mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-05 06:42:12 +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>
690 lines
23 KiB
TypeScript
690 lines
23 KiB
TypeScript
/**
|
|
* Combo structure resolution extracted from combo.ts.
|
|
*
|
|
* Runtime-step normalization, nested-combo / DAG expansion, weighted/direct
|
|
* target resolution, and request-compatibility filtering moved out of the
|
|
* combo.ts god-file (Quality Gate v2 / Fase 9). Logic unchanged; the public
|
|
* entry points (resolveComboTargets, resolveNestedComboTargets, getComboFromData,
|
|
* getComboModelsFromData, validateComboDAG, resolveNestedComboModels,
|
|
* filterTargetsByRequestCompatibility) are re-exported from combo.ts for the
|
|
* ~20 external consumers (chatCore.ts, the /api/combos routes, embeddings, etc.).
|
|
* No barrel import — depends only on sibling leaves.
|
|
*/
|
|
|
|
import { getModelContextLimit } from "../../../src/lib/modelCapabilities";
|
|
import { getComboModelString, normalizeComboStep } from "../../../src/lib/combos/steps.ts";
|
|
import { estimateTokens } from "../contextManager.ts";
|
|
import { getResolvedModelCapabilities } from "../modelCapabilities.ts";
|
|
import { parseModel } from "../model.ts";
|
|
import { dedupeTargetsByExecutionKey, isRecord } from "./comboData.ts";
|
|
import { getTargetProvider, MAX_COMBO_DEPTH } from "./comboPredicates.ts";
|
|
import {
|
|
normalizeModelEntry,
|
|
orderTargetsForWeightedFallback,
|
|
selectWeightedTarget,
|
|
} from "./targetSorters.ts";
|
|
import type {
|
|
ComboCollectionLike,
|
|
ComboInput,
|
|
ComboLike,
|
|
ComboLogger,
|
|
ComboRuntimeStep,
|
|
NestedComboMode,
|
|
ResolvedComboTarget,
|
|
ResolvedComboUnit,
|
|
} from "./types.ts";
|
|
|
|
function toTrimmedString(value: unknown): string | null {
|
|
return typeof value === "string" && value.trim().length > 0 ? value.trim() : null;
|
|
}
|
|
|
|
function toComboLike(combo: ComboInput): ComboLike {
|
|
return {
|
|
...combo,
|
|
id: toTrimmedString(combo.id) || undefined,
|
|
name: toTrimmedString(combo.name) || "",
|
|
models: Array.isArray(combo.models) ? combo.models : [],
|
|
config: isRecord(combo.config) ? combo.config : null,
|
|
autoConfig: isRecord(combo.autoConfig) ? combo.autoConfig : null,
|
|
context_cache_protection:
|
|
typeof combo.context_cache_protection === "boolean" ||
|
|
typeof combo.context_cache_protection === "number"
|
|
? combo.context_cache_protection
|
|
: undefined,
|
|
system_message: typeof combo.system_message === "string" ? combo.system_message : null,
|
|
};
|
|
}
|
|
|
|
function getCombosArray(allCombos: ComboCollectionLike): ComboLike[] {
|
|
const combos = Array.isArray(allCombos) ? allCombos : allCombos?.combos || [];
|
|
return combos.map((combo) => toComboLike(combo));
|
|
}
|
|
|
|
function buildExecutionKey(path: string[], stepId: string): string {
|
|
return [...path, stepId].join(">");
|
|
}
|
|
|
|
function normalizeRuntimeStep(
|
|
entry: unknown,
|
|
comboName: string,
|
|
index: number,
|
|
allCombos: ComboCollectionLike,
|
|
path: string[] = []
|
|
): ComboRuntimeStep | null {
|
|
const step = normalizeComboStep(entry, {
|
|
comboName,
|
|
index,
|
|
allCombos,
|
|
});
|
|
if (!step) return null;
|
|
|
|
const executionKey = buildExecutionKey(path, step.id);
|
|
const label = typeof step.label === "string" ? step.label : null;
|
|
const weight = step.weight || 0;
|
|
|
|
if (step.kind === "combo-ref") {
|
|
return {
|
|
kind: "combo-ref",
|
|
stepId: step.id,
|
|
executionKey,
|
|
comboName: step.comboName,
|
|
weight,
|
|
label,
|
|
};
|
|
}
|
|
|
|
const modelStr = getComboModelString(step);
|
|
if (!modelStr) return null;
|
|
|
|
return {
|
|
kind: "model",
|
|
stepId: step.id,
|
|
executionKey,
|
|
modelStr,
|
|
provider: getTargetProvider(modelStr, step.providerId),
|
|
providerId: step.providerId || null,
|
|
connectionId: step.connectionId || null,
|
|
// #3266: a per-step account allowlist scopes round-robin/weighted selection
|
|
// to a subset of the provider's connections. This is the second writer of
|
|
// `allowedConnectionIds` (tag routing is the first); both feed the existing
|
|
// credential-selection filter in auth.ts.
|
|
...(Array.isArray(step.allowedConnectionIds) && step.allowedConnectionIds.length > 0
|
|
? { allowedConnectionIds: step.allowedConnectionIds }
|
|
: {}),
|
|
weight,
|
|
label,
|
|
} satisfies ResolvedComboTarget;
|
|
}
|
|
|
|
function getDirectComboTargets(combo: ComboLike): ResolvedComboTarget[] {
|
|
return getOrderedTopLevelRuntimeSteps(combo, null).filter(
|
|
(entry): entry is ResolvedComboTarget => entry?.kind === "model"
|
|
);
|
|
}
|
|
|
|
function getTopLevelRuntimeSteps(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
path: string[] = []
|
|
): ComboRuntimeStep[] {
|
|
return (combo.models || [])
|
|
.map((entry, index) => normalizeRuntimeStep(entry, combo.name, index, allCombos, path))
|
|
.filter((entry): entry is ComboRuntimeStep => entry !== null);
|
|
}
|
|
|
|
function getCompositeTierStepOrder(combo: ComboLike): string[] {
|
|
const compositeTiers = isRecord(combo?.config) ? combo.config.compositeTiers : null;
|
|
if (!isRecord(compositeTiers)) return [];
|
|
|
|
const defaultTier = toTrimmedString(compositeTiers.defaultTier);
|
|
const tiers = isRecord(compositeTiers.tiers) ? compositeTiers.tiers : null;
|
|
if (!defaultTier || !tiers) return [];
|
|
|
|
const orderedStepIds: string[] = [];
|
|
const visitedTiers = new Set<string>();
|
|
const seenStepIds = new Set<string>();
|
|
type CompositeTierEntry = readonly [
|
|
string,
|
|
{ readonly stepId: string; readonly fallbackTier: string | null },
|
|
];
|
|
const tierEntries = new Map(
|
|
Object.entries(tiers)
|
|
.map(([tierName, rawTier]) => {
|
|
if (!isRecord(rawTier)) return null;
|
|
const normalizedTierName = toTrimmedString(tierName);
|
|
const stepId = toTrimmedString(rawTier.stepId);
|
|
const fallbackTier = toTrimmedString(rawTier.fallbackTier);
|
|
if (!normalizedTierName || !stepId) return null;
|
|
return [normalizedTierName, { stepId, fallbackTier }] as const;
|
|
})
|
|
.filter((entry): entry is CompositeTierEntry => entry !== null)
|
|
);
|
|
|
|
let currentTier: string | null = defaultTier;
|
|
while (currentTier && tierEntries.has(currentTier) && !visitedTiers.has(currentTier)) {
|
|
visitedTiers.add(currentTier);
|
|
const entry = tierEntries.get(currentTier);
|
|
if (!entry) break;
|
|
if (!seenStepIds.has(entry.stepId)) {
|
|
orderedStepIds.push(entry.stepId);
|
|
seenStepIds.add(entry.stepId);
|
|
}
|
|
currentTier = entry.fallbackTier;
|
|
}
|
|
|
|
for (const entry of tierEntries.values()) {
|
|
if (!seenStepIds.has(entry.stepId)) {
|
|
orderedStepIds.push(entry.stepId);
|
|
seenStepIds.add(entry.stepId);
|
|
}
|
|
}
|
|
|
|
return orderedStepIds;
|
|
}
|
|
|
|
function hasCompositeTierRuntimeOrder(combo: ComboLike): boolean {
|
|
return getCompositeTierStepOrder(combo).length > 0;
|
|
}
|
|
|
|
function orderRuntimeStepsByCompositeTiers(
|
|
steps: ComboRuntimeStep[],
|
|
combo: ComboLike
|
|
): ComboRuntimeStep[] {
|
|
const orderedStepIds = getCompositeTierStepOrder(combo);
|
|
if (orderedStepIds.length === 0) return steps;
|
|
|
|
const byStepId = new Map(steps.map((step) => [step.stepId, step]));
|
|
const seen = new Set<string>();
|
|
const ordered: ComboRuntimeStep[] = [];
|
|
|
|
for (const stepId of orderedStepIds) {
|
|
const step = byStepId.get(stepId);
|
|
if (!step || seen.has(step.stepId)) continue;
|
|
ordered.push(step);
|
|
seen.add(step.stepId);
|
|
}
|
|
|
|
for (const step of steps) {
|
|
if (seen.has(step.stepId)) continue;
|
|
ordered.push(step);
|
|
seen.add(step.stepId);
|
|
}
|
|
|
|
return ordered;
|
|
}
|
|
|
|
function getOrderedTopLevelRuntimeSteps(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
path: string[] = []
|
|
): ComboRuntimeStep[] {
|
|
return orderRuntimeStepsByCompositeTiers(getTopLevelRuntimeSteps(combo, allCombos, path), combo);
|
|
}
|
|
|
|
function expandRuntimeStep(
|
|
step: ComboRuntimeStep,
|
|
allCombos: ComboCollectionLike,
|
|
visited = new Set<string>(),
|
|
depth = 0,
|
|
path: string[] = [],
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): ResolvedComboTarget[] {
|
|
if (step.kind === "model") return [step];
|
|
if (depth > maxDepth) return [];
|
|
|
|
const combos = getCombosArray(allCombos);
|
|
const nestedCombo = combos.find((combo) => combo.name === step.comboName);
|
|
if (!nestedCombo || visited.has(step.comboName)) return [];
|
|
|
|
return resolveNestedComboTargets(
|
|
nestedCombo,
|
|
combos,
|
|
new Set(visited),
|
|
depth + 1,
|
|
[...path, step.stepId],
|
|
maxDepth
|
|
);
|
|
}
|
|
|
|
export function resolveNestedComboTargets(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
visited = new Set<string>(),
|
|
depth = 0,
|
|
path: string[] = [],
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): ResolvedComboTarget[] {
|
|
const directTargets = (combo.models || [])
|
|
.map((entry, index) => normalizeRuntimeStep(entry, combo.name, index, null, path))
|
|
.filter((entry): entry is ResolvedComboTarget => entry?.kind === "model");
|
|
|
|
if (depth > maxDepth) return directTargets;
|
|
if (visited.has(combo.name)) return [];
|
|
visited.add(combo.name);
|
|
|
|
const runtimeSteps = getOrderedTopLevelRuntimeSteps(combo, allCombos, path);
|
|
const resolved: ResolvedComboTarget[] = [];
|
|
|
|
for (const step of runtimeSteps) {
|
|
if (step.kind === "combo-ref") {
|
|
resolved.push(...expandRuntimeStep(step, allCombos, new Set(visited), depth, path, maxDepth));
|
|
continue;
|
|
}
|
|
resolved.push(step);
|
|
}
|
|
|
|
return resolved;
|
|
}
|
|
|
|
/**
|
|
* Get combo models from combos data (for open-sse standalone use)
|
|
* @param {string} modelStr - Model string to check
|
|
* @param {Array|Object} combosData - Array of combos or object with combos
|
|
* @returns {Object|null} Full combo object or null if not a combo
|
|
*/
|
|
export function getComboFromData(
|
|
modelStr: string,
|
|
combosData: ComboCollectionLike
|
|
): ComboLike | null {
|
|
const combos = getCombosArray(combosData);
|
|
const combo = combos.find((c) => c.name === modelStr);
|
|
if (combo?.models && combo.models.length > 0) {
|
|
return combo;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* Legacy: Get combo models as string array (backward compat)
|
|
*/
|
|
export function getComboModelsFromData(
|
|
modelStr: string,
|
|
combosData: ComboCollectionLike
|
|
): string[] | null {
|
|
const combo = getComboFromData(modelStr, combosData);
|
|
if (!combo) return null;
|
|
return combo.models.map((m) => normalizeModelEntry(m).model);
|
|
}
|
|
|
|
/**
|
|
* Validate combo DAG — detect circular references and enforce max depth
|
|
* @param {string} comboName - Name of the combo to validate
|
|
* @param {Array} allCombos - All combos in the system
|
|
* @param {Set} [visited] - Set of already visited combo names (for cycle detection)
|
|
* @param {number} [depth] - Current depth level
|
|
* @throws {Error} If circular reference or max depth exceeded
|
|
*/
|
|
export function validateComboDAG(
|
|
comboName: string,
|
|
allCombos: ComboCollectionLike,
|
|
visited = new Set<string>(),
|
|
depth = 0,
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): void {
|
|
if (depth > maxDepth) {
|
|
throw new Error(`Max combo nesting depth (${maxDepth}) exceeded at "${comboName}"`);
|
|
}
|
|
if (visited.has(comboName)) {
|
|
throw new Error(`Circular combo reference detected: ${comboName}`);
|
|
}
|
|
visited.add(comboName);
|
|
|
|
const combos = getCombosArray(allCombos);
|
|
const combo = combos.find((c) => c.name === comboName);
|
|
if (!combo?.models) return;
|
|
|
|
for (const entry of combo.models) {
|
|
const modelName = normalizeModelEntry(entry).model;
|
|
// Check if this model name is itself a combo (not a provider/model pattern)
|
|
const nestedCombo = combos.find((c) => c.name === modelName);
|
|
if (nestedCombo) {
|
|
validateComboDAG(modelName, combos, new Set(visited), depth + 1, maxDepth);
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Resolve nested combos by expanding inline to a flat model list
|
|
* Respects max depth and detects cycles
|
|
* @param {Object} combo - The combo object
|
|
* @param {Array} allCombos - All combos in the system
|
|
* @param {Set} [visited] - For cycle detection
|
|
* @param {number} [depth] - Current depth
|
|
* @returns {Array} Flat array of model strings
|
|
*/
|
|
export function resolveNestedComboModels(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
visited = new Set<string>(),
|
|
depth = 0,
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): string[] {
|
|
if (depth > maxDepth) return combo.models.map((m) => normalizeModelEntry(m).model);
|
|
if (visited.has(combo.name)) return []; // cycle safety
|
|
visited.add(combo.name);
|
|
|
|
const combos = getCombosArray(allCombos);
|
|
const resolved: string[] = [];
|
|
|
|
for (const entry of combo.models || []) {
|
|
const modelName = normalizeModelEntry(entry).model;
|
|
const nestedCombo = combos.find((c) => c.name === modelName);
|
|
|
|
if (nestedCombo) {
|
|
// Recursively expand the nested combo
|
|
const nested = resolveNestedComboModels(
|
|
nestedCombo,
|
|
combos,
|
|
new Set(visited),
|
|
depth + 1,
|
|
maxDepth
|
|
);
|
|
resolved.push(...nested);
|
|
} else {
|
|
resolved.push(modelName);
|
|
}
|
|
}
|
|
|
|
return resolved;
|
|
}
|
|
|
|
/**
|
|
* Sort models by context window size (largest first) for context-optimized strategy.
|
|
* Uses models.dev synced capabilities to get context limits.
|
|
* @param {Array<string>} models - Model strings in "provider/model" format
|
|
* @returns {Array<string>} Sorted model strings (largest context first)
|
|
*/
|
|
function sortModelsByContextSize(models: string[]): string[] {
|
|
const withContext = models.map((modelStr) => {
|
|
return { modelStr, context: getModelContextLimitForModelString(modelStr) ?? 0 };
|
|
});
|
|
withContext.sort((a, b) => b.context - a.context);
|
|
return withContext.map((e) => e.modelStr);
|
|
}
|
|
|
|
export function getModelContextLimitForModelString(modelStr: string) {
|
|
const parsed = parseModel(modelStr);
|
|
const provider = parsed.provider || parsed.providerAlias || "unknown";
|
|
const model = parsed.model || modelStr;
|
|
return getModelContextLimit(provider, model);
|
|
}
|
|
|
|
type RequestCompatibilityRequirements = {
|
|
requiresTools: boolean;
|
|
requiresVision: boolean;
|
|
requiresStructuredOutput: boolean;
|
|
estimatedInputTokens: number;
|
|
requestedOutputTokens: number;
|
|
requiredContextTokens: number;
|
|
};
|
|
|
|
function getPositiveTokenCount(value: unknown): number {
|
|
const count = Number(value);
|
|
return Number.isFinite(count) && count > 0 ? Math.ceil(count) : 0;
|
|
}
|
|
|
|
function requestRequiresTools(body: Record<string, unknown>): boolean {
|
|
if (Array.isArray(body.tools) && body.tools.length > 0) return true;
|
|
if (Array.isArray(body.functions) && body.functions.length > 0) return true;
|
|
return false;
|
|
}
|
|
|
|
function requestRequiresStructuredOutput(body: Record<string, unknown>): boolean {
|
|
const responseFormat = isRecord(body.response_format) ? body.response_format : null;
|
|
const type = typeof responseFormat?.type === "string" ? responseFormat.type : null;
|
|
return type === "json_object" || type === "json_schema";
|
|
}
|
|
|
|
function estimateRequestInputTokens(body: Record<string, unknown>): number {
|
|
const estimatePayload: Record<string, unknown> = {};
|
|
for (const key of ["messages", "input", "tools", "functions", "response_format"]) {
|
|
if (body[key] !== undefined) estimatePayload[key] = body[key];
|
|
}
|
|
return Object.keys(estimatePayload).length > 0 ? estimateTokens(estimatePayload) : 0;
|
|
}
|
|
|
|
function valueContainsImagePart(value: unknown, depth = 0): boolean {
|
|
if (depth > 8 || value === null || value === undefined) return false;
|
|
if (typeof value === "string") return value.startsWith("data:image/");
|
|
if (Array.isArray(value)) return value.some((entry) => valueContainsImagePart(entry, depth + 1));
|
|
if (!isRecord(value)) return false;
|
|
|
|
const type = typeof value.type === "string" ? value.type.toLowerCase() : null;
|
|
if (type === "image" || type === "image_url" || type === "input_image") return true;
|
|
if ("image_url" in value || "input_image" in value) return true;
|
|
|
|
const source = isRecord(value.source) ? value.source : null;
|
|
const mediaType = typeof source?.media_type === "string" ? source.media_type.toLowerCase() : "";
|
|
if (mediaType.startsWith("image/")) return true;
|
|
|
|
return Object.values(value).some((entry) => valueContainsImagePart(entry, depth + 1));
|
|
}
|
|
|
|
function deriveRequestCompatibilityRequirements(
|
|
body: Record<string, unknown>
|
|
): RequestCompatibilityRequirements {
|
|
const estimatedInputTokens = estimateRequestInputTokens(body);
|
|
const requestedOutputTokens = Math.max(
|
|
getPositiveTokenCount(body.max_tokens),
|
|
getPositiveTokenCount(body.max_completion_tokens)
|
|
);
|
|
return {
|
|
requiresTools: requestRequiresTools(body),
|
|
requiresVision: valueContainsImagePart(body.messages) || valueContainsImagePart(body.input),
|
|
requiresStructuredOutput: requestRequiresStructuredOutput(body),
|
|
estimatedInputTokens,
|
|
requestedOutputTokens,
|
|
requiredContextTokens: estimatedInputTokens + requestedOutputTokens,
|
|
};
|
|
}
|
|
|
|
function exceedsKnownOutputLimit(
|
|
requestedOutputTokens: number,
|
|
maxOutputTokens: number | null
|
|
): boolean {
|
|
if (requestedOutputTokens <= 0 || maxOutputTokens === null) return false;
|
|
return maxOutputTokens < requestedOutputTokens;
|
|
}
|
|
|
|
function getTargetCompatibilityFailures(
|
|
target: ResolvedComboTarget,
|
|
requirements: RequestCompatibilityRequirements
|
|
): string[] {
|
|
const capabilities = getResolvedModelCapabilities(target.modelStr);
|
|
const failures: string[] = [];
|
|
|
|
if (
|
|
requirements.requiresTools &&
|
|
(capabilities.supportsTools === false || !capabilities.toolCalling)
|
|
) {
|
|
failures.push("tools");
|
|
}
|
|
|
|
// For a request that carries an image, only route to a target whose vision
|
|
// support is *confirmed* (`=== true`). Treat `false` AND `null` (unknown) as
|
|
// incompatible: an unknown-capability model receiving the image is exactly how
|
|
// a text-only model (e.g. ministral) ended up answering "image not provided".
|
|
// The caller keeps all targets when none qualify, so combos with no
|
|
// confirmed-vision member still behave as before.
|
|
if (requirements.requiresVision && capabilities.supportsVision !== true) {
|
|
failures.push("vision");
|
|
}
|
|
|
|
if (requirements.requiresStructuredOutput && capabilities.structuredOutput === false) {
|
|
failures.push("structured_output");
|
|
}
|
|
|
|
if (exceedsKnownOutputLimit(requirements.requestedOutputTokens, capabilities.maxOutputTokens)) {
|
|
failures.push("output_tokens");
|
|
}
|
|
|
|
const contextLimit = capabilities.maxInputTokens ?? capabilities.contextWindow ?? null;
|
|
if (
|
|
requirements.requiredContextTokens > 0 &&
|
|
contextLimit !== null &&
|
|
contextLimit !== undefined &&
|
|
contextLimit < requirements.requiredContextTokens
|
|
) {
|
|
failures.push("context_window");
|
|
}
|
|
|
|
return failures;
|
|
}
|
|
|
|
export function filterTargetsByRequestCompatibility(
|
|
targets: ResolvedComboTarget[],
|
|
body: Record<string, unknown>,
|
|
log: ComboLogger,
|
|
label = "Context-aware fallback"
|
|
): ResolvedComboTarget[] {
|
|
if (targets.length === 0) return targets;
|
|
const requirements = deriveRequestCompatibilityRequirements(body);
|
|
const needsFiltering =
|
|
requirements.requiresTools ||
|
|
requirements.requiresVision ||
|
|
requirements.requiresStructuredOutput ||
|
|
requirements.requiredContextTokens > 0;
|
|
if (!needsFiltering) return targets;
|
|
|
|
const rejected: Array<{ target: ResolvedComboTarget; reasons: string[] }> = [];
|
|
const compatible = targets.filter((target) => {
|
|
const reasons = getTargetCompatibilityFailures(target, requirements);
|
|
if (reasons.length === 0) return true;
|
|
rejected.push({ target, reasons });
|
|
return false;
|
|
});
|
|
|
|
if (compatible.length === targets.length) return targets;
|
|
if (compatible.length === 0) {
|
|
log.warn(
|
|
"COMBO",
|
|
`${label}: all ${targets.length} targets were filtered by request requirements; preserving strategy order`
|
|
);
|
|
log.debug?.(
|
|
"COMBO",
|
|
`${label}: rejected targets ${rejected
|
|
.map((entry) => `${entry.target.modelStr}(${entry.reasons.join("+")})`)
|
|
.join(", ")}`
|
|
);
|
|
return targets;
|
|
}
|
|
|
|
log.info(
|
|
"COMBO",
|
|
`${label}: kept ${compatible.length}/${targets.length} targets for request requirements`
|
|
);
|
|
log.debug?.(
|
|
"COMBO",
|
|
`${label}: rejected targets ${rejected
|
|
.map((entry) => `${entry.target.modelStr}(${entry.reasons.join("+")})`)
|
|
.join(", ")}`
|
|
);
|
|
return compatible;
|
|
}
|
|
|
|
export function sortTargetsByContextSize(targets: ResolvedComboTarget[]) {
|
|
const hasKnownContext = targets.some(
|
|
(target) => getModelContextLimitForModelString(target.modelStr) != null
|
|
);
|
|
if (!hasKnownContext) return targets;
|
|
|
|
const orderedModels = sortModelsByContextSize(targets.map((target) => target.modelStr));
|
|
const byModel = new Map<string, ResolvedComboTarget[]>();
|
|
for (const target of targets) {
|
|
const queue = byModel.get(target.modelStr) || [];
|
|
queue.push(target);
|
|
byModel.set(target.modelStr, queue);
|
|
}
|
|
return orderedModels
|
|
.map((modelStr) => {
|
|
const queue = byModel.get(modelStr);
|
|
return queue?.shift() || null;
|
|
})
|
|
.filter((target): target is ResolvedComboTarget => target !== null);
|
|
}
|
|
|
|
export function resolveComboTargets(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): ResolvedComboTarget[] {
|
|
return allCombos
|
|
? resolveNestedComboTargets(combo, allCombos, new Set<string>(), 0, [], maxDepth)
|
|
: getDirectComboTargets(combo);
|
|
}
|
|
|
|
export function resolveComboRuntimeUnits(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
mode: NestedComboMode,
|
|
maxDepth: number = MAX_COMBO_DEPTH
|
|
): ResolvedComboUnit[] {
|
|
if (mode === "flatten" || !allCombos) return resolveComboTargets(combo, allCombos, maxDepth);
|
|
validateComboDAG(combo.name, allCombos, new Set<string>(), 0, maxDepth);
|
|
return getOrderedTopLevelRuntimeSteps(combo, allCombos);
|
|
}
|
|
|
|
export function resolveWeightedStepGroups(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike
|
|
): Array<{ step: ComboRuntimeStep; targets: ResolvedComboTarget[] }> {
|
|
return getOrderedTopLevelRuntimeSteps(combo, allCombos)
|
|
.map((step) => ({
|
|
step,
|
|
targets: !allCombos
|
|
? step.kind === "model"
|
|
? [step]
|
|
: []
|
|
: expandRuntimeStep(step, allCombos, new Set([combo.name])),
|
|
}))
|
|
.filter((group) => group.targets.length > 0);
|
|
}
|
|
|
|
export function resolveWeightedTargets(
|
|
combo: ComboLike,
|
|
allCombos: ComboCollectionLike,
|
|
preferredExecutionKey: string | null = null,
|
|
eligibleExecutionKeys: ReadonlySet<string> | null = null,
|
|
stepGroups?: Array<{ step: ComboRuntimeStep; targets: ResolvedComboTarget[] }>
|
|
): {
|
|
orderedTargets: ResolvedComboTarget[];
|
|
selectedStep: ComboRuntimeStep | null;
|
|
orderedSteps: ComboRuntimeStep[];
|
|
} {
|
|
const topLevelSteps = getOrderedTopLevelRuntimeSteps(combo, allCombos).filter((step) =>
|
|
eligibleExecutionKeys ? eligibleExecutionKeys.has(step.executionKey) : true
|
|
);
|
|
if (topLevelSteps.length === 0) {
|
|
return { orderedTargets: [], selectedStep: null, orderedSteps: [] };
|
|
}
|
|
|
|
const preferredStep = preferredExecutionKey
|
|
? topLevelSteps.find((step) => step.executionKey === preferredExecutionKey) || null
|
|
: null;
|
|
const selectedStep = preferredStep || selectWeightedTarget(topLevelSteps);
|
|
if (!selectedStep) {
|
|
return { orderedTargets: [], selectedStep: null, orderedSteps: [] };
|
|
}
|
|
|
|
const orderedSteps = orderTargetsForWeightedFallback(
|
|
topLevelSteps,
|
|
selectedStep.executionKey,
|
|
hasCompositeTierRuntimeOrder(combo)
|
|
);
|
|
const targetsByStep = new Map(
|
|
(stepGroups || resolveWeightedStepGroups(combo, allCombos)).map((group) => [
|
|
group.step.executionKey,
|
|
group.targets,
|
|
])
|
|
);
|
|
const expandedTargets = orderedSteps.flatMap(
|
|
(step) => targetsByStep.get(step.executionKey) || []
|
|
);
|
|
|
|
return {
|
|
orderedTargets: dedupeTargetsByExecutionKey(expandedTargets),
|
|
selectedStep,
|
|
orderedSteps,
|
|
};
|
|
}
|