Metadata-Version: 2.4
Name: runopsy-cli
Version: 0.1.6
Summary: The Runopsy command line: diagnose agent runs and inspect the evidence
Project-URL: Homepage, https://github.com/vahit19/runopsy
Project-URL: Repository, https://github.com/vahit19/runopsy
Project-URL: Issues, https://github.com/vahit19/runopsy/issues
Project-URL: Changelog, https://github.com/vahit19/runopsy/blob/main/CHANGELOG.md
Author-email: Vahit Feryad <vahit.feryat@gmail.com>
License-Expression: Apache-2.0
Keywords: agent,cli,debugging,llm,root-cause-analysis
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Debuggers
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Topic :: System :: Monitoring
Classifier: Typing :: Typed
Requires-Python: >=3.12
Requires-Dist: click>=8.3.3
Requires-Dist: rich>=13.7
Requires-Dist: runopsy-adapter==0.1.6
Requires-Dist: runopsy-bench==0.1.6
Requires-Dist: runopsy-collector==0.1.6
Requires-Dist: runopsy-core==0.1.6
Requires-Dist: runopsy-replay==0.1.6
Requires-Dist: runopsy-semantic==0.1.6
Requires-Dist: typer>=0.12
Description-Content-Type: text/markdown

# runopsy-cli

The terminal surface: list runs, diagnose one, and read the evidence behind a finding.

The wording here is part of the product, not decoration. A diagnosis engine earns its
place by being trusted, and trust is destroyed faster by one confident wrong answer than
by ten honest "I am not sure". So the output keeps three things apart at all times:

- **Observed failure** — what the run visibly got wrong. A fact.
- **Suspected onset** — where it probably started going wrong. A hypothesis, always
  shown with its confidence and never phrased as a cause.
- **Confirmed cause** — reserved for findings a counterfactual replay or a person has
  actually validated. Nothing the deterministic pipeline produces on its own may claim
  this.

Every unconfirmed diagnosis ends by telling the user how to upgrade it, because the
point is not to sound certain — it is to make certainty cheap to obtain.
