Add grok-build-0.1 to XAI_BUILTIN_EXCLUDED_MODEL_IDS so the generated xAI
catalog only lists grok-4.3, grok-4.5 and grok-4.6. Update the exclusion
test and drop the thinking-level assertion for the removed model.
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
waitForChildProcess resolved null for the exit code when a child was killed by a signal (e.g. OOM killer), and exec mapped it with code ?? 0, so the bash tool treated killed commands as successful.
Track the termination signal and fall back to the shell convention of 128 + signal number (137 for SIGKILL) when no exit code is available.
fixes#8992closes#8882
Adds TuiAltScreenOptions.scrollToEndIndicator, composited onto the last
row of the follow-end primary scroll view while it is scrolled up. A left
press on the label resumes end-following. Minimal rebuild of #9080.
createGatewayBindingFetch (0.84.2) translated requests from a gateway
HTTPS prefix into the AI binding's universal endpoint, building the
[{provider, endpoint, headers, query}] envelope by splicing the request
body into a JSON string. The gateway now serves its provider-native
passthrough over the binding at
/ai-gateway/gateways/{gateway}/{provider}/..., the HTTPS path minus the
account id, so a model can simply name that route as its baseUrl and
there is nothing left to translate.
The fd/ripgrep auto-download resolved the latest version through
api.github.com, which shares the anonymous API quota (60 requests/hour
per IP). Behind shared egress IPs (corporate proxies, CI runners, NAT)
that quota is permanently exhausted by unrelated traffic, so the
download failed with 'GitHub API error: 403' on every launch while the
actual release download endpoint would have worked fine.
Resolve the version from the /releases/latest web redirect instead: it
carries the tag in the Location header, is not subject to the API
quota, and lives on the same origin as the binary download itself. The
redirect body is discarded so the connection can be reused, and the
pinned fd version on darwin/x64 now skips the lookup entirely.
Also improve download failure diagnostics: status messages include the
error cause chain so transport errors surface their actionable detail
instead of a bare 'fetch failed', and HTTP download errors include the
failing URL.
Fixes#8594
Co-authored-by: Terminator666666 <Terminator666666@users.noreply.github.com>
* feat(coding-agent): ingest external entries in in-memory sessions
SessionManager.inMemory() takes the entries to start from, so a session
held outside the filesystem can be resumed as it was stored.
Replaying through appendMessage/appendCompaction cannot do this: ids are
minted fresh, so every stored firstKeptEntryId, targetId and fromId has to
be remapped, timestamps are rewritten, and parentId always comes from the
current leaf, so a branched tree needs the original branch() choreography
reproduced call by call.
The entry-adoption half of _setSessionFile becomes _loadEntries, which the
constructor also uses when there are entries but no file. Entries carrying
a session header keep it; without one, the header comes from the options
and the entries become its body.
* fix(coding-agent): carry the stored version through restored entries
inMemory() took SessionEntry[], which excludes SessionHeader, so an
external store could not pass the header it saved and the header branch of
_loadEntries was unreachable through the public API. A restore therefore
always synthesised a current-version header, and the migration that ran
next read that header and skipped: a v2 session kept its hookMessage roles
forever.
Widening to FileEntry[] lets the stored header through, version included.
Migration moves inside the header branch, where a version exists to compare
against; without a header the entries are adopted as current-version, which
is the only thing they can mean.
OpenAI-compatible providers can now send vLLM's top-level 'priority'
request field (lower value = earlier handling, server default 0),
which matters when vLLM runs with --scheduling-policy priority and a
box serves both interactive and background/batch work: setting
vllmPriority on a background model defers its long prefills behind
interactive sessions.
- types.ts: OpenAICompletionsCompat.vllmPriority?: number (off by default)
- openai-completions.ts: resolved through getCompat, injected in buildParams
- model-config.ts: models.json schema accepts compat.vllmPriority
- test: priority sent when set, omitted otherwise
Co-authored-by: Daniel-Clegg <daniel.clegg@civica.co.uk>
streamProxy dropped a final SSE event that was not newline-terminated
(the residual line buffer was never flushed after the read loop) and
called stream.end() without a result when no done/error event had been
seen, leaving EventStream.result() pending forever. Consumers like
agentLoop awaiting response.result() hung indefinitely when the server
closed the connection mid-response.
Flush the decoder and process the residual buffer after EOF, and push a
synthesized error event when the stream ended without a terminal event.
fixes#8996
