Ubuntu removed the superseded 0.9.0-1ubuntu0.1 payload from its live
archive pool, so the shared Linux CI preparation step fails with HTTP
404 before tests start. Address Ubuntu's recorded Launchpad build so
future pool pruning does not invalidate the pinned download location.
Select upstream's 0.12.0 security release for CVE-2026-87766 instead of
Ubuntu's isolated 0.9.0 backport, whose regressions and support limits
are documented by upstream in Launchpad bug 2166359. Keep checksum
verification, direct extraction, and the existing namespace probe.
Verify build 33546835 against its published SHA256 and archive SHA512.
Its amd64 ELF requires at most GLIBC_2.38 and x86-64 baseline; its
packaging requires Linux 5.10. Ubuntu 24.04 provides glibc 2.39, Linux
6.8, and the required libcap2/libselinux1 versions. This changes only
the CI helper's pinned payload, not product sandbox configuration.
The slow-backend regressions start real NodeRuntime subprocesses, but
vi.waitFor silently imposed a one-second deadline on normal scheduling and
tool execution. Under concurrent Linux and Windows coverage this rejected
valid runs before the tested spill or dispatch stage was reached.
Resolve promises at the actual save-entry and dispatch-start observations,
and fail immediately if the run completes before those observations. Queue
all three requests up front in the bounded-backlog case so a missing third
start tests backpressure rather than child request timing. Cleanup releases
both queued and future spill gates and awaits execution completion.
Keep the existing outer test deadlines, product limits, result assertions,
and ordering checks. A temporary 1.2-second tool delay reproduces both old
failures and passes with these tests; temporarily removing the actual
backpressure wait still fails the third-dispatch assertion. No experiment
or product-code change is included.
Fixes#4585
The case verifies first-boot catalog browsing and an actionable
MISSING_CREDENTIAL, so it follows the default catalog instead of an
unlisted id whose route only proves pass-through.
The shipped DeepSeek catalog keeps V41 Flash and V4 Pro only; the removed
ids still pass through as text-only routes when configured explicitly.
Updates the adapter tests, the Web settings goldens that render the default
catalog, and the regenerated config catalog.
With the plugin defaulting to on, the messages e2e case that asserts an
absent `dsh_session_log` must disable it explicitly; otherwise the stub
rejects the field it did not expect and the model call finishes as an
error. Also align the wire reference and feedback subsystem docs with the
default-on field.
The per-file coverage gate measures `packages/*/*/src` at 100% branches;
a short-circuiting `||` over the two lane markers leaves the second
operand unexecuted under Vitest. Testing the marker list instead keeps
the same default without an uncovered branch.
`@deepseek-ai/dsh-session-log-deepseek` now contributes `dsh_session_log`
unless a composition sets `enabled: false`. A recorded-Session lane
(`$VITEST` or `$DSH_SNAPSHOT`) keeps the default off, because its
committed fixtures are both replay input and expected output for the
persisted log; no fixture regeneration is needed.
Both archive verbs answer with the complete set, so a reply that lands
after a newer request or after a pushed increment overwrote it. The
Client model now installs an answer only while it is still the latest
archive-set request, and the follow increment and baseline supersede it.
Also narrow the page's public surface and its states: the locale
namespace stays internal, row derivation is a memo over the framework
hooks, the search input carries one accessible name, the empty-archive
message no longer covers a set whose entries cannot be restored, and the
new package declares no client dependency edge it does not import.
The Client Cordis catalog now publishes unarchiveSession on both the
Workspace service and the UI navigation capability, and the new Settings
section adds one nav row that every settings-dialog aria snapshot carries.
Refresh those expectations; the goldens gain only that row.
Sessions could be archived from the sidebar row menu but never restored:
the registry-global archive set was a one-way display filter with no
inverse RPC and no surface listing its members.
WorkspaceRegistry.unarchiveSession drops one id from archivedSessionIds in
one durable write on the same operation chain as archive, with no
session-existence probe because a removal cannot introduce an unknown
referent. The Workspace controller exposes it as workspace.unarchiveSession
returning the complete archive set, which the existing archived follow
increment already propagates, so no frame type and no persisted field
changes.
The new client package dsh-client-ui-settings-unarchive-sessions owns the
restore surface: one localized settings.section page listing the archive
set joined with loaded session summaries, newest archive first, searchable
by title or workspace, with one Unarchive action per row.
Vitest types `Reporter.onCoverage` as `unknown`, so a payload that carries no
istanbul `data` record now fails the partition instead of silently leaving
every location uncanonicalized; a spec case pins that rejection. The module
docs keep the contract and link the Agent Note for the mechanism, the
partition spec names what it asserts (the reporter argument, not Vitest hook
ordering), and the notes correct the `Infinity` origin to ast-v8-to-istanbul,
record the reporter-ordering dependency, and name the reporter each partition
child carries.
A source file carries one istanbul statement map per Vite environment, so a
node suite and a jsdom suite that load the same module enter the merged
report through two maps that spell one statement differently. istanbul
reconciles those overlapping ranges by attributing the hits of the narrowest
containing range, but only while a location carries numeric line and column
values. ast-v8-to-istanbul ends a whole-line statement at column Infinity, and
the partition blob serializes Infinity as null, so the merge command kept the
client-only spelling as an extra, unhit statement: a file whose every statement
ran reported 96.96% and failed the per-file 100% gate.
The coordinator now passes each partition a reporter whose onCoverage hook
rewrites every non-finite end column to a finite line-end column before the
blob is written, which restores that reconciliation without weakening the
gate. The uncovered-locations reporter reads the same column as a line end.
Tianyi Cui