mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +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>
120 lines
4.9 KiB
TypeScript
120 lines
4.9 KiB
TypeScript
/**
|
|
* LEDGER-3 (#3821-review) — the Antigravity local-usage fallback (#3604) replaces a
|
|
* stale full `fetchAvailableModels` bucket (used=0) with real consumption summed from
|
|
* `usage_history`, flipping quotaSource to "localUsageHistory". Every prior #3604 test
|
|
* mocks only the HTTP layer, so the model-id match against usage_history.model was never
|
|
* exercised end-to-end. This seeds a real usage_history row keyed by the CLIENT tier id
|
|
* the fallback queries and asserts the flip — the regression guard for the id contract.
|
|
*
|
|
* Contract note: the fallback queries `usage_history WHERE model = <client tier id>`
|
|
* (e.g. gemini-3.5-flash-high), so the executor MUST log usage under that same client id
|
|
* for the fallback to fire. This test pins exactly that join.
|
|
*/
|
|
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import fs from "node:fs";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
|
|
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-ag-local-usage-"));
|
|
process.env.DATA_DIR = TEST_DATA_DIR;
|
|
process.env.API_KEY_SECRET = "test-ag-local-usage-secret";
|
|
|
|
const core = await import("../../src/lib/db/core.ts");
|
|
// Load usage.ts up-front (its index.ts proxyFetch patch runs at module eval) before mocks.
|
|
const usageModule = await import("../../open-sse/services/usage.ts");
|
|
const { getUsageForProvider } = usageModule;
|
|
|
|
const originalFetch = globalThis.fetch;
|
|
|
|
test.after(() => {
|
|
globalThis.fetch = originalFetch;
|
|
core.resetDbInstance();
|
|
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
|
|
});
|
|
|
|
test("Antigravity fetchAvailableModels(used=0) → localUsageHistory when usage_history has rows", async () => {
|
|
core.resetDbInstance();
|
|
|
|
// resetTime an hour out → the 5h local-usage window is [now-4h, now+1h).
|
|
const resetTime = new Date(Date.now() + 60 * 60 * 1000).toISOString();
|
|
const seededTimestamp = new Date(Date.now() - 30 * 60 * 1000).toISOString(); // within window
|
|
|
|
// Seed a usage_history row keyed by the CLIENT tier id the fallback queries.
|
|
const db = core.getDbInstance() as unknown as { prepare: (sql: string) => { run: (...a: unknown[]) => unknown } };
|
|
db.prepare(
|
|
`INSERT INTO usage_history (provider, model, connection_id, tokens_input, tokens_output, tokens_reasoning, success, timestamp)
|
|
VALUES (?, ?, ?, ?, ?, ?, 1, ?)`
|
|
).run("antigravity", "gemini-3.5-flash-high", "conn-local-1", 1000, 1500, 500, seededTimestamp);
|
|
// Total seeded tokens = 3000 → ceil(3000/1000) = 3 units used.
|
|
|
|
globalThis.fetch = (async (input: any) => {
|
|
const url = typeof input === "string" ? input : input?.url || "";
|
|
// retrieveUserQuota (the live signal) is unavailable → falls back to fetchAvailableModels.
|
|
if (url.includes("retrieveUserQuota")) {
|
|
return { ok: false, status: 404, json: async () => ({}) } as Response;
|
|
}
|
|
// fetchAvailableModels returns a FULL (stale) bucket: remainingFraction 1.0 + resetTime.
|
|
return {
|
|
ok: true,
|
|
json: async () => ({
|
|
models: {
|
|
"gemini-3.5-flash-high": {
|
|
quotaInfo: { remainingFraction: 1.0, resetTime },
|
|
},
|
|
},
|
|
}),
|
|
} as Response;
|
|
}) as typeof fetch;
|
|
|
|
const connection = {
|
|
id: "conn-local-1",
|
|
provider: "antigravity",
|
|
accessToken: "fake-token-local-usage-unique",
|
|
providerSpecificData: {},
|
|
projectId: undefined,
|
|
};
|
|
|
|
const result = await getUsageForProvider(connection, { forceRefresh: true });
|
|
assert.ok(result && "quotas" in result, "should return quotas");
|
|
const quota = (result as any).quotas["gemini-3.5-flash-high"];
|
|
assert.ok(quota, "should have the gemini-3.5-flash-high quota");
|
|
assert.equal(quota.quotaSource, "localUsageHistory", "stale full bucket replaced by local usage");
|
|
assert.equal(quota.used, 3, "3000 seeded tokens → 3 units used");
|
|
});
|
|
|
|
test("Antigravity stays fetchAvailableModels when usage_history has no matching rows", async () => {
|
|
core.resetDbInstance();
|
|
|
|
const resetTime = new Date(Date.now() + 60 * 60 * 1000).toISOString();
|
|
|
|
globalThis.fetch = (async (input: any) => {
|
|
const url = typeof input === "string" ? input : input?.url || "";
|
|
if (url.includes("retrieveUserQuota")) {
|
|
return { ok: false, status: 404, json: async () => ({}) } as Response;
|
|
}
|
|
return {
|
|
ok: true,
|
|
json: async () => ({
|
|
models: {
|
|
"gemini-3.5-flash-high": { quotaInfo: { remainingFraction: 1.0, resetTime } },
|
|
},
|
|
}),
|
|
} as Response;
|
|
}) as typeof fetch;
|
|
|
|
const connection = {
|
|
id: "conn-local-2",
|
|
provider: "antigravity",
|
|
accessToken: "fake-token-local-usage-empty",
|
|
providerSpecificData: {},
|
|
projectId: undefined,
|
|
};
|
|
|
|
const result = await getUsageForProvider(connection, { forceRefresh: true });
|
|
const quota = (result as any).quotas["gemini-3.5-flash-high"];
|
|
assert.ok(quota, "should have the quota");
|
|
assert.equal(quota.quotaSource, "fetchAvailableModels", "no local rows → keep the catalog view");
|
|
assert.equal(quota.used, 0, "full bucket stays at 0 used");
|
|
});
|