fix(MULTIVERSION-0001): fix version isolation, 404 on unknown version, commit-hash lookup, and searchModeUsed

Bug 1: Thread version tag from run() into crawl() via getVersionTag() helper so
LocalCrawler and GithubCrawler receive the correct ref when indexing a named
version instead of always crawling HEAD.

Bug 2: Return HTTP 404 with code VERSION_NOT_FOUND when a requested version tag
is not found in repository_versions, instead of silently falling back to a
cross-version mixed result set.

Bug 4: Before returning 404, attempt a commit_hash prefix match (min 7 chars)
so callers can request a version by full or short SHA.

Bug 3: Change HybridSearchService.search() to return
{ results, searchModeUsed } and propagate searchModeUsed through
ContextResponseMetadata and ContextJsonResponseDto so callers can see which
strategy (keyword / semantic / hybrid / keyword_fallback) was actually used.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Giancarmine Salucci
2026-03-28 10:31:15 +01:00
parent 417c6fd072
commit 255838dcc0
9 changed files with 217 additions and 41 deletions

View File

@@ -101,9 +101,12 @@ export class HybridSearchService {
*
* @param query - Raw search string (preprocessing handled by SearchService).
* @param options - Search parameters including repositoryId and alpha blend.
* @returns Ranked array of SnippetSearchResult, deduplicated by snippet ID.
* @returns Object with ranked results array and the search mode actually used.
*/
async search(query: string, options: HybridSearchOptions): Promise<SnippetSearchResult[]> {
async search(
query: string,
options: HybridSearchOptions
): Promise<{ results: SnippetSearchResult[]; searchModeUsed: string }> {
const limit = options.limit ?? 20;
const mode = options.searchMode ?? 'auto';
@@ -127,12 +130,12 @@ export class HybridSearchService {
// Semantic mode: skip FTS entirely and use vector search only.
if (mode === 'semantic') {
if (!this.embeddingProvider || !query.trim()) {
return [];
return { results: [], searchModeUsed: 'semantic' };
}
const embeddings = await this.embeddingProvider.embed([query]);
if (embeddings.length === 0) {
return [];
return { results: [], searchModeUsed: 'semantic' };
}
const queryEmbedding = embeddings[0].values;
@@ -144,7 +147,10 @@ export class HybridSearchService {
});
const topIds = vectorResults.slice(0, limit).map((r) => r.snippetId);
return this.fetchSnippetsByIds(topIds, options.repositoryId, options.type);
return {
results: this.fetchSnippetsByIds(topIds, options.repositoryId, options.type),
searchModeUsed: 'semantic'
};
}
// FTS5 mode (keyword) or hybrid/auto modes: try FTS first.
@@ -157,7 +163,7 @@ export class HybridSearchService {
// Degenerate cases: no provider or pure FTS5 mode.
if (!this.embeddingProvider || alpha === 0) {
return ftsResults.slice(0, limit);
return { results: ftsResults.slice(0, limit), searchModeUsed: 'keyword' };
}
// For auto/hybrid modes: if FTS yielded results, use them; otherwise try vector.
@@ -168,14 +174,14 @@ export class HybridSearchService {
// No FTS results: try vector search as a fallback in auto/hybrid modes.
if (!query.trim()) {
// Query is empty; no point embedding it.
return [];
return { results: [], searchModeUsed: 'keyword_fallback' };
}
const embeddings = await this.embeddingProvider.embed([query]);
// If provider fails (Noop returns empty array), we're done.
if (embeddings.length === 0) {
return [];
return { results: [], searchModeUsed: 'keyword_fallback' };
}
const queryEmbedding = embeddings[0].values;
@@ -187,7 +193,10 @@ export class HybridSearchService {
});
const topIds = vectorResults.slice(0, limit).map((r) => r.snippetId);
return this.fetchSnippetsByIds(topIds, options.repositoryId, options.type);
return {
results: this.fetchSnippetsByIds(topIds, options.repositoryId, options.type),
searchModeUsed: 'keyword_fallback'
};
}
// FTS has results: use RRF to blend with vector search (if alpha < 1).
@@ -195,7 +204,7 @@ export class HybridSearchService {
// Provider may be a Noop (returns empty array) — fall back to FTS gracefully.
if (embeddings.length === 0) {
return ftsResults.slice(0, limit);
return { results: ftsResults.slice(0, limit), searchModeUsed: 'keyword' };
}
const queryEmbedding = embeddings[0].values;
@@ -210,7 +219,10 @@ export class HybridSearchService {
// Pure vector mode: skip RRF and return vector results directly.
if (alpha === 1) {
const topIds = vectorResults.slice(0, limit).map((r) => r.snippetId);
return this.fetchSnippetsByIds(topIds, options.repositoryId, options.type);
return {
results: this.fetchSnippetsByIds(topIds, options.repositoryId, options.type),
searchModeUsed: 'semantic'
};
}
// Build ranked lists for RRF. Score field is unused by RRF — only
@@ -221,7 +233,10 @@ export class HybridSearchService {
const fused = reciprocalRankFusion(ftsRanked, vecRanked);
const topIds = fused.slice(0, limit).map((r) => r.id);
return this.fetchSnippetsByIds(topIds, options.repositoryId, options.type);
return {
results: this.fetchSnippetsByIds(topIds, options.repositoryId, options.type),
searchModeUsed: 'hybrid'
};
}
// -------------------------------------------------------------------------