Implementation Plan: T5-P4-A8-WP2 Prove planner.yaml composes valid:true under codex backend#4139
Merged
Trecek merged 8 commits intoJun 28, 2026
Conversation
Add a dedicated recipe validation test proving planner.yaml composes valid=True under the codex backend capability override set (backend_supports_git_write=false). The test exercises load_and_validate directly with the backend_name and ingredient_overrides kwargs to prove planner's recipe composition is codex-compatible independent of the parametric matrix coverage in test_bundled_recipes_dispatch_ready. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Add 5 gated smoke tests validating recipe composition, session diagnostics, and session locator resolution under the codex backend: - test_open_kitchen_implementation_valid - test_open_kitchen_planner_valid - test_reduced_codex_smoke_pipeline_no_refusals - test_session_diagnostics_field_completeness - test_composite_locator_resolves_codex_session Tests share a single codex_session fixture for the codex exec invocation, use a _FakeLocator that returns the captured rollout path for flush_session_log, and inject a stub backend into BACKEND_REGISTRY via monkeypatch for the composite locator test. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
test_smoke_codex.py imports load_and_validate from autoskillit.recipe to validate recipe composition for the codex backend. Add it to the file-level allowlists in _TEST_LAYER_ALLOWLIST and LAYER_CASCADE_CONSERVATIVE.
…on fixture into single loop
…codex_backend severity comparisons
Trecek
deleted the
t5-p4-a8-wp2-prove-that-planner-yaml-composes-valid-true-und/4026
branch
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
1 participant
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
Add a dedicated recipe validation test proving
planner.yamlcomposesvalid=Trueunder the codex backend capability override set (backend_supports_git_write=false), and add aTestCodexSmokeRecipeCompositionclass with 5 gated smoke tests validating recipe composition, session diagnostics, and session locator resolution for the codex backend.Closes #4026
Implementation Plan
Plan file:
/home/talon/projects/autoskillit-runs/impl-20260628-033104-213088/.autoskillit/temp/make-plan/t5_p4_a8_wp2_planner_codex_valid_plan_2026-06-28_035000.md🤖 Generated with Claude Code via AutoSkillit
Token Usage Summary
* Step used a non-Anthropic provider; caching behavior may differ.
Token Efficiency
Model Usage Breakdown