feat: add structure template generation for LLM prompts

[Copilot]

Users need to specify expected response formats in LLM prompts without including example data, which wastes tokens. The request was for templates like {"name":"name of the person","age":"age of the person"} in TOON format.

Changes

New API functions:

• generate_structure(schema, options) - Generates TOON structure templates from dict schemas
• generate_structure_from_pydantic(model_class, options, include_descriptions) - Generates templates from Pydantic models

Implementation:

• toon/structure_generator.py - Core template generation logic with support for nested objects, arrays, and custom delimiters
• Exports added to toon/__init__.py

Tests & Documentation:

• 16 new tests covering edge cases, nested structures, arrays, and Pydantic integration
• Example file with real-world use cases (examples/structure_template_usage.py)
• API reference and usage guide in README

Usage

from toon import generate_structure

# Dict-based schema
schema = {
    "name": "name of the person",
    "age": "age of the person",
    "occupation": "job description"
}

structure = generate_structure(schema)
# Output:
# name: <name of the person>
# age: <age of the person>
# occupation: <job description>

# Use in LLM prompt
prompt = f"Extract data in this format:\n{structure}"

# Pydantic model support
from pydantic import BaseModel, Field

class Person(BaseModel):
    name: str = Field(description="full name")
    age: int = Field(description="age in years")

structure = generate_structure_from_pydantic(Person)
# Automatically uses field descriptions

Arrays generate tabular templates:

schema = {"users": [{"id": "user id", "name": "user name"}]}
# Output:
# users[N]{id,name}:
#   <user id>,<user name>
#   ...

Closes issue regarding response structure templates without examples.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• openaipublic.blob.core.windows.net
  • Triggering command: python -m pytest tests/ -v (dns block)
  • Triggering command: python -m pytest tests/ -v --tb=short (dns block)
  • Triggering command: python -m pytest tests/ -q --tb=no (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>response structure for prompt response</issue_title>
<issue_description>Is your feature request related to a problem? Please describe.
response structure for prompt like response struct:{"name":"name of the person","age":"age of the person","occupation":"job description of the person"} like this without mentioning examples so that we can add it to the prompt
Describe the solution you'd like
universal response structure for the prompt in toon instead of json without mentioning examples

Describe alternatives you've considered
no.

Additional context
@FrancescoSaverioZuppichini
@lurenss

</issue_description>

Comments on the Issue (you are @copilot in this section)

@VinciGit00 Hi @Pavansomisetty21 thank you for the feedback,

we will take care about that.

• Fixes response structure for prompt response #8

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[github-actions]

🎉 This PR is included in version 1.5.0 🎉

The release is available on:

• v1.5.0
• GitHub release

Your semantic-release bot 📦🚀