It read as if a search field were the only way to earn it, which stopped being
true when the app and pipeline editors' rows started scrolling inside their own
box. Both are the same bargain — the box may shrink because its contents can —
and the flag is what the bar reads to allow it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Measuring the band instead of estimating it: with the canvas toggles shown the
app editor's actions are 826-911px and the trail with the summary another ~500,
so the row overflowed the bar at every width up to about 1470 — the 1100 I set
from an estimate was wrong, and the 1350 before it was too. The toggles come out
at 1500 now, and the menu entries are what keeps all three reachable below that
rather than merely out of the way.
The two widest rows — this editor's and the pipeline's — scroll inside their own
box, which is the escape the rows they replaced had (`overflow-x-auto
whitespace-nowrap`). That answers pi's finding and clears the last 23-40px of
band overflow at middling widths, which predated the conversion. Measured after:
zero horizontal overflow from 852px of bar to 1392.
From the CI round's other findings:
- The pen is offered when either the summary or the path is editable, not the
path alone: a host that allowed one and refused the other could no longer edit
the summary from the band. `PathEditPopover` takes `pathEditable` to match, and
its label names whichever it is given.
- The four editors' comments called the summary read-only, which stopped being
true when the pen beside it started editing it.
- The pipeline's "centre group" comment described a layout it no longer has.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Codex found the app editor's canvas controls unreachable on an ordinary laptop:
the owning route collapsed at 1350px, and a 1440 window with the rail out leaves
1232, so the width, theme and breakpoint toggles were hidden with nothing in the
menu to replace them — and the breakpoint is the only way onto the mobile layout.
Measured on the band, the toggles are 240px beside 334 of other actions and a
~430 trail, so they fit to about 1050: the threshold is 1100 now, and below it
each of the three keeps a menu entry rather than disappearing.
An item with no summary read as a bare `·` with an invisible pen after it, since
the plain text replaced a field that had a placeholder. It now reads "Add a
summary..." in the italic SummaryPathDisplay uses for the same state, and the pen
stops hiding when there is nothing to hover.
Three more from the review:
- `actionsFlexible` says "these actions can give width back", which is true of the
Runs filter row and not of the pipeline's row of fixed buttons.
- `pathSnapshot ?? (newEditedPath || …)` keeps the `||` chain the five rename
sites read and the declaration documents; `??` had made the rest unreachable,
since `newEditedPath` is a string that is never undefined.
- The band bridged `contexts` onto the actions alone, while the pen that decides
whether a path is the caller's to change renders in `summaryContent`. The
breadcrumb's `afterName` and the summary are bridged the same way now, so that
permission check reads the tree that registered it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Found by sweeping every route under the band: the pipeline editor drew its own
row beneath it, 48px of a second header, while the band named only the section.
Its name is the band's now, the folder it is open on sits with that name — the
switcher is how you change pipelines, so it belongs to the name rather than to
the actions — and the mode switch, deploy-all, activity, refresh and overflow
menu are the bar's actions. The arrow back to the list stays: nothing else on the
page points there, and the sidebar does not list pipelines.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
It was the last editor route drawing its own header row under the band, and the
band named it "Agents" — `navPageFor`'s first-segment fallback, because nothing
on the route registered an item. The agent's path is the breadcrumb now, its
version badge reads after that name, the sentence that was the row's second line
became the hint beside it, and the Chat/Form switch, Settings, Evals, version
history and Deploy are the band's actions.
No trail levels in the registration: this layout opens settings in a drawer and
evals over the page, so unlike the dialog it never stands on a level — `trail` is
its root alone here.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The pen opened the path alone, which left the summary with nowhere to be edited
from the band. It carries a Summary field above the path now — the item's name
first, the address it lives at below — and the band's text follows it as the user
types.
`TextInput` with a label rather than the bar's inline field: `EditableInput`'s own
docs rule itself out inside a popover, and it wraps this same input in its edit
mode, so the field, the "Add a summary..." placeholder and the trim on commit are
the behaviour that was there, in the shape the deploy drawer's Summary field
already uses. The keydown stops at the field because every editor binds keys of
its own and a summary is prose.
`summaryEditable` carries the hosts' `customUi.topBar.editableSummary` through,
and the editors' own bar passes it false: that bar keeps its inline field, and
`hidePath` would take the pen with it, leaving a condensed session pane no way to
name the item at all.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The band showed each editor's summary as an inline field, which put editing
where the page names what it is working on. The summary is text there now, with
its `title` for one the band truncates, and the pen that opens the path for
editing sits after it — the same popover the editors' own bar carries, at the end
of the name it renames. Every editor already has a field for the summary itself:
the script's settings, the flow's Settings tab, and both app editors' deploy
drawer.
The popover moves into `PathEditPopover` rather than being written out four more
times. It owns the open state and hands back the path as it was when it opened:
the band's trail reads that while the popover is open, so a path growing under
the pointer does not drag the pen — and floating-ui the popover — along with it.
`EditorHeader` renders the same component, so the session pane and the band
cannot drift apart.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This reverts commit 1da8d16740.
A folded file sidebar renders nothing of its own, so the toggle on the bar is the
only way back short of knowing ⌘B.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The band's edge listener captures every scroller in the app — Monaco, the audit
table, a run's logs — about once a frame while any of them moves, and it took two
`getBoundingClientRect()` reads before looking at `scrollTop`. It now answers from
`scrollTop` first and only measures when that answer differs from what the band
draws, which is the transition rather than the steady state. The rect check still
authorizes every change, so a scroller that does not start at the content's top
still cannot claim the edge.
The two agent routes main just added size themselves to the viewport, which is
44px more than the box the band leaves them. They measure 856 either way — the
layout's `min-h-0` column clamps them — so this is the sweep the rest of the
branch already had, making the height follow the box rather than depend on a
parent's clamp.
Six comments described the conversion rather than the code, which AGENTS.md calls
out by name. Each now states the constraint a reader could break: why the summary
keeps its popover here, why the audit hint is `afterName` and not an action, why a
run registers a `section` rather than an item, why the Runs filters are
`actionsFlexible`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The band is the workspace's header, not the raw editor's layout controls. ⌘B
still folds the file sidebar, and the editor's own bar keeps the button where it
draws one — a session pane.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The merge brought main's agents detail page, which reaches DetailPageHeader with
no `errorHandlerKind` — and the band's item required one. `WorkspaceItemKindIcon`
falls through to the script glyph for anything it does not know, so defaulting
would have labelled an agent a script; the kind is optional now and the trail
names the item without claiming it is one of the three.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A brand-new app is parked at a `draft_<uuid>` placeholder, and the band named
that rather than the path its Deploy will create — `newEditedPath` refuses the
placeholder for exactly this reason, and the editor's own bar read it. Both app
editors register it now. Verified: the trail reads `u/admin/gentle_app` while the
URL is still the draft.
The band's summary gets the `title` the editor's own bar had, so one the bar
truncates can still be read on hover.
The wrapper that hid AppExportButton on a phone never hid anything:
the component draws no trigger — it is the export drawer, which portals to
`body` — so the class toggle was inert in both states and the comment read as if
something moved. Dropped from both app editors.
Two comments corrected: `NAV_PAGES`' `icon` does reach the breadcrumb for all
eleven entries (`NavBreadcrumb` renders `routePage.icon`), so only `operatorKey`
goes unread for the four the sidebar groups separately; and the raw editor's
phone note described folding that does not happen — the file-sidebar toggle stays
in the band, Jobs and the export are already in the menu, and AI is what stands
down.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Pinning brings the sidebar's handle back, and from behind it the unpin button sat
one slot over from where the pin had just been clicked — so a second click in the
same place opened the sidebar instead. An operator is detached by default, which
makes that the default state of the feature rather than an edge case.
`NAV_PAGES` claimed one table stops a page being called one thing in the nav and
another in the header, which holds for the seven entries the sidebar's main group
is built from and not for the four grouped separately — `/routes` was "Triggers"
in the header and "HTTP" in the nav. The comment now says which is which, and
that entry is named for the page rather than its group.
`sidebarPageAllowed` gets a table test: it decides what an operator sees, and its
`=== true` is what a future `Option`-style default would silently change.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The trailing-separator guard gave up on `f/demo/` entirely, which dropped the
whole trail to the kind chip and brought `f/demo` back on the first character of
the name. The levels the path does name come back now; only the leaf waits.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
It was the one editor route still rendering its own bar under the band, so it
showed two header rows and the band named the app "Apps raw" — `navPageFor`'s
first-segment fallback, because nothing on the route registered an item. Its top
bar now becomes the page header the way the script, flow and low-code app
editors' do: the path and summary are the breadcrumb's, the file-sidebar toggle,
autosave cloud, presence mark, menu, Diff, Jobs, export, AI and Deploy are the
header's actions, and the path is a plain label since this editor renames from
its deploy drawer.
The actions render under the band, outside the subtree `RawAppEditor` declares
the operating workspace in, and `OpenInSessionButton` asks that context who the
acting user is — so the workspace travels with them.
`operatingWorkspaceContextEntry()` hands it over without exporting the key.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: make hub integrations usable as examples in global chat
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: keep web search guidance in sync with provider capability
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: resync web search guidance before the request is built
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: carry loop web search availability into every prompt rebuild
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: drop web search guidance on the completions api fallback
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: correct onBeforeIteration contract for the fallback re-entry
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: give the ai chat hub script descriptions and integration metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: treat authored hub metadata as evidence the scripts were curated
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: treat hub curated as three-state and speak only for a stated true
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: let the benchmark hub serve integration metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: benchmark the hub tool against a real integration's scripts and metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: cover two more real integrations where the scripts already answer
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: report metadata_source from whether the fixture has authored meta
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: parse the hub resource type schema instead of relaying it as a string
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: match integration suggestions on slug words instead of substrings
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: search the integration a query names outright instead of ranking past it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: reject hub integration slugs that would re-target the proxied request
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: add a mentioned integration's hits instead of filtering the search to it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep named-integration hits under the content cap and unmangle fixture placeholders
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: cut the middle of a capped hub result instead of repeating its tail
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: cap hub results by keeping the best of the ranked and named hits
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep a named integration that ranking placed below the content cap
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: let plan mode use the hub integration lookup
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* feat: mark which hub integrations carry authored provider knowledge
The hub flags the integrations whose document holds hand-written provider
knowledge, so a caller can tell before spending a call on the metadata
endpoint: 18 of ~216 qualify, and for the rest the endpoint returns what
was inferred from the same scripts a search already hands back.
Carry the flag onto search results, where the model first meets a slug, so
get_hub_integration is aimed at the few instead of guessed at. A hub that
predates the flag omits it and nothing is marked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: stop the documented mark reading as a reason not to call
The flag says the hub additionally holds provider knowledge checked against
the live API. It is not a signal to skip the lookup elsewhere: that call
still returns the resource type and the usage-ranked examples, neither of
which a search result carries, and neither guessable.
The prompt said to read a script instead when the mark is absent, which
traded those for a guess on the ~198 undocumented integrations.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep the benchmark's documented flag true to what it serves
The eval hub reported Baremetrics and Holded as undocumented while its
metadata endpoint handed back their authored notes, so a case could teach
the model the flag means nothing. Derive it from both fixture sources, and
pin the agreement.
Also trims the documentedIntegrations comment to the four lines AGENTS.md
allows, keeping the case-folding constraint.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep the benchmark hub mostly undocumented, like the real one
Adding holded and baremetrics to the documented set resolved the fixture's
contradiction the wrong way: it left five of six integrations marked, against
the live hub's 18 of ~216, and claimed authored notes for two the hub reports
as having none. Drop the notes instead. Their auth and endpoints are in their
shipped scripts, which is what the cases that use them are about.
Also drops the last two places still describing the flag as a reason to spend
or skip the metadata call.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor: let the model name the integration instead of guessing it from the query
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor: word web search guidance conditionally instead of tracking provider capability
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: open the hub metadata route to job tokens and share one integrations fetch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: record a copied hub script's source where write_script keeps it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: pin that a query narrows to the integration it was given
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: match integration suggestions on the name the hub curates
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: name an integration the hub leaves unnamed from the local word table
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
