diff --git a/gitnexus/src/core/ingestion/parsing-processor.ts b/gitnexus/src/core/ingestion/parsing-processor.ts index 88d8cd1210..c91df29536 100644 --- a/gitnexus/src/core/ingestion/parsing-processor.ts +++ b/gitnexus/src/core/ingestion/parsing-processor.ts @@ -58,6 +58,39 @@ export interface WorkerExtractedData { parsedFiles: ParsedFile[]; } +type ParsedGraphNode = ParseWorkerResult['nodes'][number]; + +function compareText(left: string, right: string): number { + return left < right ? -1 : left > right ? 1 : 0; +} + +function sourceLine(node: ParsedGraphNode): number { + const value = node.properties.startLine; + return typeof value === 'number' && Number.isFinite(value) ? value : Number.MAX_SAFE_INTEGER; +} + +function compareParsedNodeSourceOrder(left: ParsedGraphNode, right: ParsedGraphNode): number { + const leftPath = typeof left.properties.filePath === 'string' ? left.properties.filePath : ''; + const rightPath = typeof right.properties.filePath === 'string' ? right.properties.filePath : ''; + const fileOrder = compareText(leftPath, rightPath); + if (fileOrder !== 0) return fileOrder; + + const leftLine = sourceLine(left); + const rightLine = sourceLine(right); + if (leftLine !== rightLine) return leftLine < rightLine ? -1 : 1; + + return compareText(left.id, right.id); +} + +function nodesInSourceOrder(nodes: readonly ParsedGraphNode[]): readonly ParsedGraphNode[] { + for (let index = 1; index < nodes.length; index++) { + if (compareParsedNodeSourceOrder(nodes[index - 1], nodes[index]) > 0) { + return [...nodes].sort(compareParsedNodeSourceOrder); + } + } + return nodes; +} + // ============================================================================ // Worker-based parallel parsing // ============================================================================ @@ -95,7 +128,11 @@ export const mergeChunkResults = ( const allParsedFiles: ParsedFile[] = []; for (const result of chunkResults) { - for (const node of result.nodes) { + // Worker jobs and input files are already merged in stable start-index/path + // order. Canonicalize the final per-result node boundary once so graph + // insertion, cache replay, and first-wins graph indexes share source order. + // The common already-ordered path stays allocation-free and linear. + for (const node of nodesInSourceOrder(result.nodes)) { graph.addNode({ id: node.id, label: node.label as NodeLabel, diff --git a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts index 9ab1649a18..0d5abe5103 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts @@ -163,7 +163,7 @@ export function buildGraphNodeLookup(graph: KnowledgeGraph): GraphNodeLookup { } } - // Fallback key: simple name. First-wins within a file — used when + // Fallback key: simple name. Source-order first-wins within a file — used when // the caller doesn't know the qualifier (unqualified free-call // fallback, cross-file resolution where MethodRegistry already // disambiguated the owner). diff --git a/gitnexus/test/unit/scope-resolution/node-lookup-determinism.test.ts b/gitnexus/test/unit/scope-resolution/node-lookup-determinism.test.ts new file mode 100644 index 0000000000..852ab09f75 --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/node-lookup-determinism.test.ts @@ -0,0 +1,94 @@ +import type { NodeLabel } from 'gitnexus-shared'; +import { describe, expect, it } from 'vitest'; + +import { createKnowledgeGraph } from '../../../src/core/graph/graph.js'; +import { createSemanticModel } from '../../../src/core/ingestion/model/semantic-model.js'; +import { mergeChunkResults } from '../../../src/core/ingestion/parsing-processor.js'; +import { + buildGraphNodeLookup, + qualifiedKey, + simpleKey, +} from '../../../src/core/ingestion/scope-resolution/graph-bridge/node-lookup.js'; +import type { ParseWorkerResult } from '../../../src/core/ingestion/workers/parse-worker.js'; + +const FILE = 'src/service.ts'; + +interface Candidate { + id: string; + startLine?: number; +} + +function buildLookup(candidates: readonly Candidate[]) { + const graph = createKnowledgeGraph(); + const nodes = candidates.map( + (candidate) => + ({ + id: candidate.id, + label: 'Method' as NodeLabel, + properties: { + name: 'save', + qualifiedName: 'Service.save', + filePath: FILE, + ...(candidate.startLine !== undefined ? { startLine: candidate.startLine } : {}), + }, + }) satisfies ParseWorkerResult['nodes'][number], + ); + const result: ParseWorkerResult = { + nodes, + relationships: [], + symbols: [], + calls: [], + assignments: [], + routes: [], + fetchCalls: [], + fetchWrapperDefs: [], + decoratorRoutes: [], + routerIncludes: [], + routerImports: [], + toolDefs: [], + ormQueries: [], + constructorBindings: [], + fileScopeBindings: [], + parsedFiles: [], + skippedLanguages: {}, + fileCount: 1, + }; + + mergeChunkResults(graph, createSemanticModel().symbols, [result]); + return buildGraphNodeLookup(graph); +} + +describe('parse-result graph insertion determinism', () => { + it('selects the earliest source definition regardless of worker result order', () => { + const early = { id: `Method:${FILE}:Service.save#1`, startLine: 10 }; + const late = { id: `Method:${FILE}:Service.save#2`, startLine: 20 }; + + const lateFirst = buildLookup([late, early]); + const earlyFirst = buildLookup([early, late]); + + for (const key of [simpleKey(FILE, 'save'), qualifiedKey(FILE, 'Method', 'Service.save')]) { + expect(lateFirst.get(key)).toBe(early.id); + expect(earlyFirst.get(key)).toBe(early.id); + } + }); + + it('uses the stable node id when source positions are identical', () => { + const first = { id: `Method:${FILE}:Service.save#1`, startLine: 10 }; + const second = { id: `Method:${FILE}:Service.save#2`, startLine: 10 }; + + const firstLookup = buildLookup([second, first]); + const secondLookup = buildLookup([first, second]); + + expect(firstLookup.get(simpleKey(FILE, 'save'))).toBe(first.id); + expect(secondLookup.get(simpleKey(FILE, 'save'))).toBe(first.id); + }); + + it('uses the stable node id when source positions are unavailable', () => { + const first = { id: `Method:${FILE}:Service.save#1` }; + const second = { id: `Method:${FILE}:Service.save#2` }; + + const lookup = buildLookup([second, first]); + + expect(lookup.get(simpleKey(FILE, 'save'))).toBe(first.id); + }); +});