mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-14 10:52:17 +03:00
Rebased onto the current release/v3.8.51 tip as part of a combined provider-retirement/provenance merge batch (Designer Web, Felo Web, Runtime, GPL-derived removal, Qwen Web already landed). Large conflict set (this is the biggest PR in the batch — the common ChatGPT Web provider touches chat, images, count-tokens, session leases, and combos). Conflicts resolved: - `open-sse/config/providers/registry/chatgpt-web/*`, `open-sse/executors/chatgpt-web*`, `open-sse/handlers/imageGeneration/providers/chatgptWeb.ts`, and their tests: kept deleted, matching the PR's stated scope. - `open-sse/config/providers/registry/minimax/web/index.ts`, `open-sse/handlers/imageGeneration/providers/geminiWeb.ts`, `open-sse/executors/gemini-web.ts`'s stale image-mode branch: base-drift collisions against already-merged sibling retirements (#11691, #11708) — kept deleted / dropped the dead code, since this PR's own branch forked before those merged. - `src/shared/constants/reservedProviderPrefixes.ts`, `open-sse/executors/index.ts`, `executorProxy.ts`, `virtualFactory.ts`, `autoStrategy.ts`, `src/lib/db/providers.ts`, `src/sse/handlers/chat.ts`: combined the Designer + Runtime (Felo/Qwen) + common-ChatGPT-Web retirement guard calls at each shared chokepoint — compute-once-then-OR pattern, consistent with prior combinations in this batch. - `src/sse/services/model.ts` / `src/sse/handlers/chatHelpers.ts`: adopted this PR's new `getModelInfoOrRetirementResponse()` central wrapper (a real improvement over ad-hoc try/catch), and extended it to also catch the Designer + Runtime retirement errors it didn't originally cover, so the consolidation doesn't regress the other two mechanisms. - `src/app/api/v1/images/edits/route.ts`: this PR moved the retirement check earlier (before `enforceApiKeyPolicy`) but left the old later call+catch block in place from base drift — removed the now-redundant duplicate `resolveImageRouteModel()` call and merged the Designer catch into the earlier one. - `open-sse/config/imageRegistry.ts`, `tests/snapshots/executors/executor-map.json` (`keyCount` recomputed to 133), `tests/snapshots/provider/translate-path.json`: same "both sides inserted a different retired provider at the same slot" pattern — resolved by dropping both. - `tests/unit/chatcore-executor-proxy.test.ts`, `provider-node-reserved-prefix.test.ts`, `combo-auto-candidate-expansion.test.ts`, `messages-count-tokens-route.test.ts`, `virtual-auto-combo.test.ts`: split into independent per-mechanism test blocks (established pattern); `virtual-auto-combo.test.ts`'s old "includes cookie web-session providers" positive-inclusion test (which used chatgpt-web as its example) was retired along with the provider and replaced by this PR's negative-exclusion test for the same slot. - `docs/architecture/ARCHITECTURE.md`, `CODEBASE_DOCUMENTATION.md` (+ 4 i18n mirrors), `README.md`, `FREE-TIERS-GUIDE.md`, `docs/diagrams/free-tier-budget.svg`, `docs/screenshots/free-tier-budget-card.svg`, `docs/reference/PROVIDER_REFERENCE.md`: recomputed every stale count from the real merged state — 104 executors (`countFiles` gate logic), 351 providers (regenerated via `gen:provider-reference`), 152/351 `hasFree` entries, 445/438/7 free-tier catalog rows, 13 ToS-avoid providers, budget-card regenerated via its real generator script. One doc conflict (`oauth/` module list) needed picking HEAD's side specifically — theirs still listed the already-removed `raycast` module instead of the real `openference`. - `config/quality/test-masking-allowlist.json`: additive merge of the PR's 17 `_deletedWithReplacement` entries alongside the batch's existing ones (one real duplicate-key mistake in my first pass, caught and fixed via a `object_pairs_hook` duplicate-key check before finalizing). Also fixed two real, unrelated-to-my-merge issues surfaced by the focused suite: - `tests/unit/resolve-web-provider-host.test.ts`: the PR's own test had a typo — it asserted `perplexity-web`'s resolved host as `"perplexity.ai"`, but the provider's registered `website` is `"https://www.perplexity.ai"` and the resolver returns the URL's `host` verbatim (no www-stripping), so the correct value is `"www.perplexity.ai"` (consistent with the same test's own `url` assertion). - `tests/unit/hard-session-lease-bypass-inventory.test.ts`: this golden call-site inventory was already stale on the pristine post-#11713 tip (confirmed via a throwaway probe worktree) — `src/lib/db/providers.ts`'s 3 connection-fallback sites and a third `src/app/api/providers/route.ts` site were never added to the golden list by the earlier-merged #11698/#11720 PRs. Updated it to the real current inventory (dated inline comments explain each delta and which PR introduced it), plus this PR's own legitimate deltas (image-edits duplicate-call removal, `ChatGptWebExecutor.execute()` site removed). Focused suite green (433/433 across executor-proxy, reserved-prefix, hard-session-lease-bypass-inventory, resolve-web-provider-host, retirement/runtime-block/source-retirement/management-retirement/image-handler-retirement, migration-168, combo-auto-candidate-expansion, virtual-auto-combo, executor-map-golden and siblings), plus `typecheck:core`, `check-file-size`, and `check-changelog-integrity` clean. Thanks for the thorough provenance-hold retirement work — appreciated.
214 lines
8.6 KiB
TypeScript
214 lines
8.6 KiB
TypeScript
/**
|
|
* chatCore upstream-proxy executor resolver (Quality Gate v2 / Fase 9 — chatCore god-file
|
|
* decomposition, #3501).
|
|
*
|
|
* Extracted from handleChatCore: resolves the executor for a provider honoring the configured
|
|
* upstream proxy mode. `native` / disabled → the provider's own executor; `cliproxyapi` → the
|
|
* CLIProxyAPI passthrough executor; `dario` → the Dario passthrough executor; `fallback` → a
|
|
* wrapper that tries the native executor first and retries via the configured fallback backend
|
|
* (CLIProxyAPI by default, or Dario) on configured failure codes (default 5xx + 429 + network)
|
|
* or on a thrown error.
|
|
*
|
|
* Dario (@askalf/dario) is wired as a parallel, independent backend choice at both levels
|
|
* (per-connection `darioMode` + provider `mode`/`fallbackBackend`) WITHOUT changing any existing
|
|
* CLIProxyAPI behaviour. Dario needs neither the dedicated-credential substitution nor the
|
|
* per-provider model-mapping wrappers CLIProxyAPI uses: it authenticates via its own OAuth
|
|
* account pool (not a configured bearer key) and has its own server-side model-alias mechanism.
|
|
*/
|
|
|
|
import { assertRuntimeProviderAvailable } from "@/shared/constants/providerRetirement";
|
|
|
|
import { getExecutor } from "../../executors/index.ts";
|
|
import { isCliproxyapiDeepModeEnabled } from "../../executors/cliproxyapi.ts";
|
|
import { isDarioDeepModeEnabled } from "../../executors/dario.ts";
|
|
import { getCachedSettings } from "@/lib/db/readCache";
|
|
import { assertMicrosoftDesignerWebProviderAvailable } from "@/shared/constants/designerWebRetirement";
|
|
import { assertCommonChatGptWebProviderAvailable } from "@/shared/constants/chatgptWebRetirement";
|
|
import { getUpstreamProxyConfigCached } from "./comboContextCache.ts";
|
|
import type { FallbackBackend } from "@/lib/db/upstreamProxy";
|
|
import { wrapExecutorWithCliproxyapiModelMapping } from "./cliproxyModelMapping.ts";
|
|
import {
|
|
resolveDedicatedCliproxyapiApiKey,
|
|
wrapExecutorWithCliproxyapiCredentials,
|
|
} from "./cliproxyapiCredentials.ts";
|
|
|
|
type LoggerLike =
|
|
| {
|
|
info?: (...args: unknown[]) => void;
|
|
error?: (...args: unknown[]) => void;
|
|
warn?: (...args: unknown[]) => void;
|
|
}
|
|
| null
|
|
| undefined;
|
|
|
|
const DEFAULT_FALLBACK_CODES = [429, 500, 502, 503, 504];
|
|
|
|
function parseFallbackCodes(raw: unknown): number[] | null {
|
|
if (typeof raw !== "string" || !raw.trim()) return null;
|
|
const parsed = raw
|
|
.split(",")
|
|
.map((s) => Number.parseInt(s.trim(), 10))
|
|
.filter((n) => !Number.isNaN(n));
|
|
return parsed.length > 0 ? parsed : null;
|
|
}
|
|
|
|
/**
|
|
* Reads the CLIProxyAPI-related settings shared by both the direct
|
|
* `mode: "cliproxyapi"` passthrough leg and the `mode: "fallback"` retry leg:
|
|
* the custom fallback status codes and the dedicated credential (#7645).
|
|
* Falls back to defaults / no dedicated key on any read failure.
|
|
*/
|
|
async function loadCliproxyapiSettings(): Promise<{
|
|
fallbackCodes: number[];
|
|
dedicatedApiKey: string | null;
|
|
}> {
|
|
try {
|
|
const allSettings = await getCachedSettings();
|
|
return {
|
|
fallbackCodes: parseFallbackCodes(allSettings.cliproxyapi_fallback_codes) ?? [
|
|
...DEFAULT_FALLBACK_CODES,
|
|
],
|
|
dedicatedApiKey: resolveDedicatedCliproxyapiApiKey(allSettings),
|
|
};
|
|
} catch {
|
|
return { fallbackCodes: [...DEFAULT_FALLBACK_CODES], dedicatedApiKey: null };
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Resolve the CLIProxyAPI passthrough executor with its model-mapping +
|
|
* dedicated-credential wrappers applied. Used by the direct `cliproxyapi` leg
|
|
* and the CLIProxyAPI branch of `fallback`.
|
|
*/
|
|
async function resolveCliproxyapiExecutor(
|
|
cliproxyapiModelMapping: Record<string, unknown> | null,
|
|
dedicatedApiKey: string | null
|
|
) {
|
|
return wrapExecutorWithCliproxyapiCredentials(
|
|
wrapExecutorWithCliproxyapiModelMapping(
|
|
await getExecutor("cliproxyapi"),
|
|
cliproxyapiModelMapping
|
|
),
|
|
dedicatedApiKey
|
|
);
|
|
}
|
|
|
|
export async function resolveExecutorWithProxy(
|
|
prov: string,
|
|
log?: LoggerLike,
|
|
providerSpecificData?: Record<string, unknown> | null
|
|
) {
|
|
assertMicrosoftDesignerWebProviderAvailable(prov);
|
|
assertRuntimeProviderAvailable(prov);
|
|
assertCommonChatGptWebProviderAvailable(prov);
|
|
|
|
// Per-connection routing override (#6339): the resolved connection can opt itself
|
|
// into the CLIProxyAPI passthrough executor via providerSpecificData.cliproxyapiMode
|
|
// === "claude-native" (UI toggle). This takes precedence over the provider-level
|
|
// upstream_proxy_config mode — one connection can deep-route while the provider's
|
|
// default (and its other connections) stay native. Backward-compatible: connections
|
|
// without the flag fall through to the existing per-provider behaviour untouched.
|
|
if (isCliproxyapiDeepModeEnabled(providerSpecificData)) {
|
|
log?.info?.(
|
|
"UPSTREAM_PROXY",
|
|
`${prov} routed through CLIProxyAPI (per-connection claude-native override)`
|
|
);
|
|
const [cfg, { dedicatedApiKey }] = await Promise.all([
|
|
getUpstreamProxyConfigCached(prov),
|
|
loadCliproxyapiSettings(),
|
|
]);
|
|
return resolveCliproxyapiExecutor(cfg.cliproxyapiModelMapping, dedicatedApiKey);
|
|
}
|
|
|
|
// Sibling per-connection override for Dario (#dario). Checked AFTER the
|
|
// CLIProxyAPI check above by deliberate design: if a connection somehow sets
|
|
// BOTH cliproxyapiMode and darioMode to "claude-native", CLIProxyAPI's
|
|
// existing behaviour keeps winning — the least-surprising precedence for
|
|
// configs that predate this field, and the simplest to reason about.
|
|
if (isDarioDeepModeEnabled(providerSpecificData)) {
|
|
log?.info?.(
|
|
"UPSTREAM_PROXY",
|
|
`${prov} routed through Dario (per-connection claude-native override)`
|
|
);
|
|
return getExecutor("dario");
|
|
}
|
|
|
|
const cfg = await getUpstreamProxyConfigCached(prov);
|
|
if (!cfg.enabled || cfg.mode === "native") return getExecutor(prov);
|
|
|
|
if (cfg.mode === "cliproxyapi") {
|
|
log?.info?.("UPSTREAM_PROXY", `${prov} routed through CLIProxyAPI (passthrough)`);
|
|
const { dedicatedApiKey } = await loadCliproxyapiSettings();
|
|
return resolveCliproxyapiExecutor(cfg.cliproxyapiModelMapping, dedicatedApiKey);
|
|
}
|
|
|
|
if (cfg.mode === "dario") {
|
|
// Direct Dario passthrough. No credential/model-mapping wrappers: Dario
|
|
// authenticates via its own OAuth pool and has its own model-alias layer.
|
|
log?.info?.("UPSTREAM_PROXY", `${prov} routed through Dario (passthrough)`);
|
|
return getExecutor("dario");
|
|
}
|
|
|
|
// mode === "fallback": try native first, retry via the configured fallback
|
|
// backend on specific failures. The backend defaults to CLIProxyAPI so every
|
|
// pre-existing fallback config behaves exactly as before; fallbackBackend
|
|
// === "dario" opts the retry leg over to Dario instead.
|
|
const nativeExec = await getExecutor(prov);
|
|
const fallbackBackend: FallbackBackend = cfg.fallbackBackend;
|
|
const { fallbackCodes, dedicatedApiKey } = await loadCliproxyapiSettings();
|
|
|
|
// The model mapping applies only to the CLIProxyAPI retry leg (proxyExec) —
|
|
// the native leg must keep seeing the original, unmapped model.
|
|
const proxyExec =
|
|
fallbackBackend === "dario"
|
|
? await getExecutor("dario")
|
|
: await resolveCliproxyapiExecutor(cfg.cliproxyapiModelMapping, dedicatedApiKey);
|
|
const backendLabel = fallbackBackend === "dario" ? "Dario" : "CLIProxyAPI";
|
|
const isRetryableStatus = (s: number) => fallbackCodes.includes(s) || s === 0;
|
|
|
|
const wrapper = Object.create(nativeExec);
|
|
wrapper.execute = async (input: {
|
|
model: string;
|
|
body: unknown;
|
|
stream: boolean;
|
|
credentials: unknown;
|
|
signal?: AbortSignal | null;
|
|
log?: unknown;
|
|
upstreamExtraHeaders?: Record<string, string> | null;
|
|
}) => {
|
|
let result;
|
|
try {
|
|
result = await nativeExec.execute(input);
|
|
} catch (err) {
|
|
const errMsg = err instanceof Error ? err.message : String(err);
|
|
log?.info?.(
|
|
"UPSTREAM_PROXY",
|
|
`${prov} native error (${errMsg}), retrying via ${backendLabel}`
|
|
);
|
|
try {
|
|
return await proxyExec.execute(input);
|
|
} catch (proxyErr) {
|
|
const proxyMsg = proxyErr instanceof Error ? proxyErr.message : String(proxyErr);
|
|
log?.error?.("UPSTREAM_PROXY", `${prov} ${backendLabel} fallback also failed: ${proxyMsg}`);
|
|
throw proxyErr;
|
|
}
|
|
}
|
|
|
|
if (!isRetryableStatus(result.response.status)) {
|
|
return result;
|
|
}
|
|
log?.info?.(
|
|
"UPSTREAM_PROXY",
|
|
`${prov} native failed (${result.response.status}), retrying via ${backendLabel}`
|
|
);
|
|
try {
|
|
return await proxyExec.execute(input);
|
|
} catch (proxyErr) {
|
|
const proxyMsg = proxyErr instanceof Error ? proxyErr.message : String(proxyErr);
|
|
log?.error?.("UPSTREAM_PROXY", `${prov} ${backendLabel} fallback also failed: ${proxyMsg}`);
|
|
throw proxyErr;
|
|
}
|
|
};
|
|
return wrapper;
|
|
}
|