Repository navigation
docs: two scopes: the next AI feature in Studio, and how an editor talks to FlutterProbe - #767
Merged
Merged
Conversation
…lks to FlutterProbe Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
… fact, not a bug Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
…ct per feature, the redactor's families, who can reach the AI methods Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
…ot an existing property Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
…iew state and confirmation are exact Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
jay23606
added a commit
to jay23606/flutter-probe
that referenced
this pull request
Nov 17, 2026
…lks to FlutterProbe (AlphaWaveSystems#767) ## Summary Two design notes in `docs/proposals/`, no code, so the decisions can be made before anything is built. Both start from what the code does today (read from it, not from memory). - **`studio-ai-next-feature.md`**: "Explain this failed step". What it does and never does; what it may read and may send (bounded, after the outbound gate and the preview); local-first, bring-your-own-key, no relay; consent and wipe rules stated for the model like `AskClearData` (nothing the model writes is executed, no wipe or connection is reachable from its output, no skip for hosted previews, not callable from automation or MCP); a failure-mode table with what pins each; six measurable targets (including a measured usefulness number that is reported, not claimed); a first slice; open decisions. - **`ide-transport.md`**: the five local surfaces that exist and what a stray local process or a web page can reach on each; a threat model; what the transport must and must not be; six things found while reading the code that should be fixed first (cloud secrets in the terminal arguments of the VS Code extension, a workspace-scoped binary path, the whole environment passed to children, the automation discovery file not re-checking an existing folder or link, the test-only bridge's token, two MCP servers sharing one token file name); three options (a stdio child process, the automation endpoint, MCP over HTTP) with a recommendation; how it relates to the bound-method decision table and MCP; a first slice; measurable targets; open decisions. Both are public-safe: nothing about plans, pricing, customers or other projects. ## Test plan - [x] every claim about the code checked against the files and tests it names (two read-only fact sheets, then read again) - [x] disclosure scan
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.
Summary
Two design notes in
docs/proposals/, no code, so the decisions can be made before anything is built. Both start from what the code does today (read from it, not from memory).studio-ai-next-feature.md: "Explain this failed step". What it does and never does; what it may read and may send (bounded, after the outbound gate and the preview); local-first, bring-your-own-key, no relay; consent and wipe rules stated for the model likeAskClearData(nothing the model writes is executed, no wipe or connection is reachable from its output, no skip for hosted previews, not callable from automation or MCP); a failure-mode table with what pins each; six measurable targets (including a measured usefulness number that is reported, not claimed); a first slice; open decisions.ide-transport.md: the five local surfaces that exist and what a stray local process or a web page can reach on each; a threat model; what the transport must and must not be; six things found while reading the code that should be fixed first (cloud secrets in the terminal arguments of the VS Code extension, a workspace-scoped binary path, the whole environment passed to children, the automation discovery file not re-checking an existing folder or link, the test-only bridge's token, two MCP servers sharing one token file name); three options (a stdio child process, the automation endpoint, MCP over HTTP) with a recommendation; how it relates to the bound-method decision table and MCP; a first slice; measurable targets; open decisions.Both are public-safe: nothing about plans, pricing, customers or other projects.
Test plan
🤖 Generated with Claude Code
https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF