Research doc: rich agent UI — pins schema vs dedicated surface (no code change) - #966
Closed
selfcontained wants to merge 1 commit into
Closed
Research doc: rich agent UI — pins schema vs dedicated surface (no code change)#966selfcontained wants to merge 1 commit into
selfcontained wants to merge 1 commit into
Conversation
Decision-support writeup comparing two directions for richer agent-controlled UI: enriching the pins schema toward Slack Block Kit, vs a dedicated tab/surface with its own UI-definition schema. Grounded in the current Block Kit docs (docs.slack.dev, fetched 2026-08-16) and the actual pins implementation, tool schemas, and whiteboard precedent. No runtime change. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Owner
Author
|
Closing — research doc doesn't need a PR; content shared directly. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this is
A research/decision doc, not a feature. Adds
docs/rich-agent-ui-tradeoffs.md— the tradeoff analysis Brad asked for on giving agents richer UI control: enrich the pins schema toward Slack Block Kit vs. build a dedicated tab/surface with its own UI-definition schema. No runtime change.Grounding
markdown,table,data_table,data_visualization,plan,task_card), hard limits, and the interactivity/callback contract.pins.ts,pin-write.ts/pin-merge.ts/pin-run.ts, MCP tool registrations,pin-*.tsxrendering), the whiteboard as the existing dedicated-surface precedent, and the measured tools/list token budget (brain:mcp-tool-schema-size-audit, PRs Trim MCP tool responses to what a calling agent needs #945/Add batch pin writes, update-by-id, bulk delete, and collapsible groups #946/Trim launch guidance to the plugin's skills, behind a setting #955).Shape of the analysis
Block Kit's richness decomposes into (a) rich leaf content, (b) layout composition, (c) a callback/interactivity contract. The doc argues pins can absorb (a) cheaply as new flat types, while (b) and (c) fight pins' load-bearing commitments (flat merge semantics, computed layout, prompt-injection-only interactivity) and the actively-managed schema token budget — and belong, if demand materializes, on a wholesale-replaced document surface built on the whiteboard skeleton. Ends with an explicit "if I had to pick" sequencing; the decision is Brad's.
Related brain idea:
dispatch-ideas/rich-agent-ui-surface-vs-pins-schema.🤖 Generated with Claude Code