sqlsaber 0.5.0__tar.gz → 0.7.0__tar.gz

{sqlsaber-0.5.0 → sqlsaber-0.7.0}/CHANGELOG.md

@@ -4,6 +4,42 @@ All notable changes to SQLSaber will be documented in this file.
 
 ## [Unreleased]
 
+## [0.7.0] - 2025-07-01
+
+### Added
+
+- Table name autocomplete with "@" prefix in interactive mode
+
+  - Type "@" followed by table name to get fuzzy matching completions
+  - Supports schema-aware completions (e.g., "@sample" matches "public.sample")
+
+- Rich markdown display for assistant responses
+  - After streaming completes, the final response is displayed as formatted markdown
+
+## [0.6.0] - 2025-06-30
+
+### Added
+
+- Slash command autocomplete in interactive mode
+  - Commands now use slash prefix: `/clear`, `/exit`, `/quit`
+  - Autocomplete shows when typing `/` at the start of a line
+  - Press Tab to select suggestion
+- Query interruption with Ctrl+C in interactive mode
+  - Press Ctrl+C during query execution to gracefully cancel ongoing operations
+  - Preserves conversation history up to the interruption point
+
+### Changed
+
+- Updated table display for better readability: limit to first 15 columns on wide tables
+  - Shows warning when columns are truncated
+- Interactive commands now require slash prefix (breaking change)
+  - `clear` → `/clear`
+  - `exit` → `/exit`
+  - `quit` → `/quit`
+- Removed default limit of 100. Now model will decide it.
+
+## [0.5.0] - 2025-06-27
+
 ### Added
 
 - Added support for plotting data from query results.

{sqlsaber-0.5.0 → sqlsaber-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlsaber
-Version: 0.5.0
+Version: 0.7.0
 Summary: SQLSaber - Agentic SQL assistant like Claude Code
 License-File: LICENSE
 Requires-Python: >=3.12
@@ -212,23 +212,24 @@ The MCP server uses your existing SQLSaber database configurations, so make sure
 
 ## How It Works
 
-SQLSaber uses an intelligent three-step process optimized for minimal token usage:
+SQLSaber uses a multi-step process to gather the right context, provide it to the model, and execute SQL queries to get the right answers:
+
+![](./sqlsaber.svg)
 
 ### 🔍 Discovery Phase
 
 1. **List Tables Tool**: Quickly discovers available tables with row counts
-2. **Pattern Matching**: Identifies relevant tables based on your query using SQL LIKE patterns
+2. **Pattern Matching**: Identifies relevant tables based on your query
 
 ### 📋 Schema Analysis
 
-3. **Smart Introspection**: Analyzes only the specific table structures needed for your query
-4. **Selective Loading**: Fetches schema information only for relevant tables
+3. **Smart Schema Introspection**: Analyzes only the specific table structures needed for your query
 
 ### ⚡ Execution Phase
 
-5. **SQL Generation**: Creates optimized SQL queries based on natural language input
-6. **Safe Execution**: Runs queries with built-in protections against destructive operations
-7. **Result Formatting**: Presents results with syntax highlighting and explanations
+4. **SQL Generation**: Creates optimized SQL queries based on natural language input
+5. **Safe Execution**: Runs read-only queries with built-in protections against destructive operations
+6. **Result Formatting**: Presents results with explanations in tables and optionally, visualizes using plots
 
 ## Contributing
 

{sqlsaber-0.5.0 → sqlsaber-0.7.0}/README.md

@@ -191,23 +191,24 @@ The MCP server uses your existing SQLSaber database configurations, so make sure
 
 ## How It Works
 
-SQLSaber uses an intelligent three-step process optimized for minimal token usage:
+SQLSaber uses a multi-step process to gather the right context, provide it to the model, and execute SQL queries to get the right answers:
+
+![](./sqlsaber.svg)
 
 ### 🔍 Discovery Phase
 
 1. **List Tables Tool**: Quickly discovers available tables with row counts
-2. **Pattern Matching**: Identifies relevant tables based on your query using SQL LIKE patterns
+2. **Pattern Matching**: Identifies relevant tables based on your query
 
 ### 📋 Schema Analysis
 
-3. **Smart Introspection**: Analyzes only the specific table structures needed for your query
-4. **Selective Loading**: Fetches schema information only for relevant tables
+3. **Smart Schema Introspection**: Analyzes only the specific table structures needed for your query
 
 ### ⚡ Execution Phase
 
-5. **SQL Generation**: Creates optimized SQL queries based on natural language input
-6. **Safe Execution**: Runs queries with built-in protections against destructive operations
-7. **Result Formatting**: Presents results with syntax highlighting and explanations
+4. **SQL Generation**: Creates optimized SQL queries based on natural language input
+5. **Safe Execution**: Runs read-only queries with built-in protections against destructive operations
+6. **Result Formatting**: Presents results with explanations in tables and optionally, visualizes using plots
 
 ## Contributing
 

{sqlsaber-0.5.0 → sqlsaber-0.7.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sqlsaber"
-version = "0.5.0"
+version = "0.7.0"
 description = "SQLSaber - Agentic SQL assistant like Claude Code"
 readme = "README.md"
 requires-python = ">=3.12"