Files
OmniRoute/tests/unit/base-executor-sanitize-effort.test.ts
Diego Rodrigues de Sa e Souza 19d91d82e2 Release v3.8.34 (#4614)
* 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>
2026-06-23 03:08:29 -03:00

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");
});