mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-05 14:52:09 +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>
521 lines
19 KiB
TypeScript
521 lines
19 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
const { sanitizeReasoningEffortForProvider } = await import("../../open-sse/executors/base.ts");
|
|
|
|
function makeLog() {
|
|
const messages: Array<[string, string]> = [];
|
|
return {
|
|
info: (tag: string, msg: string) => messages.push([tag, msg]),
|
|
messages,
|
|
};
|
|
}
|
|
|
|
test("sanitizeReasoningEffortForProvider: xiaomi-mimo preserves xhigh by default", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "mimo-v2.5-pro",
|
|
reasoning_effort: "xhigh",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "xiaomi-mimo", "mimo-v2.5-pro", log);
|
|
assert.equal(result, body, "xhigh passes through unless the model explicitly opts out");
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
assert.equal((result as any).model, "mimo-v2.5-pro", "other fields preserved");
|
|
assert.equal(log.messages.length, 0);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: OpenRouter DeepSeek preserves xhigh", () => {
|
|
const body = {
|
|
model: "deepseek/deepseek-v4-pro",
|
|
reasoning_effort: "xhigh",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openrouter",
|
|
"deepseek/deepseek-v4-pro",
|
|
null
|
|
);
|
|
assert.equal(result, body);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: explicit xhigh opt-out downgrades to high", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "claude-opus-4-6",
|
|
reasoning_effort: "xhigh",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "claude", "claude-opus-4-6", log);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /xhigh → high/.test(m)),
|
|
"logs the downgrade"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: Anthropic-compatible dynamic provider honors xhigh opt-out", () => {
|
|
const body = {
|
|
model: "claude-opus-4-6",
|
|
reasoning_effort: "xhigh",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"anthropic-compatible-test",
|
|
"claude-opus-4-6",
|
|
null
|
|
);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: xiaomi-mimo normalizes max → xhigh by default", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "mimo-v2.5-pro",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "xiaomi-mimo", "mimo-v2.5-pro", log);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /max → xhigh/.test(m)),
|
|
"logs the normalization"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: OpenRouter DeepSeek normalizes max → xhigh", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "deepseek/deepseek-v4-pro",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openrouter",
|
|
"deepseek/deepseek-v4-pro",
|
|
log
|
|
);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /max → xhigh/.test(m)),
|
|
"logs the normalization"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: OpenRouter Claude opt-out aliases downgrade max → high", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "anthropic/claude-opus-4.6",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openrouter",
|
|
"anthropic/claude-opus-4.6",
|
|
log
|
|
);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /max → high/.test(m)),
|
|
"logs the downgrade"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: OpenAI-compatible Gemini normalizes max → xhigh", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "gemini-3.1-pro-preview",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openai-compatible-free1",
|
|
"gemini-3.1-pro-preview",
|
|
log
|
|
);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /max → xhigh/.test(m)),
|
|
"logs the normalization"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: nested OpenAI reasoning max normalizes to xhigh", () => {
|
|
const body = {
|
|
model: "gemini-3.1-pro-preview",
|
|
reasoning: { effort: "max", summary: "auto" },
|
|
input: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openai-compatible-free1",
|
|
"gemini-3.1-pro-preview",
|
|
null
|
|
);
|
|
assert.equal((result as any).reasoning.effort, "xhigh");
|
|
assert.equal((result as any).reasoning.summary, "auto", "other reasoning fields preserved");
|
|
assert.equal((result as any).reasoning_effort, undefined);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: claude preserves max for Opus/Sonnet and downgrades Haiku", () => {
|
|
const sonnetBody = {
|
|
model: "claude-sonnet-4-6",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const sonnetResult = sanitizeReasoningEffortForProvider(
|
|
sonnetBody,
|
|
"claude",
|
|
"claude-sonnet-4-6",
|
|
null
|
|
);
|
|
assert.equal(sonnetResult, sonnetBody);
|
|
assert.equal((sonnetResult as any).reasoning_effort, "max");
|
|
|
|
const opusBody = {
|
|
model: "claude-opus-4-6",
|
|
reasoning: { effort: "max", summary: "auto" },
|
|
input: [],
|
|
};
|
|
const opusResult = sanitizeReasoningEffortForProvider(
|
|
opusBody,
|
|
"anthropic-compatible-cc-test",
|
|
"claude-opus-4-6",
|
|
null
|
|
);
|
|
assert.equal(opusResult, opusBody);
|
|
assert.equal((opusResult as any).reasoning.effort, "max");
|
|
|
|
const haikuBody = {
|
|
model: "claude-haiku-4-5-20251001",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const haikuResult = sanitizeReasoningEffortForProvider(
|
|
haikuBody,
|
|
"claude",
|
|
"claude-haiku-4-5-20251001",
|
|
null
|
|
);
|
|
assert.notEqual(haikuResult, haikuBody);
|
|
assert.equal((haikuResult as any).reasoning_effort, "high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: xiaomi-mimo preserves nested xhigh by default", () => {
|
|
const body = {
|
|
model: "mimo-v2.5-pro",
|
|
reasoning: { effort: "xhigh", summary: "auto" },
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "xiaomi-mimo", "mimo-v2.5-pro", null);
|
|
assert.equal(result, body);
|
|
assert.equal((result as any).reasoning.effort, "xhigh");
|
|
assert.equal((result as any).reasoning.summary, "auto", "other reasoning fields preserved");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: explicit xhigh opt-out preserves Responses shape", () => {
|
|
const body = {
|
|
model: "claude-opus-4-6",
|
|
reasoning: { effort: "xhigh", summary: "auto" },
|
|
input: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "claude", "claude-opus-4-6", null);
|
|
assert.equal((result as any).reasoning.effort, "high");
|
|
assert.equal((result as any).reasoning_effort, undefined);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: mistral/devstral strips reasoning_effort entirely", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "devstral-2512",
|
|
reasoning_effort: "medium",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "mistral", "devstral-2512", log);
|
|
assert.equal((result as any).reasoning_effort, undefined, "reasoning_effort must be stripped");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /removed/.test(m)),
|
|
"logs the removal"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: github/claude-opus-4.6 preserves reasoning_effort (#791)", () => {
|
|
// Upstream PR decolua/9router#791 (port): Copilot now honors reasoning_effort
|
|
// on Claude Opus 4.6 and Sonnet 4.6. Older Opus variants and Haiku still strip.
|
|
const body = {
|
|
model: "claude-opus-4-6",
|
|
reasoning_effort: "high",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "github", "claude-opus-4-6", null);
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: github/claude-opus-4.7 still strips (#791)", () => {
|
|
const body = {
|
|
model: "claude-opus-4.7",
|
|
reasoning_effort: "high",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "github", "claude-opus-4.7", null);
|
|
assert.equal((result as any).reasoning_effort, undefined);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: rejecting providers strip max before normalization", () => {
|
|
const mistralBody = {
|
|
model: "devstral-2512",
|
|
reasoning_effort: "max",
|
|
messages: [],
|
|
};
|
|
const mistralResult = sanitizeReasoningEffortForProvider(
|
|
mistralBody,
|
|
"mistral",
|
|
"devstral-2512",
|
|
null
|
|
);
|
|
assert.equal((mistralResult as any).reasoning_effort, undefined);
|
|
|
|
// Pre-#791: github stripped reasoning_effort entirely for every Claude model.
|
|
// Post-#791: Opus 4.6 keeps reasoning_effort; `max` downgrades to `high`
|
|
// because github is not Claude/CC-compatible (so supportsMax=false) and
|
|
// the canonical Claude Opus 4.6 model opts out of xhigh.
|
|
const githubBody = {
|
|
model: "claude-opus-4-6",
|
|
reasoning_effort: "max",
|
|
messages: [],
|
|
};
|
|
const githubResult = sanitizeReasoningEffortForProvider(
|
|
githubBody,
|
|
"github",
|
|
"claude-opus-4-6",
|
|
null
|
|
);
|
|
assert.equal((githubResult as any).reasoning_effort, "high");
|
|
|
|
// Pre-#791 strip is preserved for github Claude models that DO NOT opt in
|
|
// (Haiku 4.5, Opus 4.7, older Sonnet, etc.).
|
|
const githubHaiku = {
|
|
model: "claude-haiku-4.5",
|
|
reasoning_effort: "max",
|
|
messages: [],
|
|
};
|
|
const githubHaikuResult = sanitizeReasoningEffortForProvider(
|
|
githubHaiku,
|
|
"github",
|
|
"claude-haiku-4.5",
|
|
null
|
|
);
|
|
assert.equal((githubHaikuResult as any).reasoning_effort, undefined);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: mistral/devstral strips reasoning object when only effort present", () => {
|
|
const body = {
|
|
model: "devstral-2512",
|
|
reasoning: { effort: "medium" },
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "mistral", "devstral-2512", null);
|
|
assert.equal((result as any).reasoning, undefined, "reasoning object dropped when emptied");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: mistral/devstral preserves reasoning when other fields remain", () => {
|
|
const body = {
|
|
model: "devstral-2512",
|
|
reasoning: { effort: "medium", summary: "auto" },
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "mistral", "devstral-2512", null);
|
|
assert.deepEqual((result as any).reasoning, { summary: "auto" });
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: codex with xhigh passes through unchanged", () => {
|
|
const body = {
|
|
model: "gpt-5.5-xhigh",
|
|
reasoning_effort: "xhigh",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "codex", "gpt-5.5-xhigh", null);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: no-op when reasoning_effort absent", () => {
|
|
const body = { model: "mimo-v2.5-pro", messages: [] };
|
|
const result = sanitizeReasoningEffortForProvider(body, "xiaomi-mimo", "mimo-v2.5-pro", null);
|
|
assert.equal(result, body, "returns original body unchanged");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: handles unknown providers as pass-through", () => {
|
|
const body = { model: "some-model", reasoning_effort: "xhigh", messages: [] };
|
|
const result = sanitizeReasoningEffortForProvider(body, "unknown-provider", "some-model", null);
|
|
assert.equal(result, body);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: non-object body returns unchanged", () => {
|
|
assert.equal(sanitizeReasoningEffortForProvider(null, "xiaomi-mimo", "x", null), null);
|
|
assert.equal(sanitizeReasoningEffortForProvider("string", "xiaomi-mimo", "x", null), "string");
|
|
const arr: unknown[] = [];
|
|
assert.equal(sanitizeReasoningEffortForProvider(arr, "xiaomi-mimo", "x", null), arr);
|
|
});
|
|
|
|
// ── Native DeepSeek (api.deepseek.com) ───────────────────────────────────────
|
|
// DeepSeek V4 thinking mode accepts reasoning_effort ONLY as {high, max}. The
|
|
// internal OmniRoute scale (low|medium|high|xhigh, xhigh = top) must be mapped
|
|
// onto DeepSeek's native vocabulary so the client's requested effort is honored
|
|
// instead of silently dropped to the default. This is the INVERSE of the
|
|
// OpenRouter-DeepSeek path, whose normalized API expects xhigh, not max.
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek maps xhigh → max", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning_effort: "xhigh",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-pro", log);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "max");
|
|
assert.equal((result as any).model, "deepseek-v4-pro", "other fields preserved");
|
|
assert.ok(
|
|
log.messages.some(([tag, m]) => tag === "REASONING_SANITIZE" && /xhigh → max/.test(m)),
|
|
"logs the xhigh → max mapping"
|
|
);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek preserves max", () => {
|
|
const log = makeLog();
|
|
const body = {
|
|
model: "deepseek-v4-flash",
|
|
reasoning_effort: "max",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-flash", log);
|
|
assert.equal(result, body, "max is DeepSeek's native top tier — passes through unchanged");
|
|
assert.equal((result as any).reasoning_effort, "max");
|
|
assert.equal(log.messages.length, 0);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek clamps low → high", () => {
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning_effort: "low",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-pro", null);
|
|
assert.notEqual(result, body, "must return a new object when mutating");
|
|
assert.equal((result as any).reasoning_effort, "high", "below the {high, max} floor → high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek clamps medium → high", () => {
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning_effort: "medium",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-pro", null);
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek preserves high unchanged", () => {
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning_effort: "high",
|
|
messages: [{ role: "user", content: "hi" }],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-pro", null);
|
|
assert.equal(result, body, "high is already valid — passes through unchanged");
|
|
assert.equal((result as any).reasoning_effort, "high");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: native deepseek maps nested reasoning.effort xhigh → max", () => {
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning: { effort: "xhigh", summary: "auto" },
|
|
input: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "deepseek", "deepseek-v4-pro", null);
|
|
assert.equal((result as any).reasoning.effort, "max");
|
|
assert.equal((result as any).reasoning.summary, "auto", "other reasoning fields preserved");
|
|
assert.equal((result as any).reasoning_effort, undefined);
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: OpenRouter DeepSeek still preserves xhigh (not native)", () => {
|
|
// Regression guard: the native-deepseek mapping must NOT touch openrouter,
|
|
// whose normalized API expects xhigh (issue earendil-works/pi#4055).
|
|
const body = {
|
|
model: "deepseek/deepseek-v4-pro",
|
|
reasoning_effort: "xhigh",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"openrouter",
|
|
"deepseek/deepseek-v4-pro",
|
|
null
|
|
);
|
|
assert.equal(result, body);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
});
|
|
|
|
// ── opencode-go DeepSeek V4 Pro effort variants (#4647) ──────────────────────
|
|
// opencode-go proxies DeepSeek with the native DeepSeek API contract, which
|
|
// accepts {high, max} literally. The OpencodeExecutor's transformRequest sets
|
|
// reasoning_effort to the variant suffix (low|medium|high|max), and the
|
|
// sanitizer must NOT rewrite `max` → `xhigh` for this provider+model combo.
|
|
|
|
test("sanitizeReasoningEffortForProvider: opencode-go DeepSeek V4 Pro preserves max", () => {
|
|
const body = {
|
|
model: "deepseek-v4-pro",
|
|
reasoning_effort: "max",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "opencode-go", "deepseek-v4-pro", null);
|
|
assert.equal(result, body, "opencode-go DeepSeek max must pass through unchanged");
|
|
assert.equal((result as any).reasoning_effort, "max");
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: opencode-go DeepSeek V4 Pro preserves variant suffix levels", () => {
|
|
for (const level of ["low", "medium", "high", "max"]) {
|
|
const body = {
|
|
model: `deepseek-v4-pro-${level}`,
|
|
reasoning_effort: level,
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(
|
|
body,
|
|
"opencode-go",
|
|
`deepseek-v4-pro-${level}`,
|
|
null
|
|
);
|
|
assert.equal(
|
|
(result as any).reasoning_effort,
|
|
level,
|
|
`opencode-go deepseek-v4-pro-${level} preserves reasoning_effort=${level}`
|
|
);
|
|
}
|
|
});
|
|
|
|
test("sanitizeReasoningEffortForProvider: opencode-go with non-DeepSeek model still normalizes max → xhigh", () => {
|
|
// The opt-in must be scoped to DeepSeek models on opencode-go only — other
|
|
// opencode-go models (e.g. glm/kimi/mimo) follow the default xhigh policy.
|
|
const body = {
|
|
model: "mimo-v2.5-pro",
|
|
reasoning_effort: "max",
|
|
messages: [],
|
|
};
|
|
const result = sanitizeReasoningEffortForProvider(body, "opencode-go", "mimo-v2.5-pro", null);
|
|
assert.notEqual(result, body);
|
|
assert.equal((result as any).reasoning_effort, "xhigh");
|
|
});
|