main fast-forwarded to release/v3.8.25 (#3863): unblocked Build+Docker via
#3864, plus #3837 (mimocode proxy) and #3862 (trivy bump). This marker
re-opens the umbrella PR for further v3.8.25 work. No version bump.
Integrated into release/v3.8.25 — feat(mimocode): per-account proxy for multi-account round-robin (runWithProxyContext per account, keyed by fingerprint). Orphan test relocated to a collected vitest path (14/14 green).
main was fast-forwarded to release/v3.8.25 (#3805); this marker re-opens the
umbrella PR so further v3.8.25 work keeps flowing to main. No version bump —
development continues on the current v3.8.25 line.
Clarifies that the Default Strategy control syncs both new combo defaults and global
account fallback routing, and updates the Round Robin sticky-limit helper text to call
out account-level fallback behavior. Copy-only change to ComboDefaultsTab + en.json.
Integrated into release/v3.8.25.
Co-authored-by: Abhishek Divekar <adivekar@utexas.edu>
Kiro's catalog is per-account / per-tier (and admin-curated for IAM Identity Center
orgs), which the static registry can't reflect. The models route now discovers the
live list from the CodeWhisperer ListAvailableModels API with the stored OAuth token
(Builder ID / social and IdC accounts; profileArn only as a retry to avoid 403,
region-matched with us-east-1 fallback), falling back to the static registry catalog
when the token is missing/expired or the upstream is unavailable so import never breaks.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Gemini / Vertex / Vertex AI Express already discover their catalog dynamically from
v1beta/models, but video (Veo) models use predictLongRunning, which was not mapped —
so they never surfaced. parseGeminiModelsList now recognizes predictLongRunning and
exposes Veo video models alongside chat/image/embedding/audio.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Diagnostic mitigation: OpenCode Go has no public quota API today (the configured
endpoints return 404 / Z.ai 401). The fetcher now logs a single latched (per-process)
404 warning pointing at the upstream tracking issues, caches the "endpoint unavailable"
result for 5 minutes to avoid hammering, and fails open. The dashboard messaging is
clarified with the OMNIROUTE_OPENCODE_GO_QUOTA_URL override hint.
Integrated into release/v3.8.25.
Co-authored-by: Abhishek Divekar <adivekar@utexas.edu>
With Auto-hide failed models on (default), a Test All sweep across 10+ models in
parallel reliably trips per-account rate limits on subscription-tier providers, and
the 429'd/timed-out models were auto-hidden — silently removing working models from
/v1/models with no easy recovery. evaluateTestAllEntry now surfaces transient failures
(rateLimited/isTimeout) as an 'error' icon but keeps them visible; only genuine
(non-transient) failures are still auto-hidden.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
The kiro table in DEFAULT_PRICING was missing models the Kiro registry serves
(most visibly claude-sonnet-4.6), so getPricingForModel() returned null and their
usage cost was reported as $0.00. Adds the missing rows.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
The request log table is given a comfortable minimum height (~10 rows) and is
user-resizable vertically, replacing the previous flex/overflow-hidden constraints that
clipped it short. Pure layout change to the logs page and RequestLoggerV2 card.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Windows does not render regional-indicator flag emojis. The LanguageSelector now maps
a flag emoji's regional-indicator code points to an ISO country code and renders the
flag from flagcdn, falling back to the raw emoji span when the glyph is not a
two-letter regional pair or the image fails to load (onError).
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
A round-robin combo serving a streaming response returned a 500
(TypeError: ReadableStream is locked). validateResponseQuality() peeks streaming
bodies via getReader(), which locks result.body and returns an unlocked replay in
quality.clonedResponse. The priority strategy already returns
`quality.clonedResponse ?? result`, but the round-robin success path returned the
locked original. This mirrors the priority strategy so the body pipes downstream.
Added a regression test (#3811) that fails (body locked) without the fix.
Integrated into release/v3.8.25.
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
Moves the account email visibility control into Settings › Appearance (above Show
Sidebar Items) and removes the page-level email reveal buttons from combos, logs,
provider detail, provider quota, quota sharing, and the edit-connection modal. The
global masking state is unchanged — existing account labels still consume the shared
emailPrivacyStore — so one toggle now governs masking everywhere. The old
EmailPrivacyToggle component is replaced by AccountEmailVisibilitySetting.
Integrated into release/v3.8.25.
Co-authored-by: R.D. <rogerproself@gmail.com>
Adds ARENA_ELO_SYNC_ENABLED to the Dashboard Feature Flags registry (DB-overridable),
routes Arena ELO startup/status checks through the shared feature-flag resolver while
preserving the existing env fallback, and refreshes env docs (adds the missing
STREAM_READINESS_TIMEOUT_MS example) so env/doc sync stays green.
Integrated into release/v3.8.25.
Co-authored-by: R.D. <rogerproself@gmail.com>
Reuse the xhigh opt-out policy for OpenAI-compatible `max` normalization: non-Claude
providers map `max` to `xhigh` unless the target model explicitly opts out (DeepSeek
via OpenRouter supports xhigh), downgrading to `high` only on explicit opt-outs.
Resolves common Claude aliases (anthropic/claude-opus-4.6, anthropic.claude-opus-4-6,
short/dated/-thinking variants) back to the canonical Claude xhigh-support list, and
keeps literal `max` pass-through for native Claude/CC providers that support it. Also
moves the mistral/github reasoning-effort rejection ahead of normalization (it was
previously dead code for `max`). Includes the v3.8.25 release file-size re-baseline.
Integrated into release/v3.8.25.
Co-authored-by: R.D. <rogerproself@gmail.com>
Reworks stream readiness as a ping/zombie filter instead of a semantic content
gate: downstream streaming is released as soon as any structured non-ping SSE
event arrives, replaying the buffered prefix. Removes the fixed 2s first-byte
cap (readiness now inherits REQUEST_TIMEOUT_MS unless STREAM_READINESS_TIMEOUT_MS
is set) so slow first-byte reasoning providers no longer false-504.
Combo stream quality stays strict: validateResponseQuality still requires an
actual content_block / known non-Claude payload before accepting a routed target.
Also normalizes multi-line data: framing, metadata-prefixed events, and final
events that arrive without a trailing blank line.
Integrated into release/v3.8.25.
Co-authored-by: R.D. <rogerproself@gmail.com>
The Claude / Claude-Code model picker (VS Code Copilot's "Effort" slider)
advertises effort variants by appending a suffix to the base model id
(claude-...-{low,medium,high,xhigh,max}). Anthropic has no such model, so the
suffixed id was forwarded verbatim and 404'd upstream — repeated 404s then
tripped the account circuit breaker, surfacing to clients as a bogus
"rate limited" cooldown.
splitClaudeEffortSuffix() strips the suffix off Claude / Claude-Code targets
(the upstream receives the real base id) and surfaces the level as
reasoning_effort so the OpenAI->Claude translator / CC bridge convert it into
thinking/effort config. Explicit client effort is never overridden; native
Claude passthrough is untouched.
Integrated into release/v3.8.25.
Co-authored-by: Felipe Almeman <felipe@aireset.com.br>
Initializes initArenaEloSync() from instrumentation-node.ts (the Next standalone startup hook) instead of the never-executed server-init.ts, so the Free Provider Rankings page (#3799) actually gets data. On by default; opt out with ARENA_ELO_SYNC_ENABLED=false.
ARENA_ELO_SYNC_ENABLED flips to on-by-default (opt out with =false) so the Free Provider Rankings page (#3799) has data out of the box. Sync stays non-blocking/never-fatal.
