chore(release): v0.5.1 — finalize LLM-reduction roadmap (#33)#52
Merged
Conversation
All four LLM-reduction levers ship and are covered by the test suite: - D content-addressed completion cache - C static verify-loop fixers - A declarative plan recipes - B mechanical task executors (python/typescript/go/rust/php) The remaining empirical 50-goal codegen-disabled LLM baseline is split into a dedicated release-validation issue and does not block this release. The repo-local closure audit still reports that gate as open by design, so partial evidence is never claimed as complete. https://claude.ai/code/session_01By9Mb3TTWTukAGLfUFt9JH
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Resumo
Release
v0.5.1que fecha o roadmap de redução de dependência de LLM (#33). As 4 alavancas estão implementadas, testadas e em produção; esta release marca formalmente o fechamento e separa a validação empírica restante.Publicado no PyPI: https://pypi.org/project/simplicio-cli/0.5.1/
O que muda
pyproject.toml,simplicio/__init__.py:0.5.0→0.5.1tests/python/test_package_metadata.py: assert de versão acompanha o bumpCHANGELOG.md: entrada[0.5.1]documentando o fechamento de feat: reduce LLM dependency across simplicio flow (roadmap, 4 levers, -68% target) #33Alavancas entregues (#33)
simplicio/_cache.py,simplicio cache stats|clearsimplicio/pipeline_fixers.pysimplicio/scratch/recipes.pysimplicio/scratch/codegen/*Validação
ruff checknos arquivos tocados → passoupytest tests/python/test_package_metadata.py→2 passedpython -m build→ sdist + wheel0.5.1twine check(packaging 26.x) →PASSED(wheel + sdist)__version__ == 0.5.1,importlib.metadata.version == 0.5.1Validação empírica diferida
O gate restante de release — baseline real de 50 goals com codegen desligado (B/codegen pass-rate + latência) — é caro (chamadas LLM reais, horas) e foi separado em #51, conforme a própria recomendação de #33. O audit local (
bench/results_issue_closure_audit.*) continua reportando esse gate como aberto por design — nenhuma evidência parcial é declarada completa.Refs #33, #51.
https://claude.ai/code/session_01By9Mb3TTWTukAGLfUFt9JH
Generated by Claude Code