolve a provider's named handler when it is
-// defined in a file OTHER than its route registration — and only honored when
-// the result is unique (see resolveSymbolByNameUnique).
+// Repo-wide lookup of a symbol by exact name. Used to resolve a provider's
+// named handler when it is defined in a file OTHER than its route registration —
+// and only honored when the result is unique (see resolveSymbolByNameUnique).
+//
+// Label filtering uses `labels(n) IN [...]` rather than the openCypher
+// disjunction `MATCH (n:A|B|C)`. NOTE: this 3-label set (Function/Method/
+// CodeElement) actually PARSES — LadybugDB only rejects a disjunction that
+// names a reserved keyword (e.g. `Macro`, `Union`) or a missing node table,
+// neither of which applies here. So this query was NOT broken by #2325; it
+// uses the `labels(n) IN` form for consistency with the manifest custom-branch
+// fix (which WAS broken) and to stay immune if a reserved-keyword label is
+// added later. `labels(n)` returns the node's single label as a string here, so
+// `IN [...]` is an exact allowlist. (Exported so integration tests can run the
+// exact production query against a real LadybugDB — the bug shipped because no
+// test ran these strings against the real parser.)
 //
 // `n.filePath <> ''` excludes synthetic non-source `CodeElement` nodes that
 // carry no real file — ORM model/table nodes (orm.ts emits `filePath: ''`) and
@@ -78,9 +89,9 @@ RETURN sym.id AS uid, sym.name AS name, sym.filePath AS filePath,
 // degenerate edge-less node NOR inflates the uniqueness count and masks the real
 // handler. `LIMIT 2` bounds materialization: distinguishing unique (1) from
 // ambiguous (>=2) never needs more than two rows (the count guard stays exact).
-const RESOLVE_BY_NAME_QUERY = `
-MATCH (n:Function|Method|CodeElement)
-WHERE n.name = $name AND n.filePath <> ''
+export const RESOLVE_BY_NAME_QUERY = `
+MATCH (n) WHERE labels(n) IN ['Function','Method','CodeElement']
+  AND n.name = $name AND n.filePath <> ''
 RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
 LIMIT 2`;
 // Resolve an IMPORTED handler by pinning it to the import's target module: the
@@ -89,9 +100,9 @@ LIMIT 2`;
 // the precise rung — it survives aliases and local same-name collisions that a
 // repo-wide name lookup cannot, and only resolves on a unique match within that
 // module. `LIMIT 2` keeps the uniqueness count exact (see RESOLVE_BY_NAME_QUERY).
-const RESOLVE_IN_MODULE_QUERY = `
-MATCH (n:Function|Method|CodeElement)
-WHERE n.name = $name AND (n.filePath STARTS WITH $fileDot OR n.filePath STARTS WITH $fileSlash)
+export const RESOLVE_IN_MODULE_QUERY = `
+MATCH (n) WHERE labels(n) IN ['Function','Method','CodeElement']
+  AND n.name = $name AND (n.filePath STARTS WITH $fileDot OR n.filePath STARTS WITH $fileSlash)
 RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
 LIMIT 2`;
 // Source-file extensions an import specifier may resolve to (stripped before

package/dist/core/group/extractors/manifest-extractor.d.ts

@@ -4,6 +4,7 @@ export interface ManifestExtractResult {
     contracts: StoredContract[];
     crossLinks: CrossLink[];
 }
+export declare const CUSTOM_CONTRACT_RESOLVE_QUERY = "MATCH (n)\n   WHERE labels(n) IN ['Function','Method','Class','Interface','Struct','Enum','Trait','Constructor','TypeAlias','Impl','Macro','Union','Typedef','Property','Record','Delegate','Annotation','Template','Const','Static','CodeElement']\n     AND n.name = $symbolName\n   RETURN n.id AS uid, n.name AS name, n.filePath AS filePath\n   ORDER BY n.filePath ASC\n   LIMIT 1";
 /**
  * Stable synthetic symbolUid for a manifest-declared contract whose target
  * symbol could not be resolved against the per-repo graph (resolveSymbol

package/dist/core/group/extractors/manifest-extractor.js

@@ -1,4 +1,18 @@
 import { logger } from '../../logger.js';
+// Repo-wide symbol lookup for `custom` workspace contracts. Exported so the
+// #2325 integration test can run the EXACT production query against a real
+// LadybugDB — a hand-copied query string in the test would silently drift
+// from this allowlist. Uses the `labels(n) IN [...]` allowlist form rather
+// than a `MATCH (n:A|B)` disjunction: this 21-label list contains the
+// reserved-keyword labels `Macro` and `Union`, and LadybugDB's parser rejects
+// a disjunction that names a reserved keyword (#2325) — which the resolver's
+// try/catch then swallowed. `labels(n) IN` has no such collision.
+export const CUSTOM_CONTRACT_RESOLVE_QUERY = `MATCH (n)
+   WHERE labels(n) IN ['Function','Method','Class','Interface','Struct','Enum','Trait','Constructor','TypeAlias','Impl','Macro','Union','Typedef','Property','Record','Delegate','Annotation','Template','Const','Static','CodeElement']
+     AND n.name = $symbolName
+   RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
+   ORDER BY n.filePath ASC
+   LIMIT 1`;
 /**
  * Canonicalize an HTTP path for matching against Route.name in the graph.
  * Mirrors core/ingestion/pipeline.ts ensureSlash semantics:
@@ -148,6 +162,18 @@ export class ManifestExtractor {
         // Cross-impact still works: the bridge query joins on the synthetic
         // uid, and the local impact engine derives the same uid for the
         // unresolved symbol — name-based hints are the additional safety net.
+        //
+        // Label filtering uses `MATCH (n) WHERE labels(n) IN [...]`, NOT the
+        // openCypher disjunction `MATCH (n:A|B|C)`. LadybugDB's parser rejects a
+        // disjunction that names a reserved keyword (`Macro` and `Union` both are)
+        // OR a label with no node table (e.g. the old `lib` branch's `Package`).
+        // The `custom` branch (reserved keywords in its list) and `lib` branch
+        // (missing `Package` table) genuinely threw (#2325) and the whole try/catch
+        // below swallowed it; the other branches parsed but use the same form for
+        // consistency and future-proofing. `labels(n)` returns the node's single
+        // label as a string here, so `IN [...]` is an exact allowlist that includes
+        // listed labels and excludes everything else — and is immune to both
+        // failure modes (no keyword collision; an unknown label is just a non-match).
         try {
             let rows;
             if (link.type === 'http') {
@@ -178,7 +204,7 @@ export class ManifestExtractor {
                 // listeners, publishers). Restrict to symbol-like labels to
                 // avoid cross-matching Files/Variables/Imports that happen to
                 // share the topic name.
-                rows = await executor(`MATCH (n:Function|Method|Class|Interface) WHERE n.name = $contract
+                rows = await executor(`MATCH (n) WHERE labels(n) IN ['Function','Method','Class','Interface'] AND n.name = $contract
            RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
            ORDER BY n.filePath ASC
            LIMIT 1`, { contract: link.contract });
@@ -199,13 +225,13 @@ export class ManifestExtractor {
                 const serviceName = link.type === 'thrift' ? (rawServiceName.split('.').pop() ?? '') : rawServiceName;
                 const methodName = parts[1]?.trim() ?? '';
                 if (methodName) {
-                    rows = await executor(`MATCH (n:Function|Method) WHERE n.name = $methodName
+                    rows = await executor(`MATCH (n) WHERE labels(n) IN ['Function','Method'] AND n.name = $methodName
              RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
              ORDER BY n.filePath ASC
              LIMIT 1`, { methodName });
                 }
                 else if (serviceName) {
-                    rows = await executor(`MATCH (n:Class|Interface) WHERE n.name = $serviceName
+                    rows = await executor(`MATCH (n) WHERE labels(n) IN ['Class','Interface'] AND n.name = $serviceName
              RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
              ORDER BY n.filePath ASC
              LIMIT 1`, { serviceName });
@@ -217,10 +243,11 @@ export class ManifestExtractor {
             else if (link.type === 'lib') {
                 // Only exact match on the symbol's name. Previous fallback to
                 // CONTAINS on n.filePath would promote "react" to "react-native"
-                // or "@types/react" — silent wrong attribution. Restrict to
-                // package-level labels so we don't return arbitrary symbols
-                // named after a library.
-                rows = await executor(`MATCH (n:Package|Module) WHERE n.name = $contract
+                // or "@types/react" — silent wrong attribution. Restrict to the
+                // package-level `Module` label so we don't return arbitrary symbols
+                // named after a library. (There is no `Package` node table — see
+                // NODE_TABLES — so a `Package` entry only ever matched nothing.)
+                rows = await executor(`MATCH (n) WHERE labels(n) IN ['Module'] AND n.name = $contract
            RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
            ORDER BY n.filePath ASC
            LIMIT 1`, { contract: link.contract });
@@ -238,11 +265,7 @@ export class ManifestExtractor {
                 const symbolName = link.contract.includes('::')
                     ? link.contract.split('::').pop()
                     : link.contract;
-                rows = await executor(`MATCH (n:Function|Method|Class|Interface|Struct|Enum|Trait|Constructor|TypeAlias|Impl|Macro|Union|Typedef|Property|Record|Delegate|Annotation|Template|Const|Static|CodeElement)
-           WHERE n.name = $symbolName
-           RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
-           ORDER BY n.filePath ASC
-           LIMIT 1`, { symbolName });
+                rows = await executor(CUSTOM_CONTRACT_RESOLVE_QUERY, { symbolName });
             }
             else {
                 return null;

package/dist/mcp/local/local-backend.js

@@ -21,6 +21,7 @@ import { listRegisteredRepos, cleanupOldKuzuFiles, canonicalizePath, getStorageP
 import { GroupService, } from '../../core/group/service.js';
 import { resolveAtGroupMemberRepoPath } from '../../core/group/resolve-at-member.js';
 import { collectBestChunks } from '../../core/embeddings/types.js';
+import { DEFAULT_MCP_VECTOR_MAX_DISTANCE, getVectorMaxDistance, } from '../../core/embeddings/config.js';
 import { rankExactEmbeddingRows, } from '../../core/embeddings/exact-search.js';
 import { EMBEDDING_TABLE_NAME, EMBEDDING_INDEX_NAME } from '../../core/lbug/schema.js';
 import { getExactScanLimit, isVectorExtensionSupportedByPlatform, } from '../../core/platform/capabilities.js';
@@ -1694,6 +1695,7 @@ export class LocalBackend {
             const queryVec = await embedQuery(query);
             const dims = getEmbeddingDims();
             const queryVecStr = `[${queryVec.join(',')}]`;
+            const maxDistance = getVectorMaxDistance(DEFAULT_MCP_VECTOR_MAX_DISTANCE);
             let bestChunks = new Map();
             if (isVectorExtensionSupportedByPlatform()) {
                 try {
@@ -1703,7 +1705,7 @@ export class LocalBackend {
               CAST(${queryVecStr} AS FLOAT[${dims}]), ${fetchLimit})
             YIELD node AS emb, distance
             WITH emb, distance
-            WHERE distance < 0.6
+            WHERE distance < ${maxDistance}
             RETURN emb.nodeId AS nodeId, emb.chunkIndex AS chunkIndex,
                    emb.startLine AS startLine, emb.endLine AS endLine, distance
             ORDER BY distance
@@ -1747,7 +1749,7 @@ export class LocalBackend {
                     endLine: row.endLine ?? row[3] ?? 0,
                     embedding: row.embedding ?? row[4] ?? [],
                 }));
-                bestChunks = new Map(rankExactEmbeddingRows(exactRows, queryVec, limit, 0.6).map((row) => [
+                bestChunks = new Map(rankExactEmbeddingRows(exactRows, queryVec, limit, maxDistance).map((row) => [
                     row.nodeId,
                     {
                         distance: row.distance,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.6.9-rc.31",
+  "version": "1.6.9-rc.33",
   "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.",
   "author": "Abhigyan Patwari",
   "license": "PolyForm-Noncommercial-1.0.0",