Skip to content

docs: two scopes: the next AI feature in Studio, and how an editor talks to FlutterProbe - #767

Merged
pbertsch merged 7 commits into
mainfrom
docs/ai-and-ide-scopes
Nov 17, 2026
Merged

pbertsch merged 7 commits into
mainfrom
docs/ai-and-ide-scopes

Conversation

@pbertsch

Copy link
Copy Markdown
Member

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

  • every claim about the code checked against the files and tests it names (two read-only fact sheets, then read again)
  • disclosure scan

🤖 Generated with Claude Code

https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF

…lks to FlutterProbe

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NxVy8Kr2nZk8HoMNcxZPFF
@pbertsch
pbertsch requested a review from a team as a code owner November 17, 2026 05:24
pbertsch and others added 6 commits November 16, 2026 23:36
… 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
@pbertsch
pbertsch merged commit e26efd7 into main Nov 17, 2026
10 of 11 checks passed
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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant