Add a clear public walkthrough and simplify the agent inspector - #2
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Make the project understandable without installation: a GitHub Pages walkthrough replays three real Python executions, with expandable inputs/results and the saved-state snapshot. The first example loads automatically; local mode remains available for custom tasks and optional live models.
Replace the oversized landing-page styling with a restrained task/result and execution-inspection layout. Add a short captured-state GIF, a layered README, annotated walkthrough, architecture tradeoffs, hosting instructions, and evidence-bounded resume notes.
Fix the demo planner saving calculator errors as values. A failed calculation now stops the dependent write and preserves existing memory.
Validation: 26 tests, Ruff, JavaScript syntax check, package build, and the fresh-process restart walkthrough pass locally. Browser checks cover initial replay, example switching, observations, real local restart/recall, failure handling, exported JSON, and mobile layout. No live-model quality or production-readiness claim is made.