mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
Release v3.8.13 (#3327)
* chore(release): open v3.8.13 development cycle Bump 3.8.12 → 3.8.13 across package.json, lockfile, electron/, open-sse/, and docs/reference/openapi.yaml; add the [3.8.13] cycle placeholder to the root CHANGELOG and the 41 i18n mirrors. Integration branch for the v3.8.13 cycle — fixes/features land here via per-issue PRs and it merges to main at release time. * fix(ci): skip auto-deploy when VPS host is unreachable from the runner (#3299) Integrated into release/v3.8.13 * fix(dev): auto-rebuild better-sqlite3 on Node ABI mismatch at dev startup (#3301) Integrated into release/v3.8.13 * feat(api): accept path-scoped API keys on client API routes (#3300) Integrated into release/v3.8.13 * fix(sse): harden against empty responses causing Copilot Chat failures (#3297) Integrated into release/v3.8.13 * fix(api): remove Completions.me rickroll provider (discussion #3293) (#3302) Integrated into release/v3.8.13 * fix(opencode-provider): extract contextLength from live model catalog (#3298) Integrated into release/v3.8.13 * feat(web-cookie): self-service login infrastructure + auto-refresh daemon (#3292) Integrated into release/v3.8.13 * docs(changelog): record the v3.8.13 PRs merged this round (#3292/#3300/#3297/#3298/#3301/#3302/#3299) * fix(auth): harden URL token extraction — drop query-string fallback, gate to client routes (security follow-up to #3300) (#3309) Security follow-up to #3300 — integrated into release/v3.8.13 * docs: rename resolve-issues → review-issues skill references * fix(dashboard): keep no-auth providers visible under 'Show configured only' (#3290) (#3312) no-auth providers (opencode, duckduckgo-web, theoldllm, veoaifree-web) never create a DB connection row so stats.total stays 0, which the configured-only filter treated as 'unconfigured' and hid them — even though they are always usable and appear unconditionally in /v1/models. filterConfiguredProviderEntries now treats displayAuthType === 'no-auth' as configured. Co-authored-by: uniQta <uniQta@users.noreply.github.com> * fix(cli): resolve update paths relative to script + recursive backup (#3295) (#3313) omniroute update always failed on a global install: - getCurrentVersion() read package.json from process.cwd(), which on a global npm/brew install is the user's working dir, not the package root → null → 'Could not determine current version'. - createBackup() resolved bin/ from cwd too, and passed the 'cli' directory to copyFileSync → EISDIR, swallowed by the catch → 'Failed to create backup'. Both now resolve package.json/bin relative to the script via import.meta.url, and the backup uses cpSync({recursive:true}) so the cli/ directory is copied. Co-authored-by: uniQta <uniQta@users.noreply.github.com> * fix(theoldllm): read upstream body once to avoid [502] body-already-read (#3296) (#3314) On the cached-token path the executor never enters the refresh branch, so the same upstream Response was read with .text() twice (token-rejection check + final body). A Response body is single-use, so the second read threw 'Body is unusable: Body has already been read', caught and surfaced as [502]. Read the body once into finalBody and only re-read after a token-rejection refetch. Co-authored-by: onizukashonan14-png <onizukashonan14-png@users.noreply.github.com> * fix(sse): strip leaked internal tool envelopes from streaming output (#3311) Integrated into release/v3.8.13 * fix(sse): expose Claude + Gemini budget tiers in the antigravity catalog (#3184) (#3303) Integrated into release/v3.8.13 (#3184) * fix(catalog): compute combo context_length from known targets only (#3304) Integrated into release/v3.8.13 — live contextLength + known-targets combo context (#3298 follow-up) * chore(i18n): add message keys for proxy UI + vscode/ollama endpoint (#3307) Integrated into release/v3.8.13 — i18n message keys for proxy UI + vscode/ollama * feat(dashboard): i18n the proxy settings UI (#3310) Integrated into release/v3.8.13 — i18n the proxy settings UI * feat(api): model catalog enrichment + MCP model-catalog tools (#3306) Integrated into release/v3.8.13 — model catalog enrichment + MCP model-catalog tools, reconciled with #3309 URL-token hardening * test(catalog): align Antigravity preview-alias test with #3303 budget tiers #3303 added the Gemini `-high`/`-low` budget tiers to ANTIGRAVITY_PUBLIC_MODELS (user-callable on the Antigravity OAuth backend, verified via #3184), but did not update the catalog-route test that asserted `antigravity/gemini-3.1-pro-high` must NOT be exposed. The assertion now reflects the intended behavior — the client-visible budget alias IS surfaced — while keeping the legacy `gemini-claude-*` alias keys unexposed. Caught running the full catalog suite on the merged release HEAD (the #3303 round only ran the antigravity-aliases and usage-hardening files). * docs(changelog): record the 6 PRs merged this review round into v3.8.13 #3306/#3307/#3310 (New Features — VS Code split: catalog+MCP, i18n keys, proxy UI i18n), #3311/#3303/#3304 (Bug Fixes — SSE envelope sanitizer, antigravity budget tiers, combo known-targets context_length). * chore(release): finalize v3.8.13 changelog and cleanup Finalize the v3.8.13 changelog with release date, maintenance notes, and contributor credits. Update MCP docs to reference the correct tool inventory diagram, exclude nested .claude worktrees from ESLint scans, and tighten a response sanitizer type guard. * fix(dashboard): refresh connections after provider auth import (#3320) Integrated into release/v3.8.13 — refresh connections after provider auth import * fix(codex): strip client-only params on native /responses passthrough (#3317) (#3325) A /v1/responses request against the built-in codex/ provider does an openai-responses -> openai-responses passthrough (CodexExecutor.transformRequest returns the body early for _nativeCodexPassthrough). It forwarded client-only fields verbatim and the Codex upstream rejected them with 400 Unsupported parameter: prompt_cache_retention / safety_identifier / user — breaking Factory Droid (which injects all three). The chat-completions path already strips these (base.ts #1884, openai-responses translator #2770) but the passthrough skips translation. Strip the three fields in the shared block before the passthrough return; user is removed unconditionally since Codex /responses always rejects it. Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> * fix(dashboard): normalize agent-bridge /state response to stop page crash (#3318) (#3326) The Agent Bridge page seeded a well-shaped initialData default then replaced it wholesale with the raw /api/tools/agent-bridge/state response. The route returns { server, agents } but the UI reads { serverState, agentStates, bypassPatterns, mappings }, so serverState became undefined and AgentBridgeServerCard crashed on serverState.running — surfaced as the full-page 'Internal Server Error' boundary (client render error, not a real 5xx). Add a shared normalizeAgentBridgeState() that maps the route shape into the page contract (server.running/certExists -> serverState) and always returns safe defaults (never undefined serverState). Wired into both the SSR loader (page.tsx) and the polling hook. The legacy 'agents' entry shape differs from AgentStateEntry so it is not coerced; full route<->page contract reconciliation (port, upstreamCa, bypassPatterns, mappings, agentStates) is a follow-up. Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> * docs: VS Code/Ollama endpoints + env & i18n tooling (#3319) Integrated into release/v3.8.13 — VS Code/Ollama docs + env & i18n tooling * feat(provider): test-all endpoint, rate-limit overrides, visibility f… (#3267) Integrated into release/v3.8.13 — provider test-all endpoint, rate-limit overrides, model visibility * feat: auto-combo optimization, playground model dropdown, only-configured toggle (#3322) Integrated into release/v3.8.13 — auto-combo candidate expansion + playground dropdown + only-configured toggle * feat(api): VS Code Copilot Ollama-compatible BYOK endpoint (#3316) Integrated into release/v3.8.13 — VS Code Copilot Ollama-compatible BYOK endpoint (reconciled with #3306/#3309 auth hardening) * chore(release): document #3320 in the v3.8.13 changelog + contributor credits --------- Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com> Co-authored-by: Wilson <pedbookmed@gmail.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: uniQta <uniQta@users.noreply.github.com> Co-authored-by: onizukashonan14-png <onizukashonan14-png@users.noreply.github.com> Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> Co-authored-by: Vinayrnani <vinayrnani@gmail.com>
This commit is contained in:
Diego Rodrigues de Sa e Souza
committed by
GitHub
GitHub
parent
78454eed5e
commit
a25d5f1ef6
@@ -129,8 +129,8 @@ export interface OmniRouteProviderOptions {
|
||||
apiKey: string;
|
||||
/** Override the display name shown in OpenCode. Default: `"OmniRoute"`. */
|
||||
displayName?: string;
|
||||
/** Override the model catalog. Defaults to `OMNIROUTE_DEFAULT_OPENCODE_MODELS`. */
|
||||
models?: readonly string[];
|
||||
/** Override the model catalog. Accepts model ids (strings) or live model entries from `fetchLiveModels`. When entries carry a `contextLength`, it is used directly — no hardcoded map needed. */
|
||||
models?: readonly (string | { id: string; contextLength?: number })[];
|
||||
/** Optional human-readable labels keyed by model id. Overridden by `modelCapabilities[id].label`. */
|
||||
modelLabels?: Record<string, string>;
|
||||
/**
|
||||
@@ -139,6 +139,12 @@ export interface OmniRouteProviderOptions {
|
||||
* for custom ids the override is used verbatim.
|
||||
*/
|
||||
modelCapabilities?: Record<string, ModelCapabilities>;
|
||||
/**
|
||||
* Optional per-model context-length overrides (tokens). Takes precedence
|
||||
* over the static `OMNIROUTE_DEFAULT_MODEL_CONTEXT_LENGTHS` map but is
|
||||
* superseded by `contextLength` on live model entries passed via `models`.
|
||||
*/
|
||||
modelContextLengths?: Record<string, string | number>;
|
||||
/**
|
||||
* Primary model for OpenCode (top-level `model` key).
|
||||
* Emitted as `"omniroute/<id>"`. When omitted the key is not written.
|
||||
@@ -248,7 +254,12 @@ export function createOmniRouteProvider(options: OmniRouteProviderOptions): Open
|
||||
const models: Record<string, OpenCodeModelEntry> = {};
|
||||
const seen = new Set<string>();
|
||||
for (const raw of modelList) {
|
||||
const id = typeof raw === "string" ? raw.trim() : "";
|
||||
const id =
|
||||
typeof raw === "object" && raw !== null && "id" in raw && typeof (raw as any).id === "string"
|
||||
? (raw as { id: string }).id.trim()
|
||||
: typeof raw === "string"
|
||||
? raw.trim()
|
||||
: "";
|
||||
if (!id || seen.has(id)) continue;
|
||||
seen.add(id);
|
||||
const defaults = OMNIROUTE_DEFAULT_MODEL_CAPABILITIES[id] ?? {};
|
||||
@@ -266,10 +277,18 @@ export function createOmniRouteProvider(options: OmniRouteProviderOptions): Open
|
||||
if (typeof merged.temperature === "boolean") entry.temperature = merged.temperature;
|
||||
if (typeof merged.tool_call === "boolean") entry.tool_call = merged.tool_call;
|
||||
|
||||
// Include context window limit when known — OpenCode reads this to
|
||||
// determine usable context length for compaction & overflow detection.
|
||||
const contextLength = OMNIROUTE_DEFAULT_MODEL_CONTEXT_LENGTHS[id];
|
||||
if (typeof contextLength === "number" && contextLength > 0) {
|
||||
// Context window: live model entry (from API catalog) > modelContextLengths > static defaults
|
||||
const liveContext =
|
||||
typeof raw === "object" && raw !== null
|
||||
? (raw as { contextLength?: number }).contextLength
|
||||
: undefined;
|
||||
const rawContextLength =
|
||||
liveContext ??
|
||||
options.modelContextLengths?.[id] ??
|
||||
OMNIROUTE_DEFAULT_MODEL_CONTEXT_LENGTHS[id];
|
||||
const contextLength =
|
||||
typeof rawContextLength === "string" ? parseInt(rawContextLength, 10) : rawContextLength;
|
||||
if (typeof contextLength === "number" && !isNaN(contextLength) && contextLength > 0) {
|
||||
entry.limit = { context: contextLength };
|
||||
}
|
||||
|
||||
@@ -508,7 +527,7 @@ export interface OmniRouteLiveModel {
|
||||
* const config = buildOmniRouteOpenCodeConfig({
|
||||
* baseURL: "http://localhost:20128",
|
||||
* apiKey: "sk_omniroute",
|
||||
* models: models.map((m) => m.id),
|
||||
* models, // OmniRouteLiveModel[] — contextLength auto-extracted
|
||||
* modelLabels: Object.fromEntries(models.map((m) => [m.id, m.name])),
|
||||
* });
|
||||
* ```
|
||||
|
||||
@@ -430,6 +430,34 @@ test("createOmniRouteProvider omits limit.context for unknown model ids", () =>
|
||||
assert.equal(entry.limit, undefined);
|
||||
});
|
||||
|
||||
test("createOmniRouteProvider reads contextLength from a live model entry for ids absent from the static map", () => {
|
||||
// #3298 regression guard: the static OMNIROUTE_DEFAULT_MODEL_CONTEXT_LENGTHS
|
||||
// map only covers the legacy 8 Claude/Gemini ids. Before this change, any
|
||||
// other model got `undefined` context (see the test above, string form) and
|
||||
// OpenCode silently fell back to its 128K internal default. A live model
|
||||
// entry carrying `contextLength` must now surface as `limit.context`.
|
||||
const provider = createOmniRouteProvider({
|
||||
baseURL: "http://localhost:20128",
|
||||
apiKey: "sk_omniroute",
|
||||
models: [{ id: "completely-unknown-model", contextLength: 262_144 }],
|
||||
});
|
||||
const entry = provider.models["completely-unknown-model"];
|
||||
assert.ok(entry.limit, "a live contextLength should produce a limit field even for ids absent from the static map");
|
||||
assert.equal(entry.limit!.context, 262_144);
|
||||
});
|
||||
|
||||
test("createOmniRouteProvider: a live model contextLength wins over the static default map", () => {
|
||||
// `cc/claude-opus-4-8` has a static default (1_000_000). A live entry carrying
|
||||
// a different contextLength must take precedence (live > modelContextLengths >
|
||||
// static defaults).
|
||||
const provider = createOmniRouteProvider({
|
||||
baseURL: "http://localhost:20128",
|
||||
apiKey: "sk_omniroute",
|
||||
models: [{ id: "cc/claude-opus-4-8", contextLength: 524_288 }],
|
||||
});
|
||||
assert.equal(provider.models["cc/claude-opus-4-8"].limit!.context, 524_288);
|
||||
});
|
||||
|
||||
test("createOmniRouteProvider serialises limit.context to JSON", () => {
|
||||
const provider = createOmniRouteProvider({
|
||||
baseURL: "http://localhost:20128",
|
||||
|
||||
Reference in New Issue
Block a user