feat(correction): add correction model and CLI hooks #181

New issue

Closed

opened 2026-02-22 23:39:53 +00:00 by freemo · 0 comments

freemo commented

2026-02-22 23:39:53 +00:00

Owner

Metadata

Commit: feat(correction): add correction model and CLI hooks
Branch: feature/m4-correction-model

Subtasks

Add correction models (correction request, target decision, reason, mode) and CLI scaffolding.
Add docs/reference/decision_correction.md with correction modes and command usage.
Tests (Behave): Add scenarios for correction request validation and CLI output.
Tests (Robot): Add Robot test for plan correct --dry-run output.
Tests (ASV): Add benchmarks/decision_correction_model_bench.py for model overhead.
Verify coverage >=97% via nox -s coverage_report. If coverage is <97% then review the current unit test coverage report at build/coverage.xml and use it to write new Behave based unit tests to improve code coverage. Specifically, write Behave style unit tests that are descriptively named and specifically improves coverage on whichever file has the most uncovered lines by writing tests that will target the uncovered lines in the report. Once that is done rerun nox -s coverage_report to verify all tests pass and coverage is above >=97%. Only mark this as complete once coverage is >=97%, if not repeat this task as many times as is needed until coverage reaches >=97%.
Run nox (all default sessions, including benchmark), fix any errors if needed ensuring nox passes across entire code base, do not ignore any failure even if it seems unrelated to this commit, fix it.

Section: #### M4: Corrections + Subplans + Checkpoints (Day 22)
Status: Completed

## Metadata - **Commit**: `feat(correction): add correction model and CLI hooks` - **Branch**: `feature/m4-correction-model` ## Subtasks - [x] Add correction models (correction request, target decision, reason, mode) and CLI scaffolding. - [x] Add `docs/reference/decision_correction.md` with correction modes and command usage. - [x] Tests (Behave): Add scenarios for correction request validation and CLI output. - [x] Tests (Robot): Add Robot test for `plan correct --dry-run` output. - [x] Tests (ASV): Add `benchmarks/decision_correction_model_bench.py` for model overhead. - [x] Verify coverage >=97% via `nox -s coverage_report`. If coverage is <97% then review the current unit test coverage report at `build/coverage.xml` and use it to write new Behave based unit tests to improve code coverage. Specifically, write Behave style unit tests that are descriptively named and specifically improves coverage on whichever file has the most uncovered lines by writing tests that will target the uncovered lines in the report. Once that is done rerun `nox -s coverage_report` to verify all tests pass and coverage is above >=97%. Only mark this as complete once coverage is >=97%, if not repeat this task as many times as is needed until coverage reaches >=97%. - [x] Run `nox` (all default sessions, including benchmark), fix any errors if needed ensuring nox passes across **entire** code base, do not ignore any failure even if it seems unrelated to this commit, fix it. **Section**: #### M4: Corrections + Subplans + Checkpoints (Day 22) **Status**: Completed

Rows
Columns