feat: Unify approvals and verification - #113
Merged
Merged
Conversation
…ool runs Introduce a shared durable approval lifecycle for caller-tool and provider executions. Provider approvals can now be resolved without turn or model-call records, while caller-tool approvals retain credential-scoped identity and validation. Add migration rerun safeguards and integration coverage for approval persistence, expiry, cancellation, and resolution.
Unify command, prompt, and fixture checks across CLI and agent runs, with typed reports, progress events, and persisted iteration history. Fail loudly when verification, models, timeouts, or runners are unconfigured instead of passing silently. BREAKING CHANGE: Remove the captain dod command and hooks; use workflow verification via captain verify.
Pass the resolved run spec to verifier factories so nested graders inherit the run's model and permissions. Allow hosts with their own commit pipeline to suppress duplicate commit hooks while retaining workflow declarations for validation.
…t workflows Centralize prompt-run iteration persistence so CLI and embedding hosts record generated and verify-only runs consistently, including complete verification rounds. Add comprehensive AI agent, verification, approvals, and embedding documentation, expose batched latest-verification queries, and surface rejected capability changes accessibly. Keep `captain verify` local-only to prevent unauthenticated remote command execution.
|
Important Review skippedToo many files! This PR contains 148 files, which is 48 over the limit of 100. To get a review, reduce the PR to 100 files or fewer by splitting it into smaller PRs or changing its base branch. Upgrade to a paid plan to raise the limit. This review couldn't start because sufficient usage credits or metered capacity aren't available. Add credits or update usage-based reviews in the billing tab, then retry. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Team Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (148)
You can disable this status message by setting the Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Gavel summary
Totals: 0 passed · 0 failed · 0 skipped · - |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Gavel summary
Totals: 4855 passed · 0 failed · 12 skipped · 14m27s |
Validate workflow judge prompts before provider construction so invalid declarations remain attributable even when provider setup fails. Also correct result JSON map capacity estimation.
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.
What
Notes
captain dodand hooks; usecaptain verify.