Design Studio: durable exploration, verified prototypes, and reviewed handoff

.gitignore

@@ -42,7 +42,7 @@ Thumbs.db
 tmp/*
 
 # Local agent troubleshooting notes
-.papercuts/
+**/.papercuts/
 
 # Local git worktrees
 .worktrees/

.memory/studio-research-improvements.md

@@ -0,0 +1,55 @@
+# Studio PR #85 — 2026-09-22
+
+Preserved `feature/stitch-design-studio` (original head 37c7d37fa) in isolated
+`feature/studio-research-upgrade`. Main integration is separate commit 1edd2781.
+See docs/plans/completed/studio-research-improvements-plan.md for verified sources, changes,
+explicit deferrals, review findings and acceptance scope. Existing PR must be
+updated, never duplicated; no merge/release/deploy authorized.
+
+Integration preserved both sides of 13 conflicts, including detached generation
+recovery, Aiden Live, Studio ownership and DataStore publication receipts.
+Sol medium review found a task-chip spacing mismatch; fixed. Three source tests
+were adapted for conditional Studio layout and its prepared workspace argument.
+122 focused tests and type checks passed.
+
+Post-change reviewers caught fallback History dates/provenance, a redundant
+post-edit source read, incompatible connected-source context on Explore, duplicate
+preview document allocation, and loss of process failure state after cleanup.
+Fixes preserve exact authorization and visible failure recovery. Native Design
+exclusion remains unchanged; Android parity checks and iOS generic hardware test compilation passed, as did
+production build, type/lint and remote checks (462 pass, one skip). Hosted
+exact-head checks remain pending.
+
+Follow-up at 2026-09-22 11:38 UTC: head 133b96c55 has successful Ubuntu
+checks, while CI run 35719548500 still has verify and Deterministic Electron
+E2E queued with unassigned macos-26 runners. PR comments and review threads are
+empty. This is an external runner blocker, not passing CI. Removed previously
+tracked papercut scratch from Git while retaining the ignored local file, per
+the updated project instructions; no implementation changed.
+
+Hosted verify run 35722837750/job 106729478113 subsequently failed at the
+source-designer browser test: Undo's Vite reload interrupted page.goto with
+Chromium's alternate same-page navigation message. All 451 Design tests passed;
+the browser retry passed but fail-on-flaky correctly failed the job. Prepared a
+test-only fix in tests/generative-ui/source-designer.spec.ts matching the exact
+target and cleaned same-origin/path destination, with positive/negative cases.
+Both independent Sol medium reviewers found no issues. Classifier test passed
+three repetitions; browser integration could not launch under the newly
+restricted sandbox (MachPortRendezvousServer permission denied). Git metadata
+is read-only and coordinator notification was denied by the tool because
+approval policy is never. Patch retained at /tmp/studio-pr85-vite-reload.patch;
+fix is uncommitted and unpushed. Do not claim hosted CI or browser reruns passed.
+
+12:43 UTC follow-up: head remains 15700da226; Deterministic Electron E2E
+job 106729477692 succeeded. Release consumer contract also succeeded; verify
+still failed as above, with its downstream native/build steps skipped. No PR
+comments or review threads. Local fix lint and TypeScript checks passed.
+
+14:07 UTC: unrestricted permissions restored. Real source-designer browser
+tests passed all nine cases across three repetitions with retries disabled,
+including Apply/Undo and ambiguous-component rejection. Both prior Sol reviews
+cover this unchanged test-only fix. Coordinator notification now succeeded.
+The full Generative UI browser suite also passed all 12 tests with retries
+disabled. Hosted acceptance still requires the new pushed head's checks.
+
+14:41 UTC: all applicable hosted checks passed on 241ef9272416dffb433145d345d9b1e1ed53c5e8 (CI35738331314 and release contract35738331308). Android path-skipped; no comments/review threads. Plan archived as complete. Documentation-only completion commit will receive its own exact-head check before monitoring closes.

AGENTS.md

@@ -32,7 +32,7 @@ OpenRouter benchmark insights are also manual-only. The live app may contact onl
 
 ## Papercuts
 
-For complex workflows, record concise implementation friction in `.papercuts/troubleshooting.md` as it occurs.
+Papercut notes are machine-local scratch and are intentionally ignored by Git. For complex workflows, record concise implementation friction in `.papercuts/troubleshooting.md` as it occurs, but do not commit the folder or its contents.
 
 ## Tests
 

README.md

@@ -21,6 +21,7 @@ I don't come from a coding background. I'd been bouncing between the coding agen
 ## Features
 
 - **Aiden Live (Beta)** - use the blue orb for an explicitly started voice session with visible listening, thinking, speaking, approval, and error states. First use walks through model access, microphone, and Screen & Accessibility permissions once; computer actions and scheduled tasks retain Aiden's existing approval boundaries.
+- **Design Workspace** - open Design from the persistent sidebar and work on a durable React Flow-powered canvas of live, network-free HTML artboards and image references. Projects restore their exact canvas, history, comments, and source connection; Preview, Code, export, design-system context, reviewed multi-file actions, hash-safe Undo, and recoverable workspace handoff are built in. See the [shipped MVP](docs/plans/completed/design-workspace-plan.md) and [completed durable-project follow-on](docs/plans/completed/design-workspace-claude-alignment-plan.md).
 - **Command palette and shortcuts** - `⌘K` searches commands, chats, models, providers, Settings, and appearance actions. One typed command system also powers native menus, visible shortcut labels, transactional global hotkeys, and the searchable Keyboard Shortcuts editor.
 - **Commands and explicit skills** - type `/` at the start of the composer to search Aiden app commands, or `$` to search the active workspace's available skills. Commands reuse canonical app workflows; an explicitly selected skill is revalidated for the active workspace, applies to one accepted message, and persists only safe display provenance.
 - **Native Subagents** - a foreground chat can delegate up to four fresh `scout`, `planner`, or `reviewer` tasks. Children are read/search-only, inherit the approved workspace and model, stop with the parent, and appear as live chips plus an inspectable **Subagents** view in Environment.
@@ -38,6 +39,7 @@ I don't come from a coding background. I'd been bouncing between the coding agen
 The roadmap is maintained in [the plan index](docs/plans/README.md). These bullets name only the unfinished parts of partially shipped work or features with no runtime implementation yet; they are directions, not release promises:
 
 - **Designer Mode** - no Designer Mode runtime exists yet. The proposed flow selects UI in a local Vite app, requests a bounded change, requires approval, and reviews the exact action diff; Phase 0 remains a go/no-go validation gate. See the [Designer Mode plan](docs/plans/designer-mode-plan.md).
+- **Durable Design Projects and handoff** - named local projects persist the full canvas and expose Preview, Code, History, deterministic standalone/ZIP export, managed-worktree-first **Continue in workspace**, local design-system context, comments, bounded direct manipulation, and reviewed source changes. See the [completed Design Workspace follow-on plan](docs/plans/completed/design-workspace-claude-alignment-plan.md).
 - **Static-catalog overlays and provider completion** - Pi built-in discovery, encrypted credentials, provider-owned authentication, native streaming, stored dynamic catalogs, manual refresh, and voice credential lookup already ship. Remaining work includes remote overlays for otherwise-static hosted catalogs, Pi-native custom-endpoint composition, historical message provenance, scalable large-catalog recovery UX, and rollout cleanup. See the [Dynamic Model Catalog](docs/plans/dynamic-model-catalog-plan.md) and [Pi Provider Integration](docs/plans/pi-provider-integration-plan.md) plans.
 - **Truthful generation progress notes** - no progress-note runtime exists yet. The plan would show one temporary acknowledgement after an otherwise-silent start, using an explicitly selected on-device or verified hosted route without exposing hidden reasoning. See the [Generation Progress Notes plan](docs/plans/generation-progress-notes-plan.md).
 - **Long-session context and run control** - model-aware deterministic compaction already ships. Remaining work includes visible compaction activity, reconstructable structured checkpoints, durable-versus-working memory separation, queued follow-up messages, and safe mid-run redirects. See the [Compaction](docs/plans/compaction-plan.md) and [Taracodlab Learnings](docs/plans/taracodlab-learnings-plan.md) plans.

THIRD_PARTY_NOTICES.md

@@ -59,6 +59,22 @@ Copyright (c) 2013-2026 Khan Academy and other contributors
 
 MIT License. See https://github.com/KaTeX/KaTeX/blob/main/LICENSE.txt
 
+## React Flow
+
+`@xyflow/react` powers the spatial Design Workspace canvas.
+
+Copyright (c) 2019-2025 webkid GmbH
+
+MIT License. See https://github.com/xyflow/xyflow/blob/main/LICENSE
+
+## React Grab
+
+A minimized bundle of `react-grab/primitives` is vendored into `resources/generative-ui` for Design-only element hit testing inside sandboxed preview guests. Aiden does not initialize React Grab's full overlay or telemetry path.
+
+Copyright (c) 2025 Aiden Bai
+
+MIT License. See https://github.com/aidenybai/react-grab/blob/main/LICENSE
+
 ## rpiv extensions
 
 Aiden's native extensions adapt interaction and state-management ideas from

docs/architecture/design-comments-direct-edits.md

@@ -0,0 +1,86 @@
+# Design comments and bounded direct edits
+
+Status: Implemented. Comments, direct-edit IPC, pointer/keyboard controls, durable connected review,
+prototype revision creation, and exact immutable undo are wired.
+
+## Authority boundary
+
+Comments and direct-manipulation gestures are context. They never grant repository, command,
+network, Git, preview-session, or artifact-write authority.
+
+A comment target is durable only when all of these identities are present:
+
+- Design Project ID;
+- artboard lineage ID;
+- immutable revision media ID;
+- an exact, single-match selector identity; and
+- either the generated artifact content hash or a relative, source-version/range/preimage-hash
+  connected-source identity.
+
+An ephemeral React Grab selection or preview capability is insufficient and is never persisted.
+When the current immutable revision or full source binding changes, the store marks the older
+comment stale. Stale comments remain visible and can be resolved or reopened, but are never
+silently retargeted.
+
+The comment store is main-owned, atomic, schema- and byte-bounded, and written with mode `0600`.
+All writes use both database revision CAS and, for existing comments, comment revision CAS.
+Corrupt or unsupported on-disk data makes the store unavailable rather than allowing a later
+write to replace it.
+
+## Literal edit matrix
+
+The direct-edit core accepts only:
+
+- margin, padding, and gap spacing literals;
+- width and height literals;
+- enumerated alignment values;
+- semantic CSS custom-property token names for color roles;
+- border-radius literals; and
+- bounded static plain text.
+
+CSS expressions, URLs, raw colors, arbitrary properties, negative values, markup-like text,
+localized or dynamic text, rich text, computed classes, ambiguous selector/component matches,
+and repeated literal-definition matches fail closed. Proof facts must report exactly one selector,
+component, and literal definition match.
+
+Within one accepted gesture envelope, the proposal and undo identities are deterministic. That
+gives the integration coordinator one idempotency key and one future undo record. A renderer IPC
+retry is a new attended gesture with a newly minted gesture ID; it is not deduplicated against a
+previous ambiguous request.
+
+## Origin-specific output
+
+Prototype edits produce a `prototype-revision-request` pinned to the base media ID and artifact
+hash. The request instructs an artifact adapter to create a new immutable revision; the core never
+overwrites artifact bytes.
+
+The main adapter re-reads the committed source, verifies its SHA-256 identity, proves one exact
+`data-aiden-id` target and one literal inline definition, and derives a deterministic new media ID
+from the proposal. It stages the new bytes, CAS-appends the lineage in the Design Project, appends
+the chat artifact idempotently, and only then commits the staged bytes. A pre-CAS failure discards
+only the exact pending row. A post-CAS interruption deliberately leaves the pending row for the
+existing startup recovery path, so retries and restarts converge on one immutable revision.
+
+Connected-app edits produce a `designer-action-request` carrying the relative path, full source
+version, exact range, preimage, and independently verified preimage hash. The core never writes
+source. An integration adapter must turn that semantic literal edit into one exact replacement,
+then submit it through the existing Designer Action review/apply/undo transaction. Full permission
+must not bypass that review.
+
+The connected adapter resolves the live source-selection capability again, compares every path,
+version, range, preimage, hash, and selector fact with the proposal, and parses the canonical TSX.
+Only a single literal inline JSX style property or a single plain JSX text node is rewritten. The
+caller must also provide a trusted source-graph proof that the enclosing component has one use;
+missing or ambiguous graph evidence fails closed. The result is submitted to
+`SourceDesignerActionService.propose`, so apply and undo retain the same review transaction as
+every other Designer Action.
+
+## Intentional limitations
+
+The
+prototype adapter intentionally supports only literal inline HTML style declarations and plain
+text nodes. The connected adapter intentionally supports only literal inline JSX style objects and
+plain JSX text nodes. Stylesheets, classes, spreads, expressions, component indirection, localized
+text, rich children, ambiguous selectors, and repeated definitions fail closed instead of being
+guessed. Color changes additionally require the main caller to resolve the token from the current
+trusted design-system snapshot; renderer-reported token names are never sufficient authority.