Add project_archives table and MCP tools (CF-264)
- Created migration 009: project_archives table with semantic search - Implemented archives.ts: archiveAdd, archiveSearch, archiveList, archiveGet - Registered archive tools in index.ts and tools/index.ts - Archive types: session, research, audit, investigation, completed, migration - Uses project_key (TEXT) FK to projects table - Tested: archive_add and archive_list working correctly Replaces filesystem archives with database-backed storage. Eliminates context pollution from Glob/Grep operations. Task: CF-264 Session: session_20260119111342_66de546b Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Christian Gick
264
src/tools/archives.ts
Normal file
264
src/tools/archives.ts
Normal file
@@ -0,0 +1,264 @@
|
||||
// Project archives operations for database-backed archival
|
||||
|
||||
import { query, queryOne, execute } from '../db.js';
|
||||
import { getEmbedding, formatEmbedding } from '../embeddings.js';
|
||||
|
||||
type ArchiveType = 'session' | 'research' | 'audit' | 'investigation' | 'completed' | 'migration';
|
||||
|
||||
interface Archive {
|
||||
id: number;
|
||||
project_key: string;
|
||||
archive_type: ArchiveType;
|
||||
title: string;
|
||||
content: string;
|
||||
original_path: string | null;
|
||||
file_size: number | null;
|
||||
archived_at: string;
|
||||
archived_by_session: string | null;
|
||||
metadata: Record<string, unknown>;
|
||||
created_at: string;
|
||||
updated_at: string;
|
||||
}
|
||||
|
||||
interface ArchiveAddArgs {
|
||||
project: string;
|
||||
archive_type: ArchiveType;
|
||||
title: string;
|
||||
content: string;
|
||||
original_path?: string;
|
||||
file_size?: number;
|
||||
archived_by_session?: string;
|
||||
metadata?: Record<string, unknown>;
|
||||
}
|
||||
|
||||
interface ArchiveSearchArgs {
|
||||
query: string;
|
||||
project?: string;
|
||||
archive_type?: ArchiveType;
|
||||
limit?: number;
|
||||
}
|
||||
|
||||
interface ArchiveListArgs {
|
||||
project?: string;
|
||||
archive_type?: ArchiveType;
|
||||
since?: string;
|
||||
limit?: number;
|
||||
}
|
||||
|
||||
interface ArchiveGetArgs {
|
||||
id: number;
|
||||
}
|
||||
|
||||
/**
|
||||
* Verify project exists
|
||||
*/
|
||||
async function verifyProject(projectKey: string): Promise<boolean> {
|
||||
const result = await queryOne<{ key: string }>(
|
||||
'SELECT key FROM projects WHERE key = $1',
|
||||
[projectKey]
|
||||
);
|
||||
return !!result;
|
||||
}
|
||||
|
||||
/**
|
||||
* Add a new archive entry
|
||||
*/
|
||||
export async function archiveAdd(args: ArchiveAddArgs): Promise<string> {
|
||||
const { project, archive_type, title, content, original_path, file_size, archived_by_session, metadata } = args;
|
||||
|
||||
// Verify project exists
|
||||
const exists = await verifyProject(project);
|
||||
if (!exists) {
|
||||
return `Error: Project not found: ${project}`;
|
||||
}
|
||||
|
||||
// Generate embedding for semantic search
|
||||
const embedText = `${title}. ${content.substring(0, 1000)}`; // Limit content length for embedding
|
||||
const embedding = await getEmbedding(embedText);
|
||||
const embeddingValue = embedding ? formatEmbedding(embedding) : null;
|
||||
|
||||
if (embeddingValue) {
|
||||
await execute(
|
||||
`INSERT INTO project_archives
|
||||
(project_key, archive_type, title, content, original_path, file_size, archived_by_session, metadata, embedding)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)`,
|
||||
[
|
||||
project,
|
||||
archive_type,
|
||||
title,
|
||||
content,
|
||||
original_path || null,
|
||||
file_size || null,
|
||||
archived_by_session || null,
|
||||
JSON.stringify(metadata || {}),
|
||||
embeddingValue
|
||||
]
|
||||
);
|
||||
} else {
|
||||
await execute(
|
||||
`INSERT INTO project_archives
|
||||
(project_key, archive_type, title, content, original_path, file_size, archived_by_session, metadata)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8)`,
|
||||
[
|
||||
project,
|
||||
archive_type,
|
||||
title,
|
||||
content,
|
||||
original_path || null,
|
||||
file_size || null,
|
||||
archived_by_session || null,
|
||||
JSON.stringify(metadata || {})
|
||||
]
|
||||
);
|
||||
}
|
||||
|
||||
const sizeStr = file_size ? ` (${Math.round(file_size / 1024)}KB)` : '';
|
||||
return `Archived: [${archive_type}] ${title}${sizeStr}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Search archives semantically
|
||||
*/
|
||||
export async function archiveSearch(args: ArchiveSearchArgs): Promise<string> {
|
||||
const { query: searchQuery, project, archive_type, limit = 5 } = args;
|
||||
|
||||
// Generate embedding for search
|
||||
const embedding = await getEmbedding(searchQuery);
|
||||
|
||||
if (!embedding) {
|
||||
return 'Error: Could not generate embedding for search';
|
||||
}
|
||||
|
||||
const embeddingStr = formatEmbedding(embedding);
|
||||
|
||||
let whereClause = 'WHERE embedding IS NOT NULL';
|
||||
const params: unknown[] = [embeddingStr, limit];
|
||||
let paramIndex = 3;
|
||||
|
||||
if (project) {
|
||||
whereClause += ` AND project_key = $${paramIndex++}`;
|
||||
params.splice(params.length - 1, 0, project);
|
||||
}
|
||||
if (archive_type) {
|
||||
whereClause += ` AND archive_type = $${paramIndex++}`;
|
||||
params.splice(params.length - 1, 0, archive_type);
|
||||
}
|
||||
|
||||
const archives = await query<Archive & { similarity: number }>(
|
||||
`SELECT id, archive_type, title, original_path, file_size,
|
||||
to_char(archived_at, 'YYYY-MM-DD') as archived_at,
|
||||
1 - (embedding <=> $1) as similarity
|
||||
FROM project_archives
|
||||
${whereClause}
|
||||
ORDER BY embedding <=> $1
|
||||
LIMIT $2`,
|
||||
params
|
||||
);
|
||||
|
||||
if (archives.length === 0) {
|
||||
return 'No relevant archives found';
|
||||
}
|
||||
|
||||
const lines = ['Relevant archives:\n'];
|
||||
for (const a of archives) {
|
||||
const sim = Math.round(a.similarity * 100);
|
||||
const sizeStr = a.file_size ? ` (${Math.round(a.file_size / 1024)}KB)` : '';
|
||||
lines.push(`**[${a.archive_type}]** ${a.title} (${sim}% match)`);
|
||||
lines.push(` Archived: ${a.archived_at}${sizeStr}`);
|
||||
if (a.original_path) {
|
||||
lines.push(` Path: ${a.original_path}`);
|
||||
}
|
||||
lines.push('');
|
||||
}
|
||||
|
||||
return lines.join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
* List archives (non-semantic)
|
||||
*/
|
||||
export async function archiveList(args: ArchiveListArgs): Promise<string> {
|
||||
const { project, archive_type, since, limit = 20 } = args;
|
||||
|
||||
let whereClause = 'WHERE 1=1';
|
||||
const params: unknown[] = [];
|
||||
let paramIndex = 1;
|
||||
|
||||
if (project) {
|
||||
whereClause += ` AND project_key = $${paramIndex++}`;
|
||||
params.push(project);
|
||||
}
|
||||
if (archive_type) {
|
||||
whereClause += ` AND archive_type = $${paramIndex++}`;
|
||||
params.push(archive_type);
|
||||
}
|
||||
if (since) {
|
||||
whereClause += ` AND archived_at >= $${paramIndex++}`;
|
||||
params.push(since);
|
||||
}
|
||||
|
||||
params.push(limit);
|
||||
|
||||
const archives = await query<Archive>(
|
||||
`SELECT id, archive_type, title, original_path, file_size,
|
||||
to_char(archived_at, 'YYYY-MM-DD') as archived_at
|
||||
FROM project_archives
|
||||
${whereClause}
|
||||
ORDER BY archived_at DESC
|
||||
LIMIT $${paramIndex}`,
|
||||
params
|
||||
);
|
||||
|
||||
if (archives.length === 0) {
|
||||
return `No archives found${project ? ` for project ${project}` : ''}`;
|
||||
}
|
||||
|
||||
const lines = [`Archives${project ? ` (${project})` : ''}:\n`];
|
||||
for (const a of archives) {
|
||||
const sizeStr = a.file_size ? ` (${Math.round(a.file_size / 1024)}KB)` : '';
|
||||
lines.push(`• [${a.archive_type}] ${a.title} - ${a.archived_at}${sizeStr}`);
|
||||
if (a.original_path) {
|
||||
lines.push(` ${a.original_path}`);
|
||||
}
|
||||
}
|
||||
|
||||
return lines.join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
* Get specific archive by ID
|
||||
*/
|
||||
export async function archiveGet(args: ArchiveGetArgs): Promise<string> {
|
||||
const archive = await queryOne<Archive>(
|
||||
`SELECT id, project_key, archive_type, title, content, original_path, file_size,
|
||||
to_char(archived_at, 'YYYY-MM-DD') as archived_at,
|
||||
archived_by_session, metadata
|
||||
FROM project_archives
|
||||
WHERE id = $1`,
|
||||
[args.id]
|
||||
);
|
||||
|
||||
if (!archive) {
|
||||
return `Archive not found: ${args.id}`;
|
||||
}
|
||||
|
||||
const sizeStr = archive.file_size ? ` (${Math.round(archive.file_size / 1024)}KB)` : '';
|
||||
const lines = [
|
||||
`# Archive #${archive.id}\n`,
|
||||
`**Type:** ${archive.archive_type}`,
|
||||
`**Title:** ${archive.title}`,
|
||||
`**Archived:** ${archive.archived_at}${sizeStr}`,
|
||||
];
|
||||
|
||||
if (archive.original_path) {
|
||||
lines.push(`**Original Path:** ${archive.original_path}`);
|
||||
}
|
||||
if (archive.archived_by_session) {
|
||||
lines.push(`**Session:** ${archive.archived_by_session}`);
|
||||
}
|
||||
|
||||
lines.push('\n---\n');
|
||||
lines.push(archive.content);
|
||||
|
||||
return lines.join('\n');
|
||||
}
|
||||
Reference in New Issue
Block a user