Skip to main content

Deterministic cost-bounded execution for multi-step LLM workflows

Project description

Execution Constraint Engine (ECE)

Runtime decision layer for enforcing cost constraints in multi-step LLM workflows.

ECE evaluates projected cost before each step and returns a BLOCK decision when execution would exceed a defined budget.


Install

pip install veloryn

Minimal usage

from veloryn import execute

def run_task():
    return {
        "output": "model response",
        "usage": {
            "input_tokens": 120,
            "output_tokens": 300,
        },
    }

execute(
    task_id="demo",
    run_task=run_task,
    input_data="Analyze input",
    model="gpt-4o",
    max_cost=0.05,
)

run_task must return usage (input/output tokens).
ECE does not infer cost automatically.


Full documentation and examples:
https://github.com/veloryn-intel/execution-constraint-engine

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

veloryn-0.1.2.tar.gz (7.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

veloryn-0.1.2-py3-none-any.whl (9.5 kB view details)

Uploaded Python 3

File details

Details for the file veloryn-0.1.2.tar.gz.

File metadata

  • Download URL: veloryn-0.1.2.tar.gz
  • Upload date:
  • Size: 7.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for veloryn-0.1.2.tar.gz
Algorithm Hash digest
SHA256 d397ae0508194ae9cbfa1c939d437e0c9df362e40c64c1133c2917fa22756146
MD5 184fcea4b7ea457f2b415a1938e14f5e
BLAKE2b-256 6f2ad98c541fc4c5e57906a976541b3e9d681eb7f84c4ac9394fd297141127d9

See more details on using hashes here.

File details

Details for the file veloryn-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: veloryn-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 9.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for veloryn-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 83ad1c04b7128593d14aa30ff337ea21cb6b19beaffcc49174499e3b5b5b42f7
MD5 a0e6e19d02a17e9b1d28d8f86942b022
BLAKE2b-256 6e5c71cb6dfee671a755c40b7702178246c2af2daceeeee92eebba487967f85e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page