Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

PromptCadence

A plan-approved, tier-routed agent loop over LoadCoach in which every step is proposed in a plan, the plan is approved against governance policy and remaining budget before any step executes, and every turn that does execute is fully reconstructable afterwards — which model ran it, on which tier, on what data, at what cost, under whose approval.

Status: Phase 3 (LoadCoach client, bypass loop, events and recovery), unreleased. A bypassed trajectory executes end to end: promptcadence run "…" --bypass-planning --follow queues it, the worker claims it under a lease, mints its ExecutionIntent, runs each turn through LoadCoach's /generate, records the turn with its provenance and every deviation, streams the events over SSE, and survives a kill -9 mid-turn with no duplicated turn and no orphaned LoadCoach job. Planning, tools, budget enforcement and egress policy arrive in the phases that follow; a planned trajectory is claimed and failed with that cause rather than queued forever. See the development plan for what each phase adds.

Part of the Local AI Suite. Reaches a model only through LoadCoach's HTTP API — it never imports a model provider directly (ADR-0045 in the suite's shared documentation).

Install

pip install promptcadence
promptcadence serve

Starts on 127.0.0.1:8768 with zero configuration. Health reports the loadcoach component degraded (not unavailable) when no LoadCoach is reachable — PromptCadence requires LoadCoach for execution, never for startup. See docs/apps/promptcadence/spec.md §12 for the full configuration surface and PROMPTCADENCE_* environment variables.

Quickstart

pip install promptcadence
promptcadence serve            # starts the API on 127.0.0.1:8768
promptcadence health --json    # same health data the API reports, from the CLI
promptcadence run "summarize the files in ./notes" --bypass-planning --follow
promptcadence trajectory list
promptcadence --help

A note on LoadCoach versions: PromptCadence never reads an undeclared finish as success (spec §11 contract 6), and it reads the provider's declared reason from output.finish_reason, which LoadCoach renders since its commit 846348b. Against an older LoadCoach (1.0.0, 01170a7), which recorded the reason but rendered it nowhere, a free-text tier halts on its first turn with that cause on the row, and only a tier whose task profile validates a JSON Schema completes.

Documentation

Read this For
docs/apps/promptcadence/spec.md Purpose, scope, non-goals, public contracts, configuration, acceptance criteria
docs/apps/promptcadence/lifecycle.md The trajectory state machine, deviation categories and estimator
docs/apps/promptcadence/development-plan.md The phased build plan: goals, work, tests, acceptance criteria per phase

Development

python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pre-commit install
pytest -m "not live and not performance"

See SECURITY.md for how to report a vulnerability.

License

Apache-2.0 — see LICENSE.

Download files

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

Source Distribution

promptcadence-0.9.0b0.tar.gz (530.6 kB view details)

Uploaded Source

Built Distribution

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

promptcadence-0.9.0b0-py3-none-any.whl (335.5 kB view details)

Uploaded Python 3

File details

Details for the file promptcadence-0.9.0b0.tar.gz.

File metadata

  • Download URL: promptcadence-0.9.0b0.tar.gz
  • Upload date:
  • Size: 530.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for promptcadence-0.9.0b0.tar.gz
Algorithm Hash digest
SHA256 cb2ca5776db8f739f03cd31b0052b07c3b0bb19ee8c6df5e32cfcd2ead796ce1
MD5 f4be15b06471b07029aa5c36a9a6ba38
BLAKE2b-256 d694a458011257a63b4ea23483aad4adbadbefda5a87c33de25df0fcf56b8f46

See more details on using hashes here.

Provenance

The following attestation bundles were made for promptcadence-0.9.0b0.tar.gz:

Publisher: release.yml on JPKell/PromptCadence

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file promptcadence-0.9.0b0-py3-none-any.whl.

File metadata

  • Download URL: promptcadence-0.9.0b0-py3-none-any.whl
  • Upload date:
  • Size: 335.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for promptcadence-0.9.0b0-py3-none-any.whl
Algorithm Hash digest
SHA256 2bd5a99e4a1dba2693a9123449d42233ad285e356733a0bc372858dd2a775b58
MD5 f8e515637b067427250164f5219fda6b
BLAKE2b-256 a4786b1ed884615a03b43375d5420adb5a76bbba3c32a9a1a3e0222443ddaf84

See more details on using hashes here.

Provenance

The following attestation bundles were made for promptcadence-0.9.0b0-py3-none-any.whl:

Publisher: release.yml on JPKell/PromptCadence

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

1.1.0

2 files

1.0.1

2 files

1.0.0

2 files

This release

0.9.0b0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page