Multi-LLM Council CLI: production-ready fixes and improvements#10
Merged
Conversation
…safety, docs A) Fix all 44 ruff lint errors (unused imports, import sorting, ambiguous variable names, unnecessary f-strings, ternary refactors, combined with statements). ruff check . now passes cleanly. B) Fix --dry-run semantics: previously marked runs as "failed" because the dry-run exit path shared the same branch as "both tools failed". Now returns a _DRY_RUN_SENTINEL, marks all rounds as "skipped", and sets state status to "dry_run". Exits with code 0. C) Fix multi-candidate + resume correctness: the chosen candidate name (e.g. claude_2) was only held in a local variable and never persisted. On resume, _load_round_output always loaded the base candidate. Now persists chosen_candidates dict in state.json round 0 details and reads it back on resume. D) Add working-tree safety to council apply: refuses to apply patches on a dirty working tree unless --force is passed. --check (read-only) skips the dirty-tree check. E) Update README with all missing documentation: council resume, council apply (with --check/--yes/--apply-to/--force), --no-save, --redact-paths, --smart-context, --structured-review, --claude-n/--codex-n, updated run artifacts section (state.json, review files, multi-candidate files). F) Add council list command to list recent runs with status/metadata. Tests: 297 passed (up from 285), ruff check clean. https://claude.ai/code/session_01NLdqwmPoeinJoc4ojUEAma
Applies consistent formatting (ruff format .) to all 26 Python files. No logic changes — formatting only. ruff check: All checks passed ruff format --check: 32 files already formatted pytest: 297 passed https://claude.ai/code/session_01NLdqwmPoeinJoc4ojUEAma
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.
Summary
--dry-runnow marks state asdry_runwith roundsskipped, exits code 0, never marks run as failedstate.json; resume loads the correct selected candidatecouncil applychecks for dirty working tree, requires--forceto proceedresume,apply,--no-save,--redact-paths,--smart-context,--structured-review,--claude-n/--codex-n, and updated Run Artifacts sectionTest plan
ruff check .passesruff format --check .passes (32 files formatted)pytest— 297 tests passhttps://claude.ai/code/session_01NLdqwmPoeinJoc4ojUEAma