sqlseed 0.1.20__tar.gz → 0.2.0__tar.gz

{sqlseed-0.1.20 → sqlseed-0.2.0}/CHANGELOG.md

@@ -119,7 +119,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `ColumnMapper` exact match rules expanded from 68 to 74
 
 #### AI Plugin (sqlseed-ai)
-- Auto model selection: `_model_selector` picks the best free model from OpenRouter by priority
+- Auto model selection: `_model_selector` picks the best Gemma 4 model by priority (26B MoE → 31B Dense → 4B → 2B), with multi-backend support (Google AI Studio, LM Studio, Ollama)
 - Structured output: `response_format: json_object` forces LLM to return JSON
 - Few-shot example library: 4 typical scenarios (users, projects, orders, employees)
 - `AiConfigRefiner` self-correction loop: auto-detects and fixes invalid configs, up to 3 retries

{sqlseed-0.1.20 → sqlseed-0.2.0}/CHANGELOG.zh-CN.md

@@ -119,7 +119,7 @@
 - `ColumnMapper` 精确匹配规则从 68 扩展到 74 条
 
 #### AI 插件（sqlseed-ai）
-- 自动模型选择：`_model_selector` 从 OpenRouter 免费模型列表中按优先级自动选择
+- 自动模型选择：`_model_selector` 按 Gemma 4 优先级自动选择（26B MoE → 31B Dense → 4B → 2B），支持多后端（Google AI Studio、LM Studio、Ollama）
 - 结构化输出：`response_format: json_object` 强制 LLM 返回 JSON
 - Few-shot 示例库：4 个典型场景（用户表、银行卡表、订单表、员工表）
 - `AiConfigRefiner` 自纠正闭环：自动检测并修复无效配置，最多 3 轮重试

{sqlseed-0.1.20 → sqlseed-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlseed
-Version: 0.1.20
+Version: 0.2.0
 Summary: Declarative SQLite test data generation toolkit
 Project-URL: Homepage, https://github.com/sunbos/sqlseed
 Project-URL: Documentation, https://github.com/sunbos/sqlseed#readme
@@ -240,6 +240,12 @@ mypy src/sqlseed/
 
 ## 🚀 Quick Start
 
+### Interactive Quickstart
+
+```bash
+python scripts/quickstart.py
+```
+
 ### Try with Demo Database
 
 Want to try sqlseed right away? Build the demo database:
@@ -712,7 +718,6 @@ pip install sqlseed-ai
 
 # Set API key
 export SQLSEED_AI_API_KEY="your-api-key"
-export SQLSEED_AI_BASE_URL="https://your-llm-api-endpoint"
 
 # AI analysis and config generation
 sqlseed ai-suggest app.db --table projects --output projects.yaml
@@ -720,9 +725,27 @@ sqlseed ai-suggest app.db --table projects --output projects.yaml
 # AI suggestions with self-correction (3 rounds by default)
 sqlseed ai-suggest app.db --table projects --output projects.yaml --verify
 
-# Specify model (defaults to most popular free model)
-sqlseed ai-suggest app.db --table projects --output projects.yaml --model nvidia/nemotron-3-super-120b-a12b:free
+# Specify model (defaults to Gemma 4 26B via Google AI Studio)
+sqlseed ai-suggest app.db --table projects --output projects.yaml --model gemma-4-26b-it
+
+# Use local LM Studio / Ollama
+sqlseed ai-suggest app.db --table projects --output projects.yaml --backend lm_studio --model google/gemma-4-e4b
+```
 
+**Gemma 4 Native Function Calling (GEMMA_TOOLS)**:
+
+sqlseed-ai supports Gemma 4 model family (2B/4B/26B/31B) with Native Function Calling via GEMMA_TOOLS protocol. Supported backends:
+
+| Backend | Description | Configuration |
+| :------ | :---------- | :------------ |
+| **Google AI Studio** | Official API, recommended for Gemma 4 26B/31B | `--backend google_ai_studio` or `SQLSEED_AI_BACKEND=google_ai_studio` |
+| **LM Studio** | Local inference, suitable for Gemma 4 2B/4B | `--backend lm_studio` or `SQLSEED_AI_BACKEND=lm_studio` |
+| **Ollama** | Local inference, suitable for Gemma 4 2B/4B/26B | `--backend ollama` or `SQLSEED_AI_BACKEND=ollama` |
+| **OpenAI-compatible** | Generic OpenAI-compatible endpoint (e.g., OpenRouter, DeepSeek) | `--backend openai_compat` or `SQLSEED_AI_BACKEND=openai_compat` |
+
+> **💡 OpenRouter (Free)**: For users without a paid API key, OpenRouter provides free models. Set `SQLSEED_AI_BACKEND=openai_compat`, `SQLSEED_AI_BASE_URL=https://openrouter.ai/api/v1`, and `SQLSEED_AI_MODEL=<free-model-name>`.
+
+```bash
 # Skip cache
 sqlseed ai-suggest app.db --table projects --output projects.yaml --no-cache
 ```
@@ -738,7 +761,7 @@ sqlseed ai-suggest app.db --table projects --output projects.yaml --no-cache
 6. Up to 3 self-correction rounds, outputs validated YAML config
 ```
 
-> **💡 Environment Variables**: Supports `SQLSEED_AI_API_KEY`, `SQLSEED_AI_BASE_URL`, `SQLSEED_AI_MODEL`. Also supports `OPENAI_API_KEY` / `OPENAI_BASE_URL` as fallback. Defaults to auto-selecting the most popular free model from OpenRouter (base_url `https://openrouter.ai/api/v1`). Set `--model` or `SQLSEED_AI_MODEL` to specify a model.
+> **💡 Environment Variables**: Supports `SQLSEED_AI_API_KEY`, `SQLSEED_AI_BASE_URL`, `SQLSEED_AI_MODEL`, `SQLSEED_AI_BACKEND`. Also supports `OPENAI_API_KEY` / `OPENAI_BASE_URL` as fallback. Defaults to Gemma 4 26B via Google AI Studio. Supported backends: `google_ai_studio`, `lm_studio`, `ollama`, `openai_compat`.
 
 ***
 
@@ -777,6 +800,9 @@ python -m mcp_server_sqlseed
 | 🔍 Tool | `sqlseed_inspect_schema` | Inspect schema (columns, FK, indexes, samples, schema_hash) |
 | 🤖 Tool | `sqlseed_generate_yaml` | AI-driven YAML config generation with self-correction. Supports `api_key`/`base_url`/`model` overrides |
 | ⚡ Tool | `sqlseed_execute_fill` | Execute data generation (supports YAML config string, includes `enrich` option) |
+| 🧠 Tool | `sqlseed_gemma4_analyze` | Analyze schema using Gemma 4 with Native Function Calling |
+| 🧠 Tool | `sqlseed_gemma4_agent_fill` | End-to-end Agent workflow (analyze -> config -> fill) |
+| 🧠 Tool | `sqlseed_list_gemma_models` | List available Gemma 4 models and backend status |
 
 This means you can tell your AI assistant:
 
@@ -1053,7 +1079,7 @@ Tests cover all core modules, with path structure mirroring `src/`: `test_core/`
 | `sqlseed[faker]` | + faker>=30.0 | Faker data engine |
 | `sqlseed[mimesis]` | + mimesis>=18.0 | Mimesis data engine (recommended) |
 | `sqlseed[docs]` | + mkdocs-material, mkdocstrings | Documentation build |
-| `sqlseed-ai` | sqlseed, **openai>=1.0** | AI plugin, auto-registered via entry-point |
+| `sqlseed-ai` | sqlseed, **openai>=1.0**, **google-generativeai>=0.8** | AI plugin (Gemma 4 Native Function Calling), auto-registered via entry-point |
 | `mcp-server-sqlseed` | sqlseed, **mcp>=1.0** | MCP server, standalone CLI tool |
 | `mcp-server-sqlseed[ai]` | + sqlseed-ai | MCP server with AI support |
 

{sqlseed-0.1.20 → sqlseed-0.2.0}/README.md

@@ -180,6 +180,12 @@ mypy src/sqlseed/
 
 ## 🚀 Quick Start
 
+### Interactive Quickstart
+
+```bash
+python scripts/quickstart.py
+```
+
 ### Try with Demo Database
 
 Want to try sqlseed right away? Build the demo database:
@@ -652,7 +658,6 @@ pip install sqlseed-ai
 
 # Set API key
 export SQLSEED_AI_API_KEY="your-api-key"
-export SQLSEED_AI_BASE_URL="https://your-llm-api-endpoint"
 
 # AI analysis and config generation
 sqlseed ai-suggest app.db --table projects --output projects.yaml
@@ -660,9 +665,27 @@ sqlseed ai-suggest app.db --table projects --output projects.yaml
 # AI suggestions with self-correction (3 rounds by default)
 sqlseed ai-suggest app.db --table projects --output projects.yaml --verify
 
-# Specify model (defaults to most popular free model)
-sqlseed ai-suggest app.db --table projects --output projects.yaml --model nvidia/nemotron-3-super-120b-a12b:free
+# Specify model (defaults to Gemma 4 26B via Google AI Studio)
+sqlseed ai-suggest app.db --table projects --output projects.yaml --model gemma-4-26b-it
+
+# Use local LM Studio / Ollama
+sqlseed ai-suggest app.db --table projects --output projects.yaml --backend lm_studio --model google/gemma-4-e4b
+```
 
+**Gemma 4 Native Function Calling (GEMMA_TOOLS)**:
+
+sqlseed-ai supports Gemma 4 model family (2B/4B/26B/31B) with Native Function Calling via GEMMA_TOOLS protocol. Supported backends:
+
+| Backend | Description | Configuration |
+| :------ | :---------- | :------------ |
+| **Google AI Studio** | Official API, recommended for Gemma 4 26B/31B | `--backend google_ai_studio` or `SQLSEED_AI_BACKEND=google_ai_studio` |
+| **LM Studio** | Local inference, suitable for Gemma 4 2B/4B | `--backend lm_studio` or `SQLSEED_AI_BACKEND=lm_studio` |
+| **Ollama** | Local inference, suitable for Gemma 4 2B/4B/26B | `--backend ollama` or `SQLSEED_AI_BACKEND=ollama` |
+| **OpenAI-compatible** | Generic OpenAI-compatible endpoint (e.g., OpenRouter, DeepSeek) | `--backend openai_compat` or `SQLSEED_AI_BACKEND=openai_compat` |
+
+> **💡 OpenRouter (Free)**: For users without a paid API key, OpenRouter provides free models. Set `SQLSEED_AI_BACKEND=openai_compat`, `SQLSEED_AI_BASE_URL=https://openrouter.ai/api/v1`, and `SQLSEED_AI_MODEL=<free-model-name>`.
+
+```bash
 # Skip cache
 sqlseed ai-suggest app.db --table projects --output projects.yaml --no-cache
 ```
@@ -678,7 +701,7 @@ sqlseed ai-suggest app.db --table projects --output projects.yaml --no-cache
 6. Up to 3 self-correction rounds, outputs validated YAML config
 ```
 
-> **💡 Environment Variables**: Supports `SQLSEED_AI_API_KEY`, `SQLSEED_AI_BASE_URL`, `SQLSEED_AI_MODEL`. Also supports `OPENAI_API_KEY` / `OPENAI_BASE_URL` as fallback. Defaults to auto-selecting the most popular free model from OpenRouter (base_url `https://openrouter.ai/api/v1`). Set `--model` or `SQLSEED_AI_MODEL` to specify a model.
+> **💡 Environment Variables**: Supports `SQLSEED_AI_API_KEY`, `SQLSEED_AI_BASE_URL`, `SQLSEED_AI_MODEL`, `SQLSEED_AI_BACKEND`. Also supports `OPENAI_API_KEY` / `OPENAI_BASE_URL` as fallback. Defaults to Gemma 4 26B via Google AI Studio. Supported backends: `google_ai_studio`, `lm_studio`, `ollama`, `openai_compat`.
 
 ***
 
@@ -717,6 +740,9 @@ python -m mcp_server_sqlseed
 | 🔍 Tool | `sqlseed_inspect_schema` | Inspect schema (columns, FK, indexes, samples, schema_hash) |
 | 🤖 Tool | `sqlseed_generate_yaml` | AI-driven YAML config generation with self-correction. Supports `api_key`/`base_url`/`model` overrides |
 | ⚡ Tool | `sqlseed_execute_fill` | Execute data generation (supports YAML config string, includes `enrich` option) |
+| 🧠 Tool | `sqlseed_gemma4_analyze` | Analyze schema using Gemma 4 with Native Function Calling |
+| 🧠 Tool | `sqlseed_gemma4_agent_fill` | End-to-end Agent workflow (analyze -> config -> fill) |
+| 🧠 Tool | `sqlseed_list_gemma_models` | List available Gemma 4 models and backend status |
 
 This means you can tell your AI assistant:
 
@@ -993,7 +1019,7 @@ Tests cover all core modules, with path structure mirroring `src/`: `test_core/`
 | `sqlseed[faker]` | + faker>=30.0 | Faker data engine |
 | `sqlseed[mimesis]` | + mimesis>=18.0 | Mimesis data engine (recommended) |
 | `sqlseed[docs]` | + mkdocs-material, mkdocstrings | Documentation build |
-| `sqlseed-ai` | sqlseed, **openai>=1.0** | AI plugin, auto-registered via entry-point |
+| `sqlseed-ai` | sqlseed, **openai>=1.0**, **google-generativeai>=0.8** | AI plugin (Gemma 4 Native Function Calling), auto-registered via entry-point |
 | `mcp-server-sqlseed` | sqlseed, **mcp>=1.0** | MCP server, standalone CLI tool |
 | `mcp-server-sqlseed[ai]` | + sqlseed-ai | MCP server with AI support |
 

{sqlseed-0.1.20 → sqlseed-0.2.0}/README.zh-CN.md

@@ -178,6 +178,14 @@ mypy src/sqlseed/
 
 ## 🚀 快速开始
 
+### 一键体验脚本
+
+```bash
+python scripts/quickstart.py
+```
+
+该脚本会自动创建示例数据库、填充数据并展示结果，适合首次体验。
+
 ### 使用示例数据库体验
 
 想立即体验 sqlseed？构建示例数据库：
@@ -553,22 +561,27 @@ sqlseed ai-suggest app.db --table projects --output projects.yaml
 # 带自纠正的 AI 建议（默认 3 轮修正）
 sqlseed ai-suggest app.db --table projects --output projects.yaml --verify
 
-# 指定模型
-sqlseed ai-suggest app.db --table projects -o projects.yaml --model deepseek/deepseek-chat
+# 指定模型（支持多后端：Google AI Studio、LM Studio、Ollama、OpenAI-compatible）
+sqlseed ai-suggest app.db --table projects -o projects.yaml --model gemma-4-26b-it --backend google_ai_studio
+sqlseed ai-suggest app.db --table projects -o projects.yaml --model gemma-4-31b-it --backend google_ai_studio
+sqlseed ai-suggest app.db --table projects -o projects.yaml --model google/gemma-4-e4b --backend lm_studio
+sqlseed ai-suggest app.db --table projects -o projects.yaml --model gemma-4-4b-it --backend ollama
 ```
 
-**AI 工作流程**：
+**Gemma 4 原生函数调用（GEMMA_TOOLS）**：
 
-```
-1. 提取 Schema 上下文（列信息、索引、样本数据、外键、数据分布）
-2. 构建带 Few-shot 示例的 LLM Prompt
-3. LLM 返回 JSON 格式的列配置建议
-4. AiConfigRefiner 自动验证配置的正确性
-5. 若发现错误，自动向 LLM 发送修正请求
-6. 最多 3 轮自纠正，输出经过验证的 YAML 配置
-```
+sqlseed-ai 支持 Gemma 4 系列模型（2B/4B/26B/31B）通过 GEMMA_TOOLS 协议实现原生函数调用，无需 JSON Mode 模拟。支持的后端：
+
+| 后端 | 说明 | 配置方式 |
+| :--- | :--- | :--- |
+| **Google AI Studio** | 官方 API，推荐 Gemma 4 26B/31B | `--backend google_ai_studio` 或 `SQLSEED_AI_BACKEND=google_ai_studio` |
+| **LM Studio** | 本地推理，适合 Gemma 4 2B/4B | `--backend lm_studio` 或 `SQLSEED_AI_BACKEND=lm_studio` |
+| **Ollama** | 本地推理，适合 Gemma 4 2B/4B/26B | `--backend ollama` 或 `SQLSEED_AI_BACKEND=ollama` |
+| **OpenAI-compatible** | 通用 OpenAI 兼容端点（如 OpenRouter、DeepSeek） | `--backend openai_compat` 或 `SQLSEED_AI_BACKEND=openai_compat` |
 
-> **💡 环境变量**：支持 `SQLSEED_AI_API_KEY`、`SQLSEED_AI_BASE_URL`、`SQLSEED_AI_MODEL`。也支持 `OPENAI_API_KEY` / `OPENAI_BASE_URL` 作为回退。
+> **💡 OpenRouter（免费方案）**：没有付费 API Key 的用户，可以使用 OpenRouter 的免费模型。设置 `SQLSEED_AI_BACKEND=openai_compat`、`SQLSEED_AI_BASE_URL=https://openrouter.ai/api/v1`、`SQLSEED_AI_MODEL=<免费模型名>`。
+
+> **💡 环境变量**：支持 `SQLSEED_AI_API_KEY`、`SQLSEED_AI_BASE_URL`、`SQLSEED_AI_MODEL`、`SQLSEED_AI_BACKEND`。也支持 `OPENAI_API_KEY` / `OPENAI_BASE_URL` 作为回退。
 
 ***
 
@@ -598,6 +611,9 @@ pip install mcp-server-sqlseed[ai]
 | 🔍 Tool | `sqlseed_inspect_schema` | 检查 Schema（列、外键、索引、样本数据、schema_hash） |
 | 🤖 Tool | `sqlseed_generate_yaml` | AI 驱动的 YAML 配置生成（含自纠正） |
 | ⚡ Tool | `sqlseed_execute_fill` | 执行数据生成（支持 YAML 配置字符串，含 `enrich` 选项） |
+| 🤖 Tool | `sqlseed_gemma4_analyze` | Gemma 4 原生函数调用分析 Schema（GEMMA_TOOLS 协议） |
+| 🤖 Tool | `sqlseed_gemma4_agent_fill` | Gemma 4 Agent 模式端到端数据生成（分析→配置→填充） |
+| 📋 Tool | `sqlseed_list_gemma_models` | 列出可用的 Gemma 4 模型及后端支持情况 |
 
 ***
 
@@ -679,6 +695,12 @@ sqlseed ai-suggest app.db -t users -o users.yaml --verify
 sqlseed ai-suggest app.db -t users -o users.yaml --api-key sk-xxx --base-url https://api.openai.com/v1
 sqlseed ai-suggest app.db -t users -o users.yaml --max-retries 0
 sqlseed ai-suggest app.db -t users -o users.yaml --no-cache
+
+# ═══ AI 后端选择 ═══
+sqlseed ai-suggest app.db -t users -o users.yaml --backend google_ai_studio --model gemma-4-26b-it
+sqlseed ai-suggest app.db -t users -o users.yaml --backend ollama --model gemma-4-4b-it
+sqlseed ai-suggest app.db -t users -o users.yaml --backend lm_studio --model google/gemma-4-e4b
+sqlseed ai-suggest app.db -t users -o users.yaml --backend openai_compat --model your-model --base-url https://your-api-endpoint
 ```
 
 ***
@@ -805,7 +827,7 @@ mypy src/sqlseed/                   # 类型检查
 | `sqlseed[faker]` | + faker>=30.0 | Faker 数据引擎 |
 | `sqlseed[mimesis]` | + mimesis>=18.0 | Mimesis 数据引擎（推荐） |
 | `sqlseed[docs]` | + mkdocs-material, mkdocstrings | 文档构建 |
-| `sqlseed-ai` | sqlseed, **openai>=1.0** | AI 插件，通过 entry-point 自动注册 |
+| `sqlseed-ai` | sqlseed, **openai>=1.0**, **google-generativeai>=0.8** | AI 插件，通过 entry-point 自动注册，支持 Gemma 4 GEMMA_TOOLS |
 | `mcp-server-sqlseed` | sqlseed, **mcp>=1.0** | MCP 服务器，独立 CLI 工具 |
 | `mcp-server-sqlseed[ai]` | + sqlseed-ai | MCP 服务器含 AI 支持 |
 

{sqlseed-0.1.20 → sqlseed-0.2.0}/examples/notebooks/02-column-mapping.ipynb

@@ -1353,7 +1353,7 @@
     "    fk_columns = {fk.column for fk in fk_info}\n",
     "    print(\"members 表列映射分析:\")\n",
     "    for col in col_info:\n",
-    "        if col.name.endswith(\"_id\") or col.name.endswith(\"_no\"):\n",
+    "        if col.name.endswith((\"_id\", \"_no\")):\n",
     "            is_fk = col.name in fk_columns\n",
     "            gen_type = \"foreign_key\" if is_fk else \"integer/string\"\n",
     "            print(f\"  {col.name}: {gen_type} (FK={is_fk})\")"

sqlseed-0.2.0/scripts/_create_demo_db.py

@@ -0,0 +1,52 @@
+"""Create demo database with 3 tables for quickstart script."""
+
+from __future__ import annotations
+
+import sqlite3
+import sys
+from pathlib import Path
+
+
+def main() -> None:
+    db_path_str = sys.argv[1] if len(sys.argv) > 1 else "quickstart_demo.db"
+    db_path = Path(db_path_str)
+    if db_path.exists():
+        db_path.unlink()
+
+    conn = sqlite3.connect(str(db_path))
+    conn.executescript("""
+        CREATE TABLE users (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            name TEXT NOT NULL,
+            email TEXT NOT NULL UNIQUE,
+            age INTEGER,
+            city TEXT,
+            created_at DATETIME DEFAULT CURRENT_TIMESTAMP
+        );
+        CREATE TABLE projects (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            name TEXT NOT NULL,
+            description TEXT,
+            status TEXT DEFAULT 'Planning',
+            owner_id INTEGER REFERENCES users(id),
+            budget REAL,
+            deadline DATE,
+            created_at DATETIME DEFAULT CURRENT_TIMESTAMP
+        );
+        CREATE TABLE orders (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            user_id INTEGER REFERENCES users(id),
+            project_id INTEGER REFERENCES projects(id),
+            amount REAL NOT NULL,
+            status TEXT DEFAULT 'pending',
+            order_date DATE,
+            created_at DATETIME DEFAULT CURRENT_TIMESTAMP
+        );
+    """)
+    conn.commit()
+    conn.close()
+    print(f"  Database created: {db_path} (3 tables: users, projects, orders)")
+
+
+if __name__ == "__main__":
+    main()

sqlseed-0.2.0/scripts/quickstart.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python
+"""sqlseed + Gemma 4 one-click setup script (cross-platform).
+
+Usage:
+    python scripts/quickstart.py [--backend lm_studio|ollama|google] [--model MODEL_NAME]
+    python scripts/quickstart.py --skip-install   # Skip pip install, use current env
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+import subprocess
+import sys
+import urllib.request
+from pathlib import Path
+
+PROJECT_ROOT = Path(__file__).resolve().parent.parent
+DB_PATH = PROJECT_ROOT / "quickstart_demo.db"
+
+
+def run(cmd: list[str], check: bool = True) -> subprocess.CompletedProcess[str]:
+    """Run a command and print it."""
+    print(f"  $ {' '.join(str(c) for c in cmd)}")
+    return subprocess.run(cmd, check=check, text=True)
+
+
+def check_lm_studio() -> bool:
+    """Check if LM Studio is running."""
+    try:
+        with urllib.request.urlopen("http://127.0.0.1:1234/v1/models", timeout=3) as r:
+            return r.status == 200
+    except OSError:
+        return False
+
+
+def check_ollama() -> bool:
+    """Check if Ollama is running."""
+    try:
+        with urllib.request.urlopen("http://localhost:11434/api/tags", timeout=3) as r:
+            return r.status == 200
+    except OSError:
+        return False
+
+
+def sqlseed_cmd(python: str) -> list[str]:
+    """Build a sqlseed CLI invocation."""
+    return [python, "-c", "from sqlseed.cli.main import cli; cli()", "--"]
+
+
+def _fill_data(python: str) -> None:
+    """Fill the demo database with sample data using sqlseed CLI."""
+    cmd = sqlseed_cmd(python)
+    for table, count in (("users", 500), ("projects", 200), ("orders", 1000)):
+        run([*cmd, "fill", str(DB_PATH), "-t", table, "-n", str(count)])
+
+    print()
+    print("  Data fill complete!")
+
+
+def _run_ai_analysis_step(args: argparse.Namespace, python: str) -> None:
+    """Run the Gemma 4 AI schema analysis step."""
+    print("[5/5] Gemma 4 AI Schema Analysis...")
+    print(f"  Backend: {args.backend}")
+    print(f"  Model:   {args.model}")
+    print()
+
+    os.environ["SQLSEED_AI_BACKEND"] = args.backend
+    os.environ["SQLSEED_AI_MODEL"] = args.model
+
+    ai_ok = False
+    if args.backend == "lm_studio":
+        if check_lm_studio():
+            ai_ok = True
+        else:
+            print("  Skipped: LM Studio is not running")
+            print("  Please start LM Studio and load a Gemma 4 model")
+            print("  Download: https://lmstudio.ai/")
+    elif args.backend == "ollama":
+        if check_ollama():
+            ai_ok = True
+        else:
+            print("  Skipped: Ollama is not running")
+            print("  Example: ollama pull gemma4:4b")
+    elif args.backend == "google":
+        if os.environ.get("GOOGLE_API_KEY"):
+            ai_ok = True
+        else:
+            print("  Skipped: GOOGLE_API_KEY not set")
+            print("  Example: export GOOGLE_API_KEY=your-key")
+
+    if ai_ok:
+        output_yaml = str(PROJECT_ROOT / "projects_config.yaml")
+        cmd = sqlseed_cmd(python)
+        run([*cmd, "ai-suggest", str(DB_PATH), "-t", "projects", "-o", output_yaml, "--timeout", "300"])
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="GemmaSQLSeed one-click setup")
+    parser.add_argument(
+        "--backend",
+        choices=["lm_studio", "ollama", "google"],
+        default=os.environ.get("SQLSEED_AI_BACKEND", "lm_studio"),
+        help="AI backend (default: lm_studio)",
+    )
+    parser.add_argument(
+        "--model",
+        default=os.environ.get("SQLSEED_AI_MODEL", "google/gemma-4-e4b"),
+        help="Model name (default: google/gemma-4-e4b)",
+    )
+    parser.add_argument(
+        "--skip-install",
+        action="store_true",
+        help="Skip dependency installation, use current Python environment",
+    )
+    args = parser.parse_args()
+
+    print("=" * 50)
+    print("  GemmaSQLSeed Quick Start")
+    print("=" * 50)
+    print()
+
+    # Determine which python to use
+    if args.skip_install:
+        # Use current Python (already has sqlseed installed)
+        python = sys.executable
+        print("[1/5] Using current Python environment (skip-install)")
+        print("[2/5] Skipping installation (--skip-install)")
+    else:
+        # Create venv and install
+        venv_path = PROJECT_ROOT / ".venv"
+        if not venv_path.exists():
+            print("[1/5] Creating virtual environment...")
+            run([sys.executable, "-m", "venv", str(venv_path)])
+        else:
+            print("[1/5] Virtual environment exists, skipping")
+
+        if sys.platform == "win32":
+            python = str(venv_path / "Scripts" / "python.exe")
+        else:
+            python = str(venv_path / "bin" / "python")
+
+        print("[2/5] Installing dependencies (may take a few minutes on first run)...")
+        run([python, "-m", "pip", "install", "-q", "-e", f"{PROJECT_ROOT}[dev,all]"])
+        run([python, "-m", "pip", "install", "-q", "-e", str(PROJECT_ROOT / "plugins" / "sqlseed-ai")])
+        run([python, "-m", "pip", "install", "-q", "-e", str(PROJECT_ROOT / "plugins" / "mcp-server-sqlseed")])
+
+    # ── Step 3: Create test database ─────────────────────────────────
+    print("[3/5] Creating test database...")
+    if DB_PATH.exists():
+        DB_PATH.unlink()
+
+    create_db_script = Path(__file__).parent / "_create_demo_db.py"
+    run([python, str(create_db_script), str(DB_PATH)])
+
+    # ── Step 4: Fill data ────────────────────────────────────────────
+    print("[4/5] Filling data (zero-config)...")
+    _fill_data(python)
+
+    # ── Step 5: Gemma 4 AI analysis ──────────────────────────────────
+    _run_ai_analysis_step(args, python)
+
+    # ── Done ─────────────────────────────────────────────────────────
+    print()
+    print("=" * 50)
+    print("  Setup Complete!")
+    print("=" * 50)
+    print()
+    print(f"  Database:    {DB_PATH}")
+    cli_call = 'python -c "from sqlseed.cli.main import cli; cli()" --'
+    print(f"  Preview:     {cli_call} preview {DB_PATH} -t users -n 5")
+    print(f"  Inspect:     {cli_call} inspect {DB_PATH} --show-mapping")
+    print(f"  AI Suggest:  {cli_call} ai-suggest {DB_PATH} -t users -o config.yaml")
+    print("  MCP Server:  mcp-server-sqlseed")
+    print()
+
+
+if __name__ == "__main__":
+    main()

{sqlseed-0.1.20 → sqlseed-0.2.0}/src/sqlseed/cli/main.py

@@ -475,15 +475,19 @@ def ai_suggest(
     ai_config = AIConfig.from_env().apply_overrides(api_key=api_key, base_url=base_url, model=model)
     ai_config.timeout = timeout
 
-    if not ai_config.api_key:
+    if not ai_config.resolve_api_key():
         click.echo(
-            "Error: AI API key not configured. Set SQLSEED_AI_API_KEY or OPENAI_API_KEY, or use --api-key.",
+            "Error: AI API key not configured. "
+            "Set SQLSEED_AI_API_KEY or OPENAI_API_KEY. "
+            "For Google AI Studio, set GOOGLE_API_KEY. "
+            "For LM Studio/Ollama, set SQLSEED_AI_BACKEND=lm_studio or ollama.",
             err=True,
         )
         raise SystemExit(1)
 
     resolved_model = ai_config.resolve_model()
-    click.echo(f"Using AI model: {resolved_model} (via OpenRouter)")
+    backend_name = ai_config.backend.value.replace("_", " ").title()
+    click.echo(f"Using AI model: {resolved_model} (via {backend_name})")
 
     analyzer = SchemaAnalyzer(config=ai_config)
     total_timeout = timeout * 2
@@ -491,13 +495,15 @@ def ai_suggest(
     old_handler: Any = None
     if hasattr(signal, "SIGALRM"):
         old_handler = signal.signal(signal.SIGALRM, lambda _s, _f: _sigalrm_handler(total_timeout))
-        signal.alarm(int(total_timeout))
+        _alarm_fn = vars(signal)["alarm"]
+        _alarm_fn(int(total_timeout))
 
     try:
         result = _run_ai_analysis(analyzer, db_path, table, verify, max_retries, no_cache)
     finally:
         if hasattr(signal, "SIGALRM"):
-            signal.alarm(0)
+            _alarm_fn = vars(signal)["alarm"]
+            _alarm_fn(0)
             if old_handler is not None:
                 signal.signal(signal.SIGALRM, old_handler)