mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-08 08:12:20 +03:00
* chore(release): open v3.8.21 development cycle
* fix: pass through valid max_tokens-truncated responses instead of fake 502 (#3572) (#3595)
* fix: /v1/completions returns legacy text-completion format, not chat (#3571) (#3596)
* fix: z.ai/GLM coding plan no longer shows Monthly 0% when no monthly cap (#3580) (#3597)
* docs: mark DISCOVERY_TOOL_DESIGN endpoints as Phase-2 not-yet-implemented (#3498) (#3599)
* fix(agent-bridge): add validate-only upstream-ca/test route (#3488) (#3600)
* fix(gamification): add level/badges/badges-earned profile routes (#3484)
* security(oauth): migrate 5 public client_ids to resolvePublicCred (#3493)
* fix(mcp): ship MCP server source closure in npm files + coverage gate (#3578)
* fix: add reasoning token buffer for combo routing (fixes #3587) (#3588)
Integrated into release/v3.8.21
* Refactor: Extract chatCore phases into modular files (#3598)
Integrated into release/v3.8.21 — chatCore phase modularization. Adjusted: re-derive idempotencyKey for the save path after the check moved into the module (co-authored). Thanks @oyi77!
* docs(changelog): credit #3598 (chatCore modularization) + #3588 (combo reasoning buffer)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(api): implement GET /api/guardrails + POST /api/guardrails/test, drop shadow/guardrails doc-fiction (#3496) (#3602)
Integrated into release/v3.8.21 — implements GET /api/guardrails + POST /api/guardrails/test, removes shadow/guardrails doc-fiction. TDD-validated (5/5) + check-docs-symbols/typecheck/eslint green.
* fix(gemini): isolate textual reasoning wrappers (#3605)
Split-out PR C from #3584. Isolates textual reasoning wrappers (<think>/<thinking>/<thought>/<internal_thought>, including malformed/open tags) into reasoning_content across both the non-streaming sanitizer and the Gemini streaming translator, with split-chunk buffering. Additive to the existing textual tool-call pipeline; does not touch the #3569 native functionResponse path. Integrated into release/v3.8.21. Thanks @dhaern!
* fix(antigravity): normalize Gemini 3.5 Flash tier IDs (#3603)
Split-out PR A from #3584. Normalizes the Antigravity/agy Gemini 3.5 Flash tier IDs to clean public names (gemini-3.5-flash-low/medium/high), maps them to the live upstream IDs at the executor boundary, and removes Antigravity from the global model resolver so the executor owns wire normalization. Maintainer follow-up: kept gemini-3.5-flash-preview as a hidden backward-compat alias routing to the High tier (so saved combos/configs keep working). Live-validated the tier set via the agy CLI catalog. Integrated into release/v3.8.21. Thanks @dhaern!
* fix(agent-bridge): surface real MITM startup-failure cause, not always port 443 (#3606) (#3608)
Integrated into release/v3.8.21 (#3606)
* fix(oauth): surface real Kiro import-token failure cause, not a bare 500 (#3589) (#3609)
Integrated into release/v3.8.21 (#3589)
* docs(opencode-provider): soft-deprecate in favor of @omniroute/opencode-plugin (#3419) (#3613)
Integrated into release/v3.8.21 (#3419)
* fix(usage): normalize Antigravity and agy provider quotas (#3604)
Split-out PR B from #3584. Normalizes Antigravity/agy provider quotas: prefers retrieveUserQuota for live consumption, falls back to fetchAvailableModels and local usage_history, sanitizes cached Provider Limits so retired upstream IDs are not re-exposed, and schedules a deduplicated post-usage refresh. Maintainer follow-up: decoupled the post-usage refresh via a lightweight usageEvents bus (usageHistory no longer dynamic-imports providerLimits) so it does not pull the executors/translator graph into the typecheck-core surface — typecheck:core stays at 0. Integrated into release/v3.8.21. Thanks @dhaern!
* feat(cli): add autostart on/off/toggle shorthand for headless serve mode (#3331) (#3614)
Integrated into release/v3.8.21 (#3331)
* docs(changelog): credit #3603 (Flash tier IDs) + #3604 (provider quotas) + #3605 (reasoning wrappers)
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(review): resolve findings from /review-reviews battery (v3.8.21 hardening) (#3618)
Pre-release hardening from the /review-reviews battery — 15 findings resolved (L1-L13,L15) + L14 live-verified WONTFIX, convergence re-review clean. lint/typecheck:core/test:vitest(146)/build green; zero new test:unit failures vs baseline 797de433f.
* chore(release): v3.8.21 CHANGELOG + i18n + env-doc sync
---------
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Raxxoor <manker_lol@hotmail.com>
235 lines
11 KiB
TypeScript
235 lines
11 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import {
|
|
ANTIGRAVITY_PUBLIC_MODELS,
|
|
getClientVisibleAntigravityModelName,
|
|
isUserCallableAntigravityModelId,
|
|
resolveAntigravityModelId,
|
|
toClientAntigravityModelId,
|
|
toClientAntigravityQuotaModelId,
|
|
} from "../../open-sse/config/antigravityModelAliases.ts";
|
|
import { AntigravityExecutor } from "../../open-sse/executors/antigravity.ts";
|
|
import { openaiToAntigravityRequest } from "../../open-sse/translator/request/openai-to-gemini.ts";
|
|
|
|
function getPublicModel(id: string) {
|
|
return ANTIGRAVITY_PUBLIC_MODELS.find((model) => model.id === id) as any;
|
|
}
|
|
|
|
// #3821-review LEDGER-5 — the upstream quota-bucket → client-tier remap is now the single
|
|
// source of truth here (was duplicated as an inline if-ladder in usage.ts). It operates on
|
|
// the UPSTREAM quota namespace, where `gemini-3.5-flash-low` is the Medium tier's bucket.
|
|
test("toClientAntigravityQuotaModelId maps upstream quota buckets to client tiers", () => {
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3.5-flash-extra-low"), "gemini-3.5-flash-low");
|
|
// Dual-meaning id: in the quota namespace this bucket is the Medium tier.
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3.5-flash-low"), "gemini-3.5-flash-medium");
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3-flash-agent"), "gemini-3.5-flash-high");
|
|
// Non-tier ids fall back to the standard reverse alias map.
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3.1-pro"), "gemini-3-pro-preview");
|
|
// Always-allowed bucket passes through unchanged.
|
|
assert.equal(toClientAntigravityQuotaModelId("credits"), "credits");
|
|
// Retired preview buckets are dropped (hidden from clients).
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3.5-flash-preview"), null);
|
|
assert.equal(toClientAntigravityQuotaModelId("gemini-3-flash-preview"), null);
|
|
assert.equal(toClientAntigravityQuotaModelId(""), null);
|
|
});
|
|
|
|
test("resolveAntigravityModelId maps the documented Antigravity aliases to upstream IDs", () => {
|
|
assert.equal(resolveAntigravityModelId("gemini-3-pro-preview"), "gemini-3.1-pro");
|
|
assert.equal(resolveAntigravityModelId("gemini-3-pro-image-preview"), "gemini-3-pro-image");
|
|
assert.equal(
|
|
resolveAntigravityModelId("gemini-2.5-computer-use-preview-10-2025"),
|
|
"rev19-uic3-1p"
|
|
);
|
|
assert.equal(resolveAntigravityModelId("gemini-3.5-flash-low"), "gemini-3.5-flash-extra-low");
|
|
assert.equal(resolveAntigravityModelId("gemini-3.5-flash-medium"), "gemini-3.5-flash-low");
|
|
assert.equal(resolveAntigravityModelId("gemini-3.5-flash-high"), "gemini-3-flash-agent");
|
|
// Backward-compat: retired flagship public id routes to the High tier upstream.
|
|
assert.equal(resolveAntigravityModelId("gemini-3.5-flash-preview"), "gemini-3-flash-agent");
|
|
assert.equal(resolveAntigravityModelId("gemini-claude-sonnet-4-5"), "claude-sonnet-4-6");
|
|
assert.equal(resolveAntigravityModelId("gemini-claude-sonnet-4-5-thinking"), "claude-sonnet-4-6");
|
|
assert.equal(
|
|
resolveAntigravityModelId("gemini-claude-opus-4-5-thinking"),
|
|
"claude-opus-4-6-thinking"
|
|
);
|
|
assert.equal(resolveAntigravityModelId("unknown-model"), "unknown-model");
|
|
});
|
|
|
|
test("toClientAntigravityModelId exposes client-visible aliases for known upstream IDs", () => {
|
|
assert.equal(toClientAntigravityModelId("gemini-3.1-pro"), "gemini-3-pro-preview");
|
|
assert.equal(toClientAntigravityModelId("gemini-3.5-flash-extra-low"), "gemini-3.5-flash-low");
|
|
assert.equal(toClientAntigravityModelId("gemini-3-flash-agent"), "gemini-3.5-flash-high");
|
|
assert.equal(toClientAntigravityModelId("gpt-oss-120b-medium"), "gpt-oss-120b-medium");
|
|
assert.equal(toClientAntigravityModelId("claude-sonnet-4-6"), "claude-sonnet-4-6");
|
|
assert.equal(toClientAntigravityModelId("claude-opus-4-6-thinking"), "claude-opus-4-6-thinking");
|
|
});
|
|
|
|
test("isUserCallableAntigravityModelId only allows public chat-capable model IDs", () => {
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3-pro-preview"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.1-pro"), true);
|
|
// Retired flagship id stays callable as a hidden backward-compat alias (routes to High),
|
|
// even though it is no longer exposed in the public catalog.
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.5-flash-preview"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3-flash-agent"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.1-flash-lite"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-2.5-pro"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-2.5-flash"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-2.5-flash-lite"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-2.5-flash-thinking"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-pro-agent"), true);
|
|
// #3184: Claude IS user-callable through the Antigravity OAuth provider (same backend as
|
|
// `agy`, verified empirically). An earlier assumption that it was removed in Antigravity
|
|
// 2.0 was wrong.
|
|
assert.equal(isUserCallableAntigravityModelId("claude-opus-4-6-thinking"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("claude-sonnet-4-6"), true);
|
|
// Antigravity 2.0.4 exposes Gemini 3.5 Flash as separate UI tiers.
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.1-pro-high"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.1-pro-low"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.5-flash-low"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.5-flash-medium"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.5-flash-high"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("gemini-3.5-flash-extra-low"), true);
|
|
assert.equal(isUserCallableAntigravityModelId("tab_flash_lite_preview"), false);
|
|
assert.equal(isUserCallableAntigravityModelId("unknown-model"), false);
|
|
});
|
|
|
|
test("ANTIGRAVITY_PUBLIC_MODELS exposes captured Antigravity 2.0.1 names and capabilities", () => {
|
|
// #3184: Claude is exposed in the antigravity catalog (same backend as `agy`, verified).
|
|
assert.deepEqual(getPublicModel("claude-opus-4-6-thinking"), {
|
|
id: "claude-opus-4-6-thinking",
|
|
name: "Claude Opus 4.6 (Thinking)",
|
|
contextLength: 200000,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
});
|
|
assert.equal(getPublicModel("claude-sonnet-4-6").name, "Claude Sonnet 4.6 (Thinking)");
|
|
assert.deepEqual(getPublicModel("gemini-3.5-flash-high"), {
|
|
id: "gemini-3.5-flash-high",
|
|
name: "Gemini 3.5 Flash (High)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
});
|
|
assert.equal(
|
|
getClientVisibleAntigravityModelName("gemini-3.5-flash-medium"),
|
|
"Gemini 3.5 Flash (Medium)"
|
|
);
|
|
assert.equal(getClientVisibleAntigravityModelName("gemini-2.5-flash"), "Gemini 2.5 Flash");
|
|
assert.equal(
|
|
getClientVisibleAntigravityModelName("gemini-2.5-flash-lite"),
|
|
"Gemini 2.5 Flash Lite"
|
|
);
|
|
assert.equal(
|
|
getClientVisibleAntigravityModelName("gemini-2.5-flash-thinking"),
|
|
"Gemini 2.5 Flash Thinking"
|
|
);
|
|
assert.deepEqual(getPublicModel("gpt-oss-120b-medium"), {
|
|
id: "gpt-oss-120b-medium",
|
|
name: "GPT-OSS 120B (Medium)",
|
|
contextLength: 131072,
|
|
maxOutputTokens: 32768,
|
|
supportsReasoning: true,
|
|
toolCalling: true,
|
|
});
|
|
assert.equal(getPublicModel("gemini-3-pro-image-preview").contextLength, undefined);
|
|
assert.equal(
|
|
getPublicModel("gemini-2.5-computer-use-preview-10-2025").maxOutputTokens,
|
|
undefined
|
|
);
|
|
});
|
|
|
|
test("ANTIGRAVITY_PUBLIC_MODELS has no duplicate model IDs", () => {
|
|
const ids = ANTIGRAVITY_PUBLIC_MODELS.map((model) => model.id);
|
|
const seen = new Set<string>();
|
|
const duplicates = ids.filter((id) => {
|
|
if (seen.has(id)) return true;
|
|
seen.add(id);
|
|
return false;
|
|
});
|
|
assert.deepEqual(duplicates, [], `duplicate model IDs found: ${duplicates.join(", ")}`);
|
|
});
|
|
|
|
test("AntigravityExecutor.transformRequest resolves alias models before dispatching upstream", async () => {
|
|
const executor = new AntigravityExecutor();
|
|
const result = await executor.transformRequest(
|
|
"antigravity/gemini-3-pro-preview",
|
|
{
|
|
request: {
|
|
contents: [{ role: "user", parts: [{ text: "Hello" }] }],
|
|
},
|
|
},
|
|
true,
|
|
{ projectId: "project-1" }
|
|
);
|
|
|
|
if (result instanceof Response) throw new Error("Unexpected Response from transformRequest");
|
|
assert.equal(result.model, "gemini-3.1-pro");
|
|
});
|
|
|
|
test("AntigravityExecutor.transformRequest maps Gemini 3.5 Flash tiers to live upstream IDs", async () => {
|
|
const executor = new AntigravityExecutor();
|
|
const result = await executor.transformRequest(
|
|
"antigravity/gemini-3.5-flash-high",
|
|
{
|
|
request: {
|
|
contents: [{ role: "user", parts: [{ text: "Hello" }] }],
|
|
},
|
|
},
|
|
true,
|
|
{ projectId: "project-1" }
|
|
);
|
|
|
|
if (result instanceof Response) throw new Error("Unexpected Response from transformRequest");
|
|
// The "High" tier resolves to the live upstream id; the request body is forwarded
|
|
// under that id. (Dropped four assertions on modelConfigId/model_config_id — the
|
|
// executor never sets those fields, so they were vacuously true and gave false
|
|
// confidence. #3821-review LEDGER-10.)
|
|
assert.equal(result.model, "gemini-3-flash-agent");
|
|
assert.deepEqual(result.request.contents, [
|
|
{ role: "user", parts: [{ text: "Hello" }] },
|
|
]);
|
|
});
|
|
|
|
test("AntigravityExecutor.transformRequest sends Claude through Gemini-compatible Cloud Code schema", async () => {
|
|
const executor = new AntigravityExecutor();
|
|
const bridged = openaiToAntigravityRequest(
|
|
"claude-opus-4-6-thinking",
|
|
{
|
|
messages: [{ role: "user", content: "Hello" }],
|
|
max_completion_tokens: 32_000,
|
|
temperature: 0.5,
|
|
reasoning_effort: "high",
|
|
},
|
|
true,
|
|
{ projectId: "project-1" } as any
|
|
);
|
|
|
|
const result = await executor.transformRequest(
|
|
"antigravity/claude-opus-4-6-thinking",
|
|
bridged,
|
|
true,
|
|
{
|
|
projectId: "project-1",
|
|
}
|
|
);
|
|
|
|
if (result instanceof Response) throw new Error("Unexpected Response from transformRequest");
|
|
const request = result.request as any;
|
|
assert.deepEqual(request.contents, [{ role: "user", parts: [{ text: "Hello" }] }]);
|
|
assert.equal(request.generationConfig.maxOutputTokens, 32769);
|
|
assert.equal(request.generationConfig.temperature, 0.5);
|
|
assert.equal(request.generationConfig.topK, 40);
|
|
assert.equal(request.generationConfig.topP, 1);
|
|
assert.equal(request.messages, undefined);
|
|
assert.equal(request.system, undefined);
|
|
assert.equal(request.max_tokens, undefined);
|
|
assert.equal(request.stream, undefined);
|
|
assert.equal(request.temperature, undefined);
|
|
assert.equal(request.thinking, undefined);
|
|
assert.equal(request.generationConfig.thinkingConfig, undefined);
|
|
});
|