bump to 0.1.0 release with improvement in models selction

Author: Shashikant86

CHANGELOG.md

@@ -8,8 +8,99 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Added
+- Planned:
+  - **Plan / Code modes** in interactive CLI (explicit “planning” vs “coding” flows for complex tasks).
+  - First‑class support for **open‑source models via third‑party providers** (e.g. OpenRouter, Groq and similar gateways), alongside existing Ollama + cloud integrations.
+
+### Changed
+- Intent routing to further reduce/eliminate **duplicate code generation**, especially with large open‑source models and remote providers.
+
+### Fixed
 - TBC
 
+---
+
+## [0.1.0] - 2025-11-26
+
+### Overview
+- **First public release** of DSPy Code: an AI-powered, interactive development and optimization assistant for DSPy (think "Claude Code for DSPy").
+
+### Added
+- **Interactive CLI & Workflows**
+  - Rich TUI with animated thinking indicators, status panels, and history-aware prompts.
+  - Fully conversational flow: describe what you want in natural language, get DSPy code, ask follow‑ups.
+  - Two core workflows:
+    - **Development**: `/init` → describe task → generate → `/validate` → `/run` → iterate.
+    - **Optimization**: `/data` → `/optimize` → `/eval` → `/export`.
+- **Model Connection & Providers**
+  - Support for local **Ollama** models.
+  - Cloud providers: **OpenAI**, **Anthropic (Claude)**, **Google Gemini**.
+  - New interactive `/model` command:
+    - Auto-detect and list Ollama models, pick by number.
+    - Cloud flow to pick provider, then type model name (e.g. `gpt-5-nano`, `claude-sonnet-4.5`, `gemini-2.5-flash`).
+  - Direct `/connect <provider> <model>` command for advanced users.
+  - `/models`, `/status`, `/disconnect` for model management.
+- **LLM Integration & SDK Support**
+  - OpenAI integration compatible with `openai>=2.x` chat completions API.
+  - Anthropic integration via the current `anthropic` Python SDK.
+  - Gemini integration via the official `google-genai` SDK, with fallback to `google-generativeai` when present.
+  - Local Ollama integration with configurable HTTP timeouts for large models (`OLLAMA_HTTP_TIMEOUT`, `OLLAMA_TEST_TIMEOUT`).
+  - Optional extras in `pyproject.toml`:
+    - `dspy-code[openai]`, `dspy-code[anthropic]`, `dspy-code[gemini]`, `dspy-code[llm-all]`.
+- **DSPy-Aware Code Generation**
+  - Natural language → DSPy **Signatures**, **Modules**, and full **Programs**.
+  - Support for major DSPy patterns: predictors, ChainOfThought, ReAct, RAG, etc.
+  - Templates and examples for:
+    - RAG systems
+    - Question answering
+    - Classification (e.g. sentiment analyzer)
+    - Optimization/evaluation workflows
+- **Validation & Execution**
+  - `/validate` to check generated code against DSPy best practices and structure.
+  - `/run` and `/test` to execute and test generated programs within a sandboxed engine.
+  - Validation support for signatures, modules, predictors, adapters, metrics, and anti‑patterns.
+- **GEPA Optimization**
+  - End‑to‑end optimization workflows:
+    - `/optimize` for one‑shot optimization scripts.
+    - `/optimize-start`, `/optimize-status`, `/optimize-resume`, `/optimize-cancel` for long‑running GEPA jobs.
+  - Integration with evaluation metrics (Accuracy, F1, ROUGE, BLEU, etc.).
+  - Documentation and warnings about cloud costs and recommended hardware (32 GB RAM for heavy local optimization).
+- **MCP (Model Context Protocol) Integration**
+  - Built‑in MCP client with commands:
+    - `/mcp-connect`, `/mcp-disconnect`, `/mcp-servers`, `/mcp-tools`, `/mcp-call`, `/mcp-resources`, `/mcp-read`, `/mcp-prompts`, `/mcp-prompt`.
+  - Enables connecting DSPy Code to external tools and data sources.
+- **Project & Session Management**
+  - `/init` and `/project` for initializing and inspecting DSPy projects.
+  - Codebase indexing and RAG support for answering questions about your own code.
+  - Session management commands: `/sessions`, `/session`, `/history`, `/clear`, `/save-data`, export/import.
+  - Export/import of sessions and packages for deployment via `/export` and `/import`.
+- **Documentation & Examples**
+  - Full docs site (MkDocs Material) with:
+    - Getting Started (installation, quick start, first program, understanding DSPy Code).
+    - Guides (model connection, interactive mode, natural language commands, optimization, project management, validation, slash commands).
+    - Tutorials (RAG system, question answering, sentiment analyzer, GEPA optimization).
+    - Reference (commands, configuration, templates, troubleshooting, FAQ, security).
+  - Homepage and README aligned around DSPy Code as:
+    - **Development assistant** (build DSPy apps quickly).
+    - **Optimization engine** (real GEPA).
+    - **Learning environment** for DSPy concepts.
 
 ### Changed
-- First release
+- Default Ollama generation timeout increased to 120 seconds to better support large models.
+- Examples across README and docs updated to use modern models (e.g. `gpt-5-nano`, `claude-sonnet-4.5`, `gemini-2.5-flash`, `gpt-oss:120b`) and to recommend `/model` as the primary way to connect.
+- Quick Start and model‑connection docs now make model connection mandatory and show clear virtual‑env + provider‑SDK installation flows using `dspy-code[...]` extras and `uv`/`pip`.
+- Interactive UI improved with modern Rich versions and a `DSPY_CODE_SIMPLE_UI` mode for environments with limited emoji/spinner support.
+- Natural language intent routing in interactive mode refined to:
+  - Prefer natural‑language answers for questions.
+  - Avoid double code generation and incorrect `/explain` follow‑ups.
+- MkDocs navigation configuration tuned (tabs, sections) to keep the left nav stable and highlight the active page correctly.
+
+### Fixed
+- OpenAI deprecation issues (`APIRemovedInV1`) by migrating from `ChatCompletion` to the new client API, and removing unsupported `max_tokens`/`temperature` parameters for models like `gpt-5-nano`.
+- Interactive mode errors:
+  - `name 'explanations' is not defined` during `/explain`.
+  - Syntax errors in `nl_command_router` debug logging.
+- Ollama timeout handling for large models, with clearer error messages on connection/generation failures.
+- Documentation glitches:
+  - Stray `\n` in callouts.
+  - Navigation behavior that caused pages to disappear or not highlight correctly.

README.md

@@ -312,8 +312,8 @@ dspy-code
 # Initialize your project (creates config and scans your environment)
 /init
 
-# Connect to a model (example with Ollama)
-/connect ollama llama3.1:8b
+# Connect to a model (interactive selector)
+/model
 
 # Generate your first program using natural language
 Create a sentiment analyzer that takes text and outputs positive or negative
@@ -339,7 +339,8 @@ DSPy Code is **interactive-only** - all commands are slash commands. Here are th
 - `/exit` - Exit the interactive session
 
 ### 🤖 Model Connection
-- `/connect <provider> <model>` - Connect to LLM (ollama, openai, anthropic, gemini)
+- `/model` - Interactive model selection (local via Ollama or cloud providers)
+- `/connect <provider> <model>` - Directly connect to LLM when you know the model name
 - `/disconnect` - Disconnect current model
 - `/models` - List available models
 - `/status` - Show current connection status
@@ -411,7 +412,7 @@ DSPy Code is **interactive-only** - all commands are slash commands. Here are th
 ```bash
 dspy-code
 /init
-/connect ollama llama3.1:8b
+/model
 Create a RAG system for document Q&A
 /save rag_system.py
 /validate
@@ -481,20 +482,25 @@ dspy-code
 Connect to any LLM provider:
 
 ```bash
+# Recommended: interactive model selector
+/model
+
+# Or connect directly if you know the model name:
+
 # Ollama (local, free)
-/connect ollama llama3.1:8b
+/connect ollama gpt-oss:120b
 
 # OpenAI (example small model)
 /connect openai gpt-5-nano
 
 # Anthropic (paid key required)
-/connect anthropic claude-3-5-sonnet-20241022
+/connect anthropic claude-sonnet-4.5
 
 # Google Gemini (example model)
 /connect gemini gemini-2.5-flash
 ```
 
-> 💡 **Tip:** These are just starting points. Check your provider docs for the **latest models** (for example gpt-4o / gpt‑5 family, Gemini 2.5, latest Claude Sonnet/Opus) and plug them into `/connect`.
+> 💡 **Tip:** These are just starting points. Check your provider docs for the **latest models** (for example gpt-4o / gpt‑5 family, Gemini 2.5, latest Claude Sonnet/Opus) and either pick them via `/model` or plug them into `/connect`.
 
 ## 🧬 GEPA Optimization
 
@@ -555,8 +561,11 @@ pip install -e .
 ### With uv (Faster)
 
 ```bash
-# Always get the latest version
+# Always get the latest version into your current environment
 uv pip install --upgrade dspy-code
+
+# Or add it to your project's pyproject.toml in one step
+uv add dspy-code
 ```
 
 ## 🏗️ Architecture

docs/getting-started/installation.md

@@ -67,6 +67,9 @@ source .venv/bin/activate.fish
     ```bash
     # If you use uv, you can install dspy-code like this
     uv pip install --upgrade dspy-code
+
+    # Or add it to your project dependencies (pyproject.toml) in one step
+    uv add dspy-code
     ```
 
 That's it! DSPy Code is now installed in your project.

docs/getting-started/quick-start.md

@@ -92,9 +92,22 @@ You'll see a beautiful welcome screen with the DSPy version and helpful tips.
 
 Before you do anything else in the CLI, you **must connect to a model**. DSPy Code relies on an LLM for code generation and understanding.
 
+**Easiest (recommended): use the interactive selector**
+
+```bash
+/model
+```
+
+This lets you:
+
+- Choose **Ollama** local models from a numbered list
+- Choose a **cloud provider** (OpenAI, Anthropic, Gemini) and then type a model name (for example `gpt-5-nano`, `claude-sonnet-4.5`, `gemini-2.5-flash`)
+
+**Direct connect (advanced users):**
+
 ```bash
 # Ollama (local, free)
-/connect ollama llama3.1:8b
+/connect ollama gpt-oss:120b
 
 # Or OpenAI (example small model)
 /connect openai gpt-5-nano

docs/getting-started/understanding.md

@@ -43,7 +43,7 @@ All commands are slash commands in interactive mode:
 ```
 dspy-code
   → /init
-  → /connect ollama llama3.1:8b
+  → /model
   → Create a sentiment analyzer
   → /save sentiment.py
   → /validate

docs/guide/interactive-mode.md

@@ -93,7 +93,7 @@ Use `/` prefix for specific commands:
 ```
 /help
 /init
-/connect ollama llama3.1:8b
+/model
 /save my_module.py
 /validate
 /run
@@ -223,7 +223,8 @@ Clear conversation history:
 **2. Connect model:**
 
 ```
-→ /connect ollama llama3.1:8b
+→ /model
+  [Pick Ollama vs cloud, then choose a model]
   ✓ Connected!
 ```
 

docs/guide/model-connection.md

@@ -17,10 +17,22 @@ DSPy Code supports both **local** and **cloud** LLMs:
 
 ## Quick Connect
 
-### Ollama (Local - Recommended for Beginners)
+### Easiest: Interactive Model Selector
 
+```bash
+/model
 ```
-/connect ollama llama3.1:8b
+
+This walks you through:
+
+- Picking **Ollama** (local) vs **cloud** providers
+- For Ollama: selecting from detected models (for example `gpt-oss:120b`, `llama3.2`) by number
+- For cloud: picking **OpenAI**, **Anthropic**, or **Gemini** and then typing a model name (for example `gpt-5-nano`, `claude-sonnet-4.5`, `gemini-2.5-flash`)
+
+### Ollama (Local - Recommended for Beginners)
+
+```bash
+/connect ollama gpt-oss:120b
 ```
 
 **Advantages:**
@@ -31,7 +43,7 @@ DSPy Code supports both **local** and **cloud** LLMs:
 
 **Requirements:**
 - Ollama installed
-- Model downloaded: `ollama pull llama3.1:8b`
+- Model downloaded: `ollama pull gpt-oss:120b`
 
 ### OpenAI (Cloud)
 

docs/guide/natural-language-commands.md

@@ -4,27 +4,39 @@ DSPy Code supports **natural language for all commands**! You don't need to reme
 
 ## 🎯 How It Works
 
-Instead of typing `/connect ollama llama3.1:8b`, you can simply say:
+Instead of remembering exact slash commands, you can either:
+
+- Use the **interactive selector**: `/model`
+- Or just describe what you want in natural language.
+
+For example, instead of typing `/connect ollama gpt-oss:120b`, you can say:
 
 ```
-connect to ollama llama3.1:8b
+connect to ollama gpt-oss:120b
 ```
 
-DSPy Code automatically understands your intent and routes it to the appropriate command.
+DSPy Code automatically understands your intent and routes it to the appropriate command (for example, `/model` or `/connect`).
 
 ---
 
 ## 📋 Supported Natural Language Commands
 
 ### Connection Commands
 
-**Instead of:** `/connect ollama llama3.1:8b`  
+**Instead of:** `/model` (interactive selector)  
+**You can say:**
+- "help me pick a model"
+- "connect a model for me"
+- "set up a model"
+- "select a model to use"
+
+**Instead of:** `/connect ollama gpt-oss:120b`  
 **You can say:**
-- "connect to ollama llama3.1:8b"
-- "use model ollama llama3.1:8b"
-- "switch to ollama llama3.1:8b"
-- "set up model ollama llama3.1:8b"
-- "configure model ollama llama3.1:8b"
+- "connect to ollama gpt-oss:120b"
+- "use model ollama gpt-oss:120b"
+- "switch to ollama gpt-oss:120b"
+- "set up model ollama gpt-oss:120b"
+- "configure model ollama gpt-oss:120b"
 
 **Instead of:** `/disconnect`  
 **You can say:**

docs/guide/slash-commands.md

@@ -189,43 +189,53 @@ Browse DSPy templates and patterns.
 
 ## Model Connection Commands
 
-### /connect
+### /model
 
-Connect to a language model.
+Interactively select and connect to a model.
 
-**Ollama (Local):**
+**Basic usage:**
 
+```bash
+/model
 ```
-/connect ollama llama3.1:8b
-```
 
+You will be prompted to choose:
+
+- Local models via **Ollama** (auto-detected from your Ollama installation)
+- Cloud providers: **OpenAI**, **Anthropic**, **Gemini** (you then type the model name, e.g. `gpt-5-nano`, `claude-sonnet-4.5`, `gemini-2.5-flash`)
+
+**Shortcuts:**
+
+```bash
+/model ollama   # Only show local Ollama models and pick one by number
+/model cloud    # Pick a cloud provider, then type the model name
 ```
+
+### /connect
+
+Directly connect to a specific model if you already know the name.
+
+**Ollama (Local):**
+
+```bash
 /connect ollama gpt-oss:120b
 ```
 
 **OpenAI:**
 
-```
-/connect openai gpt-4
-```
-
-```
+```bash
 /connect openai gpt-5-nano
 ```
 
 **Anthropic Claude:**
 
-```
+```bash
 /connect anthropic claude-sonnet-4.5
 ```
 
-```
-/connect anthropic claude-opus-4.5
-```
-
 **Google Gemini:**
 
-```
+```bash
 /connect gemini gemini-2.5-flash
 ```