mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
* chore(release): open v3.8.34 development cycle * chore(quality): release-green pre-flight validator + nightly signal (C+D) (#4622) C — scripts/quality/validate-release-green.mjs (npm run check:release-green): reproduces the release-equivalent validation (typecheck, eslint, db-rules, public-creds, full unit, vitest, ratchets, optional --with-build package-artifact) against the current working tree and classifies each red as HARD (real defect, exit 1) vs DRIFT (ratchet — reported, never affects exit / never blocks). Pure helpers exported + orchestration behind a direct-run guard; unit-tested. D — .github/workflows/nightly-release-green.yml: runs C on the active release branch nightly (and on workflow_dispatch) and opens/updates a single tracking issue on HARD failures. Never a required check, never touches a contributor PR. Closes the gap where the full gate (ci.yml) only ran on the release PR, so reds accrued silently on release/** and surfaced in 40-min layers at release time. Non-blocking by construction; drift is the maintainer's to rebaseline at release. Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> * fix(providers): show revealed connection API keys (#4583) Integrated into release/v3.8.34 * fix(resilience): respect upstream retry hint toggle (#4585) Integrated into release/v3.8.34 * feat(settings): expose stream recovery feature flags (#4586) Integrated into release/v3.8.34 * fix(logs): make active request stale sweep configurable (#4599) Integrated into release/v3.8.34 * fix(plugin): auto-prefix providerId with 'opencode-' for OC 1.17.8+ native gate (#4527) Integrated into release/v3.8.34 (supersedes #4445) * fix(models): treat unknown output caps as unset (#4584) Integrated into release/v3.8.34 * fix(executors): strip temperature for GitHub Copilot gpt-5.4 family (#4564) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(oauth): update Qwen OAuth URLs from chat.qwen.ai to qwen.ai (#4561) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(api/settings): prevent cached /api/settings responses (port from 9router#951) (#4566) Integrated into release/v3.8.34 (rebuilt onto tip) * feat(audio): MiniMax T2A v2 TTS dispatch in audioSpeech (port #1043) (#4553) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(dashboard): surface manual config CTA when Open Claw CLI auto-detect fails (#4562) Integrated into release/v3.8.34 (rebuilt onto tip) * feat(providers): optional model ID for custom API-key validation (#4555) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(cli): align data dir and env loading with runtime (#4607) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(quota): expose Bailian quota windows (#4610) Integrated into release/v3.8.34 (rebuilt onto tip) * fix: retain provider cooldowns for configured max window (#4588) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix: reject invalid provider cooldown bounds (#4589) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix: preserve production combo metrics on shadow eviction (#4590) Integrated into release/v3.8.34 (rebuilt — bundled commits stripped) * fix(stream): estimate input tokens when upstream reports prompt_tokens=0 (#4615) Integrated into release/v3.8.34 (rebuilt onto tip) * fix(catalog): shorten no-thinking gateway prefix to no-think/ (#4525) Integrated into release/v3.8.34 (rebuilt — kept only the prefix rename, dropped stale-base reverts) * fix(relay): apply IP rate limit to bifrost sidecar (#4593) Integrated into release/v3.8.34 (rebuilt onto tip; merge before #4612) * fix(bifrost): finalize SSE relay usage after stream (#4612) Integrated into release/v3.8.34 (rebuilt + reconciled with #4593) * feat(compression): per-request `x-omniroute-compression` header (Phase 3) (#4645) * docs(compression): Phase 3 per-request header design spec Approved brainstorming output for the x-omniroute-compression header: header-first precedence, name-first combo matching (Decision A), explicit value bypasses auto-trigger (Decision B), DerivedPlan.source, and the X-OmniRoute-Compression response header. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(compression): Phase 3 per-request header implementation plan 4-task TDD plan (resolver header-first + source, parser, chatCore wiring + response header, docs/file-size) with full code and exact commands. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): header-first resolver + plan source (Phase 3 core) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): resolveCompressionHeader parser (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(compression): wire x-omniroute-compression header + response header (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(compression): extract plan-resolution leaf (planResolution.ts) under size cap (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(compression): document x-omniroute-compression header (Phase 3) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(compression): harden named-combo map + trim engine: header id (Phase 3 review) Addresses gemini-code-assist review on #4645: - Extract buildNamedComboLookup (pure) so a blank/whitespace/null combo name contributes only its id key (no '' key, no throw that disables all combos). - Trim the engine:<id> header value so 'engine: rtk' resolves. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix: exclude exhausted connections from auto scoring (#4592) Integrated into release/v3.8.34 (rebuilt + opt-in gate fix) * fix(dashboard): memoize compatible provider groups (#4613) Integrated into release/v3.8.34 (rebuilt + test added) * fix(dashboard): isolate quota widget refresh clock (#4611) Integrated into release/v3.8.34 (rebuilt + jsdom test) * fix(dashboard): gate topology side effects behind widget visibility (#4606) Integrated into release/v3.8.34 (rebuilt + jsdom test) * fix(dashboard): keep play_arrow spinning on provider Test All buttons (#4563) Integrated into release/v3.8.34 (rebuilt onto tip; UI-cosmetic per owner) * fix(db): schedule retention cleanup + fix cleanup table/column names (extracted from #4428) (#4691) Integrated into release/v3.8.34 (cleanup core extracted from #4428, credit @oyi77) * fix(telemetry): back off live-WS event forwarding when the sidecar is unreachable (#4604) (#4687) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(api): serve GET /v1/models/{model} as JSON, not the HTML dashboard (#4674) (#4677) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * feat(opencode): add go deepseek reasoning variants (#4647) Integrated into release/v3.8.34 * fix(executors): robust deepseek-web tool-call parsing and agentic context retention (#4644) Integrated into release/v3.8.34 * fix(cli): authenticate `omniroute logs` and honor active context (#4638) Integrated into release/v3.8.34 (authored by Rahul Sharma, AI co-author trailer stripped per project policy) * fix(proxy): apply pipelining:0 + connections cap to the direct dispatcher (#4580) (#4684) Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> * fix(executors): Firecrawl web_fetch 500 with include_metadata=true (#4692) Integrated into release/v3.8.34 * fix(routing): include all noAuth models in auto-combos + add reka-flash + best-free template (#4621) Integrated into release/v3.8.34 (dead getFirstRegistryModelId dropped, rebuilt onto tip) * fix(dashboard): gate home topology live-WS networking (#4596) (#4618) Integrated into release/v3.8.34 (adapted onto #4606's extracted topology section: default-hidden flip + enabled gate on useLiveDashboard) * fix(cli): align `omniroute` env loading with the runtime data dir (#4597) (#4619) Integrated into release/v3.8.34 (data-dir.mjs refactor reconciled with #4607; loadEnvFile aligned to getDefaultDataDir) * chore(quality): reconcile file-size baseline for #4644 (deepseek-web.ts 1117->1125) (#4695) file-size reconcile for #4644 * Support quota scraping for OpenCode Go and Ollama Cloud (#4642) Integrated into release/v3.8.34 (Ollama Cloud + OpenCode Go dashboard quota scraping; rebuilt onto tip, gates green: typecheck/public-creds/file-size/lint/docs-sync + 31 tests) * feat(executors): land M365 Copilot pure framing + connection helpers (#4042) (#4696) Land M365 pure modules ahead of draft #4400 * deps: bump production + development groups; migrate js-yaml to v5 ESM (#4697) Incorporates Dependabot #4667 + #4668 + js-yaml v5 ESM migration into release/v3.8.34 * fix: noAuth provider validation + kimi executor routing (#4699) Integrated into release/v3.8.34 (noAuth in NOAUTH_PROVIDERS dynamic check + remove misrouted kimi web alias; 9 tests) * refactor(imageGeneration): extract 8 provider families to co-located files (#4609) Integrated into release/v3.8.34 (extraction completed: added missing imports/exports per module, main imports handlers locally; 145 image-gen tests pass, typecheck/cycles/file-size green) * chore(release): v3.8.34 — finalize changelog, rebaseline drift, fix release-green reds - Finalize CHANGELOG [3.8.34] (43 bullets, full contributor attribution) + seed i18n mirrors - Rebaseline inherited cycle drift surfaced by release-green pre-flight: eslint warnings 3900->3907, cognitive-complexity 797->801 (release-finalize touches no prod code; all drift is from this cycle's contributor merges) - fix(providers): keep reka-flash-3 as the Reka provider default. #4621 inserted reka-flash at the head of the model list, silently changing the default from reka-flash-3 (the free-tier model) to reka-flash; reorder so reka-flash-3 stays default, reka-flash retained. - test: align provider-models-config / provider-models-route / web-cookie-providers-new with #4621 (reka-flash now in the Reka catalog) and #4699 (the `kimi` API-key provider correctly falls through to DefaultExecutor instead of KimiWebExecutor) - chore(quality): allowlist the COMPRESSION_GUIDE doc name in check-fabricated-docs (false-positive env-var match; docs/compression/COMPRESSION_GUIDE.md exists) * fix(release-green): resolve release-PR full-CI reds for v3.8.34 Surfaced only on the release PR (these gates don't run on PR->release fast-gates): - fix(quota): complete HTML-comment sanitization in opencodeOllamaUsage SSR reset-time parsing — strip any <!--...--> generically instead of the two literal React hydration markers, so no partial "<!--" can survive (CodeQL js/incomplete-multi-character- sanitization, HIGH, introduced by #4642). Regression test added. - test(codex): correct the Codex-fingerprint body key order assertion to match the canonical bodyFieldOrder (prompt_cache_key precedes include); #4584 flipped the two and integration tests don't run on fast-gates so it never executed until the release PR. - chore(quality): rebaseline inherited cycle drift surfaced by full CI — zizmorFindings 152->155 (+3 unpinned-uses in nightly-release-green.yml from #4622, same @vN convention as ci.yml) and openapiCoverage.pct 38.4->37.8 (-0.6, contributor routes added faster than openapi docs). Release-finalize touches no prod routes. * fix(release-green): complete CodeQL sanitization + rebaseline complexity drift - fix(quota): handle unterminated HTML comments in opencodeOllamaUsage SSR reset-time parsing — the `(?:-->|$)` arm consumes a trailing "<!--" with no closing "-->", so no partial "<!--" can survive (CodeQL js/incomplete-multi-character-sanitization persisted with the plain <!--...--> form because an unclosed comment could still leave "<!--"). - chore(quality): rebaseline cyclomatic complexity 1915->1916 (+1) — inherited v3.8.34 cycle drift (contributor feature branches); check:complexity does not run on PR->release fast-gates so it surfaced only on the release PR. Release-finalize adds 0 complexity (measured 1916 with/without the regex tweak). dead-code/cognitive/type-coverage/ compression-budget/codeql ratchets all pass. --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com> Co-authored-by: Abhishek Divekar <adivekar@utexas.edu> Co-authored-by: Rahul sharma <sharmaR0810@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com> Co-authored-by: Ronald Estacion <DevEstacion@users.noreply.github.com> Co-authored-by: Igor <60442260+BugsBag@users.noreply.github.com> Co-authored-by: Oonishi <275808243+ponkcore@users.noreply.github.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Jan Leon <Jan.gaschler@gmail.com>
154 lines
5.9 KiB
TypeScript
154 lines
5.9 KiB
TypeScript
/**
|
|
* No-thinking gateway model IDs (free-claude-code port, Fase 8.1).
|
|
*
|
|
* Some clients — most notably Claude Code — always attach a `thinking` block to
|
|
* certain Claude models and offer no UI to turn it off. To let an operator force a
|
|
* thinking-capable model into a no-thinking mode purely by *model selection*, the
|
|
* gateway exposes a synthetic catalog id:
|
|
*
|
|
* no-think/<provider>/<model>
|
|
*
|
|
* When such an id arrives on a request we strip the prefix back to the real
|
|
* `<provider>/<model>` and suppress reasoning (`thinking:{type:"disabled"}` for the
|
|
* Claude/Messages path; drop `reasoning`/`reasoning_effort` for the OpenAI path).
|
|
* The existing `normalizeThinkingForModel()` still runs downstream, so models that
|
|
* reject `disabled` are handled exactly as before.
|
|
*
|
|
* Catalog visibility is gated (see `shouldExposeNoThinkingAlias`): we only advertise
|
|
* the variant for Claude-family models that actually support thinking AND honor
|
|
* `disabled` — advertising it for a model that ignores suppression would be a lie.
|
|
* An explicit registry override (`ModelSpec.noThinkingAlias`) wins over the default.
|
|
*/
|
|
import { getModelSpec } from "@/shared/constants/modelSpecs";
|
|
|
|
export const NO_THINKING_PREFIX = "no-think/";
|
|
|
|
/** True when `modelId` carries the no-thinking gateway prefix. */
|
|
export function isNoThinkingAlias(modelId: unknown): modelId is string {
|
|
return typeof modelId === "string" && modelId.startsWith(NO_THINKING_PREFIX);
|
|
}
|
|
|
|
/** Remove the gateway prefix, returning the real `<provider>/<model>` (plain ids pass through). */
|
|
export function stripNoThinkingAlias(modelId: string): string {
|
|
return isNoThinkingAlias(modelId) ? modelId.slice(NO_THINKING_PREFIX.length) : modelId;
|
|
}
|
|
|
|
/** Wrap a real qualified model id in the no-thinking gateway prefix. */
|
|
export function toNoThinkingAlias(qualifiedModelId: string): string {
|
|
return `${NO_THINKING_PREFIX}${qualifiedModelId}`;
|
|
}
|
|
|
|
interface ApplyResult {
|
|
applied: boolean;
|
|
realModel?: string;
|
|
}
|
|
|
|
/**
|
|
* Request-side hook: if `body.model` is a no-thinking alias, rewrite it to the real
|
|
* model and suppress reasoning in place. No-op (and body untouched) otherwise.
|
|
*/
|
|
export function applyNoThinkingAlias(
|
|
body: Record<string, unknown> | null | undefined,
|
|
opts: { claudeFormat?: boolean } = {}
|
|
): ApplyResult {
|
|
if (!body || typeof body !== "object") return { applied: false };
|
|
const model = body.model;
|
|
if (!isNoThinkingAlias(model)) return { applied: false };
|
|
|
|
const realModel = stripNoThinkingAlias(model);
|
|
if (!realModel) return { applied: false }; // malformed: nothing after the prefix
|
|
|
|
body.model = realModel;
|
|
if (opts.claudeFormat === true) {
|
|
body.thinking = { type: "disabled" };
|
|
}
|
|
delete body.reasoning_effort;
|
|
delete body.reasoning;
|
|
return { applied: true, realModel };
|
|
}
|
|
|
|
interface CatalogModelEntry {
|
|
id?: unknown;
|
|
owned_by?: unknown;
|
|
name?: unknown;
|
|
[key: string]: unknown;
|
|
}
|
|
|
|
/** Strip a `<provider>/` prefix to get the bare model name for spec lookup. */
|
|
function bareModelName(id: string): string {
|
|
const slash = id.lastIndexOf("/");
|
|
return slash >= 0 ? id.slice(slash + 1) : id;
|
|
}
|
|
|
|
/**
|
|
* Whether the catalog should advertise a no-thinking variant for this entry.
|
|
*
|
|
* Default rule: Claude-family model that supports thinking and does NOT reject
|
|
* `thinking:{type:"disabled"}`. An explicit `ModelSpec.noThinkingAlias` boolean
|
|
* overrides the default in either direction (operator opt-in / opt-out).
|
|
*/
|
|
export function shouldExposeNoThinkingAlias(model: CatalogModelEntry): boolean {
|
|
if (!model || typeof model !== "object") return false;
|
|
const id = model.id;
|
|
if (typeof id !== "string" || id.length === 0) return false;
|
|
if (model.owned_by === "combo") return false; // combos are virtual
|
|
if (isNoThinkingAlias(id)) return false; // never double-alias
|
|
|
|
const name = bareModelName(id);
|
|
const spec = getModelSpec(name);
|
|
if (!spec) return false;
|
|
|
|
if (spec.noThinkingAlias === true) return true;
|
|
if (spec.noThinkingAlias === false) return false;
|
|
|
|
return (
|
|
spec.supportsThinking === true && spec.rejectsThinkingDisabled !== true && /claude/i.test(name)
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Normalize the provider prefix inside a qualified model id using an alias→canonical map.
|
|
* e.g. "cc/claude-opus-4-6" → "claude/claude-opus-4-6" when aliasToCanonical["cc"]="claude".
|
|
* Ids without a "/" or whose prefix is not in the map are returned unchanged.
|
|
*/
|
|
function normalizeProviderPrefix(
|
|
qualifiedId: string,
|
|
aliasToCanonical: Record<string, string>
|
|
): string {
|
|
const slash = qualifiedId.indexOf("/");
|
|
if (slash < 0) return qualifiedId;
|
|
const prefix = qualifiedId.slice(0, slash);
|
|
const canonical = aliasToCanonical[prefix];
|
|
return canonical && canonical !== prefix
|
|
? `${canonical}${qualifiedId.slice(slash)}`
|
|
: qualifiedId;
|
|
}
|
|
|
|
/**
|
|
* Append a no-thinking variant for every eligible model. Returns the original array
|
|
* reference unchanged when nothing is eligible (no allocation in the common case).
|
|
*
|
|
* @param aliasToCanonical - When provided, the inner provider prefix of each variant id is
|
|
* normalized to its canonical form (e.g. "cc" → "claude"). Pass this when the catalog is
|
|
* emitting canonical-prefixed ids so no-think variants stay consistent with the prefix mode.
|
|
*/
|
|
export function appendNoThinkingVariants<T extends CatalogModelEntry>(
|
|
models: T[],
|
|
aliasToCanonical?: Record<string, string>
|
|
): T[] {
|
|
if (!Array.isArray(models)) return models;
|
|
const variants: T[] = [];
|
|
for (const model of models) {
|
|
if (!shouldExposeNoThinkingAlias(model)) continue;
|
|
const rawId = model.id as string;
|
|
const qualifiedId = aliasToCanonical ? normalizeProviderPrefix(rawId, aliasToCanonical) : rawId;
|
|
const aliasId = toNoThinkingAlias(qualifiedId);
|
|
const variant: T = { ...model, id: aliasId, root: aliasId };
|
|
if (typeof model.name === "string" && model.name) {
|
|
variant.name = `${model.name} (no thinking)`;
|
|
}
|
|
variants.push(variant);
|
|
}
|
|
return variants.length > 0 ? [...models, ...variants] : models;
|
|
}
|