Repository navigation
feat(visualize): draw with the harness's own renderers when text can't carry it - #47
Merged
Merged
Conversation
…t carry it /visualize had one way to show a picture that text can't carry: write an HTML file and `open` it. That steered agents past renderers the harness already provides (an Artifact tool, a board's show_page, docs with diagram blocks) and past the harness's own drawing guidance. The skill now checks what the session can render with before it picks a form. The question still picks the form; a renderer only draws it. When several renderers qualify, it uses the one that reaches the user where they are looking. It loads the drawing guidance for that renderer and keeps the file:line anchors and ASSUMED tags on the rendered nodes. Uploading counts as publishing, and a subagent hands the picture back unless it was asked to render. With no renderer in the session, the text forms work as before. Checked with two fresh-context runs. In a dry run, a simple request stayed a text call tree and a dense one picked a renderer. A real run rendered the repo-to-clients flow on the Ateam board with 53 file:line anchors, all of which resolve.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
/visualize had one way to show a picture that text can't carry: write an
HTML file and
openit. That steered agents past renderers the harnessalready provides (an Artifact tool, a board's show_page, docs with diagram
blocks) and past the harness's own drawing guidance.
The skill now checks what the session can render with before it picks a
form. The question still picks the form; a renderer only draws it. When
several renderers qualify, it uses the one that reaches the user where they
are looking. It loads the drawing guidance for that renderer and keeps the
file:line anchors and ASSUMED tags on the rendered nodes. Uploading counts
as publishing, and a subagent hands the picture back unless it was asked to
render. With no renderer in the session, the text forms work as before.
Checked with two fresh-context runs. In a dry run, a simple request stayed
a text call tree and a dense one picked a renderer. A real run rendered the
repo-to-clients flow on the Ateam board with 53 file:line anchors, all of
which resolve.