mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 12:22:14 +03:00
* chore(release): open v3.8.38 development cycle
* fix(executors): strip client_metadata for cerebras and mistral (#4727)
Integrated into release/v3.8.38 (leva 5)
* fix(codebuddy): only send reasoning params when client requests reasoning (#5019)
Integrated into release/v3.8.38 (leva 5)
* fix(sse): keep streaming for forceStream providers when client requests JSON (#5021)
Integrated into release/v3.8.38 (leva 5)
* fix(sse): guard non-JSON SSE lines and duplicate [DONE] (#4937)
Integrated into release/v3.8.38 (leva 5)
* feat(blackbox): refresh provider model catalog (#4935)
Integrated into release/v3.8.38 (leva 5)
* fix(sse): dedupe case-variant Anthropic version/beta headers (#4846)
Integrated into release/v3.8.38 (leva 5)
* feat(sse): Kiro inline <thinking> stream splitter (#4911)
Integrated into release/v3.8.38 (leva 5)
* feat(cursor): parse Composer DeepSeek-style inline tool calls (#4912)
Integrated into release/v3.8.38 (leva 5)
* feat(proxy): auth-less host:port batch import (#4938)
Integrated into release/v3.8.38 (leva 5)
* fix(oauth): support Kiro IDC (organization) token import (#4944)
Integrated into release/v3.8.38 (leva 5)
* fix(translator): preserve cache_control for DashScope OpenAI-compat providers (port from 9router#2069) (#5013)
Integrated into release/v3.8.38 (leva 5)
* fix(tts): resolve Gemini TTS models from catalog (#4934)
Integrated into release/v3.8.38 (leva 5)
* fix(sse): don't cool down the connection on a self-inflicted upstream timeout (504) (#5064)
Integrated into release/v3.8.38 (leva 5)
* fix(sse): robust Anthropic /v1/messages streaming — real ping keepalive + client-disconnect guard (#5063)
Integrated into release/v3.8.38 (leva 5)
* feat(video): add Alibaba DashScope (wan2.7-t2v) provider (#5051)
Integrated into release/v3.8.38 (leva 5)
* fix: preserve model hidden flags (isHidden) across model sync (#5086)
Integrated into release/v3.8.38 (leva 5)
* fix(models): derive model discovery config from registry modelsUrl (#5087)
Integrated into release/v3.8.38 (leva 5)
* fix(compression): replace fileURLToPath(import.meta.url) with runtime anchors for standalone bundle (#5089)
Integrated into release/v3.8.38 (leva 5)
* feat(cc): add summarized thinking display toggle (#5055)
Integrated into release/v3.8.38 (leva 5)
* Harden selected API error responses (#5032)
Integrated into release/v3.8.38 (leva 5)
* chore(quality): rebaseline file-size for leva 5 PR batch drift
6 frozen files grew from merged leva-5 PRs (cursor #4912, kiro #4911,
videoGeneration #5051, default #4727, base #4846, chat #5064); all covered
by per-PR tests. See _rebaseline_2026_06_26_leva5 in the baseline.
* feat(compression): compression playground (Play + Compare tabs) in the studio (#5080)
Integrated into release/v3.8.38
* fix(combo): fail over on empty-content 502 instead of exhausting the provider (#5085) (#5104)
* fix(dashboard): surface detailed credential-validation error in add-connection modal (#5088) (#5106)
* feat(providers): allow local/private provider URLs by default with scoped metadata-safe guard (#5066) (#5107)
* fix(diagnostics): treat non-streaming Claude messages shape as valid output (#5108) (#5116)
* fix(db): translate pt-BR SQLite driver-fallback log lines to English (#5103) (#5115)
* fix(sse): repair release base-reds — malformed-response false positives + header casing + stale tests (#5117)
Repairs the release/v3.8.38 base-reds; unblocks #5078.
* chore(quality): rebaseline file-size for responseSanitizer (#5117) + AddApiKeyModal drift
* fix(translator): forward image tool_result blocks as image_url (#5100)
Base-reds fixed (#5117); image tool_result→image_url. Integrated into release/v3.8.38.
* fix(responses): default text.format for openai-compatible responses providers (#5101)
Base-reds fixed (#5117); default text.format + file-size rebaseline. Integrated into release/v3.8.38.
* feat(dashboard): expose Fusion judgeModel + fusionTuning in the combo editor (#5074)
Base-reds fixed (#5117); Fusion editor + file-size rebaseline. Integrated into release/v3.8.38.
* feat(quota): add opt-in Codex/Claude auto-ping keepalive (#5102)
Base-reds fixed (#5117); auto-ping keepalive + file-size rebaseline. Integrated into release/v3.8.38.
* test(release): relocate 2 orphan test files into the collected flat tests/unit dir (#5120)
Unblocks Lint (test-discovery) on #5078. Integrated into release/v3.8.38.
* fix(translator): preserve reasoning-replay reasoning_content + repair 3 release-green test reds (#5122)
Repairs 3 release-green test reds + test-masking; unblocks #5078.
* test(golden): redact live Node version from provider translate-path snapshot (#5125)
Final golden unblock for #5078.
* test(golden): redact OmniRoute app version from translate-path snapshot (#5126)
Coverage shard golden unblock for #5078.
* Ignore disconnect races during in-band stream error handling (#5007)
Integrated into release/v3.8.38
* Track final connection IDs in failover logs (#5016)
Integrated into release/v3.8.38
* fix(sse): convert Gemini body to OpenAI format in antigravity MITM handler (#4845)
Integrated into release/v3.8.38 (rebased on tip, CHANGELOG re-injected)
* feat(providers): add ZenMux Free session-cookie provider (#5105)
Integrated into release/v3.8.38 (rebased on tip, CHANGELOG re-injected)
* feat(dashboard): click-to-edit model alias in provider page (#5119)
Integrated into release/v3.8.38 (rebased on tip, i18n scope verified, CHANGELOG re-injected)
* feat(mcp): web-session robustness — cookie dedup (PR6) + browser-pool observability (PR7) (#3368) (#5121)
Integrated into release/v3.8.38 (rebased on tip; cookie-dedup branch extracted to findExistingCookieConnection helper → complexity-neutral; CHANGELOG added)
* fix(usage): dedupe request-usage logging and debounce stats (#4940)
Integrated into release/v3.8.38 (rebased on tip; DB-handle hang was stale-base artifact — resetDbInstance already closes the handle, test green 5/5; file-size drift consolidated at release; CHANGELOG re-injected)
* fix(dashboard): key model visibility toggle on canonical providerId (#5091)
Integrated into release/v3.8.38 (retargeted main→release; .tsx visibility-key test green 2/2)
* chore(deps): bump actions/cache from 5.0.5 to 6.0.0 (#5112)
Integrated into release/v3.8.38 (retargeted main→release; workflow-only actions/cache bump — unit failures were stale main base-reds)
* fix(streaming): harden long OpenAI-compatible SSE streams (#5124)
Integrated into release/v3.8.38 (rebased on tip; streamHandler conflict with #5007 disconnect-guard resolved — both coexist, stream-handler 22/22 green)
* feat: Add Grok Build (xAI) provider with OAuth import-token flow (#5020)
Integrated into release/v3.8.38 (rebased on tip; Hard Rule #11 fix — Grok public client_id now via resolvePublicCred(grok_id), 3 literals removed; grok-oauth 7/7 + check:public-creds green)
* feat(providers): add Factory (factory.ai) as a subscription gateway provider (#5065)
Integrated into release/v3.8.38 (rebased on tip; added factory registry test for PR Test Policy + fixed check:env-doc-sync phantom FACTORY_API_KEY; factory loads in PROVIDERS, no Zod issue — that flag was a false positive)
* chore(test): reconcile golden snapshot + apikey count for new providers
#5020 (grok-cli), #5065 (factory), #5105 (zenmux-free) added providers but did
not regenerate tests/snapshots/provider/translate-path.json (now +3 entries) nor
bump the APIKEY_PROVIDERS count (159->160 for the factory gateway). Test-only
reconciliation; no production change.
* fix(resilience): harden quota and model lockout edge cases (#5093)
Integrated into release/v3.8.38 (rebased on tip). TRUST-BUT-VERIFY: dropped the PR's 0dd7df641 'fix unit gates' commit which reverted #5122 reasoning-replay (preserveReasoningContent) + re-introduced #4849 O(n^2) growth, and restored 5 tests it had realigned. Kept only the 3 declared resilience fixes (quota cutoff guard, gemini MIME, model-lockout maxCooldownMs); 23/23 green.
* Hydrate quota cache and scope auto combo candidates (#5015)
Integrated into release/v3.8.38 (rebased on tip). Kept core quota-cache hydration + auto-combo candidate scoping + combos UI; dropped out-of-scope toolCloaking refactor (conflicted with #4813 stripEnumDescriptions — took tip) and the unrelated sse-auth test split. Added quota-cache-hydrate-5015 regression test (Rule #18); combo-account-allowlist 8/8 + hydration 2/2 green.
* chore(quality): reconcile complexity + file-size baselines for v3.8.38 owner-PR batch
complexity 1972->1978 (+6) and file-size providers.ts 1093->1107 / usageHistory.ts
934->983 — drift from the /review-prs merge batch (#4845/#5105/#5020/#4940/#5093/
#5015 + #5121 cookie-dedup helper extraction). check:complexity/check:file-size do
not run on the PR->release fast-path, so the branch accrued unmeasured; all legit
feature/fix growth, not regression. See per-key justifications in each baseline.
* fix(security): exact-host Anthropic baseUrl check (CodeQL js/incomplete-url-substring-sanitization #674) (#5130)
The anthropic-compatible Bearer-fallback gate decided whether a configured baseUrl
targeted the official api.anthropic.com host via a substring `.includes("api.anthropic.com")`.
A look-alike upstream such as `https://api.anthropic.com.evil.test` or
`https://evil.test/?x=api.anthropic.com` matched the substring and was wrongly treated as
official, suppressing the Bearer fallback meant for third-party gateways
(CodeQL #674, js/incomplete-url-substring-sanitization, high).
Replace the substring test with an exported `isOfficialAnthropicBaseUrl()` helper that
parses the URL and compares the hostname for exact equality. Empty baseUrl stays official;
scheme-less hosts are parsed with an assumed https://; an unparseable baseUrl falls back to
third-party (Bearer emitted) as the safer default. Behavior for legitimate official/third-party
baseUrls is unchanged.
Adds tests/unit/anthropic-official-baseurl-host.test.ts covering official, look-alike,
scheme-less, and unparseable inputs plus a static guard that the substring pattern is gone.
* fix(proxy): repair one-click Deno & Cloudflare relay deployments (#5128) (#5132)
* fix(services): embed WS proxy honours LIVE_WS_HOST; reject empty messages early (#5110) (#5133)
* fix(api): resolve /v1/models/{id} case-insensitively (#5082) (#5135)
* fix(providers): add MiniMax M3 & Nemotron 3 Ultra to Cline catalog (#3321) (#5136)
* fix(proxy): make SOCKS5 handshake timeout tunable via SOCKS_HANDSHAKE_TIMEOUT_MS (#5109) (#5137)
* feat(sidebar): add support for colored menu icons (#3812)
Integrated into release/v3.8.38 (recreated on tip — fork had unrelated history; added getSidebarIconAccent regression test, Rule #18). Clean 2-file UI feature.
* fix(providers): complete grok-cli OAuth wiring + zenmux-free web-session metadata
Base-red repair for #5020 (grok-cli) and #5105 (zenmux-free), surfaced by the
full CI on the release PR (#5078) — the PR->release fast-path does not run the
oauth-providers-config / web-session-credentials / provider-consistency gates.
- grok-cli: register in OAUTH_PROVIDERS (providers.ts canonical list, fixes
check:provider-consistency), add OAUTH_PROVIDER_IDS.GROK_CLI + GROK_CLI_CONFIG
in oauth constants (provider config now sourced there, not a local literal),
align oauth-providers-config.test.ts (EXPECTED_PROVIDER_KEYS + config map).
- zenmux-free: declare its web-session credential requirement (full Cookie header)
in WEB_SESSION_CREDENTIAL_REQUIREMENTS.
Local: oauth-providers-config 27/27, web-session-credentials 4/4, grok-cli-oauth
7/7, check:provider-consistency OK, +115 OAUTH_PROVIDERS tests green.
* Fix resilience settings page response mapping (#5139)
Integrated into release/v3.8.38. Thanks @rdself for the fix and the regression test.
* fix(kiro): retire claude-sonnet-4.5 from catalog + pin 400 model-unavailable test (#5140)
Extracted the real change from #5140 (the bot PR regenerated the entire
freeModelCatalog.data.ts + touched package-lock.json; only the targeted
edits are kept here):
- remove claude-sonnet-4.5 from the Kiro registry entry
- remove the matching kiro free-model catalog row
- pin Kiro's verbatim 400 "Invalid model..." to isModelUnavailableError
Closes #4484
* fix(sidebar): drop orphan `settings` accent color (typecheck:core red) (#5142)
SIDEBAR_ICON_ACCENTS is typed Partial<Record<HideableSidebarItemId, string>>,
but `settings` is not a hideable item id (only `settings-general`,
`settings-appearance`, … and `context-settings` exist; there is no item with
`id: "settings"`), so the accent was unreachable. It broke `typecheck:core`
on the release tip ("'settings' does not exist in type …", introduced by
#3812 colored menu icons). Removing the orphan key restores a clean
typecheck:core (rc=0).
* feat: salvage batch 2 — diagnostics null-guard (#5096) + observed quota reset windows (#5025) (#5141)
* fix(diagnostics): null-guard content blocks in detectMalformedNonStream
A null (or non-object) entry in a Claude-native `content` array made the
non-stream classifier throw `TypeError: Cannot read properties of null
(reading 'type')`, crashing the malformed-response detection path. Guard
before type-asserting each block: a null/non-object block is simply skipped.
Two regression tests added (null block among valid blocks → null; only-null
blocks → empty_choices).
Salvaged from closed PR #5096 (base-stale; only the defensive guard — the
Claude-shape recognition it also carried already landed via #5108).
Co-authored-by: herjarsa <herjarsa@users.noreply.github.com>
* feat(quota): persist observed provider quota reset windows
Adds `provider_quota_reset_events` (migration 108) + `db/quotaResetEvents.ts`
to record real upstream weekly-quota window transitions whenever a quota
refresh shows the reset rolling to a new cycle (different day, later resetAt).
`apiKeyUsageLimits` now prefers the observed window start over the inferred
`resetAt − 7d`, falling back to snapshot inference when no event is recorded
yet. `quotaCache.setQuotaCache` records the transition opportunistically.
`recordProviderQuotaResetEventIfChanged` only fires for the primary weekly
window (not daily/sonnet), is idempotent (INSERT OR IGNORE on the unique
window key), and no-ops when the reset didn't actually roll. 4 unit tests
(tests/unit/lib/quota-reset-events.test.ts).
Salvaged from closed PR #5025 (which bundled this with two unrelated
features + a colliding migration 104). Renumbered to 108; module re-exported
from localDb (Rule #2).
Co-authored-by: Witroch4 <175152067+Witroch4@users.noreply.github.com>
---------
Co-authored-by: herjarsa <herjarsa@users.noreply.github.com>
Co-authored-by: Witroch4 <175152067+Witroch4@users.noreply.github.com>
* docs(i18n): sync 3.8.38 CHANGELOG section to 41 mirrors (unblock docs-accuracy) (#5144)
The root CHANGELOG [3.8.38] section grew with this cycle's merged PRs, but the
docs/i18n/<lang>/CHANGELOG.md mirrors were not re-synced — drifting >25% in body
size and failing check:docs-sync (the "Docs accuracy" fast-gate step) for every
open PR against the release.
Ran scripts/release/sync-changelog-i18n.mjs 3.8.38 3.8.37 to copy the root
[3.8.38] section into all 41 mirrors. check:docs-all now passes (exit 0).
Sections are copied verbatim; the per-language translation pass runs at release
time via i18n:run — this only restores the size-sync the gate enforces.
* feat(compression): pure per-step fidelity checker (4 invariants, fail-open)
* feat(compression): fidelityGate config + rejected breakdown fields
* feat(compression): wire per-step fidelity gate into stacked pipeline (opt-in)
* feat(compression): preview route accepts fidelityGate flag (playground)
* feat(compression): playground fidelity-gate toggle + lane rejection display
* docs(compression): note fidelityGate advanced thresholds are intentionally API-omitted
* refactor(compression): extract fidelity-gate step helpers to shrink strategySelector (file-size gate)
bodyToText and gateAdvance moved to fidelityGateStep.ts; StackAccumulator exported.
strategySelector: 889->854 (-35). Residual +6 vs pre-Milestone-B frozen 848 is the
irreducible StackOptions.fidelityGate field + two stacked-loop dispatch reads + import.
Baseline updated to 854 with justification. No cycle introduced (import type only).
940 compression tests pass; typecheck clean.
* test(usage): wire usageHistoryDedup under unit runner brace-list (#5145)
Integrated into release/v3.8.38.
* feat: salvage batch from closed stale PRs (#5038, #5057, #5076) (#5138)
Integrated into release/v3.8.38.
* test(combo): deterministic routing-decision matrix for all 17 strategies (#5146)
Integrated into release/v3.8.38.
* feat(compression): fuzzy near-duplicate dedup (session-dedup 2nd pass + playground toggle) (#5143)
Integrated into release/v3.8.38.
* chore(quality): rebaseline file-size for sidebarVisibility.ts + chat.ts drift (#5147)
Mid-cycle drift on release/v3.8.38 from already-merged PRs that the fast-path
(PR->release skips check:file-size) let accumulate without a bump:
- src/shared/constants/sidebarVisibility.ts 1100->1198 (#3812 colored menu
icons, per-item accent map; #5142 dropped one orphan, net still above frozen)
- src/sse/handlers/chat.ts 1560->1575 (#5064 self-inflicted-timeout cooldown
skip + #5124 long OpenAI-compatible SSE hardening + #5110 embed-WS
LIVE_WS_HOST honour / early empty-message reject)
Each covered by its own PR tests; structural shrink of chat.ts tracked in #3501.
Unblocks the Fast Quality Gates for PRs targeting release/v3.8.38.
* chore(release): finalize v3.8.38 CHANGELOG + cycle reconciliation
- Reconcile [3.8.38]: +18 bullets (compression fidelity-gate/fuzzy-dedup #5143,
quota keepalive #5102, web-session robustness #5121, MiniMax/Nemotron #5136,
model-visibility #5091, failover logs #5016, disconnect races #5007, sidebar
orphan #5142, SRE playbooks salvage #5138, new Security #5130 + Maintenance roll-up)
- Credit salvaged-PR authors (@JxnLexn / @KooshaPari / @herjarsa / @Witroch4)
- Remove phantom bullet for CLOSED-not-merged #5092 (setup aggregator never landed)
- Fix isHidden bullet PR citation #4389 -> #5086 (@herjarsa)
- Back-fill forgotten v3.8.36 bullet: #5026 crypto.randomUUID ID-gen (@hamsa0x7)
- Sync 41 i18n CHANGELOG mirrors; README What's New -> v3.8.38
- Rebaseline cycle drift: eslint 3987->4002, cognitive 833->841, dead-exports
345->346, cyclomatic 1978->1980 (file-size handled by #5147)
* fix(i18n): add missing English UI labels (#5153)
Integrated into release/v3.8.38
* Preserve non-stream reasoning fields for compatible clients (#5155)
Integrated into release/v3.8.38
* feat(compression): ionizer engine — lossy JSON-array sampling reversible via CCR (#5148)
Integrated into release/v3.8.38
* test(combo): gated live smoke for combo strategies (in-process + VPS HTTP) (#5151)
Integrated into release/v3.8.38
* test: refresh release expectations to match current code (#5150)
Integrated into release/v3.8.38 (test-only base-red alignment extracted from #5150)
---------
Co-authored-by: Éder Costa <eder.almeida.costa@gmail.com>
Co-authored-by: José Victor Ferreira <root@josevictor.me>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: fulorgnas <46461624+fulorgnas@users.noreply.github.com>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Jan Leon <Jan.gaschler@gmail.com>
Co-authored-by: R. Beltran <rbeltran8000@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com>
Co-authored-by: Ramel Tecnologia - Rafa Martins <146174365+rafacpti23@users.noreply.github.com>
Co-authored-by: herjarsa <herjarsa@users.noreply.github.com>
Co-authored-by: Witroch4 <175152067+Witroch4@users.noreply.github.com>
881 lines
28 KiB
TypeScript
881 lines
28 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
const {
|
|
resolveComboConfig,
|
|
getDefaultComboConfig,
|
|
resolveComboTargetTimeoutMs,
|
|
DEFAULT_COMBO_TARGET_TIMEOUT_MS,
|
|
resolveComboQueueDepth,
|
|
} = await import("../../open-sse/services/comboConfig.ts");
|
|
const { createComboSchema, updateComboDefaultsSchema } =
|
|
await import("../../src/shared/validation/schemas.ts");
|
|
const { MAX_TIMER_TIMEOUT_MS } = await import("../../src/shared/utils/runtimeTimeouts.ts");
|
|
|
|
test("getDefaultComboConfig returns a fresh copy of the defaults", () => {
|
|
const first = getDefaultComboConfig();
|
|
const second = getDefaultComboConfig();
|
|
|
|
assert.notEqual(first, second);
|
|
assert.equal(first.strategy, "priority");
|
|
assert.equal(first.maxRetries, 1);
|
|
assert.equal(first.retryDelayMs, 2000);
|
|
assert.equal(first.fallbackDelayMs, 0);
|
|
assert.ok(!("timeoutMs" in first));
|
|
assert.ok(!("healthCheckEnabled" in first));
|
|
assert.equal(first.handoffThreshold, 0.85);
|
|
assert.equal(first.maxMessagesForSummary, 30);
|
|
assert.deepEqual(first.handoffProviders, ["codex"]);
|
|
assert.equal(first.nestedComboMode, "flatten");
|
|
assert.equal(first.failoverBeforeRetry, true);
|
|
assert.equal(first.maxSetRetries, 0);
|
|
assert.equal(first.setRetryDelayMs, 2000);
|
|
assert.equal(first.reasoningTokenBufferEnabled, true);
|
|
assert.equal(first.zeroLatencyOptimizationsEnabled, false);
|
|
assert.equal(first.hedging, false);
|
|
assert.equal(first.fallbackCompressionMode, "lite");
|
|
assert.equal(first.fallbackCompressionThreshold, 1000);
|
|
assert.equal(first.predictiveTtftMs, 0);
|
|
assert.equal(first.evalRouting.enabled, false);
|
|
assert.equal(first.evalRouting.maxAgeHours, 720);
|
|
|
|
first.strategy = "weighted";
|
|
assert.equal(second.strategy, "priority");
|
|
});
|
|
|
|
test("resolveComboConfig applies the full cascade from defaults to combo overrides", () => {
|
|
const result = resolveComboConfig(
|
|
{
|
|
config: {
|
|
maxRetries: 4,
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
strategy: "round-robin",
|
|
timeoutMs: 120000,
|
|
targetTimeoutMs: 90000,
|
|
},
|
|
providerOverrides: {
|
|
openai: {
|
|
timeoutMs: 60000,
|
|
targetTimeoutMs: 45000,
|
|
retryDelayMs: 500,
|
|
fallbackDelayMs: 100,
|
|
},
|
|
},
|
|
},
|
|
"openai"
|
|
);
|
|
|
|
assert.equal(result.strategy, "round-robin");
|
|
assert.equal(result.retryDelayMs, 500);
|
|
assert.equal(result.fallbackDelayMs, 100);
|
|
assert.equal(result.maxRetries, 4);
|
|
assert.equal(result.targetTimeoutMs, 45000);
|
|
assert.ok(!("timeoutMs" in result));
|
|
assert.ok(!("healthCheckEnabled" in result));
|
|
});
|
|
|
|
test("resolveComboConfig cascades reasoning token buffer feature flag", () => {
|
|
const providerDisabled = resolveComboConfig(
|
|
{},
|
|
{
|
|
comboDefaults: {
|
|
reasoningTokenBufferEnabled: true,
|
|
},
|
|
providerOverrides: {
|
|
openai: {
|
|
reasoningTokenBufferEnabled: false,
|
|
},
|
|
},
|
|
},
|
|
"openai"
|
|
);
|
|
|
|
const comboEnabled = resolveComboConfig(
|
|
{
|
|
config: {
|
|
reasoningTokenBufferEnabled: true,
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
reasoningTokenBufferEnabled: false,
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(providerDisabled.reasoningTokenBufferEnabled, false);
|
|
assert.equal(comboEnabled.reasoningTokenBufferEnabled, true);
|
|
});
|
|
|
|
test("resolveComboConfig preserves nested routing defaults for partial overrides", () => {
|
|
const result = resolveComboConfig(
|
|
{
|
|
config: {
|
|
shadowRouting: { enabled: true },
|
|
evalRouting: { enabled: true, suiteIds: ["coding-proficiency"] },
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
shadowRouting: { sampleRate: 0.5 },
|
|
evalRouting: { maxAgeHours: 168 },
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.shadowRouting.enabled, true);
|
|
assert.equal(result.shadowRouting.sampleRate, 0.5);
|
|
assert.equal(result.shadowRouting.maxTargets, 2);
|
|
assert.equal(result.shadowRouting.timeoutMs, 30000);
|
|
assert.equal(result.evalRouting.enabled, true);
|
|
assert.deepEqual(result.evalRouting.suiteIds, ["coding-proficiency"]);
|
|
assert.equal(result.evalRouting.maxAgeHours, 168);
|
|
assert.equal(result.evalRouting.minCases, 1);
|
|
assert.equal(result.evalRouting.cacheTtlMs, 60000);
|
|
});
|
|
|
|
test("resolveComboConfig ignores null, undefined, and legacy resilience overrides", () => {
|
|
const result = resolveComboConfig(
|
|
{
|
|
config: {
|
|
timeoutMs: null,
|
|
trackMetrics: false,
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
timeoutMs: undefined,
|
|
queueTimeoutMs: 15000,
|
|
},
|
|
providerOverrides: {
|
|
openai: {
|
|
strategy: null,
|
|
concurrencyPerModel: 9,
|
|
},
|
|
},
|
|
},
|
|
"openai"
|
|
);
|
|
|
|
assert.ok(!("timeoutMs" in result));
|
|
assert.equal(result.queueTimeoutMs, 15000);
|
|
assert.equal(result.concurrencyPerModel, 9);
|
|
assert.equal(result.trackMetrics, false);
|
|
assert.equal(result.strategy, "priority");
|
|
});
|
|
|
|
test("updateComboDefaultsSchema accepts arbitrarily large timeout defaults and provider overrides", () => {
|
|
const parsed = updateComboDefaultsSchema.parse({
|
|
comboDefaults: {
|
|
timeoutMs: 3600000,
|
|
targetTimeoutMs: 30000,
|
|
reasoningTokenBufferEnabled: false,
|
|
},
|
|
providerOverrides: {
|
|
anthropic: {
|
|
timeoutMs: 5400000,
|
|
targetTimeoutMs: 45000,
|
|
reasoningTokenBufferEnabled: false,
|
|
},
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.comboDefaults.timeoutMs, 3600000);
|
|
assert.equal(parsed.comboDefaults.targetTimeoutMs, 30000);
|
|
assert.equal(parsed.comboDefaults.reasoningTokenBufferEnabled, false);
|
|
assert.equal(parsed.providerOverrides.anthropic.timeoutMs, 5400000);
|
|
assert.equal(parsed.providerOverrides.anthropic.targetTimeoutMs, 45000);
|
|
assert.equal(parsed.providerOverrides.anthropic.reasoningTokenBufferEnabled, false);
|
|
});
|
|
|
|
test("combo config schema accepts explicit zero-latency opt-in controls", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "zero-latency-opt-in",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
config: {
|
|
zeroLatencyOptimizationsEnabled: true,
|
|
hedging: true,
|
|
hedgeDelayMs: 250,
|
|
fallbackCompressionMode: "lite",
|
|
fallbackCompressionThreshold: 2500,
|
|
predictiveTtftMs: 1800,
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.zeroLatencyOptimizationsEnabled, true);
|
|
assert.equal(parsed.config.hedging, true);
|
|
assert.equal(parsed.config.hedgeDelayMs, 250);
|
|
assert.equal(parsed.config.fallbackCompressionMode, "lite");
|
|
assert.equal(parsed.config.fallbackCompressionThreshold, 2500);
|
|
assert.equal(parsed.config.predictiveTtftMs, 1800);
|
|
});
|
|
|
|
test("combo config schema auto-promotes the zero-latency gate for legacy configs without opt-in", () => {
|
|
// Pre-3.8.33 combos carry zero-latency subfeatures without the
|
|
// zeroLatencyOptimizationsEnabled gate. The schema now auto-promotes the gate
|
|
// (instead of 400-ing on the first GUI edit) so they round-trip. See #4774/#4382.
|
|
const result = createComboSchema.safeParse({
|
|
name: "zero-latency-legacy",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
config: {
|
|
hedging: true,
|
|
fallbackCompressionMode: "lite",
|
|
predictiveTtftMs: 1800,
|
|
},
|
|
});
|
|
|
|
assert.equal(result.success, true);
|
|
assert.equal(result.data.config.zeroLatencyOptimizationsEnabled, true);
|
|
// The enabled subfeatures are preserved verbatim.
|
|
assert.equal(result.data.config.hedging, true);
|
|
assert.equal(result.data.config.fallbackCompressionMode, "lite");
|
|
assert.equal(result.data.config.predictiveTtftMs, 1800);
|
|
});
|
|
|
|
test("combo config schema leaves the zero-latency gate untouched when no subfeature is enabled", () => {
|
|
// A plain config with no zero-latency subfeature must NOT be auto-promoted —
|
|
// the gate stays at its default (false) so we don't silently flip optimizations on.
|
|
const result = createComboSchema.safeParse({
|
|
name: "no-zero-latency",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
config: {
|
|
fallbackCompressionMode: "off",
|
|
},
|
|
});
|
|
|
|
assert.equal(result.success, true);
|
|
assert.notEqual(result.data.config.zeroLatencyOptimizationsEnabled, true);
|
|
});
|
|
|
|
test("combo config schema no longer rejects v3.8.31-era removed config keys (#4382 round-trip)", () => {
|
|
// Keys dropped after v3.8.31 still live in stored JSON. The schema switched
|
|
// .strict() (which 400'd) → .passthrough(); the route + migration 103 scrub them.
|
|
const result = createComboSchema.safeParse({
|
|
name: "legacy-removed-keys",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
config: {
|
|
queueDepth: 4,
|
|
fallbackDelayMs: 200,
|
|
maxComboDepth: 3,
|
|
shadowRouting: { enabled: false },
|
|
resetAwareEnabled: true,
|
|
},
|
|
});
|
|
|
|
assert.equal(result.success, true);
|
|
});
|
|
|
|
test("combo config schema allows zero-latency tuning fields when subfeatures stay disabled", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "zero-latency-disabled-tuning",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
config: {
|
|
hedgeDelayMs: 250,
|
|
fallbackCompressionMode: "off",
|
|
fallbackCompressionThreshold: 2500,
|
|
predictiveTtftMs: 0,
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.hedgeDelayMs, 250);
|
|
assert.equal(parsed.config.fallbackCompressionMode, "off");
|
|
assert.equal(parsed.config.fallbackCompressionThreshold, 2500);
|
|
assert.equal(parsed.config.predictiveTtftMs, 0);
|
|
});
|
|
|
|
test("resolveComboTargetTimeoutMs inherits the upstream timeout and only shortens it", () => {
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 600000), 600000);
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 30000 }, 600000), 30000);
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 900000 }, 600000), 600000);
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 0 }, 600000), 600000);
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 30000 }, 0), 30000);
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 0), 0);
|
|
assert.equal(
|
|
resolveComboTargetTimeoutMs({ targetTimeoutMs: 999999999999 }, 0),
|
|
MAX_TIMER_TIMEOUT_MS
|
|
);
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 999999999999), MAX_TIMER_TIMEOUT_MS);
|
|
});
|
|
|
|
test("resolveComboTargetTimeoutMs falls back to the saner combo default when unset", () => {
|
|
// The combo default is the documented 120s fallback-latency cap.
|
|
assert.equal(DEFAULT_COMBO_TARGET_TIMEOUT_MS, 120000);
|
|
// Unset config → use the default (capped at the ceiling), NOT the full upstream ceiling.
|
|
// This is what shortens a hung-target failover from 600s to 120s (escalated cmqlrhd7c).
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 600000, 120000), 120000);
|
|
// Operators can still extend beyond the default, up to the ceiling.
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 300000 }, 600000, 120000), 300000);
|
|
// Explicit config above the ceiling is still capped at the ceiling.
|
|
assert.equal(resolveComboTargetTimeoutMs({ targetTimeoutMs: 900000 }, 600000, 120000), 600000);
|
|
// A default larger than the ceiling is clamped to the ceiling.
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 100000, 120000), 100000);
|
|
// Backward-compat: omitting the default arg keeps the legacy inherit-the-ceiling behavior.
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 600000), 600000);
|
|
// Disabled upstream timeout (0 = unbounded) stays unbounded even with a default present.
|
|
assert.equal(resolveComboTargetTimeoutMs({}, 0, 120000), 0);
|
|
});
|
|
|
|
test("combo timeout schema rejects values beyond the safe timer limit", () => {
|
|
const result = createComboSchema.safeParse({
|
|
name: "unsafe-timeout",
|
|
models: ["openai/gpt-4"],
|
|
config: {
|
|
targetTimeoutMs: MAX_TIMER_TIMEOUT_MS + 1,
|
|
},
|
|
});
|
|
|
|
assert.equal(result.success, false);
|
|
});
|
|
|
|
test("resolveComboConfig preserves explicit empty handoffProviders overrides", () => {
|
|
const result = resolveComboConfig(
|
|
{
|
|
config: {
|
|
handoffProviders: [],
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
handoffProviders: ["codex"],
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.deepEqual(result.handoffProviders, []);
|
|
});
|
|
|
|
test("resolveComboConfig skips provider overrides when provider is absent", () => {
|
|
const result = resolveComboConfig(
|
|
{ config: {} },
|
|
{
|
|
comboDefaults: { strategy: "random" },
|
|
providerOverrides: {
|
|
openai: { strategy: "weighted" },
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.strategy, "random");
|
|
});
|
|
|
|
test("resolveComboConfig tolerates invalid or missing inputs and falls back to defaults", () => {
|
|
assert.deepEqual(resolveComboConfig(null, null, "openai"), getDefaultComboConfig());
|
|
assert.deepEqual(resolveComboConfig({}, { comboDefaults: null }, null), getDefaultComboConfig());
|
|
});
|
|
|
|
test("createComboSchema accepts context-relay strategy with handoff config", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "codex-relay",
|
|
models: ["codex/gpt-5.4"],
|
|
strategy: "context-relay",
|
|
config: {
|
|
handoffThreshold: 0.85,
|
|
maxMessagesForSummary: 24,
|
|
handoffModel: "",
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.strategy, "context-relay");
|
|
assert.equal(parsed.config.handoffThreshold, 0.85);
|
|
assert.equal(parsed.config.maxMessagesForSummary, 24);
|
|
});
|
|
|
|
test("createComboSchema accepts eval-driven routing config", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "eval-ranked",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
strategy: "priority",
|
|
config: {
|
|
evalRouting: {
|
|
enabled: true,
|
|
suiteIds: ["golden-set", "coding-proficiency"],
|
|
maxAgeHours: 168,
|
|
minCases: 5,
|
|
qualityWeight: 0.9,
|
|
latencyWeight: 0.1,
|
|
cacheTtlMs: 30000,
|
|
},
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.evalRouting.enabled, true);
|
|
assert.deepEqual(parsed.config.evalRouting.suiteIds, ["golden-set", "coding-proficiency"]);
|
|
});
|
|
|
|
test("createComboSchema accepts SLA-aware auto routing config", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "sla-auto",
|
|
models: ["openai/gpt-4o-mini", "gemini/gemini-2.5-flash"],
|
|
strategy: "auto",
|
|
config: {
|
|
routerStrategy: "sla-aware",
|
|
slaTargetP95Ms: "1500",
|
|
slaMaxErrorRate: "0.05",
|
|
slaMaxCostPer1MTokens: "4.5",
|
|
slaHardConstraints: true,
|
|
sla: {
|
|
targetP95Ms: "2000",
|
|
maxErrorRate: "0.1",
|
|
hardConstraints: false,
|
|
},
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.strategy, "auto");
|
|
assert.equal(parsed.config.routerStrategy, "sla-aware");
|
|
assert.equal(parsed.config.slaTargetP95Ms, 1500);
|
|
assert.equal(parsed.config.slaMaxErrorRate, 0.05);
|
|
assert.equal(parsed.config.slaMaxCostPer1MTokens, 4.5);
|
|
assert.equal(parsed.config.slaHardConstraints, true);
|
|
assert.equal(parsed.config.sla.targetP95Ms, 2000);
|
|
assert.equal(parsed.config.sla.maxErrorRate, 0.1);
|
|
});
|
|
|
|
test("createComboSchema accepts structured combo steps with pinned connection and combo refs", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "codex-pinned",
|
|
strategy: "priority",
|
|
models: [
|
|
{
|
|
kind: "model",
|
|
id: "step-codex-a",
|
|
providerId: "codex",
|
|
model: "gpt-5.4",
|
|
connectionId: "conn-codex-a",
|
|
weight: 10,
|
|
},
|
|
{
|
|
kind: "combo-ref",
|
|
id: "step-fallback",
|
|
comboName: "backup-codex",
|
|
weight: 5,
|
|
},
|
|
],
|
|
});
|
|
|
|
assert.equal(parsed.models[0].kind, "model");
|
|
assert.equal(parsed.models[0].providerId, "codex");
|
|
assert.equal(parsed.models[0].connectionId, "conn-codex-a");
|
|
assert.equal(parsed.models[1].kind, "combo-ref");
|
|
assert.equal(parsed.models[1].comboName, "backup-codex");
|
|
});
|
|
|
|
test("createComboSchema accepts composite tiers that reference normalized combo steps", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "tiered-codex",
|
|
strategy: "priority",
|
|
models: [
|
|
{
|
|
kind: "model",
|
|
id: "step-primary",
|
|
providerId: "codex",
|
|
model: "gpt-5.4",
|
|
connectionId: "conn-codex-a",
|
|
},
|
|
{
|
|
kind: "model",
|
|
id: "step-backup",
|
|
providerId: "codex",
|
|
model: "gpt-5.4",
|
|
connectionId: "conn-codex-b",
|
|
},
|
|
],
|
|
config: {
|
|
compositeTiers: {
|
|
defaultTier: "primary",
|
|
tiers: {
|
|
primary: {
|
|
stepId: "step-primary",
|
|
fallbackTier: "backup",
|
|
label: "Codex A",
|
|
},
|
|
backup: {
|
|
stepId: "step-backup",
|
|
description: "Fallback account",
|
|
},
|
|
},
|
|
},
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.compositeTiers.defaultTier, "primary");
|
|
assert.equal(parsed.config.compositeTiers.tiers.primary.stepId, "step-primary");
|
|
assert.equal(parsed.config.compositeTiers.tiers.primary.fallbackTier, "backup");
|
|
assert.equal(parsed.config.compositeTiers.tiers.backup.stepId, "step-backup");
|
|
});
|
|
|
|
test("updateComboDefaultsSchema rejects composite tiers in global defaults and provider overrides", () => {
|
|
const result = updateComboDefaultsSchema.safeParse({
|
|
comboDefaults: {
|
|
compositeTiers: {
|
|
defaultTier: "primary",
|
|
tiers: {
|
|
primary: {
|
|
stepId: "step-primary",
|
|
},
|
|
},
|
|
},
|
|
},
|
|
providerOverrides: {
|
|
codex: {
|
|
compositeTiers: {
|
|
defaultTier: "backup",
|
|
tiers: {
|
|
backup: {
|
|
stepId: "step-backup",
|
|
},
|
|
},
|
|
},
|
|
},
|
|
},
|
|
});
|
|
|
|
assert.equal(result.success, false);
|
|
assert.deepEqual(
|
|
result.error.issues.map((issue) => ({
|
|
path: issue.path.join("."),
|
|
message: issue.message,
|
|
})),
|
|
[
|
|
{
|
|
path: "comboDefaults.compositeTiers",
|
|
message: "compositeTiers is only supported on concrete combos",
|
|
},
|
|
{
|
|
path: "providerOverrides.codex.compositeTiers",
|
|
message: "compositeTiers is only supported on concrete combos",
|
|
},
|
|
]
|
|
);
|
|
});
|
|
|
|
test("createComboSchema accepts failoverBeforeRetry, maxSetRetries and setRetryDelayMs", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "failover-test",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: {
|
|
failoverBeforeRetry: true,
|
|
maxSetRetries: 3,
|
|
setRetryDelayMs: 1500,
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.failoverBeforeRetry, true);
|
|
assert.equal(parsed.config.maxSetRetries, 3);
|
|
assert.equal(parsed.config.setRetryDelayMs, 1500);
|
|
});
|
|
|
|
test("createComboSchema accepts nestedComboMode and rejects invalid values", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "nested-execute",
|
|
models: [{ kind: "combo-ref", comboName: "child" }],
|
|
strategy: "priority",
|
|
config: { nestedComboMode: "execute" },
|
|
});
|
|
assert.equal(parsed.config.nestedComboMode, "execute");
|
|
|
|
const flatten = createComboSchema.parse({
|
|
name: "nested-flatten",
|
|
models: ["openai/gpt-4o-mini"],
|
|
config: { nestedComboMode: "flatten" },
|
|
});
|
|
assert.equal(flatten.config.nestedComboMode, "flatten");
|
|
|
|
const invalid = createComboSchema.safeParse({
|
|
name: "nested-invalid",
|
|
models: ["openai/gpt-4o-mini"],
|
|
config: { nestedComboMode: "redirect" },
|
|
});
|
|
assert.equal(invalid.success, false);
|
|
});
|
|
|
|
test("createComboSchema accepts per-combo stickyRoundRobinLimit and rejects out-of-range", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "sticky-override",
|
|
models: ["openai/gpt-4o-mini"],
|
|
strategy: "round-robin",
|
|
config: { stickyRoundRobinLimit: 2 },
|
|
});
|
|
assert.equal(parsed.config.stickyRoundRobinLimit, 2);
|
|
|
|
const tooHigh = createComboSchema.safeParse({
|
|
name: "sticky-too-high",
|
|
models: ["openai/gpt-4o-mini"],
|
|
strategy: "round-robin",
|
|
config: { stickyRoundRobinLimit: 1001 },
|
|
});
|
|
assert.equal(tooHigh.success, false);
|
|
});
|
|
|
|
test("createComboSchema accepts per-combo stickyWeightedLimit and rejects out-of-range", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "sticky-weighted",
|
|
models: [{ model: "openai/gpt-4o-mini", weight: 100 }],
|
|
strategy: "weighted",
|
|
config: { stickyWeightedLimit: 2 },
|
|
});
|
|
assert.equal(parsed.config.stickyWeightedLimit, 2);
|
|
|
|
const tooHigh = createComboSchema.safeParse({
|
|
name: "sticky-weighted-too-high",
|
|
models: [{ model: "openai/gpt-4o-mini", weight: 100 }],
|
|
strategy: "weighted",
|
|
config: { stickyWeightedLimit: 1001 },
|
|
});
|
|
assert.equal(tooHigh.success, false);
|
|
});
|
|
|
|
test("createComboSchema coerces string numbers for maxSetRetries and setRetryDelayMs", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "coerce-test",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: {
|
|
maxSetRetries: "2",
|
|
setRetryDelayMs: "500",
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.maxSetRetries, 2);
|
|
assert.equal(parsed.config.setRetryDelayMs, 500);
|
|
});
|
|
|
|
test("createComboSchema rejects maxSetRetries out of range", () => {
|
|
const tooHigh = createComboSchema.safeParse({
|
|
name: "bad-max",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: { maxSetRetries: 11 },
|
|
});
|
|
assert.equal(tooHigh.success, false);
|
|
|
|
const negative = createComboSchema.safeParse({
|
|
name: "bad-max",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: { maxSetRetries: -1 },
|
|
});
|
|
assert.equal(negative.success, false);
|
|
});
|
|
|
|
test("createComboSchema rejects setRetryDelayMs out of range", () => {
|
|
const tooHigh = createComboSchema.safeParse({
|
|
name: "bad-delay",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: { setRetryDelayMs: 60001 },
|
|
});
|
|
assert.equal(tooHigh.success, false);
|
|
|
|
const negative = createComboSchema.safeParse({
|
|
name: "bad-delay",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "priority",
|
|
config: { setRetryDelayMs: -1 },
|
|
});
|
|
assert.equal(negative.success, false);
|
|
});
|
|
|
|
test("resolveComboConfig cascades nestedComboMode", () => {
|
|
const result = resolveComboConfig(
|
|
{ config: { nestedComboMode: "execute" } },
|
|
{ comboDefaults: { nestedComboMode: "flatten" } }
|
|
);
|
|
assert.equal(result.nestedComboMode, "execute");
|
|
|
|
const defaulted = resolveComboConfig({ config: {} }, { comboDefaults: {} });
|
|
assert.equal(defaulted.nestedComboMode, "flatten");
|
|
});
|
|
|
|
test("resolveComboConfig cascades failoverBeforeRetry, maxSetRetries and setRetryDelayMs", () => {
|
|
const result = resolveComboConfig(
|
|
{
|
|
config: {
|
|
failoverBeforeRetry: true,
|
|
maxSetRetries: 2,
|
|
setRetryDelayMs: 3000,
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
failoverBeforeRetry: false,
|
|
maxSetRetries: 0,
|
|
setRetryDelayMs: 2000,
|
|
},
|
|
}
|
|
);
|
|
|
|
assert.equal(result.failoverBeforeRetry, true);
|
|
assert.equal(result.maxSetRetries, 2);
|
|
assert.equal(result.setRetryDelayMs, 3000);
|
|
});
|
|
|
|
// Issue #3872: combo round-robin always queued ~20 deep before cascading on
|
|
// semaphore saturation because handleRoundRobinCombo never threaded a queue depth
|
|
// into accountSemaphore.acquire (it fell back to the hardcoded DEFAULT_MAX_QUEUE_SIZE
|
|
// of 20). Expose `queueDepth` as combo config so operators can shrink the pre-cascade
|
|
// queue (0 = fail over immediately) for faster failover, while keeping 20 as the
|
|
// backward-compatible default.
|
|
test("getDefaultComboConfig exposes the backward-compatible queueDepth default of 20", () => {
|
|
assert.equal(getDefaultComboConfig().queueDepth, 20);
|
|
});
|
|
|
|
test("resolveComboConfig cascades queueDepth from defaults through provider and combo overrides", () => {
|
|
const fromDefault = resolveComboConfig({ config: {} }, { comboDefaults: {} });
|
|
assert.equal(fromDefault.queueDepth, 20);
|
|
|
|
const cascaded = resolveComboConfig(
|
|
{
|
|
config: {
|
|
queueDepth: 1,
|
|
},
|
|
},
|
|
{
|
|
comboDefaults: {
|
|
queueDepth: 10,
|
|
},
|
|
providerOverrides: {
|
|
openai: {
|
|
queueDepth: 5,
|
|
},
|
|
},
|
|
},
|
|
"openai"
|
|
);
|
|
|
|
// Most specific (combo.config) wins over provider override and global default.
|
|
assert.equal(cascaded.queueDepth, 1);
|
|
});
|
|
|
|
test("resolveComboQueueDepth defaults to 20, honors configured values, and clamps the range", () => {
|
|
assert.equal(resolveComboQueueDepth(null), 20);
|
|
assert.equal(resolveComboQueueDepth({}), 20);
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: 5 }), 5);
|
|
// 0 is a valid, meaningful value: queue nothing → fail over to the next member immediately.
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: 0 }), 0);
|
|
// Invalid / negative inputs fall back to the safe default.
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: -3 }), 20);
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: Number.NaN }), 20);
|
|
// Out-of-range high values are clamped, not trusted.
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: 99999 }), 100);
|
|
// Fractional values floor to an integer queue slot count.
|
|
assert.equal(resolveComboQueueDepth({ queueDepth: 3.9 }), 3);
|
|
});
|
|
|
|
test("createComboSchema accepts queueDepth, coerces strings, and allows 0 for immediate failover", () => {
|
|
const parsed = createComboSchema.parse({
|
|
name: "fast-failover",
|
|
models: ["openai/gpt-4o-mini", "anthropic/claude-3-haiku"],
|
|
strategy: "round-robin",
|
|
config: {
|
|
queueDepth: "0",
|
|
},
|
|
});
|
|
|
|
assert.equal(parsed.config.queueDepth, 0);
|
|
});
|
|
|
|
test("createComboSchema rejects queueDepth outside the supported range", () => {
|
|
const tooHigh = createComboSchema.safeParse({
|
|
name: "bad-queue-depth-high",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "round-robin",
|
|
config: { queueDepth: 101 },
|
|
});
|
|
assert.equal(tooHigh.success, false);
|
|
|
|
const negative = createComboSchema.safeParse({
|
|
name: "bad-queue-depth-negative",
|
|
models: ["openai/gpt-4"],
|
|
strategy: "round-robin",
|
|
config: { queueDepth: -1 },
|
|
});
|
|
assert.equal(negative.success, false);
|
|
});
|
|
|
|
// ─── Fusion strategy config (judgeModel + fusionTuning) ──────────────────
|
|
// Backs the dashboard combo-editor Fusion fields (judge model + tuning). The
|
|
// editor only writes these; the backend (open-sse/services/fusion.ts) reads
|
|
// config.judgeModel / config.fusionTuning. The schema must accept + bound them.
|
|
|
|
test("createComboSchema accepts judgeModel and fusionTuning for a fusion combo", () => {
|
|
const result = createComboSchema.safeParse({
|
|
name: "fusion-panel",
|
|
models: ["cc/claude-opus-4-7", "cx/gpt-5.5", "glm/glm-5.1"],
|
|
strategy: "fusion",
|
|
config: {
|
|
judgeModel: "cc/claude-opus-4-7",
|
|
fusionTuning: { minPanel: 2, stragglerGraceMs: 8000, panelHardTimeoutMs: 90000 },
|
|
},
|
|
});
|
|
assert.equal(result.success, true);
|
|
assert.equal(result.data.config.judgeModel, "cc/claude-opus-4-7");
|
|
assert.deepEqual(result.data.config.fusionTuning, {
|
|
minPanel: 2,
|
|
stragglerGraceMs: 8000,
|
|
panelHardTimeoutMs: 90000,
|
|
});
|
|
});
|
|
|
|
test("createComboSchema accepts a fusion combo with no fusion config (defaults apply at runtime)", () => {
|
|
const result = createComboSchema.safeParse({
|
|
name: "fusion-bare",
|
|
models: ["cc/claude-opus-4-7", "cx/gpt-5.5"],
|
|
strategy: "fusion",
|
|
config: {},
|
|
});
|
|
assert.equal(result.success, true);
|
|
});
|
|
|
|
test("createComboSchema coerces numeric-string fusionTuning values", () => {
|
|
const result = createComboSchema.safeParse({
|
|
name: "fusion-coerce",
|
|
models: ["a/m1", "b/m2"],
|
|
strategy: "fusion",
|
|
config: { fusionTuning: { minPanel: "3", stragglerGraceMs: "5000" } },
|
|
});
|
|
assert.equal(result.success, true);
|
|
assert.equal(result.data.config.fusionTuning.minPanel, 3);
|
|
assert.equal(result.data.config.fusionTuning.stragglerGraceMs, 5000);
|
|
});
|
|
|
|
test("createComboSchema rejects out-of-range fusionTuning values", () => {
|
|
const minPanelTooHigh = createComboSchema.safeParse({
|
|
name: "fusion-bad-minpanel",
|
|
models: ["a/m1", "b/m2"],
|
|
strategy: "fusion",
|
|
config: { fusionTuning: { minPanel: 51 } },
|
|
});
|
|
assert.equal(minPanelTooHigh.success, false);
|
|
|
|
const graceNegative = createComboSchema.safeParse({
|
|
name: "fusion-bad-grace",
|
|
models: ["a/m1", "b/m2"],
|
|
strategy: "fusion",
|
|
config: { fusionTuning: { stragglerGraceMs: -1 } },
|
|
});
|
|
assert.equal(graceNegative.success, false);
|
|
|
|
const hardTimeoutTooLow = createComboSchema.safeParse({
|
|
name: "fusion-bad-hardtimeout",
|
|
models: ["a/m1", "b/m2"],
|
|
strategy: "fusion",
|
|
config: { fusionTuning: { panelHardTimeoutMs: 500 } },
|
|
});
|
|
assert.equal(hardTimeoutTooLow.success, false);
|
|
});
|
|
|
|
test("createComboSchema rejects unknown keys inside fusionTuning (strict object)", () => {
|
|
const result = createComboSchema.safeParse({
|
|
name: "fusion-unknown-key",
|
|
models: ["a/m1", "b/m2"],
|
|
strategy: "fusion",
|
|
config: { fusionTuning: { minPanel: 2, bogusKey: 1 } },
|
|
});
|
|
assert.equal(result.success, false);
|
|
});
|