MiniMax-M3 had no MODEL_SPECS entry and capitalized MiniMax-M2.7 missed
its lowercase spec (case-sensitive lookup) → both fell to the 8192 default
cap. Add the M3 spec (512K output), alias the capitalized ids, and make
getModelSpec lookups case-insensitive.
Co-authored-by: totaltube <totaltube@users.noreply.github.com>
Assign unique aliases to HuggingChat, Kimi Web, and Qwen Web so they no longer shadow primary providers or trigger startup warnings.
Add a unit test to enforce provider alias uniqueness and prevent future collisions. Also expand local ignore and VS Code exclude rules for agent, build, and worktree artifacts.
Kiro (AWS CodeWhisperer) tops out at Claude Opus 4.7 in the registry, but the latest Opus 4.8 is already served by the Claude Code provider and Kiro's executor passes the model id through to CodeWhisperer verbatim. Expose claude-opus-4.8 on the kiro provider so clients can select it via kiro/claude-opus-4.8.
- providerRegistry: add claude-opus-4.8 (1M context, 128k output) above 4.7
- pricing: add claude-opus-4.8 (and the previously-missing 4.7) to the kiro pricing block at Kiro's standard Opus rate so usage cost is non-zero
- tests: assert kiro exposes claude-opus-4.8 with matching context/output + pricing
* feat(providers): implement bulk paste for extra API keys
Adds `parseExtraApiKeys` utility to process multi-line key inputs.
Integrates bulk paste functionality into the provider connection modal.
Users can now paste multiple API keys, one per line, into the input field.
Provides notifications for successfully added keys and ignored duplicates.
Adds a "Delete all" button to clear all extra API keys.
Updates i18n messages for new features and improved key masking/pluralization.
* refactor(providers): streamline API key bulk paste and i18n
Remove unused return from `handleAddParsedExtraKeys` to clean up code.
Adjust `onPaste` to allow default paste for single-line input, improving UX.
Remove obsolete bulk paste UI translation keys to reduce bundle size.
Update pluralization for bulk paste messages to ensure correct grammar.
Refine Portuguese (Brazil) API key translations for clarity.
* fix(logs): apply code review feedback - robust signature, immediate fetch on tab restore, reuse memoized apiKeyCount
* test(logs): extract pure polling/signature helpers + cover them (#3109)
Hard rule #8: the perf fix touched src/ without tests. Extract computeLogsSignature,
shouldAutoRefresh and resolveInitialVisibility into a pure module and unit-test
them (change-detection, first-page polling guard, SSR/hidden-tab visibility init).
Also fixes visibleRef to honor the real visibilityState on mount instead of
hardcoding true (no poll when mounted in a hidden tab).
---------
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(cli): handle Windows exe healthchecks with spaces
* Update src/shared/services/cliRuntime.ts
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* Update tests/unit/cli-runtime-extended.test.ts
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix(cli): pass command to spawn unquoted; export shouldUseShellForCommand
Remove the manual "${command}" interpolation into the shell command (hard rule
#13 violation, and redundant — Node quotes for cmd.exe when shell:true; .exe runs
with shell:false where the OS handles spaces via argv). Export the helper and add
a cross-platform test asserting non-Windows never uses the shell.
---------
Co-authored-by: Empire Rider <anuruddhawijesiri@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(sse): bound Antigravity short-retry 429 loop per endpoint
A persistent 429 on the short-retry branch (retryAfterMs ≤ 60s) looped
forever on the same endpoint because the branch did `urlIndex--; continue`
without checking the shared retry counter. Production log showed 77
consecutive 429s on one daily endpoint/account with zero fallback.
Gate the short-retry branch on `retryAttemptsByUrl[urlIndex] < MAX_AUTO_RETRIES`
(mirroring the already-bounded sibling), so a persistent 429 retries at most
3× per endpoint across all 3 base URLs then returns the 429 to the account-
fallback layer.
Regression test: 'bounds a persistent short-retry 429' in
tests/unit/executor-antigravity.test.ts — asserts 12 total attempts
(3 endpoints × 4) and a returned 429 with zero hang.
* fix(sse): lock Antigravity quota-exhausted account for full reset window
After the retry-loop bound, OmniRoute fell over to the next account but
re-selected the exhausted one first on every subsequent request (~60s wasted
per request). Root cause: the 429 body 'Individual quota reached. Contact
your administrator to enable overages. Resets in 164h27m24s.' was not
recognized as quota exhaustion, so the model was locked for only ~5s instead
of the real 6.8-day reset window.
Two detector fixes (mirrors Antigravity-Manager rate_limit.rs set_lockout_until):
1. classify429.ts — add QUOTA_PATTERNS: /individual quota reached/i,
/quota reached/i, /enable overages/i so looksLikeQuotaExhausted() fires.
2. accountFallback.ts — same patterns in classifyErrorText(); extend
parseRetryFromErrorText() to parse 'Resets? in XhYmZs' (reusing the
existing computeDurationMs helper) so the exact reset duration reaches
recordModelLockoutFailure as exactCooldownMs (uncapped, per user choice).
The lockout machinery already stores until = now + cooldownMs with no clamp,
bypasses getScaledCooldown when exactCooldownMs > 0, and keeps the longer of
existing/new, so the full 164h window flows through intact.
New patterns stay specific — plain 'too many requests'/'rate limit exceeded'
messages still classify as rate_limit.
Verified end-to-end against the real message:
- classify429 → quota_exhausted
- parseRetryFromErrorText → 592044000 ms (164h27m24s exactly)
- checkFallbackError → usedUpstreamRetryHint: true, cooldownMs: 592044000
* refactor(account-fallback): simplify error parsing and add cooldown safety
- Implement a 30-day cap on parsed retry durations to prevent indefinite account lockouts.
- Replace manual string matching with `looksLikeQuotaExhausted` for more robust quota detection.
- Streamline regex logic in `parseRetryFromErrorText` for better readability.
- Add unit tests for extreme cooldown values and free-tier exhaustion scenarios.
* fix(429): drop over-broad /quota reached/ pattern, keep specific matches
The bare /quota reached/ would also flag transient per-minute limits like
'request quota reached, retry in 60s' as quota_exhausted (multi-hour lock).
The Antigravity message is still caught by /individual quota reached/. Added a
regression assertion proving the transient case stays a rate_limit.
---------
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
grok-web only sent the 'sso' cookie; Grok's anti-bot now rejects (403 code 7) requests missing the paired 'sso-rw' write cookie. Adds buildGrokCookieHeader() which emits sso plus sso-rw when the pasted blob carries it (never a phantom sso-rw from a bare value), used by both the executor and the connection validator. Updates the grok-web authHint. Tests: 6 new buildGrokCookieHeader cases; grok-web 62/62 unchanged.
Add a global OMNIROUTE_CODEX_WS_ENABLED kill-switch for Codex WebSocket transport, defaulting to enabled if feature flag lookup fails.
Track Xiaomi MiMo monthly token usage from OmniRoute usage history and expose it through the usage fetcher provider list.
E2E testing on the VPS showed a normal key (empty allowedQuotas) could call a
qtSd/<group>/<provider>/<model> virtual model and route through a shared quota
pool — because the quota-exclusive enforcement (Check 3) only ran when
allowedQuotas was non-empty, so an unallocated key fell through to the normal
model checks and qtSd was served. This is the "empty allowedQuotas = all pools"
gap from the redesign.
Add Check 2.9 in enforceApiKeyPolicy: if the requested model is a qtSd model and
the key is NOT allocated to any quota pool (allowedQuotas empty), reject 403
QUOTA_NOT_ALLOCATED. Allocated keys are unchanged (Check 3 still validates scope).
This matches the owner's rule: only a key selected in a pool may use its qtSd
models. Normal (non-qtSd) model access for normal keys is unchanged.
Test: tests/unit/apikeypolicy-quota-only.test.ts — new case asserts a non-quota
key is blocked from qtSd (QUOTA_NOT_ALLOCATED) yet still uses normal models.
#3054 ("remove 9 dead/unreachable free providers") removed the petals/nanobanana
configs, registry entries and validators but left dangling references that broke
the build and the unit suite on release/v3.8.8:
- open-sse/executors/petals.ts imported the deleted ../config/petals.ts
(webpack "Module not found" → `next build` failed). Removed the executor, its
registration + re-export in executors/index.ts, and the leftover
`providerId === "petals"` branch in providerAllowsOptionalApiKey.
- Removed tests for the now-deleted providers: executor-petals.test.ts and
poolside-provider.test.ts (REGISTRY.poolside was removed), and the petals /
nanobanana validator assertions in provider-validation-specialty.test.ts,
plus the stale petals catalog assertions in providers-page-utils.test.ts,
proxy-connection-test.test.ts and providers-route-managed-catalog.test.ts.
The image/video/embed registries for nanobanana/replicate/nomic are real and
untouched — only the dead chat/api-key surfaces were removed. 146/146 affected
tests pass; typecheck / build clean.
* chore: remove 9 dead/unreachable free providers
Verified via HTTP probe — API endpoints return 000/404/empty:
- freetheai, enally, replicate, lepton, poolside, nomic
- astraflow, petals, nanobanana (phantom: catalog but no registry)
Also removed from: providerRegistry.ts, validation.ts,
staticModels.ts, imageValidation.ts, open-sse/config/petals.ts
* chore: remove dead astraflow providers
Remove astraflow and astraflow-cn (UCloud) — API endpoints unreachable.
Remaining dead providers (enally, freetheai, nanobanana, replicate,
lepton, petals, poolside, nomic) have working main sites but dead API
endpoints — need API keys. Will remove in follow-up.
* chore: remove 9 dead/unreachable free providers
Removed: freetheai, enally, replicate, lepton, poolside, nomic,
astraflow, petals, nanobanana
All verified as dead via live API probes (000/404/empty responses).
Cleaned from providers.ts, providerRegistry.ts, validation.ts,
staticModels.ts, and imageValidation.ts.
---------
Co-authored-by: oyi77 <oyi77@users.noreply.github.com>
Integrated into release/v3.8.8. Applied review fixes: moved the SELECT 1 into a pingDb() db helper (no raw SQL in route, Hard Rule #5) + the 503 catch no longer leaks err.message (Hard Rule #12). Thanks @herjarsa!
Task B9: QuotaSharePageClient fetches /api/quota/groups, renders a group bar
(select + New group + Rename group actions), and filters pool cards by the
selected group. PoolWizard adds a group picker in step 1 and POSTs groupId;
default pool name now uses provider slug instead of the raw connection
label/email. EditAllocationsModal adds a group allocation note. i18n parity
for 7 new quotaShare keys in en + pt-BR. PoolCreateSchema gains optional
groupId field. Test: tests/unit/quota-groups-ui.test.ts (21 source-scan
assertions, all green).
Add GET/POST /api/quota/groups and PATCH/DELETE /api/quota/groups/[id].
PATCH rename calls renameGroup then re-syncs quotaShared-* combos (via
dynamic-import syncQuotaCombos) for every pool in the group, since combo
names embed the group slug. DELETE maps the deleteGroup throw (protected
group-demo or pools still referencing the group) to 409 Conflict via
buildErrorBody — never 500. All handlers are management-gated via
requireManagementAuth and route all errors through buildErrorBody (Hard
Rule #12). 37-assertion source-scan test verifies auth, error sanitisation,
response shapes, Zod validation, PATCH re-sync wiring, and DELETE 409 logic.
Replace the old quotaShared-<poolSlug>-<provider>/<model> format with
qtSd/<groupSlug>/<provider>/<model>. Adds quotaGroupSlug() as the canonical
helper; keeps quotaPoolSlug() as a delegating alias so existing callers
(quotaKey.ts, quotaCombos.ts) compile without changes. parseQuotaModelName
now returns { groupSlug, provider, model }. Updates quotaCombos.ts,
apiKeyPolicy.ts, and all tests that referenced the old field name or the
old hardcoded prefix literal.
Mark duckduckgo-web in WEB_COOKIE_PROVIDERS with noAuth and include it in providerAllowsOptionalApiKey. Update getProviderCredentials to check both NOAUTH_PROVIDERS and WEB_COOKIE_PROVIDERS for noAuth providers (returning synthetic credentials) and import WEB_COOKIE_PROVIDERS accordingly. This enables anonymous/anonymous-cookie web providers to be handled without DB lookups.
Custom models (added via the UI) on opencode-go / openai-compatible nodes always
routed as OpenAI-compatible because there was no per-model targetFormat: addCustomModel
didn't accept it, the API schema stripped it, and getModelTargetFormat (static-registry
only) never saw it — so a custom model needing the Anthropic Messages shape fell back to
the provider default 'openai'.
Thread an optional targetFormat through addCustomModel / replaceCustomModels /
updateCustomModel + the providerModelMutationSchema + the POST/PUT route, surface it from
getModelInfo (one combined custom-model metadata lookup alongside apiFormat), and use it
in chatCore's targetFormat resolution before the provider default.
Closes#2905
Custom providers (openai-compatible-<uuid> / anthropic-compatible-<uuid>) showed
the raw UUID id instead of the user-given node name in the active-requests panel,
proxy logger, and home-page provider topology. Only RequestLoggerV2 resolved it
(via a local helper + /api/provider-nodes fetch).
Extract the resolver into a shared util (src/shared/utils/providerDisplayLabel.ts,
unit-tested), reuse it in RequestLoggerV2, and apply it (with a provider-nodes
fetch) in ActiveRequestsPanel, ProxyLogger, and the HomePageClient topology so all
surfaces show the user-defined provider name.
Closes#2968
- PoolCreateSchema: add optional connectionIds[] + .refine() that enforces primary membership
- PoolWizard: replace single-select dropdown with checkbox multi-select; first checked = primary (badge); step-2 adds helper note for additional connections; step-3 preview grouped by provider with +N more; POST body sends both connectionId and connectionIds
- PoolCard: optional providers[] prop renders a row of ProviderIcon (up to 3 + badge) instead of a single icon when pool has multiple connections
- i18n: 4 new keys added to both en.json and pt-BR.json (wizardConnectionsLabel, wizardPrimaryBadge, wizardAdditionalConnectionsNote, wizardPreviewMoreModels) — parity maintained (23 wizard keys each)
- Tests: quota-pool-wizard-multi.test.ts (21 tests) covering schema accept/reject, structural wizard assertions, and i18n parity
Keys with non-empty allowedQuotas may only use models whose provider belongs
to their pools' provider set; anything outside → 403 QUOTA_ONLY.
Normal allowedModels/allowedCombos checks are bypassed for quota-exclusive keys.
- search-tools: export modal no longer opens by default / stuck — guard on
exportOpen and drop the invalid isOpen prop the modal never read.
- logs: remove duplicate proxy/console tabs + SegmentedControl (dedicated
/dashboard/logs/proxy and /console pages already exist in the menu).
- memory: order tabs Memories -> Engine -> Playground.
- ui(Select): render children and suppress the placeholder/options branch when
children are provided — fixes the "empty" memory type/strategy dropdowns
(children were being shadowed by the component's own option list).
- test: source-level regression guards for all four.
