mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-04 22:32:12 +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>
111 lines
4.4 KiB
TypeScript
111 lines
4.4 KiB
TypeScript
/**
|
|
* LEDGER-6 (#3821-review) — the chatCore modularization (#3598) relocated ~300 lines into
|
|
* open-sse/handlers/chatCore/{idempotency,sanitization,semanticCache,memorySkillsInjection}.ts
|
|
* with no direct tests at the new seam. The extraction shipped a real `ReferenceError`
|
|
* (idempotencyKey) that no test caught. These tests pin the pure/extractable pieces:
|
|
* - sanitizeChatRequestBody (token-field normalization, empty-name stripping, tool filter)
|
|
* - checkIdempotencyCache now returns { hit, idempotencyKey } so the save site reuses the
|
|
* single derivation (no dual getIdempotencyKey call).
|
|
*/
|
|
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
import { sanitizeChatRequestBody } from "../../open-sse/handlers/chatCore/sanitization.ts";
|
|
import { checkIdempotencyCache } from "../../open-sse/handlers/chatCore/idempotency.ts";
|
|
import { FORMATS } from "../../open-sse/translator/formats.ts";
|
|
import { saveIdempotency } from "../../src/lib/idempotencyLayer.ts";
|
|
|
|
test("sanitizeChatRequestBody: Chat Completions target maps max_output_tokens → max_tokens", () => {
|
|
const out = sanitizeChatRequestBody({ max_output_tokens: 256 }, FORMATS.OPENAI, FORMATS.OPENAI);
|
|
assert.equal(out.max_tokens, 256);
|
|
assert.equal(out.max_output_tokens, undefined);
|
|
});
|
|
|
|
test("sanitizeChatRequestBody: Responses target maps max_completion_tokens → max_output_tokens", () => {
|
|
const out = sanitizeChatRequestBody(
|
|
{ max_completion_tokens: 512 },
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI_RESPONSES
|
|
);
|
|
assert.equal(out.max_output_tokens, 512);
|
|
assert.equal(out.max_completion_tokens, undefined);
|
|
});
|
|
|
|
test("sanitizeChatRequestBody: Responses target maps max_tokens → max_output_tokens", () => {
|
|
const out = sanitizeChatRequestBody({ max_tokens: 128 }, FORMATS.OPENAI_RESPONSES, FORMATS.OPENAI);
|
|
assert.equal(out.max_output_tokens, 128);
|
|
assert.equal(out.max_tokens, undefined);
|
|
});
|
|
|
|
test("sanitizeChatRequestBody: strips empty message name and filters nameless tools", () => {
|
|
const out = sanitizeChatRequestBody(
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "hi", name: "" },
|
|
{ role: "assistant", content: "yo", name: "keepme" },
|
|
],
|
|
tools: [
|
|
{ type: "function", function: { name: "real_tool", parameters: {} } },
|
|
{ type: "function", function: { name: "" } }, // dropped — empty name
|
|
{ type: "function", function: {} }, // dropped — no name
|
|
],
|
|
},
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI
|
|
);
|
|
|
|
const messages = out.messages as Array<Record<string, unknown>>;
|
|
assert.ok(!("name" in messages[0]), "empty name stripped");
|
|
assert.equal(messages[1].name, "keepme", "non-empty name kept");
|
|
|
|
const tools = out.tools as Array<Record<string, unknown>>;
|
|
assert.equal(tools.length, 1, "only the named tool survives");
|
|
assert.equal((tools[0].function as Record<string, unknown>).name, "real_tool");
|
|
});
|
|
|
|
test("checkIdempotencyCache returns { hit:null, idempotencyKey } on a miss", async () => {
|
|
const headers = new Headers({ "idempotency-key": "idem-miss-3821" });
|
|
const result = await checkIdempotencyCache({
|
|
clientRawRequest: { headers },
|
|
provider: "openai",
|
|
model: "gpt-4.1",
|
|
effectiveServiceTier: undefined,
|
|
startTime: 0,
|
|
log: undefined,
|
|
});
|
|
assert.equal(result.hit, null);
|
|
assert.equal(result.idempotencyKey, "idem-miss-3821");
|
|
});
|
|
|
|
test("checkIdempotencyCache returns a hit Response reusing the same key after a save", async () => {
|
|
const key = "idem-hit-3821";
|
|
saveIdempotency(key, { object: "chat.completion", choices: [], usage: {} }, 200);
|
|
|
|
const headers = new Headers({ "idempotency-key": key });
|
|
const result = await checkIdempotencyCache({
|
|
clientRawRequest: { headers },
|
|
provider: "openai",
|
|
model: "gpt-4.1",
|
|
effectiveServiceTier: undefined,
|
|
startTime: 0,
|
|
log: undefined,
|
|
});
|
|
|
|
assert.equal(result.idempotencyKey, key, "the resolved key is returned for the save site to reuse");
|
|
assert.ok(result.hit, "a cached entry produces a hit");
|
|
assert.equal(result.hit!.response.headers.get("X-OmniRoute-Idempotent"), "true");
|
|
});
|
|
|
|
test("checkIdempotencyCache resolves a null key when no idempotency headers are present", async () => {
|
|
const result = await checkIdempotencyCache({
|
|
clientRawRequest: { headers: new Headers() },
|
|
provider: "openai",
|
|
model: "gpt-4.1",
|
|
effectiveServiceTier: undefined,
|
|
startTime: 0,
|
|
log: undefined,
|
|
});
|
|
assert.equal(result.hit, null);
|
|
assert.equal(result.idempotencyKey, null);
|
|
});
|