samuelgoofus-boop
dca74a683e
Fixes surfaced running SkillOpt end-to-end on the bundled `claude` backend
(local Claude CLI) on Windows. None changes the OpenAI/GPT happy path.
1. skillopt/engine/trainer.py — the final test-eval directory
(test_eval_final/) is written to before being created; add
os.makedirs(..., exist_ok=True), matching the two sibling test-eval dirs.
Without it, summary.json raises FileNotFoundError when a rollout yields
zero predictions.
2. skillopt/model/claude_backend.py
a. Pass the prompt via stdin (not argv): on Windows the whole command line
is capped at ~32 KB and a large optimizer prompt (the success-analyst
minibatch carrying several report trajectories) overflows it with
[WinError 206], killing the run after retries.
b. Pass the system prompt via --append-system-prompt-file (a temp file),
not argv. The system prompt here is the skill being optimized, which
SkillOpt grows over training; since the ~32 KB cap applies to the SUM of
all argv, a grown skill would re-hit [WinError 206] even with the prompt
on stdin.
c. Pin the subprocess encoding to utf-8 (errors="replace"). With text=True
and no encoding=, stdin is encoded with the system codepage; on a zh-CN
box (cp936/GBK) a prompt containing an emoji or some Latin-1 characters
raises UnicodeEncodeError before the CLI even starts, failing every retry.
3. skillopt/model/codex_backend.py — the same utf-8 encoding pin on its
subprocess.run(input=...) call (identical unpinned-encoding pattern).
4. skillopt/utils/json_utils.py — extract_json() returned None for valid-
looking JSON that strict json.loads rejects (unescaped ASCII quotes inside
CJK string values, trailing commas), silently dropping the analyst's edits
on non-schema backends (Claude/Qwen): reflect produces N edits, 0 applied.
Add a json_repair fallback, but only on a single unambiguous object — a
balanced-brace extractor plus a refuse-on-multiple-objects guard — so a
chain-of-thought "scratch + final" response can't make repair silently
return the wrong (discarded) object, which would be worse than None (None is
detectable and retryable; a wrong-but-valid edit is applied blind). Declare
json_repair in requirements.txt and the claude/qwen optional extras so the
fallback is actually present (it otherwise no-ops, dropping edits silently).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
81 lines
2.4 KiB
TOML
81 lines
2.4 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=68.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "skillopt"
|
|
version = "0.1.0"
|
|
description = "SkillOpt: Agentic Skill Optimization via Reflective Training Loops"
|
|
readme = "README.md"
|
|
license = {text = "MIT"}
|
|
requires-python = ">=3.10"
|
|
authors = [
|
|
{name = "SkillOpt Team"},
|
|
]
|
|
keywords = ["agent", "prompt-optimization", "skill-learning", "LLM", "agentic"]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Science/Research",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
]
|
|
dependencies = [
|
|
"openai>=1.30.0",
|
|
"pyyaml>=6.0",
|
|
"numpy>=1.24.0",
|
|
"openpyxl>=3.1.0",
|
|
"azure-identity>=1.15.0",
|
|
"azure-core>=1.30.0",
|
|
"httpx>=0.27.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
# Benchmark-specific dependencies
|
|
alfworld = ["alfworld>=0.4.0", "gymnasium>=0.29.0"]
|
|
# Claude model backend
|
|
claude = ["claude-agent-sdk>=0.1.0", "json_repair>=0.61.0"]
|
|
# Qwen local model backend (via vLLM)
|
|
qwen = ["vllm>=0.4.0", "json_repair>=0.61.0"]
|
|
# SearchQA data materialization
|
|
searchqa = ["datasets>=2.18.0"]
|
|
# Documentation site
|
|
docs = ["mkdocs-material>=9.5.0", "mkdocstrings[python]>=0.24.0"]
|
|
# WebUI dashboard
|
|
webui = ["gradio>=4.0.0"]
|
|
# Development tools
|
|
dev = ["ruff>=0.4.0", "pytest>=8.0.0"]
|
|
# All optional dependencies (except docs/dev/webui)
|
|
all = [
|
|
"alfworld>=0.4.0",
|
|
"gymnasium>=0.29.0",
|
|
"claude-agent-sdk>=0.1.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
skillopt-train = "scripts.train:main"
|
|
skillopt-eval = "scripts.eval_only:main"
|
|
skillopt-sleep = "skillopt_sleep.__main__:main"
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/microsoft/SkillOpt"
|
|
Documentation = "https://microsoft.github.io/SkillOpt"
|
|
Repository = "https://github.com/microsoft/SkillOpt"
|
|
Issues = "https://github.com/microsoft/SkillOpt/issues"
|
|
|
|
[tool.setuptools.packages.find]
|
|
# skillopt* = the research package; skillopt_sleep = the open-source Sleep tool
|
|
# (decoupled, zero dependency on the research code).
|
|
include = ["skillopt", "skillopt.*", "skillopt_sleep", "skillopt_sleep.*", "scripts*"]
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
target-version = "py310"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "W"]
|
|
ignore = ["E501"]
|