mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-03 13:52:09 +03:00
* chore(release): open v3.8.23 development cycle
* fix(anthropic): strip top_p when temperature is set to avoid 400 (#3691)
Integrated into release/v3.8.23
* fix(vertex): support Vertex AI Express-mode API keys (#3690)
Integrated into release/v3.8.23
* fix(stream): error on empty Claude SSE instead of synthetic success (#3689)
Integrated into release/v3.8.23
* fix(oauth): stop token-refresh invalidation loop + harden proxy resolution (#3692)
Integrated into release/v3.8.23
* docs: add FUNDING.yml and Support section to README (#3698)
Integrated into release/v3.8.23
* feat: gemini - handle known ratelimits (#3686)
Integrated into release/v3.8.23
* fix: stream combo fails over on empty content-filtered response (#3685) (#3702)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(antigravity): preserve gemini-3.1-pro high/low budget tiers (#3696) (#3703)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(auto-combo): add auto-updating model intelligence scoring (#3660)
Integrated into release/v3.8.23
* fix(gemini): context-mode fallback for signatureless tool calls (#3688) (#3704)
* chore(quality-gate): reconcile file-size baseline (27 files + providerLimits.ts) (#3705)
* feat(vertex): dynamic model discovery via Generative Language models API (#3712)
Integrated into release/v3.8.23. Vertex dynamic model discovery — surfaces image models (imagen-*, gemini-*-image), embeddings and audio from the live Generative Language catalog, with cached→static fallback and the shared parseGeminiModelsList helper. Validated: parser test 5/5, typecheck:core clean.
* fix(combo): gate reasoning token buffer (#3700)
Integrated into release/v3.8.23. Makes the #3588 reasoning token buffer safe and configurable: only inflates max_tokens when the model has a known, non-default output cap and the buffered value fits inside it; otherwise preserves/clamps the client limit. Adds the reasoningTokenBufferEnabled kill switch (default ON). Validated: combo-routing-engine 81/81, combo-config 25/25, combo-quality-validator-reasoning 12/12, phase1f 10/10, typecheck:core clean.
* refactor(#3501): god-component Phase 1g-1j — client 4062→3408 LOC (-654) (#3717)
Phase 1g-1j of #3501: client 4062→3408 LOC. Pure extraction (ProviderPlaygroundPanel, useCommandCodeAuth, useExternalLinkFlow+ExternalLinkModal, useAuthFileHandlers) + loadConnProxies ReferenceError fix + phase1f test path fix.
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
* refactor(#3501): god-component Phase 1k-1m — client 3408→2553 LOC (-855) (#3721)
Phase 1k-1m of #3501: client 3408→2553 LOC. Pure extraction (useModelImportHandlers+ImportProgressModal, useModelVisibilityHandlers, ProviderModelsSection).
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
* docs(changelog): restore #3590 bullet lost on the v3.8.20 release branch
The fix itself reached main pre-tag via cherry-pick #3591, but its changelog
bullet (commit e33fdd4ab) only ever existed on release/v3.8.20 after the
squash-merge. Restored under [3.8.20] per the 2026-06-12 release-branch
leftover audit (_tasks/release-audit/release-leftovers-audit-2026-06-12.md).
* fix(kiro): resolve quota for IAM Identity Center accounts missing a profileArn (#3722)
Integrated into release/v3.8.23
* refactor(#3501): god-component Phase 1n-1s — client 2553→1376 LOC (-1177) (#3725)
Phase 1n-1s of #3501: client 2553→1376 LOC. Pure extraction (ConnectionsListPanel, ConnectionsHeaderToolbar, ZedImportCard, BatchTestResultsModal, AdaptaTutorialModal, useApiKeySave + helpers).
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
* feat(model-lockout): settings UI, backend integration, error classification, and success-decay recovery (#3629)
Integrated into release/v3.8.23
* refactor(#3501): god-component Phase 1t — client 1376→781 LOC (≤800 TARGET REACHED ✅) (#3727)
Phase 1t of #3501: client 1376→781 LOC (≤800 reached). Original god-component 12,882→781 (−94%).
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
* fix: bundle @omniroute/opencode-plugin inside omniroute + add 'setup opencode' CLI command (#3726)
Integrated into release/v3.8.23
* feat(vertex): self-tracked USD spend since account added (#3724)
Integrated into release/v3.8.23
* fix(qwen-web): migrate to v2 chat API with full cookie-jar replay (#3288) (#3723)
Integrated into release/v3.8.23
* fix(sse): make safeLogEvents async — 'await' in a sync function broke every chatHelpers import
#3692 added a lazy 'await import(proxyEgress)' for egress-IP visibility inside
safeLogEvents, which is a sync function — an ES syntax error. It went unnoticed
because typecheck:core does not cover src/sse and no test in the merge gates
loaded chatHelpers via tsx; any consumer that did (chat-context-relay and
chat-route-coverage suites, integration harnesses) failed at module load with
'await can only be used inside an async function'.
safeLogEvents is fire-and-forget logging with an outer try/catch, so making it
async (and 'void'-ing the single chat.ts call site) preserves behavior exactly.
Validation: tests/unit/chat-context-relay.test.ts + chat-route-coverage.test.ts
went from failing-at-load to green (+14 tests destravados).
* fix(sse): remove cross-provider credential leak in emergency fallback + combo/proxy audit fixes (#3699)
Integrated into release/v3.8.23
* fix(executors): inject MiMoCode anti-abuse marker so free endpoint stops 403ing (#3728)
Integrated into release/v3.8.23
* fix(dashboard): repair "Test all models" — toast crash, status icons, auto-hide (#3729)
Integrated into release/v3.8.23
* chore(deps): bump actions/upload-artifact from 4 to 7 (#3735)
Integrated into release/v3.8.23 — aligns upload-artifact to v7 (already used across ci.yml).
* chore(deps): bump actions/cache from 4 to 5 (#3734)
Integrated into release/v3.8.23 — actions/cache v4→v5.
* chore(deps): bump actions/download-artifact from 4 to 8 (#3733)
Integrated into release/v3.8.23 — download-artifact v4→v8.
* feat(fallback): add OMNIROUTE_EMERGENCY_FALLBACK env switch (#3741)
Adds an OMNIROUTE_EMERGENCY_FALLBACK env switch to disable the emergency budget-exhaustion fallback (reroute to free nvidia/gpt-oss-120b). Default unchanged (enabled). Closes #3739, related #2879.
Integrated into release/v3.8.23.
* i18n: comprehensive zh-CN translation improvements (#3736)
Aligns zh-CN to en (hundreds of entries), translates batch-action labels + settings sidebar menu, adds categoryConfig/endpointTokenSaver keys, resolves __MISSING__ stubs. Sidebar/SidebarTab hardcoded strings replaced with t(). en.json purely additive (8 new sidebar.* keys, 0 removed); cli-i18n gate green.
Integrated into release/v3.8.23.
* chore(release): v3.8.23 — 2026-06-12
- CHANGELOG: complete v3.8.23 section (28 bullets, 27 commits)
- fix(webdav): resolve promise on writeStream finish, not req end — eliminates
intermittent 500 on PUT update (writeStream may not have flushed at rename time)
- test(autoCombo): stub DB calls from PR #3660 in tieredRotation.test.ts to prevent
5s timeout in vitest (getModelIntelligenceBySource DB init path)
- chore(env-sync): add XDG_DATA_HOME + OMNIROUTE_OPENCODE_PLUGIN_DIR to IGNORE_FROM_CODE
allowlist (introduced by PR #3726 setup-open-code.mjs, not OmniRoute config vars)
- chore(cli): regenerated bin/cli/api-commands/*.mjs (7 new, 27 updated)
* fix(model-family): fallback lookup also tries bare model name with dots
getNextFamilyFallback normalized dots-to-hyphens ("gemini-3.1-pro-high" →
"gemini-3-1-pro-high") but MODEL_FAMILIES keys use the literal dot form. The
lookup always missed, returning null for any model whose dots are part of the
name rather than a version separator.
Fallback: try MODEL_FAMILIES[lookupKey] ?? MODEL_FAMILIES[bareModel] so both
naming conventions are covered. Fixes T30 test (pre-existing since v3.8.22).
* feat: expose API key cost drilldown + quota % used (#3742)
Adds all-time USD cost per API key in the API Key Manager, a per-key deep-link into the Cost Explorer (filtered + grouped by model), URL-param hydration of range/groupBy/apiKeyIds, and a '% used' quota display. Review adjustments: extracted URL-param parsers to a tested module (Rule #18), i18n'd the new strings (en + zh-CN), dropped the redundant webdav-handler entry already on release.
Integrated into release/v3.8.23.
* feat: add provider display modes — All / Configured / Compact (#3743)
Replaces the Providers page configured-only toggle with All/Configured/Compact display modes (Compact = flat deduped grid, no-auth last). Persists the preference and migrates the legacy localStorage key. Rebased onto release/v3.8.23.
Integrated into release/v3.8.23.
* fix(cache): scope semantic-cache signature to API key (#3740)
Adds the api_key_id dimension to generateSignature's SHA-256 hash so two callers with different API keys never receive each other's cached responses. Threads apiKeyId through checkSemanticCache + both write sites; migration 098 clears pre-existing key-less entries; unauthenticated requests stay isolated from keyed ones. 3 TDD tests.
Integrated into release/v3.8.23.
* fix(responses): apply OpenAI Responses API stream=false spec default (#3708)
resolveStreamFlag now applies the stream=false-when-omitted default for sourceFormat=openai-responses (same as the existing claude path), so spec-compliant /v1/responses upstreams that return JSON no longer fall through to the wildcard-Accept heuristic and trigger STREAM_EARLY_EOF / 502. Codex CLI (stream:true) and explicit text/event-stream clients unaffected.
Integrated into release/v3.8.23.
* chore(release): reconcile CI gates for v3.8.23
- file-size baseline: re-freeze 8 files grown by PRs #3742/#3743/#3740
(cost drilldown, provider display modes, cache key isolation)
- ARCHITECTURE.md: update executor count 55→60 (check:docs-counts drift)
- .env.example: add OMNIROUTE_EMERGENCY_FALLBACK (#3741, env-doc-sync)
- CHANGELOG: add formatted bullets for #3742, #3743, #3708, #3740,
model-family-fallback fix; remove duplicate raw ### Fixed section
* test: restore assert count to satisfy check:test-masking gate
Three test files had net assertion removals after behavior-changing PRs:
- chatcore-translation-paths: emergency fallback moved to routing layer
(#3699) — add body error assertion + model-name guard
- executor-vertex-extended: non-JSON is now Express API key (#3690) —
add projects/-path guard to the express-key URL test
- stream-utils: empty streams now emit error (#3685) — add code/message/
status/completePayload guards to both passthrough and translate variants
All new assertions are meaningful (code enum value, 5xx range, non-empty
message, onComplete must-not-fire contract).
* fix(ci): move rtl-logical-classes test to ui/ so vitest:ui runner collects it
---------
Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com>
Co-authored-by: NOXX - Commiter <artur1992123@mail.ru>
Co-authored-by: Nick Sullivan <142708+TechNickAI@users.noreply.github.com>
Co-authored-by: Markus Hartung <mail@hartmark.se>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: PizzaV <103120356+pizzav-xyz@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: oyi77 <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Chewji <126886556+Chewji9875@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zois Pagoulatos <zpagoulatos@hotmail.com>
Co-authored-by: sdfsdfw2 <167810361+sdfsdfw2@users.noreply.github.com>
Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
236 lines
8.3 KiB
TypeScript
236 lines
8.3 KiB
TypeScript
/**
|
|
* Model Family Fallback — Phase 2 Feature (T5)
|
|
*
|
|
* Implements two-phase model resolution:
|
|
* Phase 1 (static, pre-request): already done by model.ts alias resolution.
|
|
* Phase 2 (dynamic, post-error): when a provider returns a model-not-available
|
|
* error (400 with specific message or 404), we try sibling models within the
|
|
* same "family" before giving up.
|
|
*
|
|
* Inspired by Antigravity Manager's account-aware dynamic model remapping
|
|
* (commit 6cea566, Mar 8 2026).
|
|
*/
|
|
|
|
import { getModelContextLimit } from "../../src/lib/modelCapabilities";
|
|
import { parseModel } from "./model.ts";
|
|
import { CONTEXT_OVERFLOW_REGEX } from "./errorClassifier.ts";
|
|
import { getRegistryEntry } from "../config/providerRegistry.ts";
|
|
|
|
// ── Model Family Definitions ─────────────────────────────────────────────────
|
|
|
|
/**
|
|
* Ordered candidate lists per model family.
|
|
* First entry is the most preferred; fallback proceeds in order.
|
|
*/
|
|
const MODEL_FAMILIES: Record<string, string[]> = {
|
|
// Gemini 3 / 3.1 Pro family — ordered by preference
|
|
"gemini-3-pro": [
|
|
"gemini-3.1-pro-preview",
|
|
"gemini-3-pro-preview",
|
|
"gemini-3.1-pro-high",
|
|
"gemini-3-pro-high",
|
|
"gemini-3.1-pro-low",
|
|
"gemini-3-pro-low",
|
|
],
|
|
"gemini-3.1-pro": [
|
|
"gemini-3.1-pro-preview",
|
|
"gemini-3-pro-preview",
|
|
"gemini-3.1-pro-high",
|
|
"gemini-3-pro-high",
|
|
"gemini-3.1-pro-low",
|
|
"gemini-3-pro-low",
|
|
],
|
|
"gemini-3-pro-preview": [
|
|
"gemini-3.1-pro-preview",
|
|
"gemini-3-pro-high",
|
|
"gemini-3.1-pro-high",
|
|
"gemini-3-pro-low",
|
|
"gemini-3.1-pro-low",
|
|
],
|
|
"gemini-3.1-pro-preview": [
|
|
"gemini-3-pro-preview",
|
|
"gemini-3.1-pro-high",
|
|
"gemini-3-pro-high",
|
|
"gemini-3.1-pro-low",
|
|
"gemini-3-pro-low",
|
|
],
|
|
"gemini-3-pro-high": [
|
|
"gemini-3.1-pro-high",
|
|
"gemini-3-pro-preview",
|
|
"gemini-3.1-pro-preview",
|
|
"gemini-3-pro-low",
|
|
"gemini-3.1-pro-low",
|
|
],
|
|
"gemini-3.1-pro-high": [
|
|
"gemini-3-pro-high",
|
|
"gemini-3.1-pro-preview",
|
|
"gemini-3-pro-preview",
|
|
"gemini-3.1-pro-low",
|
|
"gemini-3-pro-low",
|
|
],
|
|
|
|
// Gemini 2.5 Pro family
|
|
"gemini-2.5-pro": ["gemini-2.5-pro-preview-06-05", "gemini-2.5-pro-exp-03-25"],
|
|
"gemini-2.5-pro-preview-06-05": ["gemini-2.5-pro", "gemini-2.5-pro-exp-03-25"],
|
|
|
|
// Claude Mythos family (Fable 5) — flagship falls to the next-best Opus
|
|
// tiers before the cheaper Sonnet, matching the Opus family ordering.
|
|
"claude-fable-5": ["claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],
|
|
|
|
// Claude Opus family
|
|
"claude-opus-4-8": ["claude-opus-4-7", "claude-opus-4-6", "claude-sonnet-4-6"],
|
|
"claude-opus-4-7": ["claude-opus-4-6", "claude-opus-4-5-20251101", "claude-sonnet-4-6"],
|
|
"claude-opus-4-6": ["claude-opus-4-6-thinking", "claude-opus-4-5-20251101", "claude-sonnet-4-6"],
|
|
"claude-opus-4-6-thinking": ["claude-opus-4-6", "claude-opus-4-5-20251101"],
|
|
|
|
// Claude Sonnet family
|
|
"claude-sonnet-4-6": ["claude-sonnet-4-5-20250929", "claude-sonnet-4-20250514"],
|
|
"claude-sonnet-4-5-20250929": ["claude-sonnet-4-6", "claude-sonnet-4-20250514"],
|
|
|
|
// GPT-5 family
|
|
"gpt-5": ["gpt-5-mini", "gpt-4o"],
|
|
"gpt-5.1": ["gpt-5.1-mini", "gpt-5", "gpt-4o"],
|
|
};
|
|
|
|
// ── Error Detection ──────────────────────────────────────────────────────────
|
|
|
|
/**
|
|
* Error message fragments that indicate the requested model is unavailable
|
|
* for the current account/provider, as opposed to a transient error.
|
|
*/
|
|
const MODEL_UNAVAILABLE_FRAGMENTS = [
|
|
"model not found",
|
|
"model_not_found",
|
|
"model not available",
|
|
"model is not available",
|
|
"no such model",
|
|
"unsupported model",
|
|
"unknown model",
|
|
"this model does not exist",
|
|
"invalid model",
|
|
"model not supported",
|
|
"does not support",
|
|
"not enabled for",
|
|
"access to model",
|
|
"improperly formed request", // Kiro 400 (model unavailable)
|
|
];
|
|
|
|
/**
|
|
* Returns true if the HTTP status + error message indicates the model
|
|
* itself is not available, not a transient server error.
|
|
*/
|
|
export function isModelUnavailableError(status: number, errorMessage: string): boolean {
|
|
if (status === 404) return true;
|
|
if (status !== 400 && status !== 403) return false;
|
|
|
|
const msg = errorMessage.toLowerCase();
|
|
return MODEL_UNAVAILABLE_FRAGMENTS.some((fragment) => msg.includes(fragment));
|
|
}
|
|
|
|
export function isContextOverflowError(status: number, errorMessage: string): boolean {
|
|
if (status !== 400) return false;
|
|
return CONTEXT_OVERFLOW_REGEX.test(errorMessage);
|
|
}
|
|
|
|
// ── Fallback Resolution ──────────────────────────────────────────────────────
|
|
|
|
/**
|
|
* Get the next fallback model from the same family.
|
|
*
|
|
* @param currentModel The model that just failed
|
|
* @param triedModels Set of model IDs already tried (to avoid cycles)
|
|
* @returns Next model to try, or null if family exhausted
|
|
*/
|
|
export function getNextFamilyFallback(
|
|
currentModel: string,
|
|
triedModels: Set<string>
|
|
): string | null {
|
|
const parsed = parseModel(currentModel);
|
|
const bareModel = parsed.model || currentModel;
|
|
const provider = parsed.provider || parsed.providerAlias || "";
|
|
const prefix = provider ? `${provider}/` : "";
|
|
|
|
// Normalize dots to hyphens so kiro/claude-opus-4.8 finds the right entry.
|
|
// Fall back to the bare model name to support keys like "gemini-3.1-pro-high"
|
|
// whose dots are part of the literal name, not a version separator.
|
|
const lookupKey = bareModel.replace(/\./g, "-");
|
|
const family = MODEL_FAMILIES[lookupKey] ?? MODEL_FAMILIES[bareModel];
|
|
if (!family) return null;
|
|
|
|
// Resolve the provider's supported model IDs so we can match notation (dot vs hyphen)
|
|
const registryEntry = provider ? getRegistryEntry(provider) : null;
|
|
const supportedIds = registryEntry ? new Set(registryEntry.models.map((m) => m.id)) : null;
|
|
|
|
for (const candidate of family) {
|
|
let resolvedCandidate = candidate;
|
|
if (supportedIds && !supportedIds.has(candidate)) {
|
|
// Try dot-notation variants: claude-opus-4-8 → claude-opus-4.8
|
|
const dotVariant = candidate.replace(/-(\d+)-(\d+)$/, "-$1.$2");
|
|
const dotVariant2 = candidate.replace(/-(\d+)-(\d+)-/, "-$1.$2-");
|
|
if (supportedIds.has(dotVariant)) resolvedCandidate = dotVariant;
|
|
else if (supportedIds.has(dotVariant2)) resolvedCandidate = dotVariant2;
|
|
}
|
|
const fullCandidate = `${prefix}${resolvedCandidate}`;
|
|
if (!triedModels.has(fullCandidate)) {
|
|
return fullCandidate;
|
|
}
|
|
}
|
|
|
|
return null; // family exhausted
|
|
}
|
|
|
|
/**
|
|
* Check if a model belongs to any registered family.
|
|
*/
|
|
export function isInModelFamily(model: string): boolean {
|
|
const parsed = parseModel(model);
|
|
const bareModel = parsed.model || model;
|
|
return bareModel in MODEL_FAMILIES;
|
|
}
|
|
|
|
/**
|
|
* Get all members of a model's family (including itself).
|
|
*/
|
|
export function getModelFamily(model: string): string[] {
|
|
const parsed = parseModel(model);
|
|
const bareModel = parsed.model || model;
|
|
const prefix =
|
|
parsed.provider || parsed.providerAlias ? `${parsed.provider || parsed.providerAlias}/` : "";
|
|
|
|
const family = MODEL_FAMILIES[bareModel];
|
|
if (!family) return [model];
|
|
return [model, ...family.map((c) => `${prefix}${c}`)];
|
|
}
|
|
|
|
/**
|
|
* Find a model with larger context window from a list of candidate models.
|
|
* Uses models.dev synced capabilities to compare context limits.
|
|
*/
|
|
export function findLargerContextModel(
|
|
currentModel: string,
|
|
availableModels: string[]
|
|
): string | null {
|
|
const currentParsed = parseModel(currentModel);
|
|
const currentProvider = currentParsed.provider || currentParsed.providerAlias || "unknown";
|
|
const currentModelId = currentParsed.model || currentModel;
|
|
const currentLimit = getModelContextLimit(currentProvider, currentModelId) ?? 0;
|
|
|
|
let bestModel: string | null = null;
|
|
let bestLimit = currentLimit;
|
|
|
|
for (const candidate of availableModels) {
|
|
if (candidate === currentModel) continue;
|
|
const parsed = parseModel(candidate);
|
|
const provider = parsed.provider || parsed.providerAlias || "unknown";
|
|
const modelId = parsed.model || candidate;
|
|
const limit = getModelContextLimit(provider, modelId) ?? 0;
|
|
|
|
if (limit > bestLimit) {
|
|
bestLimit = limit;
|
|
bestModel = candidate;
|
|
}
|
|
}
|
|
|
|
return bestModel;
|
|
}
|