[codex] add workflow handoffs and harden live harness reuse#27
Merged
Conversation
- add inspiredesign success-path follow-through guidance and canvas handoff artifacts - emit canvas plan request and design-agent handoff payloads in renderer outputs - cover runtime, workflow message, CLI, and tool surfaces with inspiredesign tests Co-authored-by: Codex <noreply@openai.com>
- add inspiredesign canvas continuation guidance to help and onboarding surfaces - point skill nudges to best-practices quick start and design-agent canvas-contract - cover the updated help and nudge wording with focused tests Co-authored-by: Codex <noreply@openai.com>
- describe the inspiredesign follow-through artifacts emitted after successful runs - document the canvas handoff flow and the optional captureMode=deep recommendation Co-authored-by: Codex <noreply@openai.com>
- centralize shared success follow-through metadata builders - return handoff guidance for research, shopping, and product-video runs - cover the new workflow contract in CLI and tool regression tests Co-authored-by: Codex <noreply@openai.com>
- inspect execution metadata before choosing macro resolve success text - keep execute-free runs unchanged while flagging blocker follow-up cases - extend CLI coverage for both blocked and successful execution paths Co-authored-by: Codex <noreply@openai.com>
- treat extension-only ops reuse as healthy relay state in live matrix recovery - cover the relay contract with focused live-regression and provider-matrix tests - refresh the active v0.0.20 release evidence ledger with the current full-suite proof Co-authored-by: Codex <noreply@openai.com>
- point workflow handoff to the bundled brief helper path - sync the skill pack guidance and regression coverage Co-authored-by: Codex <noreply@openai.com>
- make the stubborn child fixture prove handler readiness before timeout - keep the SIGKILL assertion while widening the startup budget for suite load Co-authored-by: Codex <noreply@openai.com>
- delete retired investigation docs that are no longer part of the active set - remove stale references from the docs index and workflow wrapper docs - keep the workflow surface map generator aligned with the generated markdown Co-authored-by: Codex <noreply@openai.com>
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
/opssessions are not treated as dirtyRoot cause
Workflow completion behavior was uneven across first-class lanes, so some successful runs still fell back to generic completion text while macro execution and live harness recovery surfaced weaker operator guidance than the runtime actually knew. The live matrix harnesses also treated
opsConnected=trueas automatically dirty even when the extension relay was healthy and handshake-complete.Impact
Validation
npm run lintnpm run typechecknpm run buildnpm run testnode scripts/docs-drift-check.mjsNotes