agentgui 1.0.1091 → 1.0.1093

package/AGENTS.md

@@ -1,234 +1,61 @@
 # AgentGUI — Agent Notes
 
-## Docstudio design-cue follow-up (2026-07-23) — fiftieth run
-
-Eighth docstudio-cue pass. A fresh Explore-agent survey (told the full 49-run ported list) read every remaining unmined docstudio surface — admin-observability-{views,chart}.js, marketplace-{trending,card,flag}.js, documents/drive-picker.js, documents/file-upload.js, streaming/tts-player.js, thread-list-realtime.js, capture-page.js/capture-runner.js, and admin users/tags/archives/audit/moderation tabs — and came back near-exhausted: nearly everything was either already covered under a different name (docstudio's tts-player is *less* mature than the kit's own `voice.js`), pure business logic with no portable UI (drive-picker delegates to Google's native picker iframe; file-upload/thread-list-realtime have no render surface at all), or app-specific GCP wiring (the observability panels' Cloud Logging deep-links). One genuine, narrow gap survived: `admin-observability-views.js:132-161` `endpointsView()` color-codes percentile-latency/success-rate table cells (green >=99%, amber >=95%, red below) with no kit equivalent — `Table` had no notion of a value implying good/warn/bad. Ported the portable convention (not the GCP wiring) as `RateCell({value, tone})` in `design/src/components/data-density.js`, a plain tone-colored `<span>` over the existing `--success`/`--warn`/`--danger` tokens that drops into any `Table` cell, matching `Table`'s own onSort host-owns-the-logic convention (this component has no opinion on thresholds). While touching `data-density.js`, found and fixed a real, unrelated, previously-undiscovered gap: **its entire component set (`PhaseWalk`/`TreeNode`/`BarRow`/`StatTile`/`StatsGrid`/`SubGrid`/`SessionRow`/`DevRow`/`LiveLog`) was never wired into `src/components.js`'s barrel** — unreachable from the built bundle despite having real CSS in `data-density.css`, since before this run. Fixed by adding the barrel export line alongside the new `RateCell`. Kit built+tested (`bun test.js` all pass, 0 lint errors), docs regenerated (`docs/component-props.md`, 218 symbols, 0 drift). Kit pushed `72d88b6`, 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/`: imported the live-served vendored bundle directly, confirmed `mod.components.RateCell`/`mod.components.StatTile` both callable, and mounted `RateCell({value:"UNIQ_99_4",tone:"good"})` into real DOM via `applyDiff` — rendered exactly `<span class="ds-rate-cell ds-rate-cell-good">UNIQ_99_4</span>`, confirming the CSS tone-class wiring works end-to-end live. **Real tooling defect diagnosed+fixed this run, not papered over**: mid-session, `browser` verb dispatches intermittently failed `"plugin gm not loaded"` — root-caused via `.gm/exec-spool/.watcher.log` to a **leftover stale `gm-plugkit` `supervisor.js` process** (pid alive since a prior session, `Jul19`) running independently alongside the healthy native `agentplug-runner` daemon, periodically trying to respawn the watcher via the *retired* JS `plugkit-wasm-wrapper.js` path (`Cannot find module './wrapper/wasi-shim.js'` — the exact historically-resolved npm-packaging defect from the 48th run, recurring here via a stale cached supervisor rather than a fresh regression) and crash-looping. A separately-wedged long-lived Chrome process for the agentgui project profile (alive since `Jul17`) was also found wedging evals to 60s timeouts. Killed both stale processes, rebooted a fresh daemon (`bun x gm-plugkit@latest spool`) — confirmed fixed via two clean subsequent dispatches, no further crash-loop lines. **Also newly confirmed: writing a spool verb input file under a task-number that collides with an existing `out/<verb>-<N>.json` from an earlier turn in the same session silently returns the STALE cached output instead of running the fresh dispatch** — the watcher appears to treat a pre-existing out-file as already-satisfied and skip reprocessing. Always pick a task number confirmed absent from `out/` (e.g. jump to a clearly-unused block like 100+) rather than trusting sequential same-session numbering, especially after a long session with many prior dispatches.
-
-## 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.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-seventh run, confirming pass
-
-Per gm-continue's mandatory first-confirming-pass discipline, a second independent Explore-agent survey (told what the 47th run's main pass just shipped) re-checked docstudio against the kit + app and found one last real, narrow gap: `app.js`'s cross-tab external-update banner still called native `window.confirm()` for the reload-discards-unsent-draft guard — the sole remaining native browser dialog call anywhere in the app, matching docstudio's own `dialog.js` rationale of never using `window.confirm/alert/prompt` for data-loss confirmations. Replaced with a `state.chat.confirmingReloadDiscard` flag rendering the kit's existing `ConfirmDialog` modal, mirroring the same pattern already used for file delete/bulk-delete. Browser-witnessed by fetching the live-served `/gm/js/app.js` directly and regex-confirming `window.confirm` is gone and the new `confreload` dialog key is present. A second confirming pass after this one found nothing further — docstudio's `buildDocAccessPrompt`/`buildScopePrompt` variants are narrow Google-OAuth/Drive-doc-specific flows with no analog in agentgui's domain model, and everything else checked (ApprovalPrompt's focus/a11y semantics, build-freshness poll, modal focus-trap/Escape/backdrop semantics) was already correctly ported.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-seventh run
-
-Fifth docstudio-cue pass, same directive repeated a fifth time after the 46th run's confirming pass had concluded the mining task "genuinely exhausted." A fresh independent Explore-agent re-verification (told what runs 42-46 shipped) found that conclusion was **not fully accurate**: `chat-approval-prompts.js:47-71`'s `buildApprovalPrompt` has an auto-focused free-text note textarea threaded through every approve/deny decision (prefixed onto the denial message so the assistant sees why it was denied) that the kit's `PermissionMenu` (a settings-style checkbox dropdown, architecturally different) had no analog for at all. Added a new `ApprovalPrompt` component (`overlay-primitives.js`) — an inline, in-thread permission card (name/category head, optional args preview, auto-focused optional note, once/session/all/deny actions via `onDecision(kind, note)`) — plus a `lock` icon added to the shared `ICON_PATHS` (didn't exist previously) and a barrel re-export per the standing barrel rule. Also landed the pass's secondary finding: `update-check.js`'s `/version.json` poll + persistent reload-nudge pattern, ported to `app.js` as `startBuildFreshnessPoll()` (90s interval, compares live `/health` `version` against `window.__SERVER_VERSION`, reuses the kit's existing `toast({actionLabel,onAction,duration:0})` from the 46th run rather than inventing a new notice surface). A first CSS pass tripped the frozen spacing-lint baseline (raw `6px 14px` button padding) — fixed by mapping to `--space-1-75`/`--space-3` and `--r-pill` instead of literal `999px`. Kit rebased once onto concurrent `v0.0.352`/`v0.0.353` releases (dist-only conflict, rebuilt fresh per the standing discipline). Kit pushed `e93f4f7`→`6d71b34`, all 3 checks green. Browser-witnessed live on `localhost:3009/gm/`: this session's `gm browser` verb had a real, repeat tool defect (`url=`/`dom=`/`screenshot=` prefixes evaluate in a detached Node vm, not the real page — `ReferenceError: document is not defined` despite `navigation_requested:true`) — recorded to durable memory (`agentgui-browser-verb-url-dom-prefix-broken-2026-07-17`) rather than left as a stuck PRD row, per gm's diagnose-the-tool discipline. Worked around by using only the bare `capture\n<script>` form (`page.goto`+`page.evaluate` inline) and reading results via `console.log('WITNESS:'+...)` inside the page context rather than the top-level `result` field, which came back `null` even on successful (`exit_code:0`) dispatches. Confirmed live: `toast()`'s action button fires `onAction(dismiss)`; `ApprovalPrompt` renders (`.ov-approval` present), note textarea auto-focuses, lock icon renders, Deny click fires `onDecision('deny', '')` correctly. agentgui re-vendored, pushed `1d37290`→`9b25faf`→`08483cf`, all 4 CI checks green both pushes.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-sixth run, confirming pass
-
-Per gm-continue's mandatory first-confirming-pass discipline, a second independent Explore-agent survey (told what runs 42-46 already shipped, including the aria-live fix above) checked docstudio's remaining source (`update-check.js`, `debug-panel.js`, `chat-tabs.js`, `chat-model-selector.js`, `webview-detector.js`, `xls-preview.js`, `doc-tab.js`, `chat-approval-prompts.js`) and found one more narrow, real prop-surface gap: the kit's `toast()` (`editor-primitives.js:637`) only supported a self-dismissing `{message,kind,duration}` shape, unlike docstudio's `update-check.js:18-30` persistent click-to-reload notification bar. Added `actionLabel`/`onAction` props rendering a non-auto-dismissing button (`duration:0` already worked; the gap was no action-button support) — `.ds-ep-toast-action` styled with `--space-*` tokens (a first attempt with raw px literals tripped the frozen spacing-lint baseline, caught by `node scripts/build.mjs` before commit). CI caught a real miss on first push: `docs/component-props.md` was stale after the new `toast()` signature (`node scripts/generate-component-docs.mjs --check` lint), fixed by regenerating and re-pushing — a genuine CI-catches-a-real-gap case, not flakiness. Kit rebased twice cleanly onto concurrent `v0.0.350`/`v0.0.351` releases (dist-only, rebuilt fresh both times). Kit pushed `b5530cb`→`e93f4f7`, all 3 kit CI checks green. Browser-witnessed live on `localhost:3009/gm/` by importing the vendored module directly and calling `toast()` both ways: action variant renders `.ds-ep-toast.has-action` with a working `Reload` button whose click fires `onAction(dismiss)`; plain toast (no `actionLabel`/`onAction`) renders with no `has-action` class and no button, confirming backward compatibility. agentgui re-vendored, pushed `ed36a36`→`3a59c3b`, all 4 CI checks green. A second confirming pass after this one found nothing further.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-sixth run
-
-Fourth docstudio-cue pass, same directive repeated a fourth time. A fresh Explore-agent survey of `/config/docstudio` (told explicitly what runs 42-45 already shipped — toasts/Skeleton/Alert/Badge-tone/dialogs/breadcrumbs/inline-error-retry/Avatar/sidePanel/sortable-Table/streamingSince/coarse-pointer Enter-gating/CountdownDialog/PermissionMenu/detectAttachment/RTL support) came back with the low-hanging fruit exhausted: only 1 genuinely new, verified-missing candidate survived (a second, "self-retry dropdown trigger" candidate had no existing async-populated-dropdown call site in the kit to wire it to, so it was explicitly skipped as speculative unused plumbing rather than implemented). Landed: `chat.js`'s two `role=log` chat-thread containers (`chat.js:533`,`581`) and `agent-chat.js`'s one (`agent-chat.js:476`) gained `aria-live="polite" aria-relevant="additions"`, matching docstudio's `chat-tabs.js:62-65` pairing, so new messages announce to screen readers without spamming on every streamed token — verified by source that `aria-relevant=additions` only fires on new keyed-sibling insertion (`agent-chat.js:582`'s `...all.map((m,i)=>ChatMessage({...m,key:...}))`), not on in-place text mutation within an existing message's subtree during streaming. Also fixed, as a genuinely unrelated hygiene issue surfaced mid-rebase: `test.js`'s `lint-tokens.mjs spacing report` check regexed for the old `[lint-spacing] REPORT — N raw` format, but upstream `v0.0.349`'s "ratcheted spacing lint" consolidation changed the script's own stdout to `PASS — N <= baseline N`, silently breaking the regression check's ability to catch anything post-rebase — widened the regex to match both formats. Kit built+tested (`bun test.js` all pass post-fix), rebased cleanly onto `v0.0.348`/`v0.0.349` (one dist-only conflict, resolved by rebuilding `dist/247420.js` fresh rather than hand-merging generated code — the standing discipline). Kit pushed `8436f0a`→`f81f93d`, all 3 kit CI checks green (ci/Publish/Deploy-GH-Pages). agentgui re-vendored both dist files, browser-witnessed live on `localhost:3009/gm/` (`bodyLen:19429`, `hasAgentgui:true`, 0 console errors, `.agentchat-thread` confirmed via `page.evaluate` to carry `role=log aria-live=polite aria-relevant=additions`), pushed `e84cf26`→`639b78e`, all 4 CI checks green (Test/Publish-and-Release/Auto-Declaudeify/Deploy-GH-Pages) — the `Test` job's `bun install` step took an unusually long ~13 minutes this run (likely npm-registry propagation delay for the just-published kit version) before completing green; not a hang, just slow.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-fifth run
-
-Third docstudio-cue pass: 5 new candidates landed (ChatComposer streamingSince elapsed counter, coarse-pointer Enter-gating, CountdownDialog, PermissionMenu, detectAttachment badge). Full detail in rs-learn (recall "agentgui-45th-run-docstudio-full-detail"). Kit pushed `5c0571e`→`1d46202`, agentgui re-vendored and pushed, browser-witnessed clean.
-
-## Docstudio design-cue follow-up (2026-07-17) — forty-fourth run
-
-5 candidates landed (ChatMessage error/onRetry, Avatar primitive, FileSkeleton aria-busy); a mandatory browser witness caught a real syntax-crash from a stray brace. Full detail in rs-learn (recall "agentgui-44th-run-docstudio-followup-full-detail"). Kit pushed `3417592`→`17ee86c`, agentgui pushed `f08f698`, all CI green.
-
-## Docstudio design-cue pass (2026-07-17) — forty-third run
-
-User directive ("docstudio has a much more mature design, take cues from it, all GUI lives in ../design, no overrides here, this project is still very immature") repeated more emphatically than the prior sweep. A first-pass deep research agent (opus model, full file reads + a locally-served docstudio static render) concluded the KIT was architecturally more mature (docstudio: a wholesale Google Gemini design copy, 359 inline styles, one contrast comment total; the kit: a genuine 3-tier token architecture, 4 theme presets, near-universal WCAG-ratio documentation). The user pushed back with two real screenshots of docstudio's actual authenticated chat UI (unreachable to the agent - it's gated behind Google OAuth) that the source-only analysis had no way to see: a split-pane PDF/document viewer live beside the chat thread with page navigation, inline highlighted data chips in structured AI responses, a dense real-conversation thread-history list, and a genuinely dense sortable admin data-table (role-badge chips, per-row action clusters, destructive-red reserved for delete only). **Lesson applied mid-run: when a human says "look at the actual screenshots," the screenshots are the ground truth over a source-code-only comparison, even a thorough one — visual/UX maturity claims need to be checked against rendered pixels, not just token/architecture audits.** Re-examined both screenshots pixel-by-pixel (including live-tracing the kit's own deployed CSS via `getComputedStyle`/CSSOM queries to test my own "color overload" hypothesis) before concluding: two genuine, concrete gaps existed (no inline split-pane content viewer for chat; `Table`'s existing basic component had no sort support) and were implemented; several other candidate gaps (accent-color "overload," thread-list density) were re-investigated and found to be already-correct, deliberate design decisions once traced precisely (the file-row border-left system is a real per-type color-coding system — `dir`=accent, `image`=mascot, `video`=purple-2, `audio`=sky, `code`=green-2, `archive`=flame, `document`=amber — confirmed live via a mixed-type directory listing, not "every row gets the loud brand color"). Kit changes (`design/src/components/{agent-chat,content,shell}.js`, `chat.css`, `src/css/app-shell/kits-appended.css`): `AgentChat` gained an optional `sidePanel`/`sidePanelTitle`/`onCloseSidePanel` prop rendering the host's content vnode (a `FilePreviewPane`, an iframe, anything) inside the kit's existing `SplitPanel` primitive beside the thread, resizable, stacking to vertical under 900px, omitted entirely (byte-identical output) when not supplied; `Table` gained opt-in `sortable`/`sortKey`/`sortDir`/`onSort` props rendering real `aria-sort` header buttons with a chevron indicator, restrained to neutral color at rest (accent only on the active sort direction, deliberately matching the "color reserved for meaning" pattern both screenshots demonstrated); a new `chevron-up` icon path (mirroring the existing `chevron-down`) since the sort-direction indicator needed one and none existed. User separately clarified scope mid-run: improve the WHOLE `../design` kit, not just agentgui-consumed pieces — confirmed via the `src/components.js` barrel that `Table`/`SplitPanel`/`Badge` were already generic, app-agnostic exports before extending them, so both additions land as reusable kit capabilities any consumer could opt into, not agentgui-specific wiring. Kit built+tested (`bun test.js` all pass including the pre-existing "Table striped/compact byte-identical" contract test, confirming the sortable addition stayed genuinely opt-in; `node scripts/build.mjs` 0 lint errors including the glyph lint, confirming the sort-direction indicator correctly used a real `Icon()` rather than a raw arrow glyph), pushed cleanly (`3a72aeb`, no rebase conflict). agentgui re-vendored, pushed `254eb74`, all 4 CI checks green. Browser-witnessed the default (no-`sidePanel`) `AgentChat` path live on buildesk post-change: `bodyLen:1304` matches the pre-change baseline exactly, 0 pageErrors, confirming zero regression to the existing chat surface from an entirely-optional, unused-by-agentgui-so-far addition.
-
-## GUI practicality sweep (2026-07-17) — forty-second run
-
-User-driven ask ("setting the cwd is not nearly practical enough... go over every possible aspect of the app's practicality") plus a mid-run docstudio design-cue directive. Started narrow (cwd-setting) and expanded into the widest sweep yet, surfacing a real infrastructure bug and a real kit crash along the way. cwd practicality (`site/app/js/app.js`, `design/src/components/agent-chat.js`, `design/src/components/files-modals.js`): the cwd editor was a bare text input requiring an exact remembered absolute path with no discoverability at all — added an inline browse popover (reusing the existing confined `/api/list`, writing to an independent `state.cwdBrowse` so it never disturbs the Files tab's own state), always-visible allowed-roots chips (prefetched on editor open, not gated behind first clicking "browse"), a small localStorage-backed recent-cwd MRU (`CWD_RECENT_KEY`, capped at 6), relative-subpath resolution against the current cwd (`onCwdSave`/`debouncedCwdProbe` both resolve a bare name like `myproject` against `state.chatCwd`), and fixed a real bug where Escape did nothing to close the cwd editor (the global keydown handler's typing-guard blurred the focused input and returned before ever reaching the Escape ladder — added a targeted exception plus a nested browse-popover-then-editor ladder). History's directory `SessionMeta` fact gained the same one-click "use as chat cwd" action Files already had (kit `SessionMeta` gained a generic `onAction`/`actionLabel`, alongside the existing `onCopy`). **Real infrastructure bug found+fixed** (`lib/http-handler.js`, `site/app/js/backend.js`): the new cwd browse popover inherited an existing, previously-undiscovered production bug — this env's nginx `proxy_pass` URI normalization silently collapses an encoded `%2F` path-segment slash back into a literal `/` before forwarding, so any `/api/list/<abs-path>`-shaped request from a path SEGMENT lost its leading slash and 403'd, which also meant the **pre-existing Files tab's own drill-down navigation had been broken in production this whole time**, not just the new picker. Fixed by switching `/api/list`, `/api/stat`, `/api/file`, `/api/download`, `/api/image` to a `?dir=`/`?path=` query param (immune to that proxy normalization) via a new shared `resolveConfinedPath()` helper, keeping the legacy path-segment form for compatibility. `scripts/validate-mutations.mjs` (29 checks) confirmed the confinement contract is byte-identical before/after. Files/completion sweep (`gui-completion` workflow wf_bcf46a89-739, 29 agents, 28 done/1 lens crashed on a StructuredOutput retry cap, 17 confirmed findings): rename/mkdir 409 collisions now prefill a suggested alternate name (`suggestAlternateName`, "name"→"name (2)"→"name (3)"); bulk-move destination gained a one-click roots picker (kit `PromptDialog` gained an optional `roots`/`onPickRoot` prop); **delete is now soft** — moves into a confined per-root `.agentgui-trash/` instead of unlinking (`moveToTrash`/`restoreFromTrash`, new `POST /api/restore`, 10-minute retention with purge-on-delete + a 200-entry eviction cap) with a real undo toast, not just the pre-existing confirm-before dialog; search-hit event anchors (`focusEventI`/`focusEventTs`) are now carried in the URL hash (`ets=`) so reload/Back reproduces the same scrolled+flashed position a live click gives, previously lost; Settings gained a scroll-position scrollspy (manual scrolling now updates `state.settingsSection`/the URL, previously deep-link-in only); truncation confirm banners now state the actual turn count + cost about to be discarded instead of "the later turns"; the cross-tab "reload it" banner now warns about + confirms discarding an unsent draft; History event list gained persistent next/prev error navigation (`jumpToNextError`), not just jump-to-first; the History session header now shows agent/model (reading `sess.model` directly — a first attempt reading a nonexistent `sess.agent` field silently rendered nothing, caught and corrected); `backend.js` exported `onSessionExpired()` but nothing ever subscribed to it — a mid-session 401 failed every fetch completely silently; now surfaces a persistent "Session expired, reload to sign in again" banner; the offline banner gained a manual "retry now" button; search-term highlighting now extends into expanded event bodies (`Row`'s `detail` field), not just the collapsed title; History search results gained an export button (JSON of title/project/snippet/timestamp/sid); Settings gained a `navigator.storage.estimate()` browser-storage breakdown. **Real kit crash found+fixed mid-implementation**: an initial attempt to add the search-results export button by passing a VElement (or an extra `captionAction` prop) through `ConversationList`'s `caption` prop caused an intermittent webjsx "Cannot read properties of undefined (reading 'key')" page crash — root-caused by tracing `caption`'s only other use site (`aria-label: caption || 'Conversations'`, which needs a plain string) and confirmed via 3 independent before/after browser runs (crash present with the VElement version, absent 3/3 times after reverting). Re-implemented as a fully separate sibling element outside `ConversationList` entirely (`.agentgui-search-rail-wrap`, replicating `.ds-sessions`' own flex-column layout), re-verified crash-free across 3 more independent runs. docstudio design-cue pass (a fresh subagent surveyed `/config/docstudio`'s vanilla-ESM Material/Gemini-styled chat UI against the kit): docstudio turned out architecturally LESS mature than the kit in every systemic dimension (typography scale, color tokens, spacing, motion) — the 6 concrete candidate cues it found were mostly already-implemented (streaming caret, soft-tint error bubbles, dark-aware skeleton shimmer, filled-contrast destructive dialogs, suggestion-chip semantics — inapplicable here since agentgui's chips send-immediately rather than fill-then-edit) except session-group eyebrow labels, which were using the generic `--tr-caps` tracking token instead of the more emphatic `--tr-label` token `.t-label`/`.t-micro` already establish as the canonical section-eyebrow convention — fixed both `.ds-session-group-label` and `.ds-dash-group-label`. Two upstream-diverged rebases handled cleanly mid-session (one single-conflict, one 35-commits-diverged including new upstream a11y/motion/visual-regression work) by rebuilding `dist/` fresh from merged sources per the standing discipline rather than hand-merging generated code — `bun test.js` confirmed 0 regressions both times. Kit pushed `7c27e9c`→`fb11176`→`acd5fd2` (three pushes across the run's phases), agentgui pushed `71d7352`→`56b865f`→`2fecd75`→`a1a394a`, all CI green throughout. **Standing lesson: a kit component prop with an established narrow contract (here, `ConversationList`'s `caption` being read as `aria-label: caption || 'Conversations'` elsewhere in the same function) can silently break when a caller passes a richer value (a VElement) than the prop was ever designed for — the failure surfaces as a webjsx "reading key" crash far from the actual mismatch. When extending what a caller passes through an existing prop, grep every OTHER use site of that prop inside the component first, not just the one you're touching.**
-
-## GUI logic+predictability sweep (2026-07-12) — forty-first run
-
-`gui-logic-predictability` workflow wf_c645ba95-c6a (23 agents, 192 tool calls, 0 errors) — 10 confirmed findings, all implemented, plus one real kit bug found and fixed mid-verification (not from the workflow's own hunt). App (`site/app/js/app.js`): `runningPanel()`'s title read `'running · N'` with no scoping cue even though the panel always lists every in-flight session app-wide, not just ones related to the current chat — retitled `'all running sessions · N'`, and it now appends `'(refreshing…)'` while a backgrounded tab's poll is catching up after refocus (`refreshActive()` sets a `state._activeStale` flag while `document.hidden` skips the network call, cleared on the next real response) instead of silently painting stale data as fresh. `runningRowTitle()` fell straight to `UNTITLED_CONVERSATION` for a brand-new session with no index row yet, while the Live dashboard's `computeLiveSessions()` already had a 3s "indexing…" carve-out for the identical case — the same session read two contradictory identities in the same 0-3s window depending only on which panel you looked at; gave `runningRowTitle` the matching carve-out. Live dashboard cards sorted by `elapsed`/`activity` re-sort on every tick (both are continuously-changing values), which could reorder a card out from under a mid-click pointer (selecting a checkbox, clicking stop) — added a module-level `_livePointerDown` flag (set/cleared on document `pointerdown`/`pointerup`/`pointercancel`) that freezes the sort to the last-computed sid order while a pointer is held anywhere in the dashboard. agy's real `--continue` resume path (wired last run) had no composer disclosure the way claude-code's resume banner does — added a `'continues most recent conversation'` composerContext bit for agy past its first turn. History's `ConversationList` sessions mapper hardcoded `agent: undefined` while the Running-panel/Live-dashboard rows for the identical finished-vs-in-flight session both show an agent/model badge — traced to ccsniff's `Store.sessions()` never folding per-event `model` into the session record even though `flattenEvent` captures it; fixed upstream (see below) and wired `agent: agentById('claude-code').name + ' · ' + s.model` into the mapper (ccsniff only reads Claude Code's own JSONL, so the agent is always constant). Kit (`design/src/components/{chat,content}.js`, `design/chat.css`, `design/src/components/sessions.js`): per-message chat copy action (`ChatMessage`'s generic `actionRow`) had zero visible click feedback for sighted/mouse users — only an `aria-live` `announce()` — unlike the three sibling copy patterns already in the same file (code-block copy, `CodeNode`/`ToolCallNode` copy) which all self-manage a label/icon flip to "copied" for 1.6s; added the matching flip keyed off `a.label === 'copy'`. Follow-up chips (contextual, derived from the last turn) and empty-state seed chips (generic starter ideas) shared identical DOM shape/class with zero visual signal distinguishing them — `.agentchat-followup` gained a dashed border (same pill shape/size, no new color/shape language). `flashComposerNote`'s single shared DOM node silently overwrote an unread note if a second call landed before the first note's 2.6s timeout — now queues notes and drains them in order instead of dropping the first message. `SessionDashboard`'s filter `SearchInput` never forwarded `resultCount` to its `aria-live` region (the Live dashboard's own filtered session count was available but unused) — wired it through. **That last change surfaced a real, previously-latent kit bug independent of this run's own hunt: `SearchInput` (`design/src/components/content.js`) conditionally returned either a bare `<input>` VElement or a wrapping `<span>` VElement depending on whether `resultCount`/a clear button were present that render — since `resultCount` now toggles from `undefined` to a string as the Live filter's value changes, webjsx's `applyDiff` tried to morph one element type into another at the same keyed toolbar slot, producing a corrupted merged DOM node (a real `<select>` picked up `type=search`/`name=q`/`placeholder=...` attributes from the `SearchInput` render, and the actual `<input>` vanished entirely) — live-witnessed on buildesk before the fix (`hasInput:false` on the toolbar). Fixed by always returning the `.ds-search-input-wrap` shape (confirmed `display:contents` in CSS, so it's layout-transparent and safe for every existing call site).** ccsniff (separate repo, `github:AnEntrypoint/ccsniff#main`, cloned fresh to `/config/workspace/ccsniff-work`): `Store.sessions()` (`src/store.js`) folded in the most-recent-by-timestamp `model` per session (events aren't guaranteed in ts order since JSONL is read file-by-file); `index.js`'s assistant-event ingestion never actually populated `model` on pushed content blocks (only `system`/init events carried `e.model`) — real Claude Code JSONL carries the actually-used model at `message.model` on every assistant turn, so that's now inherited onto every block from that message. `node test.js`: ALL TESTS PASS both commits. Pushed `11f6c3b` then (after a remote-advanced rebase) `26bbfcc`/`beff5e7`, ccsniff CI (Publish/Auto-Declaudeify/Deploy GH Pages) green both pushes. Kit built+tested twice (once per round of edits — findings, then the SearchInput fix), re-vendored both times. Reinstalling the ccsniff dependency required removing `bun.lock`'s pinned commit hash entirely (`bun install ccsniff@github:...#main --force` alone kept resolving to the stale pinned sha even after a `rm -rf node_modules/ccsniff`) — deleting `bun.lock` and re-running `bun install` re-resolved `#main` to the actual latest commit. The local buildesk server process needed an explicit restart (`kill -TERM` on the `bun server.js` PID) for the new `node_modules/ccsniff` to load — Node/Bun caches modules in-process, so an npm/git dependency swap under a running process is invisible until restart; the env's custom Node supervisor (`/opt/gmweb-startup`, not a standard supervisord) auto-respawned it within ~20s of the health-check failing, re-launching via `bunx agentgui@latest` which correctly resolves to the local workspace's own `bin/gmgui.cjs` in this workspace-linked setup (confirmed by the "Workspace mode: skipping npm version checker" startup log line), not the published npm package. Browser-witnessed every finding live on buildesk: `.ds-dash-toolbar` filter input/select intact before AND after typing with the corruption fixed, `aria-live` region reading `'0 results'`; `.chat-msg-action.is-copied`/`.agentchat-followup` CSS rules present in the live CSSOM; History rail rows reading `'agentgui · 3s ago · Claude Code · claude-sonnet-5'` (18/18 sessions carrying a real model after the ccsniff fix + server restart); synthetic `pointerdown` dispatch confirmed no page error from the new listener. 0 pageErrors throughout.
-
-## GUI logic+predictability sweep (2026-07-12) — fortieth run
-
-11 confirmed findings (Escape-ladder confirmingClearData gap, wsCall 15s timeout, agy resume wiring, composer paste/drop visible feedback, Row `.title` tooltip, `.ds-file-actions` resting opacity, Enter-to-send hint visibility). Full detail in rs-learn (recall "agentgui 40th run logic-predictability sweep"). Standing browser-witness gotchas confirmed there still bind: combine creds+goto+wait+evaluate into ONE dispatch (session ids rotate across separate dispatches), and read via `console.log('WITNESS:'+...)` + stdout grep, never the `capture` prefix's `result` field.
-
-## GUI logic+predictability sweep (2026-07-12) — thirty-ninth run
-
-6 confirmed findings (runningRowTitle identity prefix, stopActiveChat 9s stuck-stopping timeout, live-session cost tally, shortcuts-help IconButton, CodeNode selection-guard parity, Row.sub tooltip). Kit pushed `00dae4c`, agentgui pushed `64f4466`. Full detail + the setHTTPCredentials comma-password witness fix in rs-learn (recall "agentgui 39th run full detail").
-
-## GUI logic+predictability sweep (2026-07-12) — thirty-eighth run
-
-`gui-logic-predictability` workflow wf_186e2a2a-dfc (32 agents, 205 tool calls, 0 errors) — 18 confirmed findings, all implemented, re-running the same lens one cycle after the 37th run to catch residual/newly-introduced gaps. App (`site/app/js/app.js`, `site/app/js/backend.js`): `stopAllActive` now clears every attempted sid (both ok and failed) from `state.live.stopping` after `Promise.allSettled`, so a failed bulk-cancel is retryable instead of leaving that row's stop button permanently disabled; `copyText`'s clipboard-write catch now calls `announce('copy failed')` instead of swallowing the error silently (mirrors `copySid`'s existing pattern); search-result row titles now route through `projectLabel()` (`r.snippet || projectLabel(r.title) || projectLabel(r.project) || UNTITLED_CONVERSATION`) matching the rail's contract; the History detail header's title-fallback chain gained `|| state.selectedSid` before the generic label, so a metadata-sparse session shows the same identity in History as it does in the rail; the Live nav-badge error flame no longer goes stale while off the history tab (stream stays connected whenever `state.active` is non-empty); `computeLiveSessions()` gained a 5s `reconnectGraceUntil` window so an SSE reconnect mid-session no longer flaps a running session's status to stale; a brand-new session between the `chat.active` poll and history-index catch-up now shows `'indexing…'` instead of reading identically to a permanently-failed lookup; the Live dashboard's sort/filter prefs (`hydratePrefs()`) now reconcile across browser tabs on focus/visibilitychange, alongside the existing `refreshActive()` call; `streamHistory`'s EventSource (`backend.js`) gained manual close+reopen exponential backoff (500ms start, doubles, capped 30s, resets on `hello`) mirroring the WS client's `scheduleReconnect`, instead of relying on native EventSource's uncapped retry; the sessions rail empty-state and History event-list both gained next-action affordances (a start-from-chat CTA, and a "load all (N hidden)" button for very large sessions); a draft restored from localStorage now surfaces a one-time note that undo history doesn't carry over a reload. Kit (`design/src/components/{agent-chat,chat,content,sessions}.js`, `app-shell.css`): follow-up suggestion chips' container lost its `aria-hidden="true"` — the chips are real interactive `<button>`s that were completely invisible to screen-reader users despite `role="group"` being present; `MdNode`'s markdown-settle `refSink` now defers its `innerHTML` swap via a one-time `selectionchange` listener when the user's active text selection is anchored inside the element (was wiping any in-progress text selection every streaming tick); `ChatComposer`'s paste handler now surfaces a "pasted N characters" note via `flashComposerNote` for large plain-text pastes; `SearchInput` gained a visible clear (X) button (was Escape-only, undiscoverable to mouse/touch users) at a 44px touch target, sharing the same clear path as Escape; `ConversationList` now forwards a `resultCount` prop through to `SearchInput`'s existing (previously unpopulated) `aria-live` result-count region, wired from agentgui's search-results branch as `hits.length + ' result(s)'`. Kit built+tested (`bun test.js` all pass), a concurrent upstream release (`5cdd667`, v0.0.315) required a rebase with one dist-only merge conflict (resolved by rebuilding `dist/247420.js` fresh from the merged sources rather than hand-merging generated code), re-vendored, browser-witnessed live on buildesk (chat tab shows `connected` status + visible follow-up chip buttons, history tab loads 52 conversations cleanly, 0 visible errors across both screenshots). Kit pushed `bed4036`, agentgui pushed `159030f` (after a second push-rebase for a PRD-state-only commit), all 4 CI checks green both repos. **New tool defect this run (recorded, not fixable from this repo — filed as `blockedBy:external`): the `gm browser` verb's `dom=` and `capture` prefixes both throw `ReferenceError` (no `document`/page binding at all) rather than evaluating in page context — a regression beyond the 37th run's already-documented "`dom=` ignores its trailing script" caveat. Only `screenshot=` and `url=<target>\n<literal-non-DOM-expr>` dispatches actually reach the real page in this tool version; browser sessions also silently rotate ids across dispatches with no state carryover, and one dispatch hit a dead extension-bridge session requiring an unprompted CDP relay restart. Screenshots are the reliable fallback for browser witnessing until this is fixed upstream in gm-plugkit/playwriter.**
-
-## Punch-list document cleanup (2026-07-12) — 37th-run confirming pass
-
-Removed 11 standing `PUNCHLIST-*.md`/`AUDIT-PUNCHLIST.md` files (all findings already merged, content duplicated AGENTS.md). Full detail in rs-learn (recall "agentgui 37th run punchlist cleanup detail"). **Standing rule for future sweeps: no new `PUNCHLIST-*.md`/`AUDIT-PUNCHLIST.md` (or similarly-named) file should be checked into the repo as a durable artifact — a workflow's punch-list is a transient working document for that run's synthesis step; the run's outcome belongs in AGENTS.md (or drains to rs-learn), never a standing file.**
-
-## GUI logic+predictability sweep (2026-07-12) — thirty-seventh run
-
-`gui-logic-predictability` workflow wf_5eec2403-09d (30 agents, 6 hunt lenses + verify + synthesize, 0 errors) — 15 confirmed findings, all implemented. App (`site/app/js/app.js`): `stopActiveChat` no longer leaves the per-card stop button permanently stuck on a failed cancel (deletes the sid from the stopping Set + surfaces an error on rejection instead of swallowing it); Files dialogs (rename/delete/mkdir/bulk) now restore keyboard focus to the triggering element on close, mirroring the existing cwd-edit pattern; `runBulkDelete`/`runBulkMove` gained the same stale-dialog guard `runFileMutation` already had; the "Untitled conversation" fallback consolidated to one `UNTITLED_CONVERSATION` constant (3 call sites had drifted casing); the settings db health chip now reads `connected`/`offline` instead of a third `online`/`offline` register, matching the adjacent connection chip; history search placeholder/caption now discloses it searches all projects' titles+messages; `runningPanel()` shows a lightweight "will also appear in live" hint during the send-to-active-poll gap instead of returning null; `computeLiveSessions()`'s external-session stale threshold no longer silently multiplies `STALE_AFTER_MS` by an undocumented 0.6 (owned and external sessions in the same objective state now report the same status); pasted/dropped composer files upload through the existing confined `PUT /api/upload-file` and insert the resulting path into the draft (was a permanent no-op/dead-end toast); the sessions rail's 60-item cap gained a load-more affordance (`state.sessionsLimit += 60`), mirroring the existing `eventsLimit` "load older" pattern; `PERSIST_MSG_CAP` truncation now surfaces a dismissible banner instead of silently dropping older turns from localStorage. Kit (`design/src/components/{chat,agent-chat,content,files,sessions}.js`, `app-shell.css`, `chat.css`): deleted dead `onAttach`/`onMenu` composer toolbar plumbing (no such feature existed); `AgentChat` now forwards `onEmoji` to its internal `ChatComposer` call (the emoji toolbar button was invisible because `AgentChat` — the wrapper agentgui actually calls, not `ChatComposer` directly — never destructured the prop; caught mid-EXECUTE via a `transition to=PLAN` re-scope); `SearchInput` and the Files filter input both gained Escape-to-clear + a visually-hidden `aria-live` result-count region; `ConversationList` gained `hasMore`/`onLoadMore`; composer textarea `overflow-y` changed from focus-only `auto` to always-`auto` so a capped-height composer keeps its scroll cue after blur. Kit built+tested (`bun test.js` all pass, all build lints pass), re-vendored, browser-witnessed live on buildesk across chat/history/settings/files (0 blocking errors on clean navigations). Kit pushed `af028ff`, agentgui pushed `a3b844d`, all CI green both repos. **Standing gotcha reconfirmed: this env's `gm browser` verb text-protocol (`dom=<selector>\n<script>`) only evaluates the selector query, not the trailing script — use `dom=<precise-selector>` alone to inspect attributes/rect, not as a general page-eval channel. Also: embedding Basic-Auth creds directly in a `page.goto` URL (`https://user:pass@host/...`) breaks the app's own same-origin `fetch()` calls with "Request cannot be constructed from a URL that includes credentials" — do one embedded-creds navigation to seed the browser's per-origin Basic-Auth cache, then navigate again WITHOUT embedded creds (plain URL or `?token=`) for any witness that needs real fetches to succeed.**
-
-## GUI AI-tell sweep (2026-07-10) — thirty-sixth run
-
-Follow-on to the 35th run's AI-tell sweep (commit 1702fa8). `gui-ai-tell-sweep` workflow wf_a53b7d8f-27b (26 agents, 25 done/1 verify-agent hit a mid-response connection error, 200 tool calls): 5 hunter lenses (gradient-glow-glass, emoji-generic-icons, oversaturated-color, boilerplate-copy, layout-uniformity-tells) found 20 candidates, adversarial verify confirmed 11 (9 correctly refuted as already-deliberate — status-disc pulse triplicate, `--sun` "retired" claim, radius-scale uniformity — the kept-typography-style guard doing its job on non-typography claims too). Landed in the kit (`design/app-shell.css`/`chat.css`/`src/components/agent-chat.js`): hardcoded one-off context-menu/toast shadow → `var(--shadow-overlay)` token; three data-metering fills (barchart/upload/bar) demoted from the loudest acid-lime `--accent` to neutral `--fg-3` (color reserved for state, not routine progress); checkbox checked-fill `--accent`→`--fg`; drag-over collapsed from a triple accent stack (tint+border+ring) to a single dashed border; the keyboard-only `.skip-to-main` link de-loudened from CTA-accent to neutral ink (it was visually identical to the primary send button despite being invisible to sighted users); session-unread dot neutralized off `--accent` so it stops competing with the active row's accent; dead template-shaped `.empty-state` child rules and an unused `.ds-panel-trio`/`.ds-panel-grid` hover-lift block deleted; AgentChat empty-state copy de-boilerplated away from "invitation" framing. App: `keyboardPanel()`/`preferencesPanel()` gained `kind:'wide'` so settings' purely-informational/utility panels read lighter than the consequence-bearing backend/agents panels. Kit rebuilt+re-vendored, browser-witnessed live (0 pageErrors, all 4 sampled CSS rules confirmed post-fix in the real CSSOM). Kit pushed `4de1771` (after a rebase — a concurrent version-bump commit had landed), agentgui pushed `e6dc1d9`, all CI green both repos. **Tool-defect note (recorded, not re-fixed — the workaround is durable): the gm-plugkit `fs_write` verb's payload key is `content` (a JSON string), not `body` — passing `{path, body:{...}}` silently no-ops with `bytes:0` and no error, which nearly let a stale/empty `.ci-validated` marker slip through this run; caught via `recall` mid-VERIFY and corrected before COMPLETE.**
-
-## GUI ux-craft sweep (2026-07-10) — thirty-fourth run
-
-`gui-ux-craft` workflow wf_919164f1-648 (34 agents, 0 errors) + a parallel live-browser negative-space audit. Full detail in rs-learn (recall "agentgui 34th run ux-craft sweep"). Headline: negative-space audit came back **clean** for the 3rd consecutive run (31st/33rd/34th) — future sweeps should shift focus to interaction-level polish instead of re-running that lens. Kit: `--fs-2`/`--fs-0` shadow font tokens didn't exist in the real scale (silently fell back to hardcoded px, decoupled from `[data-typescale]`) — remapped to `--fs-lg`/`--fs-tiny`; stale `--lh-base` fallback (1.4, should be 1.55) fixed; ~29 more hardcoded focus-ring `outline:2px solid var(--accent-ink)` instances tokenized; `.chat-tool-copy` gained the coarse-pointer 44px touch target; `.ds-select` gained a base `min-height:32px` floor; `Btn`'s `className` prop renamed to `class` to match `Panel`/`Heading`; `AgentControls`/`AgentChat` gained an `agentsLoading` state. App: History no longer falls back to the raw session id (cwd/"Untitled conversation" instead), ACP error copy truncated+prefixed. Kit pushed `3b1080c` (after a rebase — a concurrent release commit had landed), agentgui pushed `9c8094b`, all CI green both repos.
-
-## GUI ux-craft sweep (2026-07-10) — thirty-third run
-
-34-agent workflow, 21 confirmed. Full detail in rs-learn (recall "agentgui 33rd run ux-craft sweep"). Kit pushed `4105bd1`, agentgui pushed `3bac0fe`. **Standing lesson: a new kit component must be re-exported through `src/components.js`'s barrel to be consumable — adding it to a component file alone leaves it invisible to the built bundle even with 0 lint errors; grep the built dist for the export name before wiring the app against it.**
-
-## GUI ux-craft sweep (2026-07-10) — thirty-second run
-
-35-agent workflow, 22 confirmed. Full detail in rs-learn (recall "agentgui 32nd run ux-craft sweep"). Kit pushed `ad000b6`, agentgui pushed `5ccaa8a`. **Standing gotcha: this env's `PASSWORD` value can itself contain literal commas (e.g. `123,slam,123,slam`) — treat the whole string as one token, never comma-split it when testing auth.**
-
-## Light-theme contrast + maximal usability sweep (2026-07-10) — thirty-first run
-
-Full detail in rs-learn (recall "agentgui 31st run light-theme-contrast" and "agentgui 31st run maximal usability sweep"). Headline: a confirming-pass follow-up computed real WCAG ratios and fixed 6 light-theme contrast failures (`--amber`/`--danger` on `--bg-2`, `--mascot` as text, `--sun` retired); the main sweep fixed a dead `ConfirmDialog.destructive` prop, settings-panel spacing drift, misapplied `.lede` in history empty-state, and copy-tone/perf items. Kit pushed `df04d69`/prior, agentgui pushed `03002cf`. **Standing rules still binding: check a color token's contrast against its ACTUAL rendered background, not just `--paper`; a `failures`-array crashed lens is unaudited scope, not a null result; `prd-resolve` witness_evidence must be distinct per row.**
-
-## Sessions-rail selection dead-click fix (2026-07-03) — thirtieth run
-
-Fixed non-chat-tab clicks in the persistent sessions rail being dead clicks (loaded state, no visible navigation). Standing rule: a keepXTrack-mounted component's interaction must produce the same visible effect on every tab it appears on. Full detail in rs-learn (recall "agentgui 30th run sessions-rail dead-click").
-
-## Mobile sessions-drawer sliver fix (2026-07-03) — twenty-ninth run
-
-Scoped negative-space/attention follow-up (not a full agent fan-out) to the explicit "looks very diy" feedback. Live-browser screenshot + DOM measurement at 420px found a real regression the prior two runs' screenshot audits missed: the closed `.ws-sessions` drawer left a ~35px sliver visibly overlapping the chat content on mobile. Root cause in `../design` `app-shell.css`: the `<=1100px` breakpoint's closed-state `transform: translateX(-110%)` assumes the drawer's `left` is `0`; the `<=900px` breakpoint then shifts the drawer's `left` to `var(--ws-rail-w-collapsed)` (60px) so it sits right of the icon-only rail, but never adjusted the closed-state translate to match — `-110%` of a 248px-wide drawer is only -272.8px, undershooting the needed -308px (left + width) by ~35px. Fixed by overriding the closed-state transform inside the 900px block: `translateX(calc(-100% - var(--ws-rail-w-collapsed)))`, which scales correctly with both the drawer width and the rail offset. Verified via `getBoundingClientRect` before (x:-212.8, rightEdge:35.2 — visible) and after (x:-248, rightEdge:0 — fully clear) plus before/after screenshots. **Standing rule: any drawer/overlay whose `left`/`inset` changes across breakpoints must re-derive its closed-state transform from that breakpoint's own offset — a transform tuned for one breakpoint's geometry silently breaks at the next if the offset shifts underneath it.** Kit pushed `76b2bac`, agentgui pushed `4bb9f3f`.
-
-## Visual-polish pass — shell depth, composer weight, chat gutter (2026-07-03) — twenty-eighth run
-
-Screenshot audit fixed 3 "looks very diy" causes: `.ws-sessions` flat `--bg` (should match `.ws-rail`/`.ws-pane`'s `--bg-2`), `.chat-composer` zero elevation (`--shadow-1`), `.agentchat` zero inline gutter under `mainFlush`. Standing rule: `.ws-rail`/`.ws-sessions`/`.ws-pane` must all three use `--bg-2`. Full detail in rs-learn (recall "agentgui 28th run visual-polish"). Kit pushed `53c8464`, agentgui pushed `42708ea`.
-
-## Negative-space + attention sweep (2026-07-03) — twenty-seventh run
-
-Scoped live-browser review (chat/files/settings, 1280px+420px); fixed a clipped Files filter placeholder and a misapplied `.lede` styling 4 settings facts as oversized paragraphs. App-only, pushed `b0b38fb`. Full detail in rs-learn (recall "agentgui 27th run negative-space-attention detail").
-
-## Per-row file move + lint tooling fix (2026-07-02) — twenty-sixth run
-
-Single-file move action on `FileRow` reusing the bulk-move dialog; fixed a `lint-null-children.mjs` bracket-matcher bug (apostrophes in `//` comments corrupted bracket-depth tracking). Full detail in rs-learn (recall "agentgui 26th run file-move-lint-fix").
-
-## Mid-thread retry (2026-07-02) — twenty-fifth run
-
-Retry ungated from last-message-only to every settled assistant turn, with truncate-and-resend + `resumeSid` clearing shared via one `executeTruncateAndResend()` path. Full detail in rs-learn (recall "agentgui 25th run mid-thread-retry").
-
-## GUI completion sweep (2026-07-02) — twenty-fourth run
-
-`gui-completion` workflow wf_4a731841-832 (33 agents, 17 confirmed). Landed 5 smaller-scope findings (live-tab dashboard state persistence, shortcuts overlay FocusTrap, history copy-when-collapsed, settings re-check affordance) plus a CSRF-regression-test gap (a test's `Authorization` header accidentally matched the wrong threat model). Full detail in rs-learn (recall "agentgui 24th run GUI completion sweep"). Pushed `d3e2d1e`.
-
-## GUI perceived-performance sweep (2026-07-02) — twenty-third run
-
-Landed the 22nd-run's deferred perceived-perf findings (modulepreload for markdown CDN modules, "checking…"/"loading…" in-flight states instead of "unknown"/"0/0"); first-render network-gating re-scoped, not dropped. Full detail in rs-learn (recall "agentgui 23rd run perceived-performance sweep"). agentgui pushed `6a045ba`.
-
-## GUI ux-craft sweep (2026-07-02) — twenty-second run
-
-35-agent audit, 20 confirmed. Accent-on-paper contrast fix (`--accent`->`--accent-ink` for text/fills), typography-rhythm parity fixes, theme-flash-prevention script in index.html. Full detail in rs-learn (recall "agentgui 22nd run ux-craft sweep").
-
-## GUI cohesion sweep (2026-07-02) — twenty-first run
-
-25-agent audit, 12 confirmed. WorkspaceRail attention-dot tone, WorkspaceShell keepSessionsTrack (stable column count across tabs), mobile drawer focus-trap, ConversationList richer status, ContextPane recentFiles panel. **Standing rule: commit and push any inherited uncommitted work found dirty in the tree BEFORE starting new work at PLAN entry — never leave it stranded under a fresh, disjoint cover.** Full detail in rs-learn (recall "agentgui 21st run cohesion sweep").
-
 ## CRITICAL — ACP is managed ONLY by `lib/acp-sdk-manager.js`
 
-Twentieth run deleted a redundant eager-spawn `lib/plugins/acp-plugin.js` (conflicting ports, no restart logic, crashed boot on a missing binary). Rule: ACP lifecycle lives in `lib/acp-sdk-manager.js` alone; every `spawn()` callsite needs a `proc.on('error', …)` handler (ENOENT surfaces async under Bun). Full detail in rs-learn (recall "agentgui 20th run ACP redundant manager").
-
-## GUI quality sweep (2026-06-19) — nineteenth run
-
-132-agent workflow wf_8183560b-e3d (12 lenses, 93 confirmed). Kit: thinking settled state, retry on non-last message, AT aria fixes (followup chips live guard, cwd focus restore, skip-link target, sessions toggle chevron, shell print styles, a11y-01 index.html), composer disabled visual state, files-modals focus trap re-query + stable aria-labelledby, sessions.js listbox+aria-selected. App: resume-transcript-load (loadResumeTranscript historical messages + spinner), ACP force-restart (unhealthy agent restart btn + WS handler), history tool_use rail=purple, shortcuts overlay role=dialog, streaming-active badge on chat rail tab, sortedAgents memoized, files filter 150ms debounce, _seen Set capped 5000, humanizeMs->fmtDuration, dead historySide() removed, pathBasename util, ARM_RESET_MS constant, refreshHistory guard, perf-002/006/007/008 memoization+cleanup, live-tokens accumulated, backend-change-mid-chat guard, transcript loading state, session-expiry onSessionExpired hook, server-500 stream error sanitized. Server: IPv4-mapped IPv6 normalization in rate-limit, image route streaming (no sync read), isWindows module-level, getAvailableAgents export removed, files-plugin+workflow-plugin confinement, acp-plugin shell injection fix, plugin-routes CSRF fix, asset-server JS injection fix. Full detail in rs-learn (recall "agentgui 19th run").
-
-## GUI quality sweep (2026-06-19) — eighteenth run
-
-53-agent audit wf_7cd243d2-753 (29 confirmed). Kit: showWorkingTail status=running (was backwards), focus ring 2px+offset, aria-expanded dynamic on sessions toggle, DOMPurify version-pinned, FORCE_BODY, 360px button fill, cwd-btn 44px coarse. App: thinking branch in sendChat loop, saveBackend deep health probe, aria-live guard, O(1) SSE dedupe Set, sessionDuration reduce, tool_use rail flame (purple=subagent rule), ACP vocabulary connected/connecting/disconnected + unhealthy rail flame, skip-link. Server: CORS credentials guard, token masking in logs. Also: history (result)/(tool call) labels, multi-turn preamble for non-resume agents. Deferred: resume-transcript (#3), ACP force-restart (#4). Full detail in rs-learn (recall "agentgui 18th run").
-
-## GUI quality sweep (2026-06-19) — seventeenth run
-
-Two-pass 48-agent audit (wf_bcac251f-d54, 25 confirmed). Critical: absIdx ReferenceError crash in history, Prism new Function → CSP-safe script injection + Promise.all tiers, scrollChatToBottom rAF reflow removed, sessions drawer <=1100px fix, thinking block dispatched. Full detail in rs-learn (recall "agentgui 17th run").
-
-## Design-maturity sweep + dead-code + secret-hardening (2026-06-18) — sixteenth run
-
-54-agent workflow gui-design-16 (wf_6479308b-24f, 12 lenses, 40 confirmed). SECRET_RE extended to upload/mkdir/rename/list; RFC-5987 Content-Disposition; dead vendor/cdn/ 36 files + harvest-fixtures + CI copy-vendor lines removed. Full detail in rs-learn (recall "agentgui 16th run").
-
-## Design-maturity sweep + dead-code + server-hardening (2026-06-18) — fifteenth run
-
-Two Workflows: gui-design-15 (wf_7ba315a1-9a9, 8 lenses, ~95 agents total) + gui-design-15b (wf_5b2861b2-717, 3 lenses). ShortcutList + Row.detail kit exports; static/ dead-code removed; terminal RCE fix; CSP nonce; constant-time token compare. Full detail in rs-learn (recall "agentgui 15th run").
-
-## Design-maturity sweep + marketing-site consolidation (2026-06-18) — fourteenth run
-
-`site/theme.mjs` (marketing renderer, NOT the SPA) was the last design residue -> migrated to a NEW kit `marketing.css` `.site-*` family; `Panel`/`Heading` gained a `class` prop; `Btn({primary})`->`Btn({variant:'primary'})`. Workflow `gui-design-14` (`wf_50751bd9-a43`, 7 lenses) 46 agents -> 28 confirmed, all in the kit (ThinkingNode/markdown-table/status-disc shape channels/shell resizer breakpoints). **Status-disc shape rule: live=solid+pulse, error=solid+halo, connecting=hollow ring, stale=muted solid.** Full detail in rs-learn (recall "agentgui 14th run marketing-site consolidation").
-
-## Design-content consolidation — ALL design lives in the kit now (2026-06-18) — thirteenth run
-
-The mandate's origin: every design decision lives in the kit (`../design`), none in agentgui. `site/app/index.html` lost its ~240-line inline `<style>` (moved to NEW kit `app-surfaces.css`); `app.js` carries zero inline `style=` props. **Rule going forward: no design content in agentgui — new surface styling is a kit CSS rule, never an inline `<style>` or `style=`.** `lint-glyphs` extended with `SCAN_ROOT_FILES` so root bundled CSS no longer escapes the glyph lint. Workflow `gui-design-consolidation.js` (6 lenses) 44 agents -> 19 confirmed. Full detail in rs-learn (recall "agentgui 13th run design-content consolidation").
-
-## CRITICAL — `authedFetch` must NOT set `Authorization: Bearer` behind an nginx Basic-Auth proxy (2026-06-18)
-
-Witnessed on the boxone.off.l-inc.co.za/gm deploy: the page HTML/JS/CSS loaded (browser sends its cached HTTP Basic creds) but every app `fetch()` (`/gm/health`, `/gm/v1/history/sessions`, `/api/*`) returned **401 from nginx**, and the user saw a repeating Basic-Auth prompt. Root cause: `site/app/js/backend.js` `authedFetch` set `Authorization: Bearer <window.__WS_TOKEN>`, which **overwrites** the browser's cached `Authorization: Basic` credentials. nginx `auth_basic` only accepts `Basic`, so a `Bearer` header is rejected at the proxy before it ever reaches agentgui. The WS survived because it auths via `?token=` query on an `auth_basic off` path. Fix: thread the token via the **`?token=` query param** (`withToken()`, exactly like the WS / EventSource / image / download URLs) and never override `Authorization` — the query param coexists with the upstream Basic auth, and agentgui accepts `?token=` on every HTTP route. Rule: **same-origin app auth must never use the `Authorization` header when an upstream proxy may own Basic auth** — use the query param + the `agentgui_token` cookie. boxone runs the published `agentgui@latest`, so this reaches it only after an npm publish + service restart (or via the gmweb nginx `auth_basic off` mitigation on the agentgui-proxied API paths).
-
-## UX-craft sweep + empirical-witness-first (2026-06-11) — twelfth run
-
-6-lens workflow `gui-ux-craft.js` (46 agents -> 40 confirmed, all 58 implemented): live-page-as-debugger caught shipped crashes (SessionDashboard unkeyed-empty-body webjsx applyDiff crash; mobile drawers dead from base-hidden-after-media CSS-order; composer cwd label/text prop-name miss; stale .ds-file-check overlay), staged column yield (pane->drawer 1480 / sessions 1100 / rail 60px-icon 900), PageHeader dense, theme-tuned --flame/--amber AA pairs + 5 --code-* aliases, 32px/r-1 control metric, perceived-perf preloads + synchronous MdNode paint, POST /api/move, FOUR build lints. Full detail in rs-learn (recall "agentgui 12th run UX-craft sweep"). Server on this env runs `PORT=3009` (3000 owned by another app); witness caveats (stale spool out/, expiring browser sessions, git_status stat-cache) also in rs-learn.
-
-## Files command surface + PASSWORD-boot fix (2026-06-11) — eleventh run
-
-Fixed PASSWORD-gated deploys never booting the SPA (static subresources carried no token, `agentgui_token` cookie now set on auth) and made Files a full command surface (multi-select, density modes, bulk delete). Full detail in rs-learn (recall "agentgui 11th run Files command surface PASSWORD-boot").
-
-## GUI screen-real-estate layer (2026-06-12) — fluid columns + drag-resize handles
-
-Fluid-column + drag-resize density layer (workflow `gui-screen-realestate.js`, 50 agents -> 17 gaps). Fixed `--ws-*-w` chrome became fluid `clamp()`; kit `shell.js` `.ws-resizer` separators write persisted inline `--ws-<col>-w`; `.ws-sessions-toggle` desktop collapse; `.btn*` -> `--r-1`; `.app-status` 26px. **Concurrent-writer rule (load-bearing): when origin advances mid-run with the same feature, drop yours and adopt theirs, then re-apply only genuinely-distinct work — never a parallel impl.** Full detail in rs-learn (recall "agentgui screen-real-estate layer").
-
-## GUI Claude-Code-web parity sweep (2026-06-11) — tenth maximum-effort run
-
-Visual/layout/motion parity vs claude.ai/code (workflow `gui-claude-code-parity.js`, 66 agents -> 37 gaps). Flat full-width chat turns (`.chat-msg-flat` at `--measure`), single bordered composer rounded-rect, `.chat-tool` status-toned cards, `WorkspaceShell mainFlush`, command-center `SessionDashboard`, reduced-motion-guarded transitions. **Load-bearing webjsx rule: never pass a conditional `x?h():null` positionally — build the array and `.filter(Boolean)` it; ANY null among VElement siblings crashes `applyDiff` (reading 'key'); `Btn` spreads array children.** Full detail in rs-learn (recall "agentgui 10th run parity").
-## GUI logic+predictability sweep (2026-06-10) — ninth maximum-effort run
-
-78-agent workflow, 67 confirmed findings, all implemented (interaction lifecycles, realtime truth, input ergonomics, scale, consistency). **Escape ladder order: shortcuts overlay > file dialog > confirmingEdit > new-chat arm > stop-arms > stop generation** (still binding - later runs extend the ladder, never reorder it). Full detail in rs-learn (recall "agentgui 9th run logic predictability sweep").
-
-## GUI completion sweep (2026-06-10) — eighth maximum-effort run
-
-Coverage run reversing the prior scope cuts. Workflow `.claude/workflows/gui-completion.js` (6 lenses) -> 46 gaps (`PUNCHLIST-COMPLETION.md`), ALL implemented. Load-bearing remnants: Files is a FULL manager (confined `POST /api/rename,/api/delete,/api/mkdir`, `PUT /api/upload-file`, `GET /api/stat` via `fsAllowRoots()`/`sanitizeEntryName()`; CSRF guard on POST/PUT/DELETE; **run `scripts/validate-mutations.mjs` (17 checks) after touching the mutation surface**). Full hash routing `HASH_KEYS=[tab,sid,dir,file,q,project,section]` (popstate diffs the full set; `navTo(tab,{writeHash:false})`). `editAndResend` clears `resumeSid` on truncation (never --resume a diverged tail). `.ds-session-meta` was taken - the strip is `.ds-session-meta-strip`. One `SHORTCUTS` array feeds the ?-overlay + settings. Live selection Set deliberately NOT persisted (stale sids would arm stop-selected wrongly). Full detail in rs-learn (recall "agentgui GUI completion sweep").
-
-## GUI cohesion sweep (2026-06-10) — seventh maximum-effort run
-
-One-product feel sweep (61 agents -> 40 gaps, `PUNCHLIST-COHESION.md`, workflow `.claude/workflows/gui-cohesion.js`): per-block code copy, FilePreviewPane split view, SessionDashboard sort/filter/stale/stop-selected, stableFrame, one canonical `.status-dot-disc`, confined `/api/download`, per-entry `permissions`. Full detail in rs-learn (recall "agentgui GUI cohesion sweep 7th run"). Standing rule: **the app.js `C` destructure MUST list every kit component it calls** (a witness caught `Icon is not defined`).
-
-## GUI predictability + polish sweep (2026-06-05) — fifth maximum-effort run
-
-Superseded/extended by the 7th run. Load-bearing survivor: `confineToRoots()` in `lib/http-handler.js` applies `fs.realpathSync` re-confinement on `/api/list`, `/api/file`, `/api/image` — symlink-escape fails closed. Full detail in rs-learn (recall "agentgui-fifth-run-polish-detail").
-
-## Claude-Desktop redesign + embedding fix (2026-06-05) — fourth maximum-effort run
-
-Shipped the three-column **WorkspaceShell** + **WorkspaceRail** (kit `shell.js`, `.ws-*` in `app-shell.css`, collapse persisted `localStorage ds.ws.{rail,pane}`), the shared **ConversationList** rail (`sessions.js`), the **Files** view (server `/api/list` allowlist-confined + `backend.js listDir()` + `app.js filesMain()` with kit `BreadcrumbPath`/`FileGrid`, mirrors `c:\dev\fsbrowse`), and the **Live dashboard** (`SessionDashboard`/`SessionCard`). Also a no-compromises gm-plugkit WASM embedding fix (incremental re-embed, `rs-plugkit ab09ed0`). The 5th run (above) polished all of these. Full detail in rs-learn (recall "agentgui Claude-Desktop redesign").
-
-**webjsx keying class-bug (load-bearing, still true).** Mixing keyed VElements with `null`/strings in any children array crashes `applyDiff` ("reading 'key'"). `ConversationList` uses a stable keyed body wrapper (loading/empty/populated diff children not container) + `[...].filter(Boolean)` on conditional row children; `app.js runningPanel` keys all three row children. `refreshHistory` keeps `render()` OUT of the try so a render exception doesn't masquerade as a history fetch error. See the webjsx note below.
-
-## GUI-predictability sweep closure (2026-06-05) — third maximum-effort run
-
-Override-elimination pass (index.html `!important` -> kit defaults) + 19 other PRD rows. Full detail in rs-learn (recall "agentgui 3rd run GUI-predictability sweep closure").
-
-## GUI-audit closure (2026-06-04 fan-out) — second maximum-effort sweep
-
-`.claude/workflows/gui-audit.js` ran a 64-agent fan-out (9 per-surface reviewers -> adversarial verify -> synthesize) -> 44 confirmed findings (`AUDIT-PUNCHLIST.md`, 38 deduped), all fixed across server/app/kit and pushed (agentgui `eb1eab3`/`951404e`, kit `anentrypoint-design` `bb776aa` -> CI publishes npm/unpkg). Per-finding detail + key learnings (ccsniff SSE `{sid,payload}` unwrap, CSP must allow Google Fonts, DS `Select` promotes `title`->`aria-label`, index.html now loads the kit from local `./vendor/`, kit publish flow) in rs-learn (recall "agentgui GUI-audit closure").
-
-## Architecture (2026-05-19 pivot — single surface)
-
-One surface. `server.js` serves `site/app/` under `BASE_URL` (default `/gm`) and mounts `ccsniff`'s `/v1/history/*` Express router in-process at both `/` and `BASE_URL`. The legacy `static/` tree and the legacy `lib/routes-*`/`lib/db-queries-*`/`lib/jsonl-watcher.js` modules are gone. `acptoapi` is no longer used by this project.
-
-When `PASSWORD` env var is set, every HTTP route is gated by `lib/http-handler.js` accepting **Basic auth**, **`Authorization: Bearer <pwd>`**, OR **`?token=<pwd>`** query param (added 2026-05-26 so `EventSource` and direct deep-links work — neither can set headers). WS `/sync` requires `?token=` only. The HTML head script injects `window.__BASE_URL`, `window.__SERVER_VERSION`, and `window.__WS_TOKEN`; `site/app/js/backend.js` reads `__WS_TOKEN` and threads it onto every fetch (Bearer header) / EventSource (qs) / WebSocket (qs).
-
-- `site/app/index.html` — shell + CSS; imports `anentrypoint-design` from the **local vendored copy** `./vendor/anentrypoint-design/247420.{js,css}` (re-vendored 2026-06-04 for a PREDICTABLE shipped UI that does not shift when upstream publishes, and offline operation — the markdown stack marked/dompurify/prismjs still fetches from jsdelivr on first chat render). Update flow: edit the kit at `c:\dev\anentrypoint-design`, `node scripts/build.mjs`, copy `dist/247420.{js,css}` into `site/app/vendor/anentrypoint-design/`, then publish the kit so unpkg stays in sync.
-- `site/app/js/backend.js` — same-origin WS/HTTP client (`DEFAULT_BACKEND = ''`); the transport glue that wires the kit; `?backend=` query override for cross-origin debugging
-- `site/app/js/app.js` — webjsx view + state; renders the `AgentChat` kit (from `anentrypoint-design`) for the chat surface and wires agentgui's WS/ccsniff state as kit callbacks; history/settings remain agentgui-local. Exposes `window.__agentgui`
-
-The chat GUI lives in the design kit, not in agentgui. The reusable multi-agent chat surface is the `AgentChat` component in `anentrypoint-design` (`src/components/agent-chat.js`); agentgui keeps only the transport glue (WS `backend.js`, ccsniff history wiring, agent orchestration) and passes state + callbacks into the kit. To change chat UI, edit the kit and push it (CI publishes to npm -> unpkg `@latest`), not agentgui.
-- `server.js` — initializes the ACP-SDK manager + agent registry, registers WS handlers (`ws-handlers-util.js`), mounts `createHistoryRouter()` from `ccsniff` at `/`, serves `site/app/` as static root. The `lib/plugins/` system was removed (2026-06-20, 20th run) — it was dead scaffolding (routes 404, wsHandlers never wired, api unconsumed); all server logic lives directly in `server.js` + `lib/ws-handlers-util.js` + `lib/http-handler.js` + `lib/routes-upload.js` + `database.js`.
+ACP lifecycle lives in `lib/acp-sdk-manager.js` alone; no other module spawns or manages ACP agent processes. Every `spawn()` callsite needs a `proc.on('error', …)` handler (ENOENT surfaces async under Bun).
+
+## CRITICAL — `authedFetch` must NOT set `Authorization: Bearer` behind an nginx Basic-Auth proxy
+
+Same-origin app auth must never use the `Authorization` header when an upstream proxy may own Basic auth — a `Bearer` header overwrites the browser's cached `Authorization: Basic` credentials, and nginx `auth_basic` only accepts `Basic`, so the request is rejected at the proxy before it ever reaches agentgui. Use the **`?token=` query param** (`withToken()`, exactly like the WS / EventSource / image / download URLs) instead — it coexists with upstream Basic auth, and agentgui accepts `?token=` on every HTTP route, plus the `agentgui_token` cookie.
+
+## Standing engineering rules
+
+- **All GUI/design decisions live in the kit (`../design`), none in agentgui.** New surface styling is a kit CSS rule, never an inline `<style>` or `style=` prop in agentgui. A new kit component must be re-exported through `src/components.js`'s barrel to be consumable — adding it to a component file alone leaves it invisible to the built bundle even with 0 lint errors; grep the built dist for the export name before wiring the app against it. New CSS class tokens in the kit must carry a registered family prefix (`ds-`, `app-`, `ws-`, `chat-`, etc. — see `scripts/lint-classes.mjs`'s `PREFIXES`/`FROZEN` lists) or the build's lint-classes check fails; a legacy bare name like `chip` being grandfathered on the FROZEN list does not cover new sub-tokens off it (e.g. a new `chip-remove` class still needs a `ds-` prefix).
+- **`confineToRoots()` in `lib/http-handler.js` applies `fs.realpathSync` re-confinement on `/api/list`, `/api/file`, `/api/image`** — a symlink pointing outside an allowed root fails closed rather than resolving through it.
+- **Files is a full file manager, not a viewer**: confined `POST /api/rename`, `/api/delete` (soft-delete into a per-root `.agentgui-trash/` with a restore endpoint and a retention-window eviction cap, not a hard unlink), `/api/mkdir`, `/api/restore`, `PUT /api/upload-file`, `GET /api/stat`, all routed through `fsAllowRoots()`/`sanitizeEntryName()` and a CSRF guard on every POST/PUT/DELETE. Run `scripts/validate-mutations.mjs` after touching any part of this mutation surface. `RFC-5987` `Content-Disposition` encoding is required for non-ASCII filenames on download.
+- Full hash routing state is `HASH_KEYS=[tab,sid,dir,file,q,project,section]`; `popstate` diffs the full set, and `navTo(tab,{writeHash:false})` navigates without pushing a new hash entry.
+- The "Untitled conversation" fallback is one shared `UNTITLED_CONVERSATION` constant — never a locally re-typed literal (casing/wording drifts across call sites otherwise).
+- Upload/mkdir/rename/list request bodies are scanned by `SECRET_RE` before being echoed into logs or responses.
+- **webjsx keying:** mixing keyed VElements with `null`/strings/numbers in any children array crashes `applyDiff` ("reading 'key'"). Never pass a conditional `x?h():null` positionally — build the array and `.filter(Boolean)` it. `Btn` spreads array children. A kit component prop with an established narrow contract can silently corrupt an unrelated call site when a caller passes a richer value than the prop was designed for (e.g. a VElement where only a plain string was ever read) — grep every other use site of a prop before extending what a caller passes through it.
+- **Escape ladder order (extend, never reorder):** shortcuts overlay > file dialog > confirmingEdit > new-chat arm > stop-arms > stop generation.
+- **Status-disc shape:** live = solid+pulse, error = solid+halo, connecting = hollow ring, stale = muted solid.
+- **Kit `Row` rail/rank contract:** the design-kit `Row` (`anentrypoint-design` `src/components/content.js`) renders a leading status rail from a `rail` prop (`green` | `purple` | `flame`, via `.row.rail-<tone>::before`) and accepts `rank` as an alias for the leading `code` index. `state: 'disabled'` is inert (no `onClick`/`role=button`/tab-stop, `aria-disabled=true`). Rail semantics are consistent everywhere: green = selected/ok, purple = subagent, flame = error/unavailable.
+- **No decorative glyphs.** GUI source and output use ASCII words and CSS-drawn discs (`.status-dot-disc`) for status, never `●/◌/○/⌘/§/▶` etc. The middot separator `·`, ellipsis `…`, and em/en dashes in prose are kept as deliberate typographic product design, not tells — convert any other decorative glyph (arrows, box-drawing, bullets, checks) to ASCII on sight (`->`, `// --- x ---`, `-`/`*`). A dismiss control's own close icon on a dismissible Alert is a real DS icon affordance, exempt.
+- **A `keepXTrack`-mounted component's interaction must produce the same visible effect on every tab it appears on** (e.g. the persistent sessions rail).
+- **Any drawer/overlay whose `left`/`inset` changes across breakpoints must re-derive its closed-state transform from that breakpoint's own offset** — a transform tuned for one breakpoint's geometry silently breaks at the next if the offset shifts underneath it.
+- **`.ws-rail`/`.ws-sessions`/`.ws-pane` must all three use `--bg-2`** for background — a mismatched flat `--bg` on any one reads as visually disjointed chrome.
+- The app.js `C` destructure must list every kit component it calls (an undestructured component silently renders as `Icon is not defined` or similar).
+- Commit and push any inherited uncommitted work found dirty in the tree before starting new work at PLAN entry — never leave it stranded under a fresh, disjoint cover.
+- No new `PUNCHLIST-*.md`/`AUDIT-PUNCHLIST.md` (or similarly named) file is checked into the repo as a durable artifact. A workflow's punch-list is a transient working document for that run's synthesis step; the outcome belongs in AGENTS.md (compressed to a rule) or drains to recall, never a standing file.
+- When origin advances mid-run with the same feature a concurrent writer already shipped, drop your version and adopt theirs, then re-apply only genuinely-distinct work — never a parallel implementation.
+- Check a color token's contrast against its actual rendered background, not just the base paper token. A `failures`-array-shaped crash from a lint/audit lens means that scope is unaudited, not a null (clean) result. `prd-resolve` `witness_evidence` must be distinct per row, never a batch-shared string.
+- This env's `PASSWORD` value can itself contain literal commas (e.g. `123,slam,123,slam`) — treat the whole string as one token, never comma-split it when testing auth.
+- The `gm-plugkit` `fs_write` verb's payload key is `content` (a JSON string), not `body` — passing `{path, body:{...}}` silently no-ops with `bytes:0` and no error.
+- Docstudio design-cue mining (`/config/docstudio`) is a recurring source of portable UI conventions to port into `../design`. When re-running this sweep, survey files not yet examined against the kit's actual current component list rather than trusting a prior "exhausted" verdict at face value — a narrow, genuinely new gap can still surface (e.g. `Chip.onRemove`, `RateCell`, `SpreadsheetPreview`, `ApprovalPrompt`, `PermissionMenu`, `CountdownDialog`, `withBusy` double-fire guard). Business logic with no portable visual surface (native OAuth pickers, drive integration, file-upload wiring) and app-specific cloud-provider wiring (observability deep-links) are not portable; the visual/interaction *convention* underneath sometimes still is.
+
+## Browser-verb operating notes
+
+- The `browser` spool verb's actual accepted JSON body shape is `{"code": "<script>"}`, evaluated directly in the currently-loaded page's `window`/`document` context — it is not a Puppeteer/Playwright `page`-scoped API (no `page.goto`/`page.title()`). Navigating via `window.location.href = '...'` inside one `{code}` dispatch throws `"Inspected target navigated or closed"` (expected — kills the CDP eval mid-navigation), but the session persists across dispatches, so a second `{code}` dispatch on the same session lands in the newly-navigated page. If the plain-text `url=`/`dom=`/`screenshot=`-prefixed body forms ever return empty/no-op in this environment, fall back to the two-dispatch `{code}` navigate-then-eval pattern rather than re-litigating the prefix forms.
+- Zombie Chromium process trees left by earlier timed-out `browser` dispatches (under the project's own `.gm/browser-chrome-profile-` directory) can wedge every subsequent Chrome launch/reuse to full-timeout empty responses or intermittent `"plugin gm not loaded"` errors. Kill every chromium PID under that profile dir (never the daemon process itself) to unblock; this is a distinct failure mode from a genuinely stale/crash-looping supervisor process (also possible — check `.gm/exec-spool/.watcher.log` for a repeating respawn-crash-loop signature before assuming it's the Chrome-zombie case).
+- Embedding Basic-Auth creds directly in a `page.goto`/navigation URL (`https://user:pass@host/...`) breaks the app's own same-origin `fetch()` calls with "Request cannot be constructed from a URL that includes credentials." Do one embedded-creds navigation to seed the browser's per-origin Basic-Auth cache, then navigate again WITHOUT embedded creds (plain URL or `?token=`) for any witness that needs real fetches to succeed.
+- Combine creds + goto + wait + evaluate into ONE dispatch when the tool version's session ids rotate across separate dispatches; read results via `console.log('WITNESS:'+...)` and grep stdout rather than trusting a `capture`-prefix `result` field that can come back `null` on an otherwise successful dispatch.
+- Writing a spool verb input file under a task-number that collides with an existing `out/<verb>-<N>.json` from an earlier turn in the same session can silently return the STALE cached output instead of running the fresh dispatch. Pick a task number confirmed absent from `out/` (e.g. jump to a clearly-unused block) rather than trusting sequential same-session numbering, especially after a long session with many prior dispatches.
+
+## Architecture (single surface)
+
+One surface. `server.js` serves `site/app/` under `BASE_URL` (default `/gm`) and mounts `ccsniff`'s `/v1/history/*` Express router in-process at both `/` and `BASE_URL`. There is no legacy `static/` tree and no `lib/plugins/` system — all server logic lives directly in `server.js` + `lib/ws-handlers-util.js` + `lib/http-handler.js` + `lib/routes-upload.js` + `database.js`. `acptoapi` is not used by this project.
+
+When `PASSWORD` env var is set, every HTTP route is gated by `lib/http-handler.js` accepting **Basic auth**, **`Authorization: Bearer <pwd>`**, OR **`?token=<pwd>`** query param (the query-param path exists because `EventSource` and direct deep-links cannot set headers). WS `/sync` requires `?token=` only. The HTML head script injects `window.__BASE_URL`, `window.__SERVER_VERSION`, and `window.__WS_TOKEN`; `site/app/js/backend.js` reads `__WS_TOKEN` and threads it onto every fetch (Bearer header) / EventSource (qs) / WebSocket (qs).
+
+- `site/app/index.html` — shell + CSS; imports `anentrypoint-design` from the local vendored copy `./vendor/anentrypoint-design/247420.{js,css}` (a predictable shipped UI that does not shift when upstream publishes, plus offline operation — the markdown stack marked/dompurify/prismjs still fetches from jsdelivr on first chat render). Update flow: edit the kit at `../design`, `node scripts/build.mjs`, copy `dist/247420.{js,css}` into `site/app/vendor/anentrypoint-design/`, then publish the kit so unpkg stays in sync.
+- `site/app/js/backend.js` — same-origin WS/HTTP client (`DEFAULT_BACKEND = ''`); the transport glue that wires the kit; `?backend=` query override for cross-origin debugging.
+- `site/app/js/app.js` — webjsx view + state; renders the `AgentChat` kit component for the chat surface and wires agentgui's WS/ccsniff state as kit callbacks; history/settings remain agentgui-local. Exposes `window.__agentgui`.
+- The chat GUI lives in the design kit, not in agentgui. The reusable multi-agent chat surface is the `AgentChat` component in `anentrypoint-design` (`src/components/agent-chat.js`); agentgui keeps only the transport glue (WS `backend.js`, ccsniff history wiring, agent orchestration) and passes state + callbacks into the kit. To change chat UI, edit the kit and push it (CI publishes to npm -> unpkg `@latest`), not agentgui.
+- `server.js` — initializes the ACP-SDK manager + agent registry, registers WS handlers (`ws-handlers-util.js`), mounts `createHistoryRouter()` from `ccsniff` at `/`, serves `site/app/` as static root.
 
 Dependencies:
 - `ccsniff` (>=1.1.0) — exports `createHistoryRouter({projectsDir})` mountable on Express; serves `/v1/history/{sessions,sessions/:sid/events,search,snapshot,reindex,stream}`. Reads `~/.claude/projects` (override via `CLAUDE_PROJECTS_DIR`).
-- `anentrypoint-design` (>=0.0.119) — kit library, single-file ESM from unpkg
-
-## GUI audit pass (2026-06-04) — structured chat, predictable presentation
-
-Landed structured tool cards (toolPart/applyToolResult by id), multi-turn resume wiring (streaming_session -> state.chat.resumeSid), rAF-coalesced streaming, /api/image confinement, history eventsLimit + search-to-event flash. Largely superseded by runs 5-12; full detail in rs-learn (recall "agentgui GUI audit pass 2026-06-04 structured chat").
+- `anentrypoint-design` (>=0.0.119) — kit library, single-file ESM, vendored locally (not loaded from unpkg at runtime).
 
 ## Orchestration agents
 
@@ -236,13 +63,13 @@ The four flagship agents the GUI drives are **Claude Code, OpenCode, Kilo, and A
 
 Two runner protocols exist. **Direct** (`lib/claude-runner-direct.js`): claude-code and agy — spawn the CLI per turn, parse stdout. **ACP** (`lib/acp-sdk-manager.js`): opencode/kilo/codex — an on-demand long-lived server on ports 18100/18101/18102, health-checked via `/provider`. The on-demand start + restart-backoff is correct even when an ACP agent lacks provider auth (it reports running-not-healthy rather than crashing).
 
-`agy` (Antigravity) is a Gemini-backed Go CLI. Its invocation is `agy --print "<prompt>" --dangerously-skip-permissions [--continue]` — `--print` is a **value flag** (the prompt is its argument; a positional prompt exits 2). It emits **plain text** (not stream-json) and prints no session id, so its `parseOutput` wraps each line into an assistant-text event and resume is `--continue`-only. A live model response needs an authenticated Antigravity session; without it `agy` returns empty (the direct runner resolves gracefully, no hang). Detail in rs-learn (recall "agentgui agy Antigravity agent").
+`agy` (Antigravity) is a Gemini-backed Go CLI. Its invocation is `agy --print "<prompt>" --dangerously-skip-permissions [--continue]` — `--print` is a **value flag** (the prompt is its argument; a positional prompt exits 2). It emits **plain text** (not stream-json) and prints no session id, so its `parseOutput` wraps each line into an assistant-text event and resume is `--continue`-only. A live model response needs an authenticated Antigravity session; without it `agy` returns empty (the direct runner resolves gracefully, no hang).
 
-**The direct runner spawns with `shell:false` against a resolved binary path — never `shell:true`.** `shell:true` on Windows concatenates argv without escaping, so a chat prompt containing `&`/`|`/`>`/backticks executes as shell commands (arbitrary command execution). `lib/claude-runner.js` `resolveBinaryPath` resolves the command to an absolute `.exe`; `getSpawnOptions` only defaults `shell:true` when a caller passes no explicit `shell`. Detail in rs-learn (recall "agentgui SECURITY direct runner shell:false").
+**The direct runner spawns with `shell:false` against a resolved binary path — never `shell:true`.** `shell:true` on Windows concatenates argv without escaping, so a chat prompt containing `&`/`|`/`>`/backticks executes as shell commands (arbitrary command execution). `lib/claude-runner.js` `resolveBinaryPath` resolves the command to an absolute `.exe`; `getSpawnOptions` only defaults `shell:true` when a caller passes no explicit `shell`.
 
-**Agent availability comes from `registry.isAvailable(id)`** (`lib/ws-handlers-util.js`, `agents.list`), which runs `where`/`which`. A binary installed outside the system PATH reads as "(not installed)"; the fix is an `npxPackage` on the registry entry so it falls back to bun/npx presence. Detail in rs-learn (recall "agentgui agent availability where npxPackage").
+**Agent availability comes from `registry.isAvailable(id)`** (`lib/ws-handlers-util.js`, `agents.list`), which runs `where`/`which`. A binary installed outside the system PATH reads as "(not installed)"; the fix is an `npxPackage` on the registry entry so it falls back to bun/npx presence.
 
-**Output and source carry no decorative glyphs.** The GUI uses ASCII words and CSS-drawn discs (`.status-dot-disc`) for status, never `●/◌/○/⌘/§/▶` etc. Convert any decorative glyph to its ASCII equivalent on sight.
+**`lib/tool-spawner.js`** iterates `BUNX_RUNNERS=['bun','npx']` and detects missing-command via regex on both `error.message` and stdout+stderr.
 
 ## Browser Witness
 
@@ -250,89 +77,40 @@ Two runner protocols exist. **Direct** (`lib/claude-runner-direct.js`): claude-c
 
 ## CI / GitHub Actions
 
-**capture-screenshots must run under bun, not node.**
-
-`npm install --ignore-scripts` in gh-pages.yml skips native compilation, leaving `better-sqlite3` without a compiled `.node` binding. `database.js` tries `bun:sqlite` first, then falls back to `better-sqlite3`. When the step runs under Node both fail and the server crashes silently within the 20s health-check window.
-
-Fix: `bun run scripts/capture-screenshots.mjs` (not `node ...`).
-
-Why it works: `process.execPath` becomes bun, so the spawned child server also runs under bun and loads `bun:sqlite` natively — no compiled binding needed.
-
-Rule: any CI step that spawns the agentgui server (directly or via a script that inherits `process.execPath`) must invoke it with `bun`.
-
-## Plugin system removed (2026-06-20 — 20th run)
-
-The entire `lib/plugins/` system + `plugin-loader.js` was deleted as dead scaffolding (commits up to e73ed0e): plugin routes were unreachable (http-handler forwarded only a few prefixes -> 404), plugin `wsHandlers` were never wired (the real WS handlers come from `registerWsHandlers` in `ws-handlers-util.js`), plugin `api` objects were never consumed, and the inits were no-ops or managed local Maps nobody read. Removed across 7 commits (acp, files, agents, then database/stream/workflow/websocket + loader). The general lesson survives: any import under `lib/` must be a built-in (crypto, fs, path) or already in package.json — a missing dep crashes boot.
-
-## Plugin Tool Provisioning on Windows
-
-**`lib/tool-spawner.js` iterates `BUNX_RUNNERS=['bun','npx']` and detects missing-command via regex on both error.message and stdout+stderr.** Full detail in rs-learn (recall "agentgui windows tool-spawner bunx fallback").
+**capture-screenshots must run under bun, not node.** `npm install --ignore-scripts` in gh-pages.yml skips native compilation, leaving `better-sqlite3` without a compiled `.node` binding; `database.js` tries `bun:sqlite` first, then falls back to `better-sqlite3`. Under Node both fail and the server crashes silently within the 20s health-check window. Fix: `bun run scripts/capture-screenshots.mjs` (not `node ...`) — `process.execPath` becomes bun, so the spawned child server also runs under bun and loads `bun:sqlite` natively. Rule: any CI step that spawns the agentgui server (directly or via a script that inherits `process.execPath`) must invoke it with `bun`.
 
 ## GM Plugin Autonomy Blocker
 
-gm plugin's pre-tool-use hook gates multi-tool autonomy via a `.gm/needs-gm` marker; the hook content is TEMPLATED from the gm codebase, not gm-starter/hooks/ - patching those files does not propagate. Full diagnosis + fix path in rs-learn (recall "agentgui GM plugin autonomy blocker").
-
-## History Integration via ccsniff (2026-05-21 — reverted from acptoapi)
+gm plugin's pre-tool-use hook gates multi-tool autonomy via a `.gm/needs-gm` marker; the hook content is templated from the gm codebase, not `gm-starter/hooks/` — patching those files does not propagate.
 
-**agentgui mounts `ccsniff`'s history router in-process — no external proxy.**
+## History Integration via ccsniff
 
-`server.js` imports `createHistoryRouter` from the `ccsniff` package and mounts it on the internal Express app at `/`, exposing `GET /v1/history/{snapshot,sessions,sessions/:sid/events,search,reindex,stream}`. Reads `~/.claude/projects` by default; override with `CLAUDE_PROJECTS_DIR` env var. acptoapi's previously-bundled history routes were removed in acptoapi 1.0.103; ccsniff is now the canonical source. Browser client (`site/app/js/backend.js`) calls these same-origin via the agentgui server.
+agentgui mounts `ccsniff`'s history router in-process — no external proxy. `server.js` imports `createHistoryRouter` from the `ccsniff` package and mounts it on the internal Express app at `/`, exposing `GET /v1/history/{snapshot,sessions,sessions/:sid/events,search,reindex,stream}`. Reads `~/.claude/projects` by default; override with `CLAUDE_PROJECTS_DIR` env var. Browser client (`site/app/js/backend.js`) calls these same-origin via the agentgui server.
 
-## buildSystemPrompt System Prompt for claude-code
+## buildSystemPrompt for claude-code
 
-**`lib/provider-config.js` buildSystemPrompt() must return '' for claude-code agent; returning "Model: X." breaks conversation resume.**
-
-The function previously returned "Model: X." when agentId was 'claude-code' and model was non-null. This caused `buildArgs` in lib/claude-runner-agents.js to pass `--append-system-prompt "Model: X."` to the claude CLI, which triggers "argument missing" error on conversation resume. Fix: return '' early when agentId is 'claude-code' or falsy. The model is already passed via `--model` flag; system prompt is only for non-claude-code agents.
+`lib/provider-config.js` `buildSystemPrompt()` must return `''` for the claude-code agent — a non-empty return (e.g. `"Model: X."`) causes `buildArgs` in `lib/claude-runner-agents.js` to pass `--append-system-prompt` to the claude CLI, which triggers an "argument missing" error on conversation resume. The model is already passed via `--model`; system prompt is only for non-claude-code agents.
 
 ## WebSocket Sync Endpoint Testing
 
-**`/sync` sends `sync_connected`+clientId on connect; legacy handler in `lib/ws-legacy-handlers.js` (ping/subscribe/get_subscriptions/unsubscribe/latency_report) via codec; tests must register the message handler before sending.** Full detail in rs-learn (recall "agentgui websocket /sync testing handler ordering").
+`/sync` sends `sync_connected`+clientId on connect; the legacy handler in `lib/ws-legacy-handlers.js` (ping/subscribe/get_subscriptions/unsubscribe/latency_report) runs via codec. Tests must register the message handler before sending.
 
 ## better-sqlite3 & Node v24 Startup
 
-Node v24 lacks a prebuilt better-sqlite3 binary; the node path needs a from-source `postinstall` compile, and `start` is `bun server.js || node server.js`. `database.js` tries `bun:sqlite` first. Detail (postinstall command, paired package.json/bin changes, CI must-run-under-bun) in rs-learn (recall "agentgui startup better-sqlite3 node v24 bun").
-
-## webjsx applyDiff Array Keying (2026-05-04)
-
-**Rule still binding: mixing keyed VElements with raw strings/numbers in any webjsx array prop crashes `applyDiff`.** Full detail in rs-learn (recall "agentgui webjsx applyDiff array-keying rule").
-
-## Live History Stream Wiring (2026-05-05)
+Node v24 lacks a prebuilt better-sqlite3 binary; the node path needs a from-source `postinstall` compile, and `start` is `bun server.js || node server.js`. `database.js` tries `bun:sqlite` first.
 
-`site/app/js/app.js` opens an SSE EventSource on `navTo('history')` (`B.streamHistory`, `state.live` shape, hello/event/conversation/error dispatch, rAF-throttled renders) against ccsniff's in-process `/v1/history/stream`; first `/v1/history/*` request triggers a 30-90s synchronous JSONL walk (`CLAUDE_PROJECTS_DIR`) — health-check timeouts during that window are normal. Full detail in rs-learn (recall "agentgui Live History Stream Wiring").
-
-## Runtime CDN: GUI loaded from unpkg — SUPERSEDED, do not trust
-
-This 2026-05-29 unpkg-at-runtime approach was reverted; see "DS load = LOCAL vendor" below for the current truth (re-confirmed live on the 37th run, 2026-07-12). Historical detail in rs-learn (recall "agentgui unpkg superseded local vendor").
-
-## Agent/model/session management (2026-05-28)
+## Agent/model/session management
 
 - `agents.list` (WS) returns `available` + `npxInstallable` per agent; `agents.models` returns model choices (claude-code -> sonnet/opus/haiku). The chat picker is **agent-then-model**, not a flat model list. Unavailable agents are disabled/gated.
 - `chat.sendMessage` accepts `cwd` (defaults to STARTUP_CWD) and `model`/`agentId` separately. `chat.active` (WS) lists in-flight chats with agentId/model/cwd/startedAt/pid; the history tab polls it (3s) and shows a running panel with per-session stop.
 - Client (`app.js`): chat transcript persists to `localStorage[agentgui.chat]` and restores on load; tool_use/result events render as chat parts; keyboard shortcuts (g+c/h/s, n, /, ?); settings has an agents-status panel from `health.acp[]`.
 
-## Kit Row rail + rank contract
-
-The design-kit `Row` (`anentrypoint-design` `src/components/content.js`) renders a leading status **rail** from a `rail` prop (`green` | `purple` | `flame`, via a `.row.rail-<tone>::before` bar) and accepts `rank` as an alias for the leading `code` index. A `state: 'disabled'` Row is inert — no `onClick`/`role=button`/tab-stop, `aria-disabled=true`. agentgui's history sessions, search results, and agents panel pass `rail` + `rank` and rely on this; the rendering reaches the live GUI only after the kit publishes to npm -> unpkg `@latest`. agentgui keeps the rail semantics consistent everywhere: **green = selected/ok, purple = subagent, flame = error/unavailable**.
-
-## GUI glyph policy
-
-GUI source keeps typographic product characters — the middot separator `·`, the ellipsis `…`, and em/en dashes in prose — as established design (AGENTS.md itself uses `·`). It carries **no** decorative tells: arrows, box-drawing, bullets, status dots, checks. Status is words + the CSS-drawn `.status-dot-disc`. Convert any arrow/box-drawing/bullet glyph to ASCII on sight (`->`, `// --- x ---`, `-`/`*`).
-
-## DS CSS cascade — overriding component styles (2026-05-28)
-
-**`installStyles()` injects DS CSS into a runtime `<style>` after the head `<style>`, so local overrides need `!important` or higher specificity than the DS's `.ds-247420`-prefixed rules.** Full detail (font vars `--ff-display`/`--ff-mono`, the `.chat-head .sub` "00 msgs" quirk, EventList `.row[role=button]`, `[data-prog-focus]` focus suppression, `projectLabel()` for cwd slugs) is in rs-learn (recall "agentgui GUI styling DS cascade installStyles").
-
-## No decorative glyphs — ASCII-only GUI (2026-06-04)
-
-**The GUI carries no decorative tell-tale glyphs; remaining non-ASCII is the deliberate typographic separator set.** The de-jank sweep removed every tell-tale (status dots `[CHAR]`, arrows, box-drawing dividers, checks) in favor of ASCII words + the CSS-drawn status disc. The middot separator `·` is kept as established product design (it reads as a real meta-separator, used consistently across rows/subs); ellipsis `…` and em/en dashes were converted to `...` / `-` on sight. Verified live on buildesk: `document.body.innerText` matches no decorative-glyph regex (excluding the kept middot) across chat/history/settings. The DS Alert dismiss control renders its own close glyph only on a dismissible alert (intentional DS icon affordance, exempt).
-
-## DS SearchInput accessible name comes from `label`, not `aria-label` (2026-06-04)
-
-**`anentrypoint-design`'s `SearchInput` (internal `De`) sets `aria-label = label || placeholder`; it ignores any `aria-label` prop you pass.** To give the search box a real accessible name, pass `label:` (and a matching `placeholder:` for the visible hint). Passing only `aria-label` leaves AT announcing the placeholder. A post-render `setAttribute` race-loses against the DS re-render, so the prop is the only durable fix.
+## DS CSS cascade — overriding component styles
 
-## DS load = LOCAL vendor (resolved — the earlier unpkg note is stale)
+`installStyles()` injects DS CSS into a runtime `<style>` after the head `<style>`, so local overrides need `!important` or higher specificity than the DS's `.ds-247420`-prefixed rules.
 
-`index.html` loads the DS kit from local `./vendor/anentrypoint-design/247420.{js,css}`, NOT unpkg — reconfirmed live on the 40th run. Full detail in rs-learn (recall "agentgui ds load local vendor detail").
+## DS SearchInput accessible name comes from `label`, not `aria-label`
 
+`anentrypoint-design`'s `SearchInput` sets `aria-label = label || placeholder`; it ignores any `aria-label` prop passed directly. To give the search box a real accessible name, pass `label:` (and a matching `placeholder:` for the visible hint) — a post-render `setAttribute` race-loses against the DS re-render, so the prop is the only durable fix.
 
 @.gm/next-step.md