mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
* chore(release): open v3.8.34 development cycle * chore(quality): release-green pre-flight validator + nightly signal (C+D) (#4622) C — scripts/quality/validate-release-green.mjs (npm run check:release-green): reproduces the release-equivalent validation (typecheck, eslint, db-rules, public-creds, full unit, vitest, ratchets, optional --with-build package-artifact) against the current working tree and classifies each red as HARD (real defect, exit 1) vs DRIFT (ratchet — reported, never affects exit / never blocks). Pure helpers exported + orchestration behind a direct-run guard; unit-tested. D — .github/workflows/nightly-release-green.yml: runs C on the active release branch nightly (and on workflow_dispatch) and opens/updates a single tracking issue on HARD failures. Never a required check, never touches a contributor PR. Closes the gap where the full gate (ci.yml) only ran on the release PR, so reds accrued silently on release/** and surfaced in 40-min layers at release time. Non-blocking by construction; drift is the maintainer's to rebaseline at release. Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> * fix(providers): show revealed connection API keys (#4583) Integrated into release/v3.8.34 * fix(resilience): respect upstream retry hint toggle (#4585) Integrated into release/v3.8.34 * feat(settings): expose stream recovery feature flags (#4586) Integrated into release/v3.8.34 * fix(logs): make active request stale sweep configurable (#4599) Integrated into release/v3.8.34 * fix(plugin): auto-prefix providerId with 'opencode-' for OC 1.17.8+ native gate (#4527) Integrated into release/v3.8.34 (supersedes #4445) * fix(models): treat unknown output caps as unset (#4584) Integrated into release/v3.8.34 * fix(executors): strip temperature for GitHub Copilot gpt-5.4 family (#4564) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(oauth): update Qwen OAuth URLs from chat.qwen.ai to qwen.ai (#4561) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(api/settings): prevent cached /api/settings responses (port from 9router#951) (#4566) Integrated into release/v3.8.34 (rebuilt onto tip) * feat(audio): MiniMax T2A v2 TTS dispatch in audioSpeech (port #1043) (#4553) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(dashboard): surface manual config CTA when Open Claw CLI auto-detect fails (#4562) Integrated into release/v3.8.34 (rebuilt onto tip) * feat(providers): optional model ID for custom API-key validation (#4555) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(cli): align data dir and env loading with runtime (#4607) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(quota): expose Bailian quota windows (#4610) Integrated into release/v3.8.34 (rebuilt onto tip) * fix: retain provider cooldowns for configured max window (#4588) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix: reject invalid provider cooldown bounds (#4589) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix: preserve production combo metrics on shadow eviction (#4590) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix(stream): estimate input tokens when upstream reports prompt_tokens=0 (#4615) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(catalog): shorten no-thinking gateway prefix to no-think/ (#4525) Integrated into release/v3.8.34 (rebuilt — kept only the prefix rename, dropped stale-base reverts) * fix(relay): apply IP rate limit to bifrost sidecar (#4593) Integrated into release/v3.8.34 (rebuilt onto tip; merge before #4612) * fix(bifrost): finalize SSE relay usage after stream (#4612) Integrated into release/v3.8.34 (rebuilt + reconciled with #4593) * feat(compression): per-request `x-omniroute-compression` header (Phase 3) (#4645) * docs(compression): Phase 3 per-request header design spec Approved brainstorming output for the x-omniroute-compression header: header-first precedence, name-first combo matching (Decision A), explicit value bypasses auto-trigger (Decision B), DerivedPlan.source, and the X-OmniRoute-Compression response header. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(compression): Phase 3 per-request header implementation plan 4-task TDD plan (resolver header-first + source, parser, chatCore wiring + response header, docs/file-size) with full code and exact commands. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): header-first resolver + plan source (Phase 3 core) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): resolveCompressionHeader parser (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): wire x-omniroute-compression header + response header (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(compression): extract plan-resolution leaf (planResolution.ts) under size cap (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(compression): document x-omniroute-compression header (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(compression): harden named-combo map + trim engine: header id (Phase 3 review) Addresses gemini-code-assist review on #4645: - Extract buildNamedComboLookup (pure) so a blank/whitespace/null combo name contributes only its id key (no '' key, no throw that disables all combos). - Trim the engine:<id> header value so 'engine: rtk' resolves. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix: exclude exhausted connections from auto scoring (#4592) Integrated into release/v3.8.34 (rebuilt + opt-in gate fix) * fix(dashboard): memoize compatible provider groups (#4613) Integrated into release/v3.8.34 (rebuilt + test added) * fix(dashboard): isolate quota widget refresh clock (#4611) Integrated into release/v3.8.34 (rebuilt + jsdom test) * fix(dashboard): gate topology side effects behind widget visibility (#4606) Integrated into release/v3.8.34 (rebuilt + jsdom test) * fix(dashboard): keep play_arrow spinning on provider Test All buttons (#4563) Integrated into release/v3.8.34 (rebuilt onto tip; UI-cosmetic per owner) * fix(db): schedule retention cleanup + fix cleanup table/column names (extracted from #4428) (#4691) Integrated into release/v3.8.34 (cleanup core extracted from #4428, credit @oyi77) * fix(telemetry): back off live-WS event forwarding when the sidecar is unreachable (#4604) (#4687) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(api): serve GET /v1/models/{model} as JSON, not the HTML dashboard (#4674) (#4677) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(opencode): add go deepseek reasoning variants (#4647) Integrated into release/v3.8.34 * fix(executors): robust deepseek-web tool-call parsing and agentic context retention (#4644) Integrated into release/v3.8.34 * fix(cli): authenticate `omniroute logs` and honor active context (#4638) Integrated into release/v3.8.34 (authored by Rahul Sharma, AI co-author trailer stripped per project policy) * fix(proxy): apply pipelining:0 + connections cap to the direct dispatcher (#4580) (#4684) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(executors): Firecrawl web_fetch 500 with include_metadata=true (#4692) Integrated into release/v3.8.34 * fix(routing): include all noAuth models in auto-combos + add reka-flash + best-free template (#4621) Integrated into release/v3.8.34 (dead getFirstRegistryModelId dropped, rebuilt onto tip) * fix(dashboard): gate home topology live-WS networking (#4596) (#4618) Integrated into release/v3.8.34 (adapted onto #4606's extracted topology section: default-hidden flip + enabled gate on useLiveDashboard) * fix(cli): align `omniroute` env loading with the runtime data dir (#4597) (#4619) Integrated into release/v3.8.34 (data-dir.mjs refactor reconciled with #4607; loadEnvFile aligned to getDefaultDataDir) * chore(quality): reconcile file-size baseline for #4644 (deepseek-web.ts 1117->1125) (#4695) file-size reconcile for #4644 * Support quota scraping for OpenCode Go and Ollama Cloud (#4642) Integrated into release/v3.8.34 (Ollama Cloud + OpenCode Go dashboard quota scraping; rebuilt onto tip, gates green: typecheck/public-creds/file-size/lint/docs-sync + 31 tests) * feat(executors): land M365 Copilot pure framing + connection helpers (#4042) (#4696) Land M365 pure modules ahead of draft #4400 * deps: bump production + development groups; migrate js-yaml to v5 ESM (#4697) Incorporates Dependabot #4667 + #4668 + js-yaml v5 ESM migration into release/v3.8.34 * fix: noAuth provider validation + kimi executor routing (#4699) Integrated into release/v3.8.34 (noAuth in NOAUTH_PROVIDERS dynamic check + remove misrouted kimi web alias; 9 tests) * refactor(imageGeneration): extract 8 provider families to co-located files (#4609) Integrated into release/v3.8.34 (extraction completed: added missing imports/exports per module, main imports handlers locally; 145 image-gen tests pass, typecheck/cycles/file-size green) * chore(release): v3.8.34 — finalize changelog, rebaseline drift, fix release-green reds - Finalize CHANGELOG [3.8.34] (43 bullets, full contributor attribution) + seed i18n mirrors - Rebaseline inherited cycle drift surfaced by release-green pre-flight: eslint warnings 3900->3907, cognitive-complexity 797->801 (release-finalize touches no prod code; all drift is from this cycle's contributor merges) - fix(providers): keep reka-flash-3 as the Reka provider default. #4621 inserted reka-flash at the head of the model list, silently changing the default from reka-flash-3 (the free-tier model) to reka-flash; reorder so reka-flash-3 stays default, reka-flash retained. - test: align provider-models-config / provider-models-route / web-cookie-providers-new with #4621 (reka-flash now in the Reka catalog) and #4699 (the `kimi` API-key provider correctly falls through to DefaultExecutor instead of KimiWebExecutor) - chore(quality): allowlist the COMPRESSION_GUIDE doc name in check-fabricated-docs (false-positive env-var match; docs/compression/COMPRESSION_GUIDE.md exists) * fix(release-green): resolve release-PR full-CI reds for v3.8.34 Surfaced only on the release PR (these gates don't run on PR->release fast-gates): - fix(quota): complete HTML-comment sanitization in opencodeOllamaUsage SSR reset-time parsing — strip any <!--...--> generically instead of the two literal React hydration markers, so no partial "<!--" can survive (CodeQL js/incomplete-multi-character- sanitization, HIGH, introduced by #4642). Regression test added. - test(codex): correct the Codex-fingerprint body key order assertion to match the canonical bodyFieldOrder (prompt_cache_key precedes include); #4584 flipped the two and integration tests don't run on fast-gates so it never executed until the release PR. - chore(quality): rebaseline inherited cycle drift surfaced by full CI — zizmorFindings 152->155 (+3 unpinned-uses in nightly-release-green.yml from #4622, same @vN convention as ci.yml) and openapiCoverage.pct 38.4->37.8 (-0.6, contributor routes added faster than openapi docs). Release-finalize touches no prod routes. * fix(release-green): complete CodeQL sanitization + rebaseline complexity drift - fix(quota): handle unterminated HTML comments in opencodeOllamaUsage SSR reset-time parsing — the `(?:-->|$)` arm consumes a trailing "<!--" with no closing "-->", so no partial "<!--" can survive (CodeQL js/incomplete-multi-character-sanitization persisted with the plain <!--...--> form because an unclosed comment could still leave "<!--"). - chore(quality): rebaseline cyclomatic complexity 1915->1916 (+1) — inherited v3.8.34 cycle drift (contributor feature branches); check:complexity does not run on PR->release fast-gates so it surfaced only on the release PR. Release-finalize adds 0 complexity (measured 1916 with/without the regex tweak). dead-code/cognitive/type-coverage/ compression-budget/codeql ratchets all pass. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com> Co-authored-by: Abhishek Divekar <adivekar@utexas.edu> Co-authored-by: Rahul sharma <sharmaR0810@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> Co-authored-by: Ronald Estacion <DevEstacion@users.noreply.github.com> Co-authored-by: Igor <60442260+BugsBag@users.noreply.github.com> Co-authored-by: Oonishi <275808243+ponkcore@users.noreply.github.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Jan Leon <Jan.gaschler@gmail.com>
314 lines
9.9 KiB
TypeScript
314 lines
9.9 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
const { claudeToGeminiRequest } =
|
|
await import("../../open-sse/translator/request/claude-to-gemini.ts");
|
|
const { DEFAULT_SAFETY_SETTINGS } =
|
|
await import("../../open-sse/translator/helpers/geminiHelper.ts");
|
|
|
|
type UnknownRecord = Record<string, unknown>;
|
|
|
|
function getFunctionDeclarationParameters(parameters: unknown) {
|
|
assert.ok(
|
|
parameters && typeof parameters === "object",
|
|
"expected function declaration parameters"
|
|
);
|
|
return parameters as UnknownRecord & {
|
|
properties?: Record<string, UnknownRecord>;
|
|
examples?: unknown;
|
|
};
|
|
}
|
|
|
|
function getFunctionCall(part: unknown) {
|
|
assert.ok(part && typeof part === "object", "expected Gemini part");
|
|
const functionCall = (part as UnknownRecord).functionCall;
|
|
assert.ok(functionCall && typeof functionCall === "object", "expected functionCall");
|
|
return functionCall as { name: string };
|
|
}
|
|
|
|
function getFunctionResponse(part: unknown) {
|
|
assert.ok(part && typeof part === "object", "expected Gemini part");
|
|
const functionResponse = (part as UnknownRecord).functionResponse;
|
|
assert.ok(functionResponse && typeof functionResponse === "object", "expected functionResponse");
|
|
return functionResponse as { name: string };
|
|
}
|
|
|
|
test("Claude -> Gemini maps system, thinking, tool use, tool result and tools", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
system: [{ text: "Rules" }],
|
|
messages: [
|
|
{
|
|
role: "assistant",
|
|
content: [
|
|
{ type: "thinking", thinking: "need tool" },
|
|
{ type: "tool_use", id: "tu_1", name: "weather", input: { city: "Tokyo" } },
|
|
],
|
|
},
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "tool_result",
|
|
tool_use_id: "tu_1",
|
|
content: [{ type: "text", text: "20C" }],
|
|
},
|
|
],
|
|
},
|
|
],
|
|
tools: [
|
|
{
|
|
name: "weather",
|
|
description: "Get weather",
|
|
input_schema: {
|
|
type: "object",
|
|
properties: { city: { type: ["string", "null"] } },
|
|
},
|
|
},
|
|
],
|
|
max_tokens: 256,
|
|
temperature: 0.4,
|
|
top_p: 0.8,
|
|
thinking: { type: "enabled", budget_tokens: 512 },
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.deepEqual(result.systemInstruction, {
|
|
role: "system",
|
|
parts: [{ text: "Rules" }],
|
|
});
|
|
assert.equal(result.contents[0].role, "model");
|
|
assert.deepEqual(result.contents[0].parts[0] as any, { thought: true, text: "need tool" });
|
|
assert.deepEqual(result.contents[0].parts[1] as any, {
|
|
functionCall: { id: "tu_1", name: "weather", args: { city: "Tokyo" } },
|
|
});
|
|
assert.deepEqual(result.contents[1].parts[0] as any, {
|
|
functionResponse: {
|
|
id: "tu_1",
|
|
name: "weather",
|
|
response: { result: { result: "20C" } },
|
|
},
|
|
});
|
|
assert.equal(result.generationConfig.maxOutputTokens, 256);
|
|
assert.match((result as any).tools[0].functionDeclarations[0].name, /^[a-zA-Z0-9_]+$/);
|
|
assert.equal(result.generationConfig.temperature, 0.4);
|
|
assert.equal(result.generationConfig.topP, 0.8);
|
|
assert.deepEqual(result.generationConfig.thinkingConfig, {
|
|
thinkingBudget: 512,
|
|
includeThoughts: true,
|
|
});
|
|
assert.deepEqual(result.safetySettings, DEFAULT_SAFETY_SETTINGS);
|
|
assert.deepEqual((result as any).tools[0].functionDeclarations[0].parameters, {
|
|
type: "object",
|
|
properties: { city: { type: "string" } },
|
|
});
|
|
});
|
|
|
|
test("Claude -> Gemini clamps maxOutputTokens to the model cap", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-flash",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "Hello" }] }],
|
|
max_tokens: 999999,
|
|
},
|
|
false
|
|
);
|
|
|
|
// #3358 added the gemini-2.5-flash model spec (real cap 65536, not the old
|
|
// 8192 default). An over-cap request clamps to the model's true max output.
|
|
assert.equal(result.generationConfig.maxOutputTokens, 65536);
|
|
});
|
|
|
|
test("Claude -> Gemini preserves requested maxOutputTokens when the model cap is unknown", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "Hello" }] }],
|
|
max_tokens: 32000,
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.equal(result.generationConfig.maxOutputTokens, 32000);
|
|
});
|
|
|
|
test("Claude -> Gemini converts text and base64 images to Gemini parts", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-flash",
|
|
{
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "Hello" },
|
|
{
|
|
type: "image",
|
|
source: { type: "base64", media_type: "image/png", data: "abc" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.deepEqual(result.contents, [
|
|
{
|
|
role: "user",
|
|
parts: [{ text: "Hello" }, { inlineData: { mimeType: "image/png", data: "abc" } }],
|
|
},
|
|
]);
|
|
});
|
|
|
|
test("Claude -> Gemini injects a fallback thoughtSignature on tool-call batches without thinking", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-flash",
|
|
{
|
|
messages: [
|
|
{
|
|
role: "assistant",
|
|
content: [{ type: "tool_use", id: "tu_1", name: "read_file", input: {} }],
|
|
},
|
|
],
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.equal(result.contents.length, 1);
|
|
assert.equal(result.contents[0].role, "model");
|
|
assert.equal((result.contents[0].parts[0] as any).functionCall.name, "read_file");
|
|
assert.equal((result.contents[0].parts[0] as any).thoughtSignature, undefined);
|
|
});
|
|
|
|
test("Claude -> Gemini sanitizes long tool names and exposes a restore map", () => {
|
|
const longToolName =
|
|
"mcp__filesystem__read_multiple_files_with_validation_and_metadata_bundle_v2";
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
messages: [
|
|
{
|
|
role: "assistant",
|
|
content: [
|
|
{ type: "tool_use", id: "tu_long_1", name: longToolName, input: { path: "/tmp/a" } },
|
|
],
|
|
},
|
|
{
|
|
role: "user",
|
|
content: [{ type: "tool_result", tool_use_id: "tu_long_1", content: "ok" }],
|
|
},
|
|
],
|
|
tools: [
|
|
{
|
|
name: longToolName,
|
|
description: "Read files",
|
|
input_schema: {
|
|
type: "object",
|
|
properties: {
|
|
path: { type: "string", "x-ui": "hidden" },
|
|
},
|
|
examples: [{ path: "/tmp/a" }],
|
|
},
|
|
},
|
|
],
|
|
},
|
|
false
|
|
);
|
|
|
|
const sanitizedToolName = (result as any).tools[0].functionDeclarations[0].name as string;
|
|
const parameters = getFunctionDeclarationParameters(
|
|
(result as any).tools[0].functionDeclarations[0].parameters
|
|
);
|
|
assert.ok(longToolName.length > 64);
|
|
assert.equal(sanitizedToolName.length, 64);
|
|
assert.equal((result as any)._toolNameMap.get(sanitizedToolName), longToolName);
|
|
assert.equal(getFunctionCall(result.contents[0].parts[0] as any).name, sanitizedToolName);
|
|
assert.equal(getFunctionResponse(result.contents[1].parts[0] as any).name, sanitizedToolName);
|
|
assert.equal(parameters.examples, undefined);
|
|
assert.equal(parameters.properties?.path?.["x-ui"], undefined);
|
|
});
|
|
|
|
test("Claude -> Gemini handles empty bodies without producing invalid content", () => {
|
|
const result = claudeToGeminiRequest("gemini-2.5-flash", {}, false);
|
|
|
|
assert.deepEqual(result.contents, []);
|
|
assert.deepEqual(result.generationConfig, {});
|
|
assert.deepEqual(result.safetySettings, DEFAULT_SAFETY_SETTINGS);
|
|
});
|
|
|
|
test("Claude -> Gemini maps output_config.effort to thinkingConfig when thinking absent", () => {
|
|
const cases: Array<{ effort: string; expected: number }> = [
|
|
{ effort: "low", expected: 1024 },
|
|
{ effort: "medium", expected: 10240 },
|
|
{ effort: "high", expected: 32768 },
|
|
{ effort: "max", expected: 131072 },
|
|
{ effort: "xhigh", expected: 131072 },
|
|
];
|
|
|
|
for (const { effort, expected } of cases) {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "hi" }] }],
|
|
output_config: { effort },
|
|
},
|
|
false
|
|
);
|
|
assert.deepEqual(
|
|
result.generationConfig.thinkingConfig,
|
|
{ thinkingBudget: expected, includeThoughts: true },
|
|
`effort ${effort} should map to budget ${expected}`
|
|
);
|
|
}
|
|
});
|
|
|
|
// Regression for #3842: output_config.effort=high must be clamped to a Flash-tier
|
|
// Gemini model's real thinking-budget cap. gemini-2.5-flash's true max is 24576;
|
|
// the previous unclamped 32768 made the upstream return HTTP 400. Pro-tier
|
|
// (gemini-2.5-pro, real cap 32768) is asserted untouched by the test above.
|
|
test("Claude -> Gemini clamps output_config.effort=high to gemini-2.5-flash cap (#3842)", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-flash",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "hi" }] }],
|
|
output_config: { effort: "high" },
|
|
},
|
|
false
|
|
);
|
|
const budget = (result.generationConfig as any).thinkingConfig.thinkingBudget;
|
|
assert.ok(budget <= 24576, `expected <= 24576 (real cap), got ${budget}`);
|
|
assert.equal(budget, 24576);
|
|
});
|
|
|
|
test("Claude -> Gemini prefers thinking.budget_tokens over output_config.effort", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "hi" }] }],
|
|
thinking: { type: "enabled", budget_tokens: 4096 },
|
|
output_config: { effort: "high" },
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.deepEqual(result.generationConfig.thinkingConfig, {
|
|
thinkingBudget: 4096,
|
|
includeThoughts: true,
|
|
});
|
|
});
|
|
|
|
test("Claude -> Gemini skips thinkingConfig for output_config.effort=none", () => {
|
|
const result = claudeToGeminiRequest(
|
|
"gemini-2.5-pro",
|
|
{
|
|
messages: [{ role: "user", content: [{ type: "text", text: "hi" }] }],
|
|
output_config: { effort: "none" },
|
|
},
|
|
false
|
|
);
|
|
|
|
assert.equal((result.generationConfig as any).thinkingConfig, undefined);
|
|
});
|