mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-09-02 17:49:20 +00:00
feat(workspace): multi-scope workspace reads (#1117)
* feat(workspace): multi-scope workspace reads Adds the ability for a workspace to read from multiple user scopes while keeping writes isolated to the primary scope. Configuration via WORKSPACE_READ_SCOPES env var (comma-separated user IDs). Includes identity file isolation (read_primary), multi-scope search, list, and read operations, WorkspaceConfig refactor, and comprehensive integration tests. * fix: address review feedback for multi-scope workspace reads - fix(memory): deduplicate timezone parsing for daily_log target parse_timezone was called twice when target was "daily_log" without a layer — once in path resolution, again in the fallback. Now computed once and reused. - fix(config): add character validation for WORKSPACE_READ_SCOPES and layer scopes — both enforce [a-zA-Z0-9_-] to prevent path traversal or injection via scope strings used as user_id in SQL queries. - fix(config): use chars().take(32) instead of byte-index slicing for scope length error messages (UTF-8 safety). - fix(error): remove unused WorkspaceError::NotFound variant Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: downgrade search log to debug, add comments on list iteration - Downgrade hybrid_search_multi tracing::info! to debug! — fires on every multi-scope search with the default backend, too noisy for info - Add comments explaining why list/list_all iterate per-scope instead of using _multi trait methods (identity path filtering needs scope attribution that merged results lose) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: [email protected] <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
This commit is contained in:
standardtoaster
@@ -502,4 +502,203 @@ impl Repository {
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
// ==================== Multi-scope search (optimized SQL) ====================
|
||||
|
||||
/// Hybrid search across multiple user scopes with efficient SQL.
|
||||
///
|
||||
/// Uses `user_id = ANY($1::text[])` instead of N separate queries.
|
||||
pub async fn hybrid_search_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
query: &str,
|
||||
embedding: Option<&[f32]>,
|
||||
config: &SearchConfig,
|
||||
) -> Result<Vec<SearchResult>, WorkspaceError> {
|
||||
let fts_results = if config.use_fts {
|
||||
self.fts_search_multi(user_ids, agent_id, query, config.pre_fusion_limit)
|
||||
.await?
|
||||
} else {
|
||||
Vec::new()
|
||||
};
|
||||
|
||||
let vector_results = if config.use_vector {
|
||||
if let Some(embedding) = embedding {
|
||||
self.vector_search_multi(user_ids, agent_id, embedding, config.pre_fusion_limit)
|
||||
.await?
|
||||
} else {
|
||||
Vec::new()
|
||||
}
|
||||
} else {
|
||||
Vec::new()
|
||||
};
|
||||
|
||||
Ok(fuse_results(fts_results, vector_results, config))
|
||||
}
|
||||
|
||||
/// FTS search across multiple user scopes.
|
||||
async fn fts_search_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
query: &str,
|
||||
limit: usize,
|
||||
) -> Result<Vec<RankedResult>, WorkspaceError> {
|
||||
let conn = self.conn().await?;
|
||||
|
||||
let rows = conn
|
||||
.query(
|
||||
r#"
|
||||
SELECT c.id as chunk_id, c.document_id, d.path as document_path,
|
||||
c.content,
|
||||
ts_rank_cd(c.content_tsv, plainto_tsquery('english', $3)) as rank
|
||||
FROM memory_chunks c
|
||||
JOIN memory_documents d ON d.id = c.document_id
|
||||
WHERE d.user_id = ANY($1::text[]) AND d.agent_id IS NOT DISTINCT FROM $2
|
||||
AND c.content_tsv @@ plainto_tsquery('english', $3)
|
||||
ORDER BY rank DESC
|
||||
LIMIT $4
|
||||
"#,
|
||||
&[&user_ids, &agent_id, &query, &(limit as i64)],
|
||||
)
|
||||
.await
|
||||
.map_err(|e| WorkspaceError::SearchFailed {
|
||||
reason: format!("FTS multi-scope query failed: {}", e),
|
||||
})?;
|
||||
|
||||
Ok(rows
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(i, row)| RankedResult {
|
||||
chunk_id: row.get("chunk_id"),
|
||||
document_id: row.get("document_id"),
|
||||
document_path: row.get("document_path"),
|
||||
content: row.get("content"),
|
||||
rank: (i + 1) as u32,
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
/// Vector search across multiple user scopes.
|
||||
async fn vector_search_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
embedding: &[f32],
|
||||
limit: usize,
|
||||
) -> Result<Vec<RankedResult>, WorkspaceError> {
|
||||
let conn = self.conn().await?;
|
||||
let embedding_vec = Vector::from(embedding.to_vec());
|
||||
|
||||
let rows = conn
|
||||
.query(
|
||||
r#"
|
||||
SELECT c.id as chunk_id, c.document_id, d.path as document_path,
|
||||
c.content, 1 - (c.embedding <=> $3) as similarity
|
||||
FROM memory_chunks c
|
||||
JOIN memory_documents d ON d.id = c.document_id
|
||||
WHERE d.user_id = ANY($1::text[]) AND d.agent_id IS NOT DISTINCT FROM $2
|
||||
AND c.embedding IS NOT NULL
|
||||
ORDER BY c.embedding <=> $3
|
||||
LIMIT $4
|
||||
"#,
|
||||
&[&user_ids, &agent_id, &embedding_vec, &(limit as i64)],
|
||||
)
|
||||
.await
|
||||
.map_err(|e| WorkspaceError::SearchFailed {
|
||||
reason: format!("Vector multi-scope query failed: {}", e),
|
||||
})?;
|
||||
|
||||
Ok(rows
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(i, row)| RankedResult {
|
||||
chunk_id: row.get("chunk_id"),
|
||||
document_id: row.get("document_id"),
|
||||
document_path: row.get("document_path"),
|
||||
content: row.get("content"),
|
||||
rank: (i + 1) as u32,
|
||||
})
|
||||
.collect())
|
||||
}
|
||||
|
||||
/// List all file paths across multiple user scopes with a single query.
|
||||
pub async fn list_all_paths_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
) -> Result<Vec<String>, WorkspaceError> {
|
||||
let conn = self.conn().await?;
|
||||
|
||||
let rows = conn
|
||||
.query(
|
||||
r#"
|
||||
SELECT DISTINCT path FROM memory_documents
|
||||
WHERE user_id = ANY($1::text[]) AND agent_id IS NOT DISTINCT FROM $2
|
||||
ORDER BY path
|
||||
"#,
|
||||
&[&user_ids, &agent_id],
|
||||
)
|
||||
.await
|
||||
.map_err(|e| WorkspaceError::SearchFailed {
|
||||
reason: format!("List paths multi-scope failed: {}", e),
|
||||
})?;
|
||||
|
||||
Ok(rows.iter().map(|row| row.get("path")).collect())
|
||||
}
|
||||
|
||||
/// Get a document by path across multiple user scopes.
|
||||
///
|
||||
/// Returns the first match (ordered by the input user_ids priority).
|
||||
pub async fn get_document_by_path_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
path: &str,
|
||||
) -> Result<MemoryDocument, WorkspaceError> {
|
||||
let conn = self.conn().await?;
|
||||
|
||||
let row = conn
|
||||
.query_opt(
|
||||
r#"
|
||||
SELECT id, user_id, agent_id, path, content,
|
||||
created_at, updated_at, metadata
|
||||
FROM memory_documents
|
||||
WHERE user_id = ANY($1::text[]) AND agent_id IS NOT DISTINCT FROM $2 AND path = $3
|
||||
ORDER BY array_position($1::text[], user_id)
|
||||
LIMIT 1
|
||||
"#,
|
||||
&[&user_ids, &agent_id, &path],
|
||||
)
|
||||
.await
|
||||
.map_err(|e| WorkspaceError::SearchFailed {
|
||||
reason: format!("get_document_by_path_multi failed: {}", e),
|
||||
})?;
|
||||
|
||||
match row {
|
||||
Some(row) => Ok(self.row_to_document(&row)),
|
||||
None => Err(WorkspaceError::DocumentNotFound {
|
||||
doc_type: path.to_string(),
|
||||
user_id: format!("[{}]", user_ids.join(", ")),
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
/// List directory contents across multiple user scopes.
|
||||
///
|
||||
/// Iterates per scope and merges results. A future migration could add an
|
||||
/// optimised SQL function, at which point this method can call it directly.
|
||||
pub async fn list_directory_multi(
|
||||
&self,
|
||||
user_ids: &[String],
|
||||
agent_id: Option<Uuid>,
|
||||
directory: &str,
|
||||
) -> Result<Vec<WorkspaceEntry>, WorkspaceError> {
|
||||
let mut all_entries = Vec::new();
|
||||
for uid in user_ids {
|
||||
all_entries.extend(self.list_directory(uid, agent_id, directory).await?);
|
||||
}
|
||||
Ok(crate::workspace::merge_workspace_entries(all_entries))
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user