feat: rescope to AI-first DB harness with multi-DB chat agent

Removes enterprise/DBA features and replaces the marginal AI bar with a
central chat agent that has progressive-discovery tools, cross-session
memory, saved-query reuse, and inline result actions. Adds ClickHouse
support alongside PostgreSQL/Greenplum.

Cleanup
- Drop ~10k LOC of advanced features: Docker, Snapshots, Validation,
  Index Advisor, Role/User Management, Data Generator, ERD, Lookup.
- Trim deps: drop @xyflow/react, dagre, @types/dagre; cut tokio features
  to rt-multi-thread/sync/time/net/macros.
- Remove unused TuskError variants and dead helpers (topological_sort,
  invalidate_schema_cache).

Multi-DB (PostgreSQL + ClickHouse)
- New src-tauri/src/db/ module: ChClient (HTTP-based, reuses reqwest),
  sql_guard (cross-flavor read-only whitelist with 8 tests).
- ConnectionConfig gains db_flavor and secure fields with serde defaults
  for backwards-compatible connections.json.
- All connection/query/schema/data commands dispatch by flavor; CH
  covers connect, execute_query, list_databases/schemas/tables/views/
  columns/completion_schema, paginated table fetch.
- Frontend: dbCapabilities matrix, ConnectionDialog engine selector
  with port auto-swap and HTTPS toggle, SqlEditor switches to
  StandardSQL dialect for CH, TableDataView surfaces CH connections as
  read-only.

AI-first chat agent
- New src/components/chat/ panel with composer, message rendering,
  collapsible tool-call/result blocks, top-level ErrorBoundary.
- Backend agent loop in commands/chat.rs with strict-JSON tool
  protocol. Nine tools: list_databases, list_tables, get_columns,
  switch_database, run_query, remember, save_query, find_queries, final.
  Forgiving parser accepts both flat and nested-input shapes.
- Compressed history: only the last 4 run_query results carry sample
  rows (≤10, cells truncated to 200 chars) into LLM context; older
  results marked omitted.
- System prompt uses lite OVERVIEW (DB list + active-DB tables only)
  instead of full DDL — schema details are loaded on demand via
  get_columns. CH OVERVIEW shows cross-DB tables since CH allows
  db.table queries.

Cross-session memory (F1)
- Per-connection markdown file at app_data_dir/memory/<connection_id>.md,
  16KB cap with oldest-block eviction. Agent appends via remember()
  tool; the file is injected into LEARNED NOTES section of every system
  prompt.
- New Memory sidebar tab with editable textarea, badge for note count,
  empty-state with template. Edits picked up on the next agent turn.

Saved-query reuse (F2)
- Tools save_query and find_queries scoped to current connection.
  save_query attaches a UUID + timestamp; find_queries returns top 10
  matches with SQL preview ≤500 chars.
- Storage shared with the sidebar Saved panel.

Inline result actions (F3)
- run_query result block in chat gets Open-full (90vw × 80vh modal with
  full ResultsTable, no row cap) and Export (reuses ExportDialog for
  CSV/JSON via existing exportCsv/exportJson commands).

Verification
- cargo check clean, zero warnings.
- cargo test --lib: 50 pass (20 chat parser + 4 memory + 8 sql_guard +
  6 clean_sql + 12 escape_ident).
- npx tsc --noEmit clean.
- npx vitest run: 20 pass.
This commit is contained in:
2026-05-06 19:30:44 +03:00
parent 652937f7f5
commit 4f7afc17f4
89 changed files with 4151 additions and 10756 deletions

View File

@@ -41,6 +41,8 @@ pub struct OllamaChatRequest {
pub model: String,
pub messages: Vec<OllamaChatMessage>,
pub stream: bool,
#[serde(skip_serializing_if = "Option::is_none")]
pub format: Option<String>,
}
#[derive(Debug, Deserialize)]
@@ -57,130 +59,3 @@ pub struct OllamaTagsResponse {
pub struct OllamaModel {
pub name: String,
}
// --- Wave 1: Validation ---
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum ValidationStatus {
Pending,
Generating,
Running,
Passed,
Failed,
Error,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ValidationRule {
pub id: String,
pub description: String,
pub generated_sql: String,
pub status: ValidationStatus,
pub violation_count: u64,
pub sample_violations: Vec<Vec<serde_json::Value>>,
pub violation_columns: Vec<String>,
pub error: Option<String>,
}
// --- Wave 2: Data Generator ---
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GenerateDataParams {
pub connection_id: String,
pub schema: String,
pub table: String,
pub row_count: u32,
pub include_related: bool,
pub custom_instructions: Option<String>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GeneratedDataPreview {
pub tables: Vec<GeneratedTableData>,
pub insert_order: Vec<String>,
pub total_rows: u32,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GeneratedTableData {
pub schema: String,
pub table: String,
pub columns: Vec<String>,
pub rows: Vec<Vec<serde_json::Value>>,
pub row_count: u32,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct DataGenProgress {
pub gen_id: String,
pub stage: String,
pub percent: u8,
pub message: String,
pub detail: Option<String>,
}
// --- Wave 3A: Index Advisor ---
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TableStats {
pub schema: String,
pub table: String,
pub seq_scan: i64,
pub idx_scan: i64,
pub n_live_tup: i64,
pub table_size: String,
pub index_size: String,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct IndexStats {
pub schema: String,
pub table: String,
pub index_name: String,
pub idx_scan: i64,
pub index_size: String,
pub definition: String,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct SlowQuery {
pub query: String,
pub calls: i64,
pub total_time_ms: f64,
pub mean_time_ms: f64,
pub rows: i64,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum IndexRecommendationType {
#[serde(rename = "create_index")]
Create,
#[serde(rename = "drop_index")]
Drop,
#[serde(rename = "replace_index")]
Replace,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct IndexRecommendation {
pub id: String,
pub recommendation_type: IndexRecommendationType,
pub table_schema: String,
pub table_name: String,
pub index_name: Option<String>,
pub ddl: String,
pub rationale: String,
pub estimated_impact: String,
pub priority: String,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct IndexAdvisorReport {
pub table_stats: Vec<TableStats>,
pub index_stats: Vec<IndexStats>,
pub slow_queries: Vec<SlowQuery>,
pub recommendations: Vec<IndexRecommendation>,
pub has_pg_stat_statements: bool,
}