mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-11 17:52:31 +03:00
* fix(ci): drop unused RadarReferrals type export — dead-code ratchet back to 227 baseline The radar referral-links feature (#9697) exported the inferred type RadarReferrals from feedSchema.ts but nothing imports it (the singular RadarReferral is the consumed type). knip counts it as a new dead export, pushing the dead-code ratchet to 228 > 227 and failing Fast Quality Gates on every PR born after the merge. RadarReferralsSchema itself stays — it is used by RadarFeedSchema. Refs #9737 * fix(ci): clear the 08-08 base-red layer — prod crash in chat.ts, Responses API payload regression, born-red stdio test, gate drifts Six independent base-reds from the 08-07 evening merge batch, each verified against the pure release/v3.8.50 tip: - src/sse/handlers/chat.ts: #9467's squash carried a refactor hunk that renamed the all-rate-limited breaker guard to an UNDEFINED variable (isAllRateLimited) — a production ReferenceError on the all-accounts-429 path (chat.ts is outside typecheck:core scope, so only tests caught it). Restore credentials?.allRateLimited. Guard: chat-rate-limit-body-lock (2/2), also un-breaks batch_api and chat-combo-live-test. - open-sse/utils/stream.ts: #9315 switched providerPayload summaries to the accumulated responseBody, but in passthrough paths that body is synthesized in chat-completion shape — Responses API lost its `response` object in the dashboard payload. Keep the events-derived summary for OPENAI_RESPONSES only. Guard: stream-utils + stream-collector-9315 suites (51/51). - tests/unit/mcp-stdio-json-purity.test.ts: born red — the full CLI chain takes ~10s (2x tsx import + DB init) and the test slept a fixed 4s. Poll for the first stdout line with a 60s deadline instead. - tests/unit/plugins-route-error-sanitization.test.ts: register #9445's new marketplace/install route in PLUGIN_ROUTES (route already sanitizes) (33/33). - tests/unit/provider-models-route-codex.test.ts: realign pinned GPT-5.6 input limit to #9432's deliberate 272000→922000 bump (7/7). - lint: fix 11 no-explicit-any errors in repro-9630 + specialty-9293 tests, prune 1 orphaned suppression, allowlist the opencode-ai devDependency (#8869, publisher-verified), and reword a doc line the fabricated-docs gate misread as an env var. Gates re-verified locally: lint:json --max-warnings 0 exit 0, dead-code 227, typecheck:core clean, check:deps OK, check:fabricated-docs OK. Refs #9737 * fix(ci): clear the third 08-08 base-red layer — invalid ru rule pack, stale event pin, orphaned UI repro test, pack/mutation/file-size drifts Follow-up to the previous layer: the serial fast-gates chain unmasked one more stratum after file-size/dead-code went green, all verified against the merged release/v3.8.50 tip: - compression rules ru/ultra.json (#9581): two rules shipped minIntensity "notes", which is not a valid CavemanIntensity (lite|full|ultra) — loading ANY language pack list threw and killed the rtk-loader suite. Mapped both to "ultra" (they are the most aggressive punctuation/case rules, matching the en pack tiers). 2/2. - plugins-welcome-banner-e2e: #9668 added the onStreamComplete builtin event (real emission path via runOnStreamCompleteHooks) and missed this pinned-list sibling. 35/35. - tests/unit/free-pool-frontend-repro (#9046): landed as .tsx with node:test semantics — no runner collects tests/unit/*.tsx, so it NEVER ran (test-discovery NEW-orphan). It contains zero JSX; renamed to .test.ts so the unit runner's existing glob collects it. 5/5 (first real run). - pack-policy: allow + require bin/mcpStdioConsoleGuard.mjs (#9281) — it is preloaded via node --import by bin/mcp-server.mjs, so a published artifact without it crashes 'omniroute --mcp' at startup. - stryker.conf.json: add 5 covering unit tests from the batch (#8779/#9204/ #9330/#9630/openrouter-passthrough) to tap.testFiles (--strict drift). - file-size-baseline: consolidate the base-drift rebaseline for the 12 files grown by the 08-06..08-08 batches (#9616's entries never reached the base; measured on this branch's tree — this PR's own source edits add zero lines to any frozen file). Local battery: file-size/deps/test-discovery/mutation/pack-policy/dead-code/ duplication/docs-all/secrets/vuln/workflows ratchets all exit 0; full lint gate --max-warnings 0 exit 0. Refs #9737 * fix(types): clear the 3 uncovered open-sse-typecheck regressions + realign combo skip-code siblings Fourth base-red layer unmasked by the serial gates. The other 4 typecheck regressions (codex.ts, kiro.ts, tierResolver.test.ts, translator/index.ts) already have dedicated open [TS7] PRs (#9748/#9753/#9742/#9747) — not duplicated here. This commit covers only what no open PR owns: - devin-agentic/serializer.ts TS2367: drop the dead 'role === "system"' branch — the guard above already narrows role to user|assistant (system throws unsupported_role). Devin suites 104/104. - raycast.ts TS2416: the buildHeaders 'override' never matched the base signature (2nd param is the signed payload string, not the stream boolean) — renamed to a private buildRaycastRequestHeaders helper so a polymorphic buildHeaders(credentials, true) call can never bind here. - modelMetadataRegistry.ts TS2352: PricingByProvider → nested-record cast now goes through unknown (shape is runtime-guarded by findInsensitive). - combo-routing-engine.test.ts: realign 2 pre-dispatch-skip expectations to #9630's deliberate ALL_TARGETS_SKIPPED contract (87/87). Refs #9737 * fix(ci): clear the fifth 08-08 base-red layer — reasoning-placeholder contract sweep, GPT-5.6 limits sweep, vi key parity The 08-08 merges (#9610 reasoning replay, #9432 GPT-5.6 limits, #9630 combo skip codes, #9336 provider key links) each changed a contract and left sibling tests pinning the old one. Full grep sweep per contract, not just the shard that happened to go red: - reasoning placeholder (#9573/#9610): the fix DELIBERATELY removed NON_ANTHROPIC_THINKING_PLACEHOLDER injection on cache miss — the model echoed the placeholder as its own reasoning (empty stop) and re-poisoned cache + client history; DeepSeek's 400 is specific to an EMPTY STRING, not an absent field. Realigned reasoning-cache (2 cases, renamed to describe omission) + tool-request-sanitization (1 case + dead import). 60/60. - GPT-5.6 Codex limits (#9432, 272000 -> 1050000 ctx / 922000 input): realigned vscode-token-routes-gpt56 (2) + vscode-token-routes (3). 43/43 together with t23-t24. - combo skip codes (#9630): t23-t24-fallback-resilience T24 now expects ALL_TARGETS_SKIPPED like the combo-routing-engine siblings. - vi.json key parity: #9336 added providers.getApiKey/getApiKeyDescription to en.json without syncing vi (the only locale with a parity gate). Translated both; providers block reordered to match en key order. 5/5. - pack-artifact-policy.test.ts: sibling of this PR's own required-paths change (bin/mcpStdioConsoleGuard.mjs). 10/10. - combo-routing-engine.test.ts: dropped the 6 comment lines added in the previous commit so the frozen test file-size stays at its baseline (the rationale lives in that commit message, not the test body). Gates: file-size, test-discovery, mutation-test-coverage, pack-policy, open-sse-typecheck, dead-code all exit 0. Refs #9737 * fix(translator): keep the reasoning_content placeholder for Xiaomi MiMo — #9610 traded one live 400 for another The xiaomi-mimo replay test (9router#1321) went red on the base after #9610 removed the NON_ANTHROPIC_THINKING_PLACEHOLDER injection globally. That test is NOT stale — it guards a documented upstream 400 ('Param Incorrect: The reasoning_content in the thinking mode must be passed back to the API'), so realigning it would have masked a reintroduced production bug. Two real bugs conflict here: - #9573: forwarding the placeholder makes the model continue its chain of thought FROM that text (echo -> empty stop) and re-poisons cache/history. - 9router#1321/#1337: omitting reasoning_content on a plain replay turn makes Xiaomi MiMo reject the request outright. #9610's evidence for omitting is provider-specific — it verified that deepseek-v4-flash accepts an ABSENT field. It does not extend to MiMo. So the omission stays for every provider #9610 covered, and the placeholder survives the cache miss only for xiaomi-mimo (new requiresReasoningContentPresence predicate next to isReasoningOnlyReplayTarget). The echo that comes back is still stripped on the way in by isInternalReasoningPlaceholder(), so #9573's cache/history poisoning stays fixed for MiMo too. Both contracts now hold simultaneously: xiaomi-mimo replay + reasoning-cache + tool-request-sanitization 61/61; placeholder-strip/responses/translator/combo regression sweep 168/168. Gates: file-size, open-sse-typecheck, dead-code, mutation-test-coverage exit 0; typecheck:core clean. A live check on the VPS (Hard Rule #18 path 2) is the only way to confirm the DeepSeek half of #9610's empirical claim; flagging it in the PR rather than widening this fix on speculation. Refs #9737 * test(translator): pin the reasoning-placeholder provider scope so neither half of the conflict can silently re-break #9610 removed the placeholder globally on the strength of ONE provider's observed behavior (deepseek-v4-flash accepting an absent reasoning_content), which re-opened the MiMo 400 (9router#1321). The previous commit scoped the placeholder to xiaomi-mimo; this pins BOTH directions in one test so the next global edit fails loudly instead of trading the bugs again: - xiaomi-mimo plain replay turn, cache miss -> reasoning_content present (narrowing the scope away from MiMo re-opens 9router#1321) - deepseek plain replay turn, cache miss -> reasoning_content absent (widening it back to DeepSeek re-opens the #9573 echo bug) Guard verified by mutation: forcing requiresReasoningContentPresence() to return true makes the DeepSeek half fail (1 pass / 1 fail), and the file was restored from the pre-probe copy before committing. Also checked kimi-coding/kimi-coding-apikey, the other strict-contract entries in REASONING_REPLAY_PROVIDERS: their originating PR (#7673) fixes capture and replay of REAL reasoning and documents no 400 on an absent field, so they stay out of the placeholder scope — evidence-scoped, not speculatively widened. Reasoning suites together: 87/87. Gates: file-size, test-discovery, mutation-test-coverage, dead-code exit 0; eslint clean. Refs #9737 --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
238 lines
6.7 KiB
TypeScript
238 lines
6.7 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
const {
|
|
coerceSchemaNumericFields,
|
|
sanitizeToolDescription,
|
|
coerceToolSchemas,
|
|
sanitizeToolDescriptions,
|
|
injectEmptyReasoningContentForToolCalls,
|
|
} = await import("../../open-sse/translator/helpers/schemaCoercion.ts");
|
|
const { translateRequest } = await import("../../open-sse/translator/index.ts");
|
|
const { FORMATS } = await import("../../open-sse/translator/formats.ts");
|
|
const { clearModelsDevCapabilities, saveModelsDevCapabilities } =
|
|
await import("../../src/lib/modelsDevSync.ts");
|
|
|
|
function buildCapability(overrides = {}) {
|
|
return {
|
|
tool_call: null,
|
|
reasoning: null,
|
|
attachment: null,
|
|
structured_output: null,
|
|
temperature: null,
|
|
modalities_input: "[]",
|
|
modalities_output: "[]",
|
|
knowledge_cutoff: null,
|
|
release_date: null,
|
|
last_updated: null,
|
|
status: null,
|
|
family: null,
|
|
open_weights: null,
|
|
limit_context: null,
|
|
limit_input: null,
|
|
limit_output: null,
|
|
interleaved_field: null,
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
test("tool sanitization: coerces numeric JSON Schema fields recursively", () => {
|
|
const schema = {
|
|
type: "object",
|
|
properties: {
|
|
count: { type: "integer", minimum: "1", maximum: "10" },
|
|
items: {
|
|
type: "array",
|
|
minItems: "2",
|
|
items: { type: "string", minLength: "3" },
|
|
},
|
|
},
|
|
};
|
|
|
|
const result = coerceSchemaNumericFields(schema);
|
|
assert.equal((result as any).properties.count.minimum, 1);
|
|
(assert as any).equal((result as any).properties.count.maximum, 10);
|
|
(assert as any).equal((result as any).properties.items.minItems, 2);
|
|
assert.equal((result as any).properties.items.items.minLength, 3);
|
|
});
|
|
|
|
test("tool sanitization: preserves non-numeric JSON Schema strings", () => {
|
|
const schema = {
|
|
type: "object",
|
|
properties: {
|
|
value: { type: "string", minimum: "abc" },
|
|
},
|
|
};
|
|
|
|
const result = coerceSchemaNumericFields(schema);
|
|
assert.equal((result as any).properties.value.minimum, "abc");
|
|
});
|
|
|
|
test("tool sanitization: normalizes descriptions across OpenAI, Claude, and Gemini shapes", () => {
|
|
const openAITool = sanitizeToolDescription({
|
|
type: "function",
|
|
function: { name: "sum", description: null, parameters: {} },
|
|
});
|
|
const claudeTool = sanitizeToolDescription({
|
|
name: "sum",
|
|
description: 42,
|
|
input_schema: { type: "object" },
|
|
});
|
|
const geminiTool = sanitizeToolDescription({
|
|
functionDeclarations: [{ name: "sum", description: false, parameters: {} }],
|
|
});
|
|
|
|
(assert as any).equal(((openAITool as any).function as any).description, "");
|
|
assert.equal((claudeTool as any).description, "42");
|
|
assert.equal((geminiTool as any).functionDeclarations[0].description, "false");
|
|
});
|
|
|
|
test("tool sanitization: coerces schemas and descriptions in tool arrays", () => {
|
|
const tools = sanitizeToolDescriptions(
|
|
coerceToolSchemas([
|
|
{
|
|
type: "function",
|
|
function: {
|
|
name: "sum",
|
|
description: 5,
|
|
parameters: {
|
|
type: "object",
|
|
properties: {
|
|
count: { type: "integer", minimum: "1" },
|
|
},
|
|
},
|
|
},
|
|
},
|
|
])
|
|
);
|
|
|
|
assert.equal(tools[0].function.description, "5");
|
|
assert.equal(tools[0].function.parameters.properties.count.minimum, 1);
|
|
});
|
|
|
|
test("translateRequest sanitizes tools before Claude output", () => {
|
|
const translated = translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.CLAUDE,
|
|
"claude-sonnet-4-6",
|
|
{
|
|
messages: [{ role: "user", content: "hello" }],
|
|
tools: [
|
|
{
|
|
type: "function",
|
|
function: {
|
|
name: "sum",
|
|
description: null,
|
|
parameters: {
|
|
type: "object",
|
|
properties: {
|
|
count: { type: "integer", minimum: "1", maximum: "9" },
|
|
},
|
|
},
|
|
},
|
|
},
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
"claude"
|
|
);
|
|
|
|
assert.equal(translated.tools[0].description, "");
|
|
assert.equal(translated.tools[0].input_schema.properties.count.minimum, 1);
|
|
assert.equal(translated.tools[0].input_schema.properties.count.maximum, 9);
|
|
});
|
|
|
|
test("translateRequest sanitizes OpenAI tool payloads on passthrough", () => {
|
|
const translated = translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI,
|
|
"gpt-5.2",
|
|
{
|
|
messages: [{ role: "user", content: "hello" }],
|
|
tools: [
|
|
{
|
|
type: "function",
|
|
function: {
|
|
name: "sum",
|
|
description: 7,
|
|
parameters: {
|
|
type: "object",
|
|
properties: {
|
|
count: { type: "integer", minimum: "2" },
|
|
},
|
|
},
|
|
},
|
|
},
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
"openai"
|
|
);
|
|
|
|
assert.equal(translated.tools[0].function.description, "7");
|
|
assert.equal(translated.tools[0].function.parameters.properties.count.minimum, 2);
|
|
});
|
|
|
|
test("tool sanitization: injects empty reasoning_content only for DeepSeek tool-call history", () => {
|
|
const messages = [
|
|
{ role: "user", content: "hello" },
|
|
{
|
|
role: "assistant",
|
|
tool_calls: [{ id: "call_1", type: "function", function: { name: "sum", arguments: "{}" } }],
|
|
},
|
|
];
|
|
|
|
const deepseekMessages = injectEmptyReasoningContentForToolCalls(
|
|
messages,
|
|
"deepseek",
|
|
"deepseek-v4-flash"
|
|
);
|
|
const openaiMessages = injectEmptyReasoningContentForToolCalls(messages, "openai", "gpt-4o");
|
|
|
|
assert.equal(deepseekMessages[1].reasoning_content, "");
|
|
assert.equal(openaiMessages[1].reasoning_content, undefined);
|
|
});
|
|
|
|
test("translateRequest omits reasoning_content for DeepSeek assistant tool calls on cache miss", () => {
|
|
clearModelsDevCapabilities();
|
|
saveModelsDevCapabilities({
|
|
deepseek: {
|
|
"deepseek-v4-flash": buildCapability({
|
|
interleaved_field: "reasoning_content",
|
|
reasoning: true,
|
|
tool_call: true,
|
|
}),
|
|
},
|
|
});
|
|
|
|
const translated = translateRequest(
|
|
FORMATS.OPENAI,
|
|
FORMATS.OPENAI,
|
|
"deepseek-v4-flash",
|
|
{
|
|
messages: [
|
|
{ role: "user", content: "hello" },
|
|
{
|
|
role: "assistant",
|
|
tool_calls: [
|
|
{ id: "call_1", type: "function", function: { name: "sum", arguments: "{}" } },
|
|
],
|
|
},
|
|
{ role: "tool", tool_call_id: "call_1", content: "3" },
|
|
],
|
|
},
|
|
false,
|
|
null,
|
|
"deepseek"
|
|
);
|
|
|
|
// #9573/#9610: the former NON_ANTHROPIC_THINKING_PLACEHOLDER injection was the root
|
|
// cause of the echo → empty-stop bug (the model continued its chain of thought from
|
|
// the placeholder and re-poisoned cache + history). On a cache miss the field is now
|
|
// omitted; DeepSeek's 400 is specific to an empty string, not an absent field.
|
|
assert.equal(translated.messages[1].reasoning_content, undefined);
|
|
clearModelsDevCapabilities();
|
|
});
|