mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-25 16:42:16 +03:00
* chore(release): open v3.8.27 development cycle * fix(security): polynomial ReDoS in comboAgentMiddleware regex (#3982) * fix(security): eliminate polynomial ReDoS in comboAgentMiddleware <omniModel> regex (CodeQL js/polynomial-redos) CACHE_TAG_PATTERN wrapped the tag in an unbounded `(?:\\n|\n|\r)*` prefix/suffix. On an unanchored `.test()`/`.exec()` that is O(n²) on inputs with many newlines (CodeQL js/polynomial-redos, alerts #612/#613). The surrounding runs are irrelevant to detecting/capturing the tag, so the detection pattern now matches only the core `<omniModel>([^<]+)</omniModel>`; the global strip pattern still consumes the wrapping newlines (combo.ts streaming, #531) but BOUNDED ({0,16}) so it stays linear. Behavior preserved: detection, model extraction, multi-tag stripping (#454) and blank-line cleanup all unchanged (107 related tests green). Adds ReDoS-safety regression tests (50k-newline inputs complete in <1ms). * docs(changelog): add #3982 ReDoS fix to [3.8.27] * ci(security): harden workflows — artipacked persist-credentials + cache-poisoning + SC2086 (#3965) * Refine provider quota card display (#3969) Integrated into release/v3.8.27 * feat: add sidebar group separator toggles (#3971) Integrated into release/v3.8.27 * Gate control-plane proxy direct fallback (#3963) Integrated into release/v3.8.27 * Capture actual upstream provider requests (#3941) Integrated into release/v3.8.27 * ci(quality): flip require-tighten + osv + Trivy to blocking (v3.8.27 cycle-end) (#3984) * fix(resilience): respect connection cooldown stored as numeric epoch (#3954) (#3995) rate_limited_until is a TEXT column, but setConnectionRateLimitUntil (Antigravity full-quota path) persists a raw epoch number that SQLite coerces to a numeric string ("1781696905131.0"). The selection predicate isAccountUnavailable then did new Date("1781696905131.0") -> NaN, so the cooling connection was never skipped and the router kept dispatching to rate-limited accounts. Normalize numeric-epoch strings (and number/Date/ISO) via a shared cooldownUntilMs() helper in isAccountUnavailable / getEarliestRateLimitedUntil / filterAvailableAccounts / parseFutureDateMs. ISO behavior preserved. * fix(providers): fetch live /models for LLM7 and BytePlus (#3976) (#3996) llm7 and byteplus carry a real modelsUrl but were not classified by any live-fetch branch of the model-import route, so their hardcoded 4-entry registry catalog was served (source local_catalog) instead of the upstream catalog. Add both to NAMED_OPENAI_STYLE_PROVIDERS so the route probes <baseUrl>/models and serves the live list, falling back to the local catalog only on fetch failure. * fix(dashboard): logs auto-refresh reads live visibility, not a stale mount ref (#3972) (#3997) The auto-refresh interval gated each tick on visibleRef, seeded once at mount and updated only by a visibilitychange event. A tab mounted while document.visibilityState is 'hidden' (background load, bfcache, embedded/proxied webviews) with no later visibilitychange left the ref false forever, so the interval ticked but never fetched — only the manual button worked. Read the live document.visibilityState in the tick instead. * feat(compression): add Indonesian caveman rules and language pack (#3975) Integrated into release/v3.8.27 (cherry picked from commitc9b5b1a892) * fix(combo): shuffle strict-random fallback remainder to spread load (#3959) (#3998) strict-random shuffled only the deck-selected slot 0 and left the fallback remainder in fixed priority order, so after a failing deck pick the chain always fell through to the same top-priority model — a persistently-failing model was retried on essentially every request and fallback load never spread across peers. Shuffle the remainder too (like the random strategy). * Add provider auth visibility controls (#3953) Integrated into release/v3.8.27 * fix(claude): forward client tool-search-tool anthropic-beta on the Claude OAuth path (#3974) (#3999) The client-negotiated anthropic-beta: tool-search-tool-2025-10-19 was dropped on both Claude code paths (default executor rebuilt from static ANTHROPIC_BETA_CLAUDE_OAUTH; selectBetaFlags only read the client beta to gate thinking/effort), so claude.ai rejected deferred-tool requests with 400 'Tool reference not found'. Add an allowlist-merge (mergeClientAnthropicBeta) that unions the client's allowlisted betas into the outbound set on both paths, preserving #3415 (no forced thinking/effort). * feat(providers): add model search filter to provider dashboard (#3950) Integrated into release/v3.8.27 * fix(vision-bridge): force bridge for tokenrouter deepseek models (#3946) Integrated into release/v3.8.27 * fix(executor): strip stream_options on non-streaming requests (#3884) (#4000) Clients that send stream_options:{include_usage:true} regardless of stream (e.g. the OpenAI Python SDK) had it passed through on non-streaming calls; NVIDIA NIM rejected it with 400 'Stream options can only be defined when stream=True'. DefaultExecutor.transformRequest only injected/cleared stream_options on the streaming branch and never stripped a client-sent value when stream=false. Add a !stream strip branch; the streaming injection path is unchanged. Global to openai-compat providers. * fix(qwen-web): cookie validation false-positive - check response body for user object (#3958) Integrated into release/v3.8.27 * fix(db): persist backup retention days (#3970) Integrated into release/v3.8.27 * 大量UI显示和i18n优化 (#3973) Integrated into release/v3.8.27 * deps: bump the npm_and_yarn group across 1 directory with 2 updates (#3943) Integrated into release/v3.8.27 * deps: bump form-data from 4.0.5 to 4.0.6 (#3944) Integrated into release/v3.8.27 * deps: bump vite from 8.0.5 to 8.0.16 (#3942) Integrated into release/v3.8.27 * chore(quality): re-baseline validation.ts 4407->4428 (#3958 qwen body-check) The qwen-web validation body-check merged in #3958 pushed validation.ts past its frozen size on the integrated release tip. Bump the baseline with justification; no logic is separately extractable from the existing qwen-web validation branch. * deps: bump the production group with 13 updates (#3915) Integrated into release/v3.8.27 — low-risk group (playwright 1.60→1.61 minor + transitive patches; fumadocs-core 16.9→16.10 minor). * chore(deps): ignore jscpd major bumps (v5 Rust rewrite breaks the duplication gate) Our duplication ratchet (scripts/check/check-duplication.mjs) is pinned to jscpd@4 and parses jscpd-report.json against a frozen baseline. jscpd v5 is a native Rust binary with no Node.js API and a different report/bin, so a major bump would break the gate. Migrate deliberately, not via dependabot. Closes the noise from #3916. * fix(perplexity-web): parse schematized diff_block stream so answers aren't empty (#4001) Integrated into release/v3.8.27 — schematized diff_block parsing follow-up to #3938. * refactor: modularize providerRegistry.ts into 159 individual provider plugins (#3993) Modularize provider registry (#3594). Integrated into release/v3.8.27 after rebase + behavior-preservation verification (provider-consistency gate 159/232/0, typecheck, registry tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(registry): restore byteplus + mimocode dropped by #3993 modularization The provider-registry modularization (#3993) was cut from a base predating the byteplus (#3877) and mimocode (#3837) registry entries, so merging it silently dropped both providers (getRegistryEntry returned undefined → validation reported 'not supported'). Re-add them as registry modules in the new structure; registered count 159→161, provider-consistency 161/232/0. Also align the pre-existing qwen-web validator test to #3958: since the validator now requires a real `user` object in the 200 body, the mock must carry one. * refactor: modularize schemas (non-stacked) (#3988) Modularize validation schemas (#3594). Integrated into release/v3.8.27 after rebase (reconciled the merged hiddenSidebarGroupLabels #3971 + intelligenceSyncRequestSchema into the new modules) + behavior verification (typecheck, 195 schema/settings/validation tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(default-executor): honor custom providerSpecificData.baseUrl for OpenAI-format providers (#4002) Integrated into release/v3.8.27 — honor custom providerSpecificData.baseUrl in DefaultExecutor (openai-format), tested. * feat(openai): honor custom base URL in model discovery + complete openai/codex pricing (#4005) Integrated into release/v3.8.27 — openai model-discovery honors custom base URL (SSRF-guarded) + pricing rows for new openai/codex models. Tested + baselines bumped. * fix(live-ws): bridge sidecar events to dashboard (#4004) Integrated into release/v3.8.27 — repair LiveWS sidecar (startup, same-origin /live-ws, main→sidecar compression.completed bridge, early-msg queue). Fixed the cookie-parse regex (\s) + added a focused unit test; baseline bumped for the non-blocking chatCore bridge. * docs(troubleshooting): note MITM proxy cannot intercept Windows-host apps under WSL (#4003) Integrated into release/v3.8.27 — MITM/WSL troubleshooting note. * fix(repo): untrack accidentally-committed root node_modules symlink + gitignore it A worktree node_modules symlink (-> the main checkout's node_modules) was staged by a `git add -A` during the #3988 merge and committed into05213ac6a. The symlink points at the repo's own node_modules path, so checking it out turns the main checkout's node_modules into a self-referential symlink (breaking tsx/all node ops). Untrack it and add a root-anchored /node_modules ignore so the symlink form can't be re-committed (the existing 'node_modules/' only matches directories). * fix(quality): allowlist socks dep (declared by #4004, never allowlisted) socks@^2.8.7 was added to package.json in #4004 (LiveWS sidecar,02302131f) as a phantom-dep cleanup but never added to dependency-allowlist.json, so check:deps has been red on the release tip ever since. socks is the standard SOCKS proxy client (dep of fetch-socks), legitimate and years old. * feat(sse): real LLMLingua-2 ONNX compression engine (stable) (#4014) Integrated into release/v3.8.27. Adjustments before merge: - Synced with the current release tip (was 11 commits behind). - Added the 3 LLMLingua-2 ONNX optional-runtime deps to dependency-allowlist.json (@atjsh/llmlingua-2, @tensorflow/tfjs, js-tiktoken) — the only gate that was red. - socks was allowlisted directly on release (separate fix d7db5c73d; it was declared by #4004 but never allowlisted, leaving check:deps red release-wide). Verified locally: check:deps OK, file-size OK, public-creds OK, provider-consistency 161/232/0, typecheck:core clean, 24/24 LLMLingua tests pass. The only remaining Fast-QG red is the pre-existing #3972 orphan test (request-logger-autorefresh-visibility-3972.test.tsx), which is release-wide and unrelated to this PR. * test(dashboard): rehome #3972 logs auto-refresh test so a runner collects it tests/unit/request-logger-autorefresh-visibility-3972.test.tsx (added by #3972 via #3997) sat at the top level of tests/unit/ as a .tsx vitest test, which NO runner collects: the node runner only globs *.test.ts, and test:vitest:ui only runs tests/unit/ui. So the #3972 regression guard never executed in CI and check:test-discovery was red release-wide. Move it under tests/unit/ui/ (the collected vitest:ui path) and fix the relative import depth. Verified: the test now runs and passes (2/2), and check:test-discovery is green. * feat(compression): capture per-engine analytics (#3960) + Lite schema fix (#3952) (#4018) Captures the net-new value from #3960 (per-engine breakdown analytics) and #3952 (Lite engine schema fix) onto release/v3.8.27. Fast QG green; 622/622 compression+analytics tests pass. * fix(sse): guard model-less registry entries in getUnsupportedParams (mimocode) (#4015) Real bugfix: guard model-less registry entries (mimocode) in getUnsupportedParams so handleChatCore no longer throws 'entry.models is not iterable' / reports 'All models failed' for unrelated requests. Includes a regression test. Fast QG green. * feat(ci): Quality Gate v2 — Onda 0 + Onda 1 (gate flips, TIA, SAST, DAST-smoke, mutation infra) (#4016) * docs(ops): add quality-gate assessment + replication playbook (Fase 9 foundation) * feat(ci): flip oasdiff breaking-change gate to blocking (ratchet) * docs(ops): deliver main branch-protection ruleset for owner to apply * fix(ci): run typecheck:core in PR->release fast-gates (close fast-gates hole, part 1) * perf(mutation): enable Stryker incremental mode + cache (scales the 60/80 rollout) * feat(ci): commit CodeQL advanced config (security-extended), replacing default-setup * feat(ci): version semgrep SAST workflow (owasp/secrets), advisory * feat(quality): TIA test-impact map builder (import-graph; map built at runtime, gitignored) * feat(quality): TIA impacted-test selector with run-all fail-safe * fix(ci): run TIA-impacted unit tests in PR->release fast-gates (build map at runtime, fail-safe full) * feat(ci): DAST-smoke per-PR (schemathesis subset + promptfoo injection-guard, blocking) * fix(ci): unbreak Fase 9 PR CI (MDX frontmatter, CodeQL conflict, dast-smoke advisory) - Add MDX frontmatter to docs/ops/{BRANCH_PROTECTION_MAIN,QUALITY_GATE_PLAYBOOK}.md. fumadocs rejects frontmatter-less docs -> 'npm run build' failed -> broke dast-smoke's build step (the release fast-gates never runs build, so this only surfaced on the PR). - codeql.yml: workflow_dispatch-only until the owner switches repo CodeQL Default->Advanced (advanced configs cannot be processed while default setup is enabled; documented inline). - dast-smoke.yml: job-level continue-on-error (advisory) so this brand-new gate matures before it blocks (repo convention: advisory -> blocking). * ci(quality): make TIA unit-test step advisory until release test-debt is cleared release/v3.8.27 carries ~17 pre-existing failing unit tests (budget #3537, apiKey #3552, several Zod schemas, Puter/Qwen executors, mimocode entry, etc.) unrelated to this PR — the new 'run tests on PR->release' gate surfaced them. Per the repo's advisory->blocking convention, this step enters advisory (it still runs + reports) so pre-existing debt doesn't block the gate program. typecheck:core stays blocking. Flip to blocking (remove continue-on-error) once the release suite is green. * fix(sse): preserve Kiro streaming finish_reason tool_calls (#3980) (#4025) * fix(guardrails): preserve original image when vision-bridge describe fails (#4012) (#4026) * feat(api): advertise combo capabilities on import surfaces (#3979) (#4027) * feat(sse): delegated Anthropic Context Editing for Claude (clear_tool_uses) (#4021) Opt-in Claude-only delegated compression: injects context_management.clear_tool_uses_20250919 at the Claude pre-serialization chokepoint (composes with clear_thinking, thinking first), threaded via ExecuteInput from handleChatCore. Pure edit-builder + 11 tests (7 unit + 4 e2e fetch-capture). Beta context-management-2025-06-27 already advertised; allowlist done. Telemetry/400-fallback/claude-web coverage deferred. * fix(opencode): map x-session-affinity to x-opencode-session for custom providers (#4022) (#4028) * fix(dashboard): Playground Compare tab loading + HTTP method guard (#4024) randomUUID non-HTTPS fallback + static CompareTab import; raw HTTP TRACE->405 method guard wired into dev + standalone servers. Integrated into release/v3.8.27. * refactor(dashboard): settings UI layout + API Keys naming (#4020) Presentation/relabel refactor of the Settings dashboard (API Manager -> API Keys), card relocations, Toggle adoption, present-but-disabled engine steps. Auth-file changes are string/comment-only (no behavior change). Integrated into release/v3.8.27. * fix: restore unit regressions dropped by lossy schema/registry modularizations (#4030) Restores schema fields (combo reasoningTokenBuffer, budget-0 #3537, openrouter preset, proxy family #3777, resilience degradation/providerCooldown), qwen-web v2 endpoint+catalog, mimocode models key — all dropped by #3988/#3993 — and aligns 3 tests to #3941/#3993. Verified: 8 failing regression tests on release tip -> 131/131 green on this branch. Integrated into release/v3.8.27. * fix(api): return 400 (not 500) for malformed JSON on /api/auth/login (#4031) Wrap request.json() so a malformed/non-JSON login body returns a structured 400 instead of falling through to the 500 catch. Fixes the schemathesis high-risk-endpoint DAST finding (verified: schemathesis step now passes). +TDD test. Integrated into release/v3.8.27. * feat(dashboard): real circuit-breaker state in the Combo Live cascade (U1b) (#4029) Overlays real provider circuit-breaker state (GET /api/monitoring/health) onto the Combo Live cascade as a 'CB: OPEN · 41s' badge. Pure enrichRunWithBreakers + fail-soft useProviderBreakerHealth poll; graceful when health is absent. +13 tests. Integrated into release/v3.8.27. * Fix promptfoo security assertion parsing (#4032) * chore(deps): dependabot security bumps + drop unused gray-matter (#4036) Integrated into release/v3.8.27 — dependabot security bumps (form-data/js-yaml/protobufjs/dompurify/hono) + drop unused gray-matter. Unblocks the npm audit:deps gate (Lint) branch-wide. * fix(ci): scope TIA to node:test unit files only (mirror test:unit glob) (#4035) Integrated into release/v3.8.27 — scopes the advisory TIA step to the test:unit node:test glob, fixing the 99 false failures. +4 TDD. * Refine compression settings, storage labels, and sidebar grouping (#4033) Integrated into release/v3.8.27 — relocate Token Saver into Compression Settings (controlled component), reorder Security/Authz tabs, storage labels + i18n relabel. Thanks @rdself! * [codex] add per-key local usage command (#4034) Integrated into release/v3.8.27 — per-key local @@om-usage command (cached quota, no upstream routing). Rebased onto modularized schemas/keys.ts + file-size rebaseline. Thanks @Witroch4! * chore(release): reconcile v3.8.27 CHANGELOG + i18n mirrors * ci(quality): unblock v3.8.27 release gates (zizmor pin + test-masking allowlist) - zizmor ratchet (151→139, no regression): SHA-pin every action ref ADDED this cycle — codeql/dast-smoke/semgrep (3 new workflows) + trivy-action (docker-publish) + actions/cache (nightly-mutation). Pre-existing tag refs keep the repo convention. - test-masking: add config/quality/test-masking-allowlist.json + allowlist support in check-test-masking.mjs (exempts ONLY the net-assert-reduction signal; tautology/skip/ deletion still fire). Allowlists 2 verified-legitimate reductions: appearance-widget-settings-schema (#4033 removed showTokenSaverOnEndpoint field) and dashboard-shell-tabs (#3973 tabs→redirect refactor, asserts replaced). +4 gate tests. * test(quality): reword test-masking self-test comments to avoid literal masking patterns The added allowlist-test comments contained the literal strings 'assert.ok(true)' and '.skip' which the masking detector's own regexes match as text — making the gate flag its own test file (net +1 tautology/skip/extended-tautology vs main). Reworded to plain prose ('a new tautology', 'a new skip marker'); test logic unchanged (24/24 pass). * fix(quality): unblock v3.8.27 release — align 3 stale tests + restore modularized settings-schema parity Release-PR full CI surfaced 3 deterministic test failures (no live product regression), all stale vs legitimate cycle changes: - settings-schema parity (#3988): the modularized updateSettingsSchema barrel (schemas/settings.ts) had diverged from the canonical settingsSchemas.ts (45 vs 85 fields — 40 dropped + 6 extra), a lossy-modularization dead-code copy. Re-export from the canonical source so the barrel can never diverge again (runtime already uses canonical). Parity test now passes. - api-manager permissions modal: #4034 added a 4th self-service switch (per-key usage allowance); a11y invariant (every switch type="button") still holds. Updated the static count 3 -> 4. - pack-artifact policy: dist/http-method-guard.cjs became a required runtime path; added it to the test's expected missing-paths list. Also documents the gate gap for Fase 9 (QUALITY_GATE_PLAYBOOK Parte 6): G1 run the deterministic unit layer + test-masking on PR->release (not just PR->main), G2 a modularization-parity gate (would have caught the #3988 drop at its PR), G3 flake quarantine. Env flakes (LiveWS startup timeout, integration server-startup cascade) are pre-existing/CI-env, triaged separately. --------- Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Veier04 <118300867+Veier04@users.noreply.github.com> Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com> Co-authored-by: WormAlien <164898390+WormAlien@users.noreply.github.com> Co-authored-by: thezukiru <121331256+thezukiru@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: NOXX - Commiter <artur1992123@mail.ru> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Demiurge The Single <megamen932@gmail.com> Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
1149 lines
38 KiB
TypeScript
1149 lines
38 KiB
TypeScript
/**
|
|
* db/settings.js — Settings, pricing, and proxy config.
|
|
*/
|
|
|
|
import { getDbInstance } from "./core";
|
|
import { backupDbFile } from "./backup";
|
|
import { PROVIDER_ID_TO_ALIAS } from "@omniroute/open-sse/config/providerModels.ts";
|
|
import { invalidateDbCache } from "./readCache";
|
|
import { getProxyRegistryGeneration, resolveProxyForScopeFromRegistry } from "./proxies";
|
|
import { getComboModelProvider as getComboEntryProvider } from "@/lib/combos/steps";
|
|
import { requestBodyLimitMbFromEnv } from "@/shared/constants/bodySize";
|
|
import { DEFAULT_RESPONSES_PREVIOUS_RESPONSE_ID_MODE } from "@/shared/constants/responsesPreviousResponseId";
|
|
|
|
type JsonRecord = Record<string, unknown>;
|
|
type PricingModels = Record<string, JsonRecord>;
|
|
type PricingByProvider = Record<string, PricingModels>;
|
|
export type PricingSource = "default" | "litellm" | "modelsDev" | "user";
|
|
export type PricingSourceMap = Record<string, Record<string, PricingSource>>;
|
|
type ProxyValue = JsonRecord | string | null;
|
|
type ProxyResolutionResult = {
|
|
proxy: ProxyValue;
|
|
level: string;
|
|
levelId: string | null;
|
|
source?: string;
|
|
};
|
|
type ProxyResolutionCacheEntry = {
|
|
generation: number;
|
|
registryGeneration: number;
|
|
result: ProxyResolutionResult;
|
|
};
|
|
|
|
const PROXY_RESOLUTION_CACHE_MAX_ENTRIES = 100;
|
|
|
|
function isTruthyEnvFlag(value: string | undefined): boolean {
|
|
return typeof value === "string" && /^(1|true|yes|on)$/i.test(value.trim());
|
|
}
|
|
|
|
let proxyConfigGeneration = 0;
|
|
const proxyResolutionCache = new Map<string, ProxyResolutionCacheEntry>();
|
|
|
|
export function bumpProxyConfigGeneration() {
|
|
proxyConfigGeneration++;
|
|
proxyResolutionCache.clear();
|
|
}
|
|
|
|
function cacheProxyResolution(
|
|
connectionId: string,
|
|
generation: number,
|
|
registryGeneration: number,
|
|
result: ProxyResolutionResult
|
|
) {
|
|
if (generation !== proxyConfigGeneration) return;
|
|
if (registryGeneration !== getProxyRegistryGeneration()) return;
|
|
if (proxyResolutionCache.size >= PROXY_RESOLUTION_CACHE_MAX_ENTRIES) {
|
|
const oldestKey = proxyResolutionCache.keys().next().value;
|
|
if (oldestKey) proxyResolutionCache.delete(oldestKey);
|
|
}
|
|
proxyResolutionCache.set(connectionId, { generation, registryGeneration, result });
|
|
}
|
|
type ProxyMap = Record<string, ProxyValue>;
|
|
|
|
interface ProxyConfig {
|
|
global: ProxyValue;
|
|
providers: ProxyMap;
|
|
combos: ProxyMap;
|
|
keys: ProxyMap;
|
|
[key: string]: unknown;
|
|
}
|
|
|
|
function toRecord(value: unknown): JsonRecord {
|
|
return value && typeof value === "object" ? (value as JsonRecord) : {};
|
|
}
|
|
|
|
function toProxyMap(value: unknown): ProxyMap {
|
|
return value && typeof value === "object" ? (value as ProxyMap) : {};
|
|
}
|
|
|
|
function toProxyValue(value: unknown): ProxyValue {
|
|
if (value === null || typeof value === "string") return value as string | null;
|
|
if (value && typeof value === "object") return value as JsonRecord;
|
|
return null;
|
|
}
|
|
|
|
// Legacy proxyConfig store (key_value namespace 'proxyConfig') predates the
|
|
// IPv6-only `family` directive, so its object configs have no family field.
|
|
// Default to "auto" so the family marker rides along the cascade end-to-end
|
|
// (consumed by proxyConfigToUrl). String configs are returned unchanged.
|
|
function withFamilyDefault(value: ProxyValue): ProxyValue {
|
|
if (value && typeof value === "object" && !Array.isArray(value)) {
|
|
const record = value as JsonRecord;
|
|
if (typeof record.family === "string") return record;
|
|
return { ...record, family: "auto" };
|
|
}
|
|
return value;
|
|
}
|
|
|
|
// ──────────────── Settings ────────────────
|
|
|
|
export async function getSettings() {
|
|
const db = getDbInstance();
|
|
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'settings'").all();
|
|
const settings: Record<string, unknown> = {
|
|
cloudEnabled: true,
|
|
tailscaleEnabled: false,
|
|
tailscaleUrl: "",
|
|
stickyRoundRobinLimit: 3,
|
|
requestRetry: 3,
|
|
maxRetryIntervalSec: 30,
|
|
antigravitySignatureCacheMode: "enabled",
|
|
requireLogin: true,
|
|
mcpEnabled: false,
|
|
a2aEnabled: false,
|
|
hiddenSidebarItems: [],
|
|
hiddenSidebarGroupLabels: [],
|
|
sidebarSectionOrder: [],
|
|
sidebarItemOrder: {},
|
|
sidebarActivePreset: null,
|
|
hideEndpointCloudflaredTunnel: false,
|
|
hideEndpointTailscaleFunnel: false,
|
|
hideEndpointNgrokTunnel: false,
|
|
preferClaudeCodeForUnprefixedClaudeModels: isTruthyEnvFlag(
|
|
process.env.OMNIROUTE_PREFER_CLAUDE_CODE_FOR_UNPREFIXED_CLAUDE_MODELS
|
|
),
|
|
autoRefreshProviderQuota: false,
|
|
autoRefreshProviderQuotaInterval: 180,
|
|
comboConfigMode: "guided",
|
|
codexServiceTier: { enabled: false },
|
|
claudeFastMode: {
|
|
enabled: false,
|
|
supportedModels: ["claude-fable-5", "claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6"],
|
|
},
|
|
codexSessionAffinityTtlMs: 0,
|
|
responsesPreviousResponseIdMode: DEFAULT_RESPONSES_PREVIOUS_RESPONSE_ID_MODE,
|
|
alwaysPreserveClientCache: "auto",
|
|
idempotencyWindowMs: 5000,
|
|
wsAuth: false,
|
|
maxBodySizeMb: requestBodyLimitMbFromEnv(process.env.MAX_BODY_SIZE_BYTES),
|
|
debugMode: true,
|
|
// LOCAL_ONLY manage-scope bypass policy defaults (T-011 / spec §Data Model).
|
|
// Preserves PR #2473 behaviour on migration — the bypass starts ENABLED
|
|
// for `/api/mcp/` so existing manage-scope Bearer clients keep working.
|
|
// Operators flip the kill-switch to false (or drop the prefix) via the
|
|
// Settings UI; the change hot-reloads through `applyRuntimeSettings` →
|
|
// `applyAuthzBypassSection` → `getAuthzBypassSnapshot()`.
|
|
localOnlyManageScopeBypassEnabled: true,
|
|
localOnlyManageScopeBypassPrefixes: ["/api/mcp/"],
|
|
customBannedSignals: [],
|
|
proxyEnabled: true,
|
|
perKeyProxyEnabled: false,
|
|
};
|
|
for (const row of rows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
settings[key] = JSON.parse(rawValue);
|
|
}
|
|
|
|
// Auto-complete onboarding for pre-configured deployments (Docker/VM)
|
|
// If INITIAL_PASSWORD is set via env, this is a headless deploy — skip the wizard
|
|
if (!settings.setupComplete && process.env.INITIAL_PASSWORD) {
|
|
settings.setupComplete = true;
|
|
settings.requireLogin = true;
|
|
db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('settings', 'setupComplete', 'true')"
|
|
).run();
|
|
db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('settings', 'requireLogin', 'true')"
|
|
).run();
|
|
}
|
|
|
|
return settings;
|
|
}
|
|
|
|
export async function updateSettings(updates: Record<string, unknown>) {
|
|
const db = getDbInstance();
|
|
const insert = db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('settings', ?, ?)"
|
|
);
|
|
const tx = db.transaction(() => {
|
|
for (const [key, value] of Object.entries(updates)) {
|
|
insert.run(key, JSON.stringify(value));
|
|
}
|
|
});
|
|
tx();
|
|
backupDbFile("pre-write");
|
|
invalidateDbCache("settings"); // Bust the read cache immediately
|
|
|
|
// Bust proxy resolution cache when proxy toggle settings change
|
|
const PROXY_TOGGLE_KEYS = ["proxyEnabled", "perKeyProxyEnabled"];
|
|
if (Object.keys(updates).some((k) => PROXY_TOGGLE_KEYS.includes(k))) {
|
|
bumpProxyConfigGeneration();
|
|
}
|
|
|
|
const nextSettings = await getSettings();
|
|
|
|
try {
|
|
const { applyRuntimeSettings } = await import("@/lib/config/runtimeSettings");
|
|
await applyRuntimeSettings(nextSettings, { source: "settings:update" });
|
|
} catch (error) {
|
|
console.warn(
|
|
"[HOT_RELOAD] Failed to apply runtime settings after update:",
|
|
error instanceof Error ? error.message : error
|
|
);
|
|
}
|
|
|
|
return nextSettings;
|
|
}
|
|
|
|
export async function isCloudEnabled() {
|
|
const settings = await getSettings();
|
|
return settings.cloudEnabled === true;
|
|
}
|
|
|
|
// ──────────────── Pricing ────────────────
|
|
|
|
function readPricingNamespace(
|
|
db: ReturnType<typeof getDbInstance>,
|
|
namespace: string
|
|
): PricingByProvider {
|
|
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = ?").all(namespace);
|
|
const pricing: PricingByProvider = {};
|
|
|
|
for (const row of rows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
|
|
try {
|
|
pricing[key] = toRecord(JSON.parse(rawValue)) as PricingModels;
|
|
} catch {
|
|
// Corrupted data — skip silently, fallback to lower layers
|
|
}
|
|
}
|
|
|
|
return pricing;
|
|
}
|
|
|
|
function mergePricingLayers(layers: PricingByProvider[]): PricingByProvider {
|
|
const mergedPricing: PricingByProvider = {};
|
|
|
|
for (const layer of layers) {
|
|
for (const [provider, models] of Object.entries(layer)) {
|
|
if (!mergedPricing[provider]) {
|
|
mergedPricing[provider] = { ...models };
|
|
continue;
|
|
}
|
|
|
|
for (const [model, pricing] of Object.entries(models)) {
|
|
mergedPricing[provider][model] = mergedPricing[provider][model]
|
|
? { ...(mergedPricing[provider][model] || {}), ...toRecord(pricing) }
|
|
: pricing;
|
|
}
|
|
}
|
|
}
|
|
|
|
return mergedPricing;
|
|
}
|
|
|
|
function buildPricingSourceMap(layers: {
|
|
defaults: PricingByProvider;
|
|
litellm: PricingByProvider;
|
|
modelsDev: PricingByProvider;
|
|
user: PricingByProvider;
|
|
}): PricingSourceMap {
|
|
const sourceMap: PricingSourceMap = {};
|
|
const mergedPricing = mergePricingLayers([
|
|
layers.defaults,
|
|
layers.litellm,
|
|
layers.modelsDev,
|
|
layers.user,
|
|
]);
|
|
|
|
for (const [provider, models] of Object.entries(mergedPricing)) {
|
|
sourceMap[provider] = {};
|
|
|
|
for (const model of Object.keys(models)) {
|
|
if (layers.user[provider]?.[model]) {
|
|
sourceMap[provider][model] = "user";
|
|
} else if (layers.modelsDev[provider]?.[model]) {
|
|
sourceMap[provider][model] = "modelsDev";
|
|
} else if (layers.litellm[provider]?.[model]) {
|
|
sourceMap[provider][model] = "litellm";
|
|
} else {
|
|
sourceMap[provider][model] = "default";
|
|
}
|
|
}
|
|
}
|
|
|
|
return sourceMap;
|
|
}
|
|
|
|
async function getPricingLayers() {
|
|
const db = getDbInstance();
|
|
|
|
// Layer 1: Hardcoded defaults (lowest priority)
|
|
const { getDefaultPricing } = await import("@/shared/constants/pricing");
|
|
return {
|
|
defaults: getDefaultPricing(),
|
|
litellm: readPricingNamespace(db, "pricing_synced"),
|
|
modelsDev: readPricingNamespace(db, "models_dev_pricing"),
|
|
user: readPricingNamespace(db, "pricing"),
|
|
};
|
|
}
|
|
|
|
export async function getPricing() {
|
|
const layers = await getPricingLayers();
|
|
// Merge: defaults → LiteLLM → models.dev → user (each layer overrides the previous)
|
|
return mergePricingLayers([layers.defaults, layers.litellm, layers.modelsDev, layers.user]);
|
|
}
|
|
|
|
export async function getPricingWithSources(): Promise<{
|
|
pricing: PricingByProvider;
|
|
sourceMap: PricingSourceMap;
|
|
}> {
|
|
const layers = await getPricingLayers();
|
|
return {
|
|
pricing: mergePricingLayers([layers.defaults, layers.litellm, layers.modelsDev, layers.user]),
|
|
sourceMap: buildPricingSourceMap(layers),
|
|
};
|
|
}
|
|
|
|
export async function getPricingForModel(provider: string, model: string) {
|
|
const pricing = await getPricing();
|
|
|
|
const findKeyInsensitive = <T>(
|
|
obj: Record<string, T> | undefined | null,
|
|
key: string
|
|
): T | undefined => {
|
|
if (!obj || !key) return undefined;
|
|
const lowerKey = key.toLowerCase();
|
|
for (const [k, v] of Object.entries(obj)) {
|
|
if (k.toLowerCase() === lowerKey) return v;
|
|
}
|
|
return undefined;
|
|
};
|
|
|
|
const pLower = (provider || "").toLowerCase();
|
|
let providerPricing = findKeyInsensitive<PricingModels>(pricing, pLower);
|
|
|
|
if (!providerPricing) {
|
|
const alias = findKeyInsensitive<string>(PROVIDER_ID_TO_ALIAS, pLower);
|
|
if (alias) providerPricing = findKeyInsensitive(pricing, alias);
|
|
}
|
|
|
|
if (!providerPricing) {
|
|
for (const [id, mappedAlias] of Object.entries(PROVIDER_ID_TO_ALIAS)) {
|
|
if (typeof mappedAlias === "string" && mappedAlias.toLowerCase() === pLower) {
|
|
providerPricing = findKeyInsensitive(pricing, id);
|
|
if (providerPricing) break;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (!providerPricing) {
|
|
const np = pLower.replace(/-cn$/, "");
|
|
if (np && np !== pLower) {
|
|
providerPricing = findKeyInsensitive(pricing, np);
|
|
}
|
|
}
|
|
|
|
if (!providerPricing) return null;
|
|
|
|
const mLower = (model || "").toLowerCase();
|
|
let modelPricing = findKeyInsensitive<JsonRecord>(providerPricing, mLower);
|
|
|
|
if (!modelPricing) {
|
|
const hyphenModel = mLower.replace(/\./g, "-");
|
|
modelPricing = findKeyInsensitive(providerPricing, hyphenModel);
|
|
}
|
|
|
|
return modelPricing || null;
|
|
}
|
|
|
|
export async function updatePricing(pricingData: PricingByProvider) {
|
|
const db = getDbInstance();
|
|
const insert = db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('pricing', ?, ?)"
|
|
);
|
|
|
|
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'pricing'").all();
|
|
const existing: PricingByProvider = {};
|
|
for (const row of rows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
existing[key] = toRecord(JSON.parse(rawValue)) as PricingModels;
|
|
}
|
|
|
|
const tx = db.transaction(() => {
|
|
for (const [provider, models] of Object.entries(pricingData)) {
|
|
insert.run(provider, JSON.stringify({ ...(existing[provider] || {}), ...models }));
|
|
}
|
|
});
|
|
tx();
|
|
backupDbFile("pre-write");
|
|
invalidateDbCache("pricing"); // Bust the pricing read cache
|
|
const updated: PricingByProvider = {};
|
|
const allRows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'pricing'").all();
|
|
for (const row of allRows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
updated[key] = toRecord(JSON.parse(rawValue)) as PricingModels;
|
|
}
|
|
return updated;
|
|
}
|
|
|
|
export async function resetPricing(provider: string, model?: string) {
|
|
const db = getDbInstance();
|
|
|
|
if (model) {
|
|
const row = db
|
|
.prepare("SELECT value FROM key_value WHERE namespace = 'pricing' AND key = ?")
|
|
.get(provider);
|
|
if (row) {
|
|
const rowRecord = toRecord(row);
|
|
const value = typeof rowRecord.value === "string" ? rowRecord.value : "{}";
|
|
const models = toRecord(JSON.parse(value));
|
|
delete models[model];
|
|
if (Object.keys(models).length === 0) {
|
|
db.prepare("DELETE FROM key_value WHERE namespace = 'pricing' AND key = ?").run(provider);
|
|
} else {
|
|
db.prepare("UPDATE key_value SET value = ? WHERE namespace = 'pricing' AND key = ?").run(
|
|
JSON.stringify(models),
|
|
provider
|
|
);
|
|
}
|
|
}
|
|
} else {
|
|
db.prepare("DELETE FROM key_value WHERE namespace = 'pricing' AND key = ?").run(provider);
|
|
}
|
|
|
|
backupDbFile("pre-write");
|
|
const allRows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'pricing'").all();
|
|
const result: Record<string, unknown> = {};
|
|
for (const row of allRows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
result[key] = JSON.parse(rawValue);
|
|
}
|
|
return result;
|
|
}
|
|
|
|
export async function resetAllPricing() {
|
|
const db = getDbInstance();
|
|
db.prepare("DELETE FROM key_value WHERE namespace = 'pricing'").run();
|
|
backupDbFile("pre-write");
|
|
return {};
|
|
}
|
|
|
|
// ──────────────── LKGP (Last Known Good Provider) ────────────────
|
|
|
|
export interface LKGPRecord {
|
|
provider: string;
|
|
connectionId?: string;
|
|
}
|
|
|
|
export async function getLKGP(comboName: string, modelId: string): Promise<LKGPRecord | null> {
|
|
const db = getDbInstance();
|
|
const key = `${comboName}:${modelId}`;
|
|
const row = db
|
|
.prepare("SELECT value FROM key_value WHERE namespace = 'lkgp' AND key = ?")
|
|
.get(key) as { value?: string } | undefined;
|
|
if (!row?.value) return null;
|
|
try {
|
|
const parsed = JSON.parse(row.value);
|
|
if (typeof parsed === "object" && parsed !== null && "provider" in parsed) {
|
|
return parsed as LKGPRecord;
|
|
}
|
|
return { provider: String(parsed) };
|
|
} catch {
|
|
return { provider: row.value };
|
|
}
|
|
}
|
|
|
|
export async function setLKGP(
|
|
comboName: string,
|
|
modelId: string,
|
|
providerId: string,
|
|
connectionId?: string
|
|
) {
|
|
const db = getDbInstance();
|
|
const key = `${comboName}:${modelId}`;
|
|
const value: LKGPRecord = { provider: providerId };
|
|
if (connectionId) value.connectionId = connectionId;
|
|
db.prepare("INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('lkgp', ?, ?)").run(
|
|
key,
|
|
JSON.stringify(value)
|
|
);
|
|
}
|
|
|
|
export function clearAllLKGP(): void {
|
|
const db = getDbInstance();
|
|
db.prepare("DELETE FROM key_value WHERE namespace = 'lkgp'").run();
|
|
}
|
|
|
|
// ──────────────── Proxy Config ────────────────
|
|
|
|
const DEFAULT_PROXY_CONFIG: ProxyConfig = { global: null, providers: {}, combos: {}, keys: {} };
|
|
const ALIAS_TO_PROVIDER_ID = Object.entries(PROVIDER_ID_TO_ALIAS).reduce(
|
|
(acc, [providerId, alias]) => {
|
|
if (alias) acc[alias] = providerId;
|
|
acc[providerId] = providerId;
|
|
return acc;
|
|
},
|
|
{} as Record<string, string>
|
|
);
|
|
|
|
function resolveProviderAliasOrId(providerOrAlias: string): string {
|
|
if (typeof providerOrAlias !== "string") return providerOrAlias;
|
|
return ALIAS_TO_PROVIDER_ID[providerOrAlias] || providerOrAlias;
|
|
}
|
|
|
|
function getComboModelProvider(modelEntry: unknown): string | null {
|
|
const providerOrAlias = getComboEntryProvider(modelEntry);
|
|
return providerOrAlias ? resolveProviderAliasOrId(providerOrAlias) : null;
|
|
}
|
|
|
|
function migrateProxyEntry(value: unknown): JsonRecord | null {
|
|
if (!value) return null;
|
|
if (typeof value === "object") {
|
|
const record = toRecord(value);
|
|
if (record.type) return record;
|
|
}
|
|
if (typeof value !== "string") return null;
|
|
|
|
try {
|
|
const url = new URL(value);
|
|
return {
|
|
type: url.protocol.replace(":", "") || "http",
|
|
host: url.hostname,
|
|
port:
|
|
url.port ||
|
|
(url.protocol === "socks5:" ? "1080" : url.protocol === "https:" ? "443" : "8080"),
|
|
username: url.username ? decodeURIComponent(url.username) : "",
|
|
password: url.password ? decodeURIComponent(url.password) : "",
|
|
};
|
|
} catch {
|
|
const parts = value.split(":");
|
|
return {
|
|
type: "http",
|
|
host: parts[0] || value,
|
|
port: parts[1] || "8080",
|
|
username: "",
|
|
password: "",
|
|
};
|
|
}
|
|
}
|
|
|
|
export async function getProxyConfig() {
|
|
const db = getDbInstance();
|
|
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = 'proxyConfig'").all();
|
|
|
|
const raw: ProxyConfig = { ...DEFAULT_PROXY_CONFIG };
|
|
for (const row of rows) {
|
|
const record = toRecord(row);
|
|
const key = typeof record.key === "string" ? record.key : null;
|
|
const rawValue = typeof record.value === "string" ? record.value : null;
|
|
if (!key || rawValue === null) continue;
|
|
raw[key] = JSON.parse(rawValue);
|
|
}
|
|
|
|
let migrated = false;
|
|
if (raw.global && typeof raw.global === "string") {
|
|
raw.global = migrateProxyEntry(raw.global);
|
|
migrated = true;
|
|
}
|
|
if (raw.providers) {
|
|
for (const [k, v] of Object.entries(raw.providers)) {
|
|
if (typeof v === "string") {
|
|
raw.providers[k] = migrateProxyEntry(v);
|
|
migrated = true;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (migrated) {
|
|
const insert = db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('proxyConfig', ?, ?)"
|
|
);
|
|
if (raw.global !== undefined) insert.run("global", JSON.stringify(raw.global));
|
|
if (raw.providers) insert.run("providers", JSON.stringify(raw.providers));
|
|
}
|
|
|
|
return raw;
|
|
}
|
|
|
|
export async function getProxyForLevel(level: string, id?: string | null) {
|
|
const config = await getProxyConfig();
|
|
if (level === "global") return config.global || null;
|
|
const map = toProxyMap(config[level + "s"] || config[level] || {});
|
|
return (id ? map[id] : null) || null;
|
|
}
|
|
|
|
export async function setProxyForLevel(level: string, id: string | null, proxy: ProxyValue) {
|
|
const db = getDbInstance();
|
|
const config = await getProxyConfig();
|
|
|
|
if (level === "global") {
|
|
config.global = proxy || null;
|
|
db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('proxyConfig', 'global', ?)"
|
|
).run(JSON.stringify(config.global));
|
|
} else {
|
|
const mapKey = level + "s";
|
|
const map = toProxyMap(config[mapKey] || {});
|
|
if (proxy && id) {
|
|
map[id] = proxy;
|
|
} else {
|
|
if (id) delete map[id];
|
|
}
|
|
config[mapKey] = map;
|
|
db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('proxyConfig', ?, ?)"
|
|
).run(mapKey, JSON.stringify(map));
|
|
}
|
|
|
|
backupDbFile("pre-write");
|
|
bumpProxyConfigGeneration();
|
|
return config;
|
|
}
|
|
|
|
export async function deleteProxyForLevel(level: string, id: string | null) {
|
|
return setProxyForLevel(level, id, null);
|
|
}
|
|
|
|
export async function resolveProxyForConnection(connectionId: string, apiKeyId?: string) {
|
|
const cacheKey = apiKeyId ? `${connectionId}:${apiKeyId}` : connectionId;
|
|
const startGeneration = proxyConfigGeneration;
|
|
const startRegistryGeneration = getProxyRegistryGeneration();
|
|
const cached = proxyResolutionCache.get(cacheKey);
|
|
if (
|
|
cached &&
|
|
cached.generation === startGeneration &&
|
|
cached.registryGeneration === startRegistryGeneration
|
|
) {
|
|
return cached.result;
|
|
}
|
|
|
|
const db = getDbInstance();
|
|
|
|
// Step 1: Check global proxyEnabled setting
|
|
// Read only the proxyEnabled key for performance instead of loading all settings.
|
|
let globalProxyEnabled = true;
|
|
try {
|
|
const proxyEnabledRow = db
|
|
.prepare("SELECT value FROM key_value WHERE namespace = 'settings' AND key = 'proxyEnabled'")
|
|
.get() as { value?: string } | undefined;
|
|
if (proxyEnabledRow?.value) {
|
|
globalProxyEnabled = JSON.parse(proxyEnabledRow.value) !== false;
|
|
}
|
|
} catch {
|
|
// Default to true on read error
|
|
}
|
|
|
|
if (!globalProxyEnabled) {
|
|
const result: ProxyResolutionResult = { proxy: null, level: "direct", levelId: null };
|
|
// Do not cache the "direct" result when global toggle is off so that
|
|
// toggling it back on takes effect immediately without a generation bump.
|
|
return result;
|
|
}
|
|
|
|
let connectionRecord: JsonRecord | null = null;
|
|
let connectionProvider: string | null = null;
|
|
let connectionProxyEnabled = true;
|
|
let connectionPerKeyProxyEnabled = false;
|
|
|
|
const row = db
|
|
.prepare(
|
|
"SELECT provider, proxy_enabled, per_key_proxy_enabled FROM provider_connections WHERE id = ?"
|
|
)
|
|
.get(connectionId);
|
|
if (row) {
|
|
connectionRecord = toRecord(row);
|
|
connectionProvider =
|
|
typeof connectionRecord.provider === "string" ? connectionRecord.provider : null;
|
|
connectionProxyEnabled = connectionRecord.proxy_enabled !== 0;
|
|
connectionPerKeyProxyEnabled = connectionRecord.per_key_proxy_enabled === 1;
|
|
}
|
|
|
|
// A connection-level Proxy Off is explicit: it must bypass every stored proxy
|
|
// source for this connection, including account, provider, global, and automatic
|
|
// fallback candidates from the proxy pool.
|
|
if (connectionRecord && !connectionProxyEnabled) {
|
|
const result: ProxyResolutionResult = { proxy: null, level: "direct", levelId: null };
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
|
|
// Step 1.5: Check global perKeyProxyEnabled setting
|
|
let globalPerKeyProxyEnabled = false;
|
|
try {
|
|
const perKeyRow = db
|
|
.prepare(
|
|
"SELECT value FROM key_value WHERE namespace = 'settings' AND key = 'perKeyProxyEnabled'"
|
|
)
|
|
.get() as { value?: string } | undefined;
|
|
if (perKeyRow?.value) {
|
|
globalPerKeyProxyEnabled = JSON.parse(perKeyRow.value) !== false;
|
|
}
|
|
} catch {
|
|
// Default to false on read error
|
|
}
|
|
|
|
const config = await getProxyConfig();
|
|
|
|
// Step 2: API key-level proxy (only if per-key proxy is enabled globally or per-connection)
|
|
if (apiKeyId) {
|
|
// Check if per-key proxy is allowed: globally OR per-connection
|
|
const perKeyEnabled = globalPerKeyProxyEnabled || connectionPerKeyProxyEnabled;
|
|
|
|
if (perKeyEnabled) {
|
|
try {
|
|
const apiKeyRow = db.prepare("SELECT proxy_id FROM api_keys WHERE id = ?").get(apiKeyId) as
|
|
| { proxy_id?: string | null }
|
|
| undefined;
|
|
if (apiKeyRow?.proxy_id) {
|
|
const proxyRow = db
|
|
.prepare(
|
|
"SELECT p.type, p.host, p.port, p.username, p.password, p.family FROM proxy_registry p WHERE p.id = ?"
|
|
)
|
|
.get(apiKeyRow.proxy_id) as
|
|
| {
|
|
type: string;
|
|
host: string;
|
|
port: number;
|
|
username: string;
|
|
password: string;
|
|
family?: string;
|
|
}
|
|
| undefined;
|
|
if (proxyRow) {
|
|
const result = {
|
|
proxy: {
|
|
type: proxyRow.type,
|
|
host: proxyRow.host,
|
|
port: proxyRow.port,
|
|
username: proxyRow.username,
|
|
password: proxyRow.password,
|
|
family: typeof proxyRow.family === "string" ? proxyRow.family : "auto",
|
|
},
|
|
level: "apiKey" as const,
|
|
levelId: apiKeyId,
|
|
source: "api_key" as const,
|
|
};
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
}
|
|
} catch {
|
|
// Fall through to existing resolution
|
|
}
|
|
}
|
|
}
|
|
|
|
// Step 3: Account-level registry
|
|
const registryAccount = await resolveProxyForScopeFromRegistry("account", connectionId);
|
|
if (registryAccount?.proxy) {
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, registryAccount);
|
|
return registryAccount;
|
|
}
|
|
|
|
// Step 4: Legacy key-level
|
|
if (connectionId && config.keys?.[connectionId]) {
|
|
const result = {
|
|
proxy: withFamilyDefault(config.keys[connectionId]),
|
|
level: "key",
|
|
levelId: connectionId,
|
|
};
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
|
|
// Step 5: Use the connection's provider for provider/combo scoped proxies.
|
|
if (connectionRecord) {
|
|
// Step 6: Provider-level registry (only if proxy_enabled)
|
|
if (connectionProvider && connectionProxyEnabled) {
|
|
const registryProvider = await resolveProxyForScopeFromRegistry(
|
|
"provider",
|
|
connectionProvider
|
|
);
|
|
if (registryProvider?.proxy) {
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, registryProvider);
|
|
return registryProvider;
|
|
}
|
|
}
|
|
|
|
// Step 7: Legacy combo-level (only if proxy_enabled)
|
|
if (connectionProxyEnabled && config.combos && Object.keys(config.combos).length > 0) {
|
|
const combos = db.prepare("SELECT id, data FROM combos").all();
|
|
for (const comboRow of combos) {
|
|
const comboRecord = toRecord(comboRow);
|
|
const comboId = typeof comboRecord.id === "string" ? comboRecord.id : null;
|
|
if (comboId && config.combos[comboId]) {
|
|
try {
|
|
const comboRaw = typeof comboRecord.data === "string" ? comboRecord.data : null;
|
|
if (!comboRaw) continue;
|
|
const combo = toRecord(JSON.parse(comboRaw));
|
|
const comboModels = Array.isArray(combo.models) ? combo.models : [];
|
|
const usesProvider = comboModels.some(
|
|
(entry) => getComboModelProvider(entry) === connectionProvider
|
|
);
|
|
if (usesProvider) {
|
|
const result = {
|
|
proxy: withFamilyDefault(config.combos[comboId]),
|
|
level: "combo",
|
|
levelId: comboId,
|
|
};
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
} catch {
|
|
// Ignore malformed combo records during proxy resolution.
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Step 8: Legacy provider-level (only if proxy_enabled)
|
|
if (connectionProvider && connectionProxyEnabled && config.providers?.[connectionProvider]) {
|
|
const result = {
|
|
proxy: withFamilyDefault(config.providers[connectionProvider]),
|
|
level: "provider",
|
|
levelId: connectionProvider,
|
|
};
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
}
|
|
|
|
// Step 9: Global registry
|
|
const registryGlobal = await resolveProxyForScopeFromRegistry("global");
|
|
if (registryGlobal?.proxy) {
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, registryGlobal);
|
|
return registryGlobal;
|
|
}
|
|
|
|
// Step 10: Legacy global
|
|
if (config.global) {
|
|
const result = { proxy: withFamilyDefault(config.global), level: "global", levelId: null };
|
|
cacheProxyResolution(cacheKey, startGeneration, startRegistryGeneration, result);
|
|
return result;
|
|
}
|
|
|
|
// Step 11: Auto-selection fallback (only when global proxy is enabled)
|
|
try {
|
|
const { selectWorkingProxyFallback } = await import("@omniroute/open-sse/utils/proxyFallback");
|
|
const fallback = await selectWorkingProxyFallback(connectionId);
|
|
if (fallback) {
|
|
// Auto-selected proxies are probed via a URL roundtrip that drops any
|
|
// per-registry family policy, so default the family marker to "auto"
|
|
// (no IPv6-only enforcement) when the fallback object omits it.
|
|
const normalizedFallback =
|
|
fallback.proxy && typeof fallback.proxy === "object"
|
|
? { ...fallback, proxy: withFamilyDefault(fallback.proxy as ProxyValue) }
|
|
: fallback;
|
|
cacheProxyResolution(
|
|
cacheKey,
|
|
startGeneration,
|
|
startRegistryGeneration,
|
|
normalizedFallback as ProxyResolutionResult
|
|
);
|
|
return normalizedFallback;
|
|
}
|
|
} catch (err) {
|
|
console.warn({ err, connectionId }, "Proxy fallback auto-selection failed");
|
|
}
|
|
|
|
// Step 12: Return direct
|
|
return { proxy: null, level: "direct", levelId: null };
|
|
}
|
|
|
|
export async function setProxyConfig(config: Record<string, unknown>) {
|
|
if (config.level !== undefined) {
|
|
const level = typeof config.level === "string" ? config.level : "global";
|
|
const id = typeof config.id === "string" ? config.id : null;
|
|
const proxy = (config.proxy as ProxyValue) || null;
|
|
return setProxyForLevel(level, id, proxy);
|
|
}
|
|
|
|
const db = getDbInstance();
|
|
const current = await getProxyConfig();
|
|
const insert = db.prepare(
|
|
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('proxyConfig', ?, ?)"
|
|
);
|
|
|
|
const tx = db.transaction(() => {
|
|
if (config.global !== undefined) {
|
|
current.global = toProxyValue(config.global);
|
|
insert.run("global", JSON.stringify(current.global));
|
|
}
|
|
for (const mapKey of ["providers", "combos", "keys"]) {
|
|
if (config[mapKey]) {
|
|
const merged = { ...toProxyMap(current[mapKey]), ...toProxyMap(config[mapKey]) };
|
|
for (const [k, v] of Object.entries(merged)) {
|
|
if (!v) delete merged[k];
|
|
}
|
|
current[mapKey] = merged;
|
|
insert.run(mapKey, JSON.stringify(merged));
|
|
}
|
|
}
|
|
});
|
|
tx();
|
|
|
|
backupDbFile("pre-write");
|
|
bumpProxyConfigGeneration();
|
|
return current;
|
|
}
|
|
|
|
// ──────────────── Cache Control Metrics ────────────────
|
|
// Cache metrics are now computed from usage_history table on-the-fly
|
|
// This avoids race conditions and keeps a single source of truth for token data
|
|
|
|
export async function getCacheMetrics() {
|
|
const db = getDbInstance();
|
|
|
|
try {
|
|
// Aggregate totals from usage_history
|
|
const totalsRow = db
|
|
.prepare(
|
|
`
|
|
SELECT
|
|
COUNT(*) as totalRequests,
|
|
SUM(tokens_input) as totalInputTokens,
|
|
SUM(tokens_cache_read) as totalCachedTokens,
|
|
SUM(tokens_cache_creation) as totalCacheCreationTokens
|
|
FROM usage_history
|
|
WHERE tokens_cache_read > 0 OR tokens_cache_creation > 0
|
|
`
|
|
)
|
|
.get() as
|
|
| {
|
|
totalRequests: number;
|
|
totalInputTokens: number | null;
|
|
totalCachedTokens: number | null;
|
|
totalCacheCreationTokens: number | null;
|
|
}
|
|
| undefined;
|
|
|
|
// Get all requests count (including those without cache activity)
|
|
const allRequestsRow = db
|
|
.prepare(
|
|
`
|
|
SELECT COUNT(*) as totalRequests
|
|
FROM usage_history
|
|
`
|
|
)
|
|
.get() as { totalRequests: number } | undefined;
|
|
|
|
// Aggregate by provider
|
|
const byProviderRows = db
|
|
.prepare(
|
|
`
|
|
SELECT
|
|
provider,
|
|
COUNT(*) as totalRequests,
|
|
SUM(CASE WHEN tokens_cache_read > 0 OR tokens_cache_creation > 0 THEN 1 ELSE 0 END) as cachedRequests,
|
|
SUM(CASE WHEN tokens_cache_read > 0 OR tokens_cache_creation > 0 THEN tokens_input ELSE 0 END) as inputTokens,
|
|
SUM(tokens_cache_read) as cachedTokens,
|
|
SUM(tokens_cache_creation) as cacheCreationTokens
|
|
FROM usage_history
|
|
WHERE provider IS NOT NULL
|
|
GROUP BY provider
|
|
HAVING cachedRequests > 0
|
|
`
|
|
)
|
|
.all() as Array<{
|
|
provider: string;
|
|
totalRequests: number;
|
|
cachedRequests: number;
|
|
inputTokens: number | null;
|
|
cachedTokens: number | null;
|
|
cacheCreationTokens: number | null;
|
|
}>;
|
|
|
|
// Aggregate by combo strategy (direct requests stored as 'direct')
|
|
const byStrategyRows = db
|
|
.prepare(
|
|
`
|
|
SELECT
|
|
COALESCE(combo_strategy, 'direct') as strategy,
|
|
COUNT(*) as requests,
|
|
SUM(tokens_input) as inputTokens,
|
|
SUM(tokens_cache_read) as cachedTokens,
|
|
SUM(tokens_cache_creation) as cacheCreationTokens
|
|
FROM usage_history
|
|
WHERE (tokens_cache_read > 0 OR tokens_cache_creation > 0)
|
|
GROUP BY combo_strategy
|
|
`
|
|
)
|
|
.all() as Array<{
|
|
strategy: string;
|
|
requests: number;
|
|
inputTokens: number | null;
|
|
cachedTokens: number | null;
|
|
cacheCreationTokens: number | null;
|
|
}>;
|
|
|
|
const tokensSaved = totalsRow?.totalCachedTokens || 0;
|
|
|
|
const AVG_INPUT_PRICE_PER_MILLION = 3;
|
|
const CACHE_DISCOUNT = 0.9;
|
|
const estimatedCostSaved =
|
|
Math.round((tokensSaved / 1_000_000) * AVG_INPUT_PRICE_PER_MILLION * CACHE_DISCOUNT * 100) /
|
|
100;
|
|
|
|
// Build byProvider object
|
|
const byProvider: Record<
|
|
string,
|
|
{
|
|
requests: number;
|
|
totalRequests: number;
|
|
cachedRequests: number;
|
|
inputTokens: number;
|
|
cachedTokens: number;
|
|
cacheCreationTokens: number;
|
|
}
|
|
> = {};
|
|
for (const row of byProviderRows) {
|
|
byProvider[row.provider] = {
|
|
requests: row.cachedRequests,
|
|
totalRequests: row.totalRequests,
|
|
cachedRequests: row.cachedRequests,
|
|
inputTokens: row.inputTokens || 0,
|
|
cachedTokens: row.cachedTokens || 0,
|
|
cacheCreationTokens: row.cacheCreationTokens || 0,
|
|
};
|
|
}
|
|
|
|
// Build byStrategy object
|
|
const byStrategy: Record<
|
|
string,
|
|
{
|
|
requests: number;
|
|
inputTokens: number;
|
|
cachedTokens: number;
|
|
cacheCreationTokens: number;
|
|
}
|
|
> = {};
|
|
for (const row of byStrategyRows) {
|
|
byStrategy[row.strategy] = {
|
|
requests: row.requests,
|
|
inputTokens: row.inputTokens || 0,
|
|
cachedTokens: row.cachedTokens || 0,
|
|
cacheCreationTokens: row.cacheCreationTokens || 0,
|
|
};
|
|
}
|
|
|
|
return {
|
|
totalRequests: allRequestsRow?.totalRequests || totalsRow?.totalRequests || 0,
|
|
requestsWithCacheControl: totalsRow?.totalRequests || 0,
|
|
totalInputTokens: totalsRow?.totalInputTokens || 0,
|
|
totalCachedTokens: totalsRow?.totalCachedTokens || 0,
|
|
totalCacheCreationTokens: totalsRow?.totalCacheCreationTokens || 0,
|
|
tokensSaved,
|
|
estimatedCostSaved,
|
|
byProvider,
|
|
byStrategy,
|
|
lastUpdated: new Date().toISOString(),
|
|
};
|
|
} catch (error) {
|
|
console.error("Failed to fetch cache metrics from usage_history:", error);
|
|
return {
|
|
totalRequests: 0,
|
|
requestsWithCacheControl: 0,
|
|
totalInputTokens: 0,
|
|
totalCachedTokens: 0,
|
|
totalCacheCreationTokens: 0,
|
|
tokensSaved: 0,
|
|
estimatedCostSaved: 0,
|
|
byProvider: {},
|
|
byStrategy: {},
|
|
lastUpdated: new Date().toISOString(),
|
|
};
|
|
}
|
|
}
|
|
|
|
export async function updateCacheMetrics(_metrics: Record<string, unknown>) {
|
|
// No-op: metrics are now computed from usage_history on-the-fly
|
|
// The usage_history table is the single source of truth
|
|
return getCacheMetrics();
|
|
}
|
|
|
|
export interface CacheTrendPoint {
|
|
timestamp: string;
|
|
requests: number;
|
|
cachedRequests: number;
|
|
inputTokens: number;
|
|
cachedTokens: number;
|
|
cacheCreationTokens: number;
|
|
}
|
|
|
|
export async function getCacheTrend(hours = 24): Promise<CacheTrendPoint[]> {
|
|
const db = getDbInstance();
|
|
|
|
try {
|
|
const rows = db
|
|
.prepare(
|
|
`
|
|
SELECT
|
|
strftime('%Y-%m-%dT%H:00:00Z', timestamp) as hour,
|
|
COUNT(*) as requests,
|
|
SUM(CASE WHEN tokens_cache_read > 0 OR tokens_cache_creation > 0 THEN 1 ELSE 0 END) as cachedRequests,
|
|
SUM(tokens_input) as inputTokens,
|
|
SUM(tokens_cache_read) as cachedTokens,
|
|
SUM(tokens_cache_creation) as cacheCreationTokens
|
|
FROM usage_history
|
|
WHERE timestamp >= datetime('now', ?)
|
|
GROUP BY hour
|
|
ORDER BY hour ASC
|
|
`
|
|
)
|
|
.all(`-${hours} hours`) as Array<{
|
|
hour: string;
|
|
requests: number;
|
|
cachedRequests: number;
|
|
inputTokens: number | null;
|
|
cachedTokens: number | null;
|
|
cacheCreationTokens: number | null;
|
|
}>;
|
|
|
|
return rows.map((r) => ({
|
|
timestamp: r.hour,
|
|
requests: r.requests,
|
|
cachedRequests: r.cachedRequests,
|
|
inputTokens: r.inputTokens || 0,
|
|
cachedTokens: r.cachedTokens || 0,
|
|
cacheCreationTokens: r.cacheCreationTokens || 0,
|
|
}));
|
|
} catch (error) {
|
|
console.error("Failed to fetch cache trend:", error);
|
|
return [];
|
|
}
|
|
}
|
|
|
|
export async function resetCacheMetrics() {
|
|
// No-op: cache metrics are computed from usage_history.
|
|
console.warn(
|
|
"resetCacheMetrics is deprecated - cache metrics are now computed from usage_history"
|
|
);
|
|
return getCacheMetrics();
|
|
}
|