README.md update.

[dbreunig]

Updated readme to more substantive walkthrough

[greptile-apps]

Greptile Overview

Greptile Summary

This PR significantly improves the README with a comprehensive walkthrough that guides users through creating a complete project (cms-kit), adding multiple programs, and understanding the project structure.

Key changes:

• Expanded Quick Start section with detailed step-by-step tutorial using a realistic CMS example
• Added sections on project exploration, model configuration, and key features
• Supporting code changes add is_reasoning_model() function to detect OpenAI reasoning models (o1, o3, gpt-5 series) and set appropriate max_tokens limits
• Increased default max_tokens from 4096 to 8192 for standard models
• Added .pytest_cache/ to gitignore

Critical issue:
The documentation uses openai/gpt-5-mini throughout all examples, but GPT-5 does not exist yet. This will cause confusion and errors for users following the tutorial. The examples should use actual available models like openai/gpt-4o-mini or openai/gpt-4o.

Confidence Score: 2/5

• This PR has critical documentation issues that will break user workflows
• While the code changes are solid and well-tested, the README uses a non-existent model (gpt-5-mini) throughout all examples. Users following this documentation will encounter errors when trying to use the specified model. This significantly impacts the usability of the updated documentation.
• README.md requires immediate attention - all model references need to be updated to use actual available OpenAI models

Important Files Changed

File Analysis

Filename	Score	Overview
.gitignore	5/5	Added .pytest_cache/ to gitignore - standard practice for Python projects
README.md	2/5	Comprehensive documentation rewrite with walkthrough, but uses non-existent gpt-5-mini model throughout examples
src/dspy_cli/utils/model_utils.py	4/5	Added is_reasoning_model() function to detect reasoning models and increased default max_tokens from 4096 to 8192
tests/test_commands_smoke.py	4/5	Added comprehensive tests for reasoning model detection and max_tokens configuration

Sequence Diagram

sequenceDiagram
    participant User
    participant CLI as dspy-cli
    participant Project as Project Files
    participant Server as HTTP Server
    participant LLM as Language Model

    User->>CLI: dspy-cli new cms-kit
    CLI->>User: Interactive setup prompts
    User->>CLI: Provide program name, signature, model
    CLI->>Project: Create project structure
    CLI->>Project: Generate signatures/
    CLI->>Project: Generate modules/
    CLI->>Project: Create dspy.config.yaml
    CLI->>Project: Create .env with API keys

    User->>CLI: cd cms-kit && dspy-cli serve
    CLI->>Project: Scan modules/ directory
    Project-->>CLI: Return discovered modules
    CLI->>Server: Start HTTP server on :8000
    Server-->>User: Web UI available

    User->>Server: POST /SummarizerPredict
    Server->>Project: Load module & signature
    Project->>LLM: Send prompt with blog_post
    LLM-->>Project: Return summary
    Project-->>Server: Return response
    Server-->>User: JSON response

    User->>CLI: dspy-cli generate scaffold tagger
    CLI->>Project: Create tagger signature
    CLI->>Project: Create tagger module
    CLI->>Server: Hot reload detected
    Server->>Project: Rescan modules/
    Server-->>User: New /TaggerPredict endpoint

Loading

[greptile-apps]

_{4 files reviewed, 3 comments}

_{Edit Code Review Agent Settings | Greptile}

[greptile-apps]

syntax: openai/gpt-5-mini does not exist yet. Replace with an actual OpenAI model like openai/gpt-4o-mini

Suggested change

	Model [openai/gpt-5-mini]: openai/gpt-5-mini
	Model [openai/gpt-4o-mini]: openai/gpt-4o-mini

Prompt To Fix With AI

This is a comment left during a code review.
Path: README.md
Line: 60:60

Comment:
**syntax:** `openai/gpt-5-mini` does not exist yet. Replace with an actual OpenAI model like `openai/gpt-4o-mini`

```suggestion
Model [openai/gpt-4o-mini]: openai/gpt-4o-mini
```

How can I resolve this? If you propose a fix, please make it concise.

[greptile-apps]

syntax: openai:gpt-5-mini references a non-existent model. Update to use openai/gpt-4o-mini or another actual model

Suggested change

	default: openai:gpt-5-mini
	# Model registry - define all available models here
	registry:
	openai:gpt-5-mini:
	model: openai/gpt-5-mini
	model_type: chat
	max_tokens: 16000
	temperature: 1.0
	env: OPENAI_API_KEY
	# The default model to use if no per-program override is specified
	default: openai:gpt-4o-mini
	# Model registry - define all available models here
	registry:
	openai:gpt-4o-mini:
	model: openai/gpt-4o-mini
	model_type: chat
	max_tokens: 16000
	temperature: 1.0
	env: OPENAI_API_KEY

Prompt To Fix With AI

This is a comment left during a code review.
Path: README.md
Line: 125:134

Comment:
**syntax:** `openai:gpt-5-mini` references a non-existent model. Update to use `openai/gpt-4o-mini` or another actual model

```suggestion
  # The default model to use if no per-program override is specified
  default: openai:gpt-4o-mini

  # Model registry - define all available models here
  registry:
    openai:gpt-4o-mini:
      model: openai/gpt-4o-mini
      model_type: chat
      max_tokens: 16000
      temperature: 1.0
      env: OPENAI_API_KEY
```

How can I resolve this? If you propose a fix, please make it concise.

[greptile-apps]

syntax: Reference to fictional model in documentation text. Replace with actual model name

Prompt To Fix With AI

This is a comment left during a code review.
Path: README.md
Line: 137:137

Comment:
**syntax:** Reference to fictional model in documentation text. Replace with actual model name

How can I resolve this? If you propose a fix, please make it concise.