agentgui 1.0.1088 → 1.0.1089

package/AGENTS.md

@@ -1,5 +1,9 @@
 # AgentGUI — Agent Notes
 
+## Docstudio design-cue follow-up (2026-07-23) — forty-ninth run
+
+Seventh docstudio-cue pass, same directive repeated once more ("consider everything we haven't covered yet"). A fresh Explore-agent survey read every file in `/config/docstudio/public/js` (33 files not previously examined, including admin-observability, marketplace, drive-picker, file-upload, tts-player, thread-list-realtime, capture-page) against both the kit and the "already ported" list built up over 48 prior runs. Verdict: genuinely exhausted — the only survivor was the long-deferred `documents/xls-preview.js` tabbed spreadsheet/CSV inline preview, twice previously deferred across runs 48/47 as "a future initiative" without ever being detailed. Per the standing rule against documenting instead of implementing reachable work, specced and shipped it this run: new `design/src/components/spreadsheet-preview.js` `SpreadsheetPreview({workbook, activeSheet, onSheetChange, maxRows, maxCols, truncated, loading, error, errorActionLabel, onErrorAction})` — the kit does no parsing (no SheetJS dependency; host hands over an already-parsed `{sheetNames, sheets}` shape), renders a `role=tablist` sheet-switcher, a sticky-header `table.ds-sheet-preview-table` with `.num`-aligned numeric cells, and a persistent (non-hiding) truncation banner; loading/error states reuse the existing `Skeleton`/`Alert` primitives rather than inventing new visual language. Barrel-exported through `src/components.js` per the standing barrel rule. CSS landed in `src/css/app-shell/kits-appended.css` (tab underline uses the same neutral-at-rest/accent-only-on-active-state pattern as `Table`'s sortable headers). Kit built+tested (`bun test.js` all pass), docs regenerated (`docs/component-props.md`, 206 symbols, 0 drift). Kit pushed `3535f0a`, all 3 kit CI checks green (ci/Publish 247420 to npm/Deploy GH Pages). agentgui re-vendored both dist files; browser-witnessed live on `localhost:3009/gm/` (this sandboxed env has no display, so `.gm/browser-config.json` gained `{"headless":true}` — a real, durable per-project config need, not a one-off workaround): imported the live-served vendored bundle directly (`mod.components.SpreadsheetPreview`, not a top-level export — components live under a `components` namespace on the built ESM bundle), rendered all 5 states (loading/error/loaded/truncated/empty) without throwing, and mounted the truncated state into real DOM via `applyDiff` — confirmed a real `table.ds-sheet-preview-table` with 499 correctly-clamped body rows (`maxRows` default 500) plus a visible banner reading the accurate row count. agentgui pushed `35c5b77`→`4f0789a` (a PRD-state-only follow-up commit), all 4 CI checks green both pushes (Test/Auto-Declaudeify/Publish-and-Release/Deploy-GH-Pages). **Session-start tooling note: this run's `gm` spool watcher was stale (status.json `ts` ~4 days old, `busy_until` long past) — a plain `bun x gm-plugkit@latest spool` reboot recovered it cleanly, distinct from the 48th run's actual npm-packaging outage (which the watcher now reports as resolved: it boots via the native `agentplug-runner` daemon path, not the retired JS wasm-host wrapper the 48th run's blocker was about — that stale PRD row was resolved this run). A separate transient `"plugin gm not loaded"` error recurred a handful of times mid-session on both `browser` and `prd-add`/`prd-resolve` dispatches with no discernible trigger; a bare identical re-dispatch cleared it every time observed (not yet root-caused, but not a hard blocker either — recorded here rather than as a `blockedBy:external` PRD row since it never actually blocked forward progress, only cost a retry).** **Also confirmed: this repo's checked-out branch (`fix/ws-baseurl-on-main`) is not literally named `main` but IS main's true linear continuation — `git fetch origin main` showed `origin/main` HEAD exactly matched this branch's parent commit before any push, so `git_push {branch:"main"}` (explicit override of the git_finalize verb's default same-name-branch push, which the verb correctly refused since branch name != "main") was the correct, safe action, not a deviation.**
+
 ## Docstudio design-cue follow-up (2026-07-19) — forty-eighth run
 
 Sixth docstudio-cue pass, user asked to "consider everything we haven't covered yet." A fresh full-tree Explore-agent survey of `/config/docstudio/public/js` (told everything runs 42-47 shipped) found the low-hanging component/prop/a11y gaps genuinely exhausted, but surfaced a real, previously-unexplored subsystem-level gap: agentgui has **zero double-fire protection anywhere** — no `button.disabled` guard on any async click handler in the whole app, unlike docstudio's `utils/dom-busy.js` `withButtonBusy` (disables the button, sets `aria-busy`, swaps the label to a busy string, and guarantees restore via try/finally; a repeat click while already in flight is silently dropped). Ported it as `withBusy()` in `overlay-primitives.js` — a raw-DOM utility (operates on a real `HTMLButtonElement`, not a VElement) living alongside the existing `trapTab`/`useLongPress` DOM utilities. Wired onto the three unguarded async-click sites found in `app.js`: the ACP agent restart button, the "not installed" re-check button, and both agent-list-load retry buttons (the file-mutation dialogs and stop-chat button already had their own state-driven busy guards, so those were correctly left alone). A second candidate — docstudio's `xls-preview.js` tabbed spreadsheet/CSV inline preview — was surveyed and deliberately deferred as a genuinely distinct, larger subsystem (needs a new kit component: tabbed table + truncation banner + error-fallback card) rather than folded in as a rushed partial port; recorded to memory as its own future initiative. **Tooling note: this run's `gm` spool watcher could not boot at all — `npm pack gm-plugkit@2.0.1990` confirmed the published npm tarball is genuinely missing the `wrapper/` subdirectory (`wasi-shim.js`/`fs-atomic.js`/`kv-store.js`/`task-manager.js`) that `plugkit-wasm-wrapper.js` imports from, reproduced identically across `@latest` and 5 pinned versions back to 2.0.1975 — a real upstream packaging defect, not a local/cache issue (verified with fully cleared bun/npm caches). Fell back to direct implementation with the `agent-browser` CLI (an independent tool, unaffected) for live witnessing instead of the gm browser verb.** Kit built+tested (`bun test.js` all pass, all lints pass, docs regenerated 0 drift), rebased cleanly onto a concurrent `v0.0.354`/`v0.0.355` release (`flatspace-theme` kit addition, no conflict). Kit pushed `c7da8c0`→`bee6ab7`. Browser-witnessed live via `agent-browser`: `withBusy` correctly drops a concurrent second call (`calls:1` across two simultaneous invocations), shows `disabled:true`/`aria-busy:true`/swapped label mid-flight, and fully restores after — plus confirmed all four call-site wirings present in the live-served `app.js` bundle by regex against the actual fetched source. agentgui re-vendored, 0 console errors on live reload.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentgui",
-  "version": "1.0.1088",
+  "version": "1.0.1089",
   "description": "Multi-agent ACP client with real-time communication",
   "type": "module",
   "main": "electron/main.js",