docs: align execution contracts and agent skills - #194
Merged
shravan-lambdatest merged 3 commits intoSep 21, 2026
Merged
shravan-lambdatest merged 3 commits into
shravan-lambdatest merged 3 commits into
Conversation
…s-2026-09-21 # Conflicts: # .agents/skills/kane-cli/references/objectives-cookbook.md # .claude/skills/kane-cli/references/objectives-cookbook.md # docs/user-guide/assurance/automation.md # docs/user-guide/assurance/context.md # docs/user-guide/assurance/overview.md # docs/user-guide/configuration.md # skill-installer/skills/references/objectives-cookbook.md
siddhant573
changed the title
15 tasks
shravan-lambdatest
approved these changes
Sep 21, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Several guides and agent skills describe outdated execution defaults and completion events. For example, they advertise replay healing as opt-in and can treat an intermediate
run_endas the end of a saved test. This change aligns the user guide, canonical skill, repository mirrors and Kiro guidance with the inspected implementation.The audit tracks 23 documentation findings as corrected. Dataset guidance (D09) is deferred until complete CLI support, including automated creation, is available; dataset pages, flags, examples and skill routing are excluded. Three areas still need verification: context-sync provider/recovery behavior, remote bug-detection/fail-fast forwarding, and mobile checkpoint parity. These are documentation corrections, not implementation fixes or a live-runtime guarantee.
Validation: latest main merged;
git diff origin/main...HEAD --checkpassed; all 36 canonical-to-mirror Markdown comparisons match; no new unresolved Markdown file links; Kiro metadata/hooks and local HTML report links, status counts and JavaScript syntax passed static checks. No live browser/device/cloud runs were performed for these edits. The local audit retains the earlier 589 passing contract tests as prior evidence, not new validation of this PR.The HTML audit and its embedded implementation excerpts remain local and are excluded from this public PR, along with the local test harness.