Skip to content

fix: parse single-line fenced LLM replies in analyzer - #46

Merged
Anai-Guo merged 1 commit into
mainfrom
chore/auto-maint-2026-10-17
Oct 18, 2026
Merged

Anai-Guo merged 1 commit into
mainfrom
chore/auto-maint-2026-10-17

Conversation

@Anai-Guo

Copy link
Copy Markdown
Owner

自动维护改动

类型:维护(小 bug 修复)
改动:Analyzer.generate_script_with_ai 剥离围栏时 str.index("\n") 对单行围栏/裸围栏回复抛 ValueError,改为 find() 并回退去掉三反引号(与 #20/#44/#45 同类修复),新增 3 个参数化回归用例(修复前 2 个失败,修复后全过)。
测试:通过(本地全量 513 passed,ruff check/format 通过)
参考:无

本 PR 由每日维护任务生成,请人工 review 后再合并。

🤖 Generated with Claude Code

generate_script_with_ai stripped the opening markdown fence with
str.index("\n"), which raises ValueError when the model returns a fenced
reply on a single line (or a bare fence). Use find() and fall back to
dropping the three backticks, matching the fix already applied to the
parameter optimizer, paper-pilot client and skill generator. Adds
parametrized regression tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@Anai-Guo
Anai-Guo merged commit d809ea9 into main Oct 18, 2026
3 checks passed
@Anai-Guo
Anai-Guo deleted the chore/auto-maint-2026-10-17 branch October 18, 2026 10:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant