t-prompts
Provenance-preserving prompts for LLMs using Python 3.14's template strings
What is t-prompts?
t-prompts turns Python 3.14+ t-strings into navigable trees that preserve full provenance information (expression text, conversions, format specs). Perfect for building, composing, and auditing LLM prompts.
Unlike f-strings which immediately evaluate to strings, t-prompts keeps the structure intact so you can:
- Trace exactly which variable produced which part of your prompt
- Navigate nested prompt components programmatically
- Compose complex prompts from smaller, reusable pieces
- Audit with complete provenance for compliance and debugging
- Validate types at prompt creation (no accidental
str(obj)surprises)
Requirements: Python 3.14+
Quick Example
from t_prompts import prompt
# Create a structured prompt
instructions = "Always answer politely."
p = prompt(t"Obey {instructions:inst}")
# Renders like an f-string
print(str(p)) # "Obey Always answer politely."
# But preserves full provenance
node = p['inst']
print(node.expression) # "instructions" (original variable name)
print(node.value) # "Always answer politely."
This enables riching tooling:
Targeted Use Cases
- Prompt Debugging: "What exactly did this tangle of code render to?"
- Prompt Optimization (Performance): "What wording / content best achieves my goal?"
- Prompt Optimization (Size): "How do I get the same result with fewer words?"
- Prompt Compacting: "LLM tells me to keep it short, now what do I do?"
Caveats
While this library targets the creation of structured multi-modal prompts, despite the name, there is nothing in particular tying this library to LLMs / Generative models. (It is more "t" than "prompts") To use it for an actual LLM call, you would need to convert the IR into a model specific form (though for text, it could be as simple as str(prompt))
Documentation
📚 Full documentation: https://habemus-papadum.github.io/t-prompts/
Installation
pip install t-prompts
Or with uv:
uv add t-prompts
Development
This project uses UV and PNPM for dependency management.
# Onetime Setup (per dev machine)
curl -LsSf https://astral.sh/uv/install.sh | sh # Other options exist!
curl -fsSL https://get.pnpm.io/install.sh | sh - # Other options exist!
./scripts/setup-visual-tests.sh
# Repo setup (per clone)
./scripts/setup.sh
# Lint and format
uv run ruff check .
uv run ruff format .
# Build documentation
uv run mkdocs serve
See Developer Setup for detailed instructions.
License
MIT License - see LICENSE file for details.
Metadata
Release files for t-prompts 0.18.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| t_prompts-0.18.1.tar.gz | 793.1 kB | Without provenance | Details for t_prompts-0.18.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| t_prompts-0.18.1-py3-none-any.whl | Python 3 | none | any | Details for t_prompts-0.18.1-py3-none-any.whl |
Total release size: 2.0 MB
Release files / t_prompts-0.18.1.tar.gz
| Download URL | t_prompts-0.18.1.tar.gz |
|---|---|
| Size | 793.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
945c22cdbeeb472aec267a344800024a59d1a6f595b91e8e76e946a5d8f49631
|
|
BLAKE2b-256 checksum How to use checksums |
b167ef6768f4c8992753ecbb91e8487377201b0c88a206cf46d43213f3279478
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-httpx/0.28.1
|
Release files / t_prompts-0.18.1-py3-none-any.whl
| Download URL | t_prompts-0.18.1-py3-none-any.whl |
|---|---|
| Size | 1.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f80bad7e5eaedc7cd839af8c049bc22dec887194467f1cb8d1774a4594a8b1f4
|
|
BLAKE2b-256 checksum How to use checksums |
33b0fe11a21a5a374a7053ca83d2eb4cdaa36dcf2442fc85431238fdb1d2cc77
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
python-httpx/0.28.1
|
Security for t-prompts 0.18.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.