74 lines
2.5 KiB
Markdown
74 lines
2.5 KiB
Markdown
|
# Task ID: 45
|
||
|
|
|
||
|
|
**Title:** Implement tag-matching algorithm for prompt selection
|
||
|
|
|
||
|
|
**Status:** done
|
||
|
|
|
||
|
|
**Dependencies:** 44 ✓
|
||
|
|
|
||
|
|
**Priority:** high
|
||
|
|
|
||
|
|
**Description:** Create a deterministic keyword-based tag matching algorithm as the no-LLM fallback for prompt selection, with byte-budget allocation and priority weighting.
|
||
|
|
|
||
|
|
**Details:**
|
||
|
|
|
||
|
|
1. Create `/src/mcplocal/src/services/tag-matcher.service.ts`:
|
||
|
|
```typescript
|
||
|
|
interface MatchedPrompt {
|
||
|
|
prompt: PromptIndex;
|
||
|
|
score: number;
|
||
|
|
matchedTags: string[];
|
||
|
|
}
|
||
|
|
|
||
|
|
export class TagMatcherService {
|
||
|
|
constructor(private byteBudget: number = 8192) {}
|
||
|
|
|
||
|
|
matchPrompts(tags: string[], promptIndex: PromptIndex[]): {
|
||
|
|
fullContent: PromptIndex[]; // Prompts to include in full
|
||
|
|
indexOnly: PromptIndex[]; // Prompts to include as index entries
|
||
|
|
remaining: PromptIndex[]; // Non-matched prompts (names only)
|
||
|
|
} {
|
||
|
|
// 1. Priority 10 prompts: always included (score = Infinity)
|
||
|
|
// 2. For each prompt, compute score:
|
||
|
|
// - Check tags against summary + chapters (case-insensitive substring)
|
||
|
|
// - score = matching_tags_count * priority
|
||
|
|
// 3. Sort by score descending
|
||
|
|
// 4. Fill byte budget from top:
|
||
|
|
// - Include full content until budget exhausted
|
||
|
|
// - Remaining matched: include as index entries
|
||
|
|
// - Non-matched: names only
|
||
|
|
}
|
||
|
|
|
||
|
|
private computeScore(tags: string[], prompt: PromptIndex): number {
|
||
|
|
if (prompt.priority === 10) return Infinity;
|
||
|
|
const matchingTags = tags.filter(tag =>
|
||
|
|
this.matchesPrompt(tag.toLowerCase(), prompt)
|
||
|
|
);
|
||
|
|
return matchingTags.length * prompt.priority;
|
||
|
|
}
|
||
|
|
|
||
|
|
private matchesPrompt(tag: string, prompt: PromptIndex): boolean {
|
||
|
|
const searchText = [
|
||
|
|
prompt.summary || '',
|
||
|
|
...(prompt.chapters || [])
|
||
|
|
].join(' ').toLowerCase();
|
||
|
|
return searchText.includes(tag);
|
||
|
|
}
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
2. Handle edge cases: empty tags, no prompts, all priority 10, etc.
|
||
|
|
|
||
|
|
**Test Strategy:**
|
||
|
|
|
||
|
|
- Unit test: Priority 10 prompts always included regardless of tags
|
||
|
|
- Unit test: Score calculation: matching_tags * priority
|
||
|
|
- Unit test: Case-insensitive matching
|
||
|
|
- Unit test: Substring matching in summary and chapters
|
||
|
|
- Unit test: Byte budget exhaustion stops full content inclusion
|
||
|
|
- Unit test: Matched prompts beyond budget become index entries
|
||
|
|
- Unit test: Non-matched prompts listed as names only
|
||
|
|
- Unit test: Sorting by score descending
|
||
|
|
- Unit test: Empty tags returns priority 10 only
|
||
|
|
- Unit test: No prompts returns empty result
|