Add interactive agent question cards and forms - #96
Merged
Merged
Conversation
Signed-off-by: Tiberiu Socaci <tsocaci@makeitfuture.com>
Signed-off-by: Tiberiu Socaci <tsocaci@makeitfuture.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agents can now ask clarification questions through requester-bound Slack cards and paginated forms. Questions support arbitrary button labels, single/multiple choices and custom text; selections stay drafts until Submit queues the complete answer set into the originating thread.
Requests and drafts persist in SQLite. Submission atomically records the continuation, duplicate/stale actions are rejected, failed Slack updates can recover, and stop/clear cancels pending forms. Access is rechecked at submission, queue promotion and restart recovery. Ordinary thread replies preserve pending-question context. The shared MCP tool and operating guide cover Claude and Codex; unattended/reduced runs do not expose the tool.
Validation: 37 focused question tests; full regression with coverage (2,558 pass, 13 existing opt-in skips); static checks, secret scan, security coverage and DCO. Production dependency audit has no high/critical findings (one existing moderate Hono advisory). Seven reproducible dual-engine live acceptance cases are documented and registered; live Slack/engine acceptance is not yet run. Beta integration only; no stable promotion.