mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-06 15:22:12 +03:00
* chore(release): open v3.8.27 development cycle * fix(security): polynomial ReDoS in comboAgentMiddleware regex (#3982) * fix(security): eliminate polynomial ReDoS in comboAgentMiddleware <omniModel> regex (CodeQL js/polynomial-redos) CACHE_TAG_PATTERN wrapped the tag in an unbounded `(?:\\n|\n|\r)*` prefix/suffix. On an unanchored `.test()`/`.exec()` that is O(n²) on inputs with many newlines (CodeQL js/polynomial-redos, alerts #612/#613). The surrounding runs are irrelevant to detecting/capturing the tag, so the detection pattern now matches only the core `<omniModel>([^<]+)</omniModel>`; the global strip pattern still consumes the wrapping newlines (combo.ts streaming, #531) but BOUNDED ({0,16}) so it stays linear. Behavior preserved: detection, model extraction, multi-tag stripping (#454) and blank-line cleanup all unchanged (107 related tests green). Adds ReDoS-safety regression tests (50k-newline inputs complete in <1ms). * docs(changelog): add #3982 ReDoS fix to [3.8.27] * ci(security): harden workflows — artipacked persist-credentials + cache-poisoning + SC2086 (#3965) * Refine provider quota card display (#3969) Integrated into release/v3.8.27 * feat: add sidebar group separator toggles (#3971) Integrated into release/v3.8.27 * Gate control-plane proxy direct fallback (#3963) Integrated into release/v3.8.27 * Capture actual upstream provider requests (#3941) Integrated into release/v3.8.27 * ci(quality): flip require-tighten + osv + Trivy to blocking (v3.8.27 cycle-end) (#3984) * fix(resilience): respect connection cooldown stored as numeric epoch (#3954) (#3995) rate_limited_until is a TEXT column, but setConnectionRateLimitUntil (Antigravity full-quota path) persists a raw epoch number that SQLite coerces to a numeric string ("1781696905131.0"). The selection predicate isAccountUnavailable then did new Date("1781696905131.0") -> NaN, so the cooling connection was never skipped and the router kept dispatching to rate-limited accounts. Normalize numeric-epoch strings (and number/Date/ISO) via a shared cooldownUntilMs() helper in isAccountUnavailable / getEarliestRateLimitedUntil / filterAvailableAccounts / parseFutureDateMs. ISO behavior preserved. * fix(providers): fetch live /models for LLM7 and BytePlus (#3976) (#3996) llm7 and byteplus carry a real modelsUrl but were not classified by any live-fetch branch of the model-import route, so their hardcoded 4-entry registry catalog was served (source local_catalog) instead of the upstream catalog. Add both to NAMED_OPENAI_STYLE_PROVIDERS so the route probes <baseUrl>/models and serves the live list, falling back to the local catalog only on fetch failure. * fix(dashboard): logs auto-refresh reads live visibility, not a stale mount ref (#3972) (#3997) The auto-refresh interval gated each tick on visibleRef, seeded once at mount and updated only by a visibilitychange event. A tab mounted while document.visibilityState is 'hidden' (background load, bfcache, embedded/proxied webviews) with no later visibilitychange left the ref false forever, so the interval ticked but never fetched — only the manual button worked. Read the live document.visibilityState in the tick instead. * feat(compression): add Indonesian caveman rules and language pack (#3975) Integrated into release/v3.8.27 (cherry picked from commitc9b5b1a892) * fix(combo): shuffle strict-random fallback remainder to spread load (#3959) (#3998) strict-random shuffled only the deck-selected slot 0 and left the fallback remainder in fixed priority order, so after a failing deck pick the chain always fell through to the same top-priority model — a persistently-failing model was retried on essentially every request and fallback load never spread across peers. Shuffle the remainder too (like the random strategy). * Add provider auth visibility controls (#3953) Integrated into release/v3.8.27 * fix(claude): forward client tool-search-tool anthropic-beta on the Claude OAuth path (#3974) (#3999) The client-negotiated anthropic-beta: tool-search-tool-2025-10-19 was dropped on both Claude code paths (default executor rebuilt from static ANTHROPIC_BETA_CLAUDE_OAUTH; selectBetaFlags only read the client beta to gate thinking/effort), so claude.ai rejected deferred-tool requests with 400 'Tool reference not found'. Add an allowlist-merge (mergeClientAnthropicBeta) that unions the client's allowlisted betas into the outbound set on both paths, preserving #3415 (no forced thinking/effort). * feat(providers): add model search filter to provider dashboard (#3950) Integrated into release/v3.8.27 * fix(vision-bridge): force bridge for tokenrouter deepseek models (#3946) Integrated into release/v3.8.27 * fix(executor): strip stream_options on non-streaming requests (#3884) (#4000) Clients that send stream_options:{include_usage:true} regardless of stream (e.g. the OpenAI Python SDK) had it passed through on non-streaming calls; NVIDIA NIM rejected it with 400 'Stream options can only be defined when stream=True'. DefaultExecutor.transformRequest only injected/cleared stream_options on the streaming branch and never stripped a client-sent value when stream=false. Add a !stream strip branch; the streaming injection path is unchanged. Global to openai-compat providers. * fix(qwen-web): cookie validation false-positive - check response body for user object (#3958) Integrated into release/v3.8.27 * fix(db): persist backup retention days (#3970) Integrated into release/v3.8.27 * 大量UI显示和i18n优化 (#3973) Integrated into release/v3.8.27 * deps: bump the npm_and_yarn group across 1 directory with 2 updates (#3943) Integrated into release/v3.8.27 * deps: bump form-data from 4.0.5 to 4.0.6 (#3944) Integrated into release/v3.8.27 * deps: bump vite from 8.0.5 to 8.0.16 (#3942) Integrated into release/v3.8.27 * chore(quality): re-baseline validation.ts 4407->4428 (#3958 qwen body-check) The qwen-web validation body-check merged in #3958 pushed validation.ts past its frozen size on the integrated release tip. Bump the baseline with justification; no logic is separately extractable from the existing qwen-web validation branch. * deps: bump the production group with 13 updates (#3915) Integrated into release/v3.8.27 — low-risk group (playwright 1.60→1.61 minor + transitive patches; fumadocs-core 16.9→16.10 minor). * chore(deps): ignore jscpd major bumps (v5 Rust rewrite breaks the duplication gate) Our duplication ratchet (scripts/check/check-duplication.mjs) is pinned to jscpd@4 and parses jscpd-report.json against a frozen baseline. jscpd v5 is a native Rust binary with no Node.js API and a different report/bin, so a major bump would break the gate. Migrate deliberately, not via dependabot. Closes the noise from #3916. * fix(perplexity-web): parse schematized diff_block stream so answers aren't empty (#4001) Integrated into release/v3.8.27 — schematized diff_block parsing follow-up to #3938. * refactor: modularize providerRegistry.ts into 159 individual provider plugins (#3993) Modularize provider registry (#3594). Integrated into release/v3.8.27 after rebase + behavior-preservation verification (provider-consistency gate 159/232/0, typecheck, registry tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(registry): restore byteplus + mimocode dropped by #3993 modularization The provider-registry modularization (#3993) was cut from a base predating the byteplus (#3877) and mimocode (#3837) registry entries, so merging it silently dropped both providers (getRegistryEntry returned undefined → validation reported 'not supported'). Re-add them as registry modules in the new structure; registered count 159→161, provider-consistency 161/232/0. Also align the pre-existing qwen-web validator test to #3958: since the validator now requires a real `user` object in the 200 body, the mock must carry one. * refactor: modularize schemas (non-stacked) (#3988) Modularize validation schemas (#3594). Integrated into release/v3.8.27 after rebase (reconciled the merged hiddenSidebarGroupLabels #3971 + intelligenceSyncRequestSchema into the new modules) + behavior verification (typecheck, 195 schema/settings/validation tests, build 556/556). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(default-executor): honor custom providerSpecificData.baseUrl for OpenAI-format providers (#4002) Integrated into release/v3.8.27 — honor custom providerSpecificData.baseUrl in DefaultExecutor (openai-format), tested. * feat(openai): honor custom base URL in model discovery + complete openai/codex pricing (#4005) Integrated into release/v3.8.27 — openai model-discovery honors custom base URL (SSRF-guarded) + pricing rows for new openai/codex models. Tested + baselines bumped. * fix(live-ws): bridge sidecar events to dashboard (#4004) Integrated into release/v3.8.27 — repair LiveWS sidecar (startup, same-origin /live-ws, main→sidecar compression.completed bridge, early-msg queue). Fixed the cookie-parse regex (\s) + added a focused unit test; baseline bumped for the non-blocking chatCore bridge. * docs(troubleshooting): note MITM proxy cannot intercept Windows-host apps under WSL (#4003) Integrated into release/v3.8.27 — MITM/WSL troubleshooting note. * fix(repo): untrack accidentally-committed root node_modules symlink + gitignore it A worktree node_modules symlink (-> the main checkout's node_modules) was staged by a `git add -A` during the #3988 merge and committed into05213ac6a. The symlink points at the repo's own node_modules path, so checking it out turns the main checkout's node_modules into a self-referential symlink (breaking tsx/all node ops). Untrack it and add a root-anchored /node_modules ignore so the symlink form can't be re-committed (the existing 'node_modules/' only matches directories). * fix(quality): allowlist socks dep (declared by #4004, never allowlisted) socks@^2.8.7 was added to package.json in #4004 (LiveWS sidecar,02302131f) as a phantom-dep cleanup but never added to dependency-allowlist.json, so check:deps has been red on the release tip ever since. socks is the standard SOCKS proxy client (dep of fetch-socks), legitimate and years old. * feat(sse): real LLMLingua-2 ONNX compression engine (stable) (#4014) Integrated into release/v3.8.27. Adjustments before merge: - Synced with the current release tip (was 11 commits behind). - Added the 3 LLMLingua-2 ONNX optional-runtime deps to dependency-allowlist.json (@atjsh/llmlingua-2, @tensorflow/tfjs, js-tiktoken) — the only gate that was red. - socks was allowlisted directly on release (separate fix d7db5c73d; it was declared by #4004 but never allowlisted, leaving check:deps red release-wide). Verified locally: check:deps OK, file-size OK, public-creds OK, provider-consistency 161/232/0, typecheck:core clean, 24/24 LLMLingua tests pass. The only remaining Fast-QG red is the pre-existing #3972 orphan test (request-logger-autorefresh-visibility-3972.test.tsx), which is release-wide and unrelated to this PR. * test(dashboard): rehome #3972 logs auto-refresh test so a runner collects it tests/unit/request-logger-autorefresh-visibility-3972.test.tsx (added by #3972 via #3997) sat at the top level of tests/unit/ as a .tsx vitest test, which NO runner collects: the node runner only globs *.test.ts, and test:vitest:ui only runs tests/unit/ui. So the #3972 regression guard never executed in CI and check:test-discovery was red release-wide. Move it under tests/unit/ui/ (the collected vitest:ui path) and fix the relative import depth. Verified: the test now runs and passes (2/2), and check:test-discovery is green. * feat(compression): capture per-engine analytics (#3960) + Lite schema fix (#3952) (#4018) Captures the net-new value from #3960 (per-engine breakdown analytics) and #3952 (Lite engine schema fix) onto release/v3.8.27. Fast QG green; 622/622 compression+analytics tests pass. * fix(sse): guard model-less registry entries in getUnsupportedParams (mimocode) (#4015) Real bugfix: guard model-less registry entries (mimocode) in getUnsupportedParams so handleChatCore no longer throws 'entry.models is not iterable' / reports 'All models failed' for unrelated requests. Includes a regression test. Fast QG green. * feat(ci): Quality Gate v2 — Onda 0 + Onda 1 (gate flips, TIA, SAST, DAST-smoke, mutation infra) (#4016) * docs(ops): add quality-gate assessment + replication playbook (Fase 9 foundation) * feat(ci): flip oasdiff breaking-change gate to blocking (ratchet) * docs(ops): deliver main branch-protection ruleset for owner to apply * fix(ci): run typecheck:core in PR->release fast-gates (close fast-gates hole, part 1) * perf(mutation): enable Stryker incremental mode + cache (scales the 60/80 rollout) * feat(ci): commit CodeQL advanced config (security-extended), replacing default-setup * feat(ci): version semgrep SAST workflow (owasp/secrets), advisory * feat(quality): TIA test-impact map builder (import-graph; map built at runtime, gitignored) * feat(quality): TIA impacted-test selector with run-all fail-safe * fix(ci): run TIA-impacted unit tests in PR->release fast-gates (build map at runtime, fail-safe full) * feat(ci): DAST-smoke per-PR (schemathesis subset + promptfoo injection-guard, blocking) * fix(ci): unbreak Fase 9 PR CI (MDX frontmatter, CodeQL conflict, dast-smoke advisory) - Add MDX frontmatter to docs/ops/{BRANCH_PROTECTION_MAIN,QUALITY_GATE_PLAYBOOK}.md. fumadocs rejects frontmatter-less docs -> 'npm run build' failed -> broke dast-smoke's build step (the release fast-gates never runs build, so this only surfaced on the PR). - codeql.yml: workflow_dispatch-only until the owner switches repo CodeQL Default->Advanced (advanced configs cannot be processed while default setup is enabled; documented inline). - dast-smoke.yml: job-level continue-on-error (advisory) so this brand-new gate matures before it blocks (repo convention: advisory -> blocking). * ci(quality): make TIA unit-test step advisory until release test-debt is cleared release/v3.8.27 carries ~17 pre-existing failing unit tests (budget #3537, apiKey #3552, several Zod schemas, Puter/Qwen executors, mimocode entry, etc.) unrelated to this PR — the new 'run tests on PR->release' gate surfaced them. Per the repo's advisory->blocking convention, this step enters advisory (it still runs + reports) so pre-existing debt doesn't block the gate program. typecheck:core stays blocking. Flip to blocking (remove continue-on-error) once the release suite is green. * fix(sse): preserve Kiro streaming finish_reason tool_calls (#3980) (#4025) * fix(guardrails): preserve original image when vision-bridge describe fails (#4012) (#4026) * feat(api): advertise combo capabilities on import surfaces (#3979) (#4027) * feat(sse): delegated Anthropic Context Editing for Claude (clear_tool_uses) (#4021) Opt-in Claude-only delegated compression: injects context_management.clear_tool_uses_20250919 at the Claude pre-serialization chokepoint (composes with clear_thinking, thinking first), threaded via ExecuteInput from handleChatCore. Pure edit-builder + 11 tests (7 unit + 4 e2e fetch-capture). Beta context-management-2025-06-27 already advertised; allowlist done. Telemetry/400-fallback/claude-web coverage deferred. * fix(opencode): map x-session-affinity to x-opencode-session for custom providers (#4022) (#4028) * fix(dashboard): Playground Compare tab loading + HTTP method guard (#4024) randomUUID non-HTTPS fallback + static CompareTab import; raw HTTP TRACE->405 method guard wired into dev + standalone servers. Integrated into release/v3.8.27. * refactor(dashboard): settings UI layout + API Keys naming (#4020) Presentation/relabel refactor of the Settings dashboard (API Manager -> API Keys), card relocations, Toggle adoption, present-but-disabled engine steps. Auth-file changes are string/comment-only (no behavior change). Integrated into release/v3.8.27. * fix: restore unit regressions dropped by lossy schema/registry modularizations (#4030) Restores schema fields (combo reasoningTokenBuffer, budget-0 #3537, openrouter preset, proxy family #3777, resilience degradation/providerCooldown), qwen-web v2 endpoint+catalog, mimocode models key — all dropped by #3988/#3993 — and aligns 3 tests to #3941/#3993. Verified: 8 failing regression tests on release tip -> 131/131 green on this branch. Integrated into release/v3.8.27. * fix(api): return 400 (not 500) for malformed JSON on /api/auth/login (#4031) Wrap request.json() so a malformed/non-JSON login body returns a structured 400 instead of falling through to the 500 catch. Fixes the schemathesis high-risk-endpoint DAST finding (verified: schemathesis step now passes). +TDD test. Integrated into release/v3.8.27. * feat(dashboard): real circuit-breaker state in the Combo Live cascade (U1b) (#4029) Overlays real provider circuit-breaker state (GET /api/monitoring/health) onto the Combo Live cascade as a 'CB: OPEN · 41s' badge. Pure enrichRunWithBreakers + fail-soft useProviderBreakerHealth poll; graceful when health is absent. +13 tests. Integrated into release/v3.8.27. * Fix promptfoo security assertion parsing (#4032) * chore(deps): dependabot security bumps + drop unused gray-matter (#4036) Integrated into release/v3.8.27 — dependabot security bumps (form-data/js-yaml/protobufjs/dompurify/hono) + drop unused gray-matter. Unblocks the npm audit:deps gate (Lint) branch-wide. * fix(ci): scope TIA to node:test unit files only (mirror test:unit glob) (#4035) Integrated into release/v3.8.27 — scopes the advisory TIA step to the test:unit node:test glob, fixing the 99 false failures. +4 TDD. * Refine compression settings, storage labels, and sidebar grouping (#4033) Integrated into release/v3.8.27 — relocate Token Saver into Compression Settings (controlled component), reorder Security/Authz tabs, storage labels + i18n relabel. Thanks @rdself! * [codex] add per-key local usage command (#4034) Integrated into release/v3.8.27 — per-key local @@om-usage command (cached quota, no upstream routing). Rebased onto modularized schemas/keys.ts + file-size rebaseline. Thanks @Witroch4! * chore(release): reconcile v3.8.27 CHANGELOG + i18n mirrors * ci(quality): unblock v3.8.27 release gates (zizmor pin + test-masking allowlist) - zizmor ratchet (151→139, no regression): SHA-pin every action ref ADDED this cycle — codeql/dast-smoke/semgrep (3 new workflows) + trivy-action (docker-publish) + actions/cache (nightly-mutation). Pre-existing tag refs keep the repo convention. - test-masking: add config/quality/test-masking-allowlist.json + allowlist support in check-test-masking.mjs (exempts ONLY the net-assert-reduction signal; tautology/skip/ deletion still fire). Allowlists 2 verified-legitimate reductions: appearance-widget-settings-schema (#4033 removed showTokenSaverOnEndpoint field) and dashboard-shell-tabs (#3973 tabs→redirect refactor, asserts replaced). +4 gate tests. * test(quality): reword test-masking self-test comments to avoid literal masking patterns The added allowlist-test comments contained the literal strings 'assert.ok(true)' and '.skip' which the masking detector's own regexes match as text — making the gate flag its own test file (net +1 tautology/skip/extended-tautology vs main). Reworded to plain prose ('a new tautology', 'a new skip marker'); test logic unchanged (24/24 pass). * fix(quality): unblock v3.8.27 release — align 3 stale tests + restore modularized settings-schema parity Release-PR full CI surfaced 3 deterministic test failures (no live product regression), all stale vs legitimate cycle changes: - settings-schema parity (#3988): the modularized updateSettingsSchema barrel (schemas/settings.ts) had diverged from the canonical settingsSchemas.ts (45 vs 85 fields — 40 dropped + 6 extra), a lossy-modularization dead-code copy. Re-export from the canonical source so the barrel can never diverge again (runtime already uses canonical). Parity test now passes. - api-manager permissions modal: #4034 added a 4th self-service switch (per-key usage allowance); a11y invariant (every switch type="button") still holds. Updated the static count 3 -> 4. - pack-artifact policy: dist/http-method-guard.cjs became a required runtime path; added it to the test's expected missing-paths list. Also documents the gate gap for Fase 9 (QUALITY_GATE_PLAYBOOK Parte 6): G1 run the deterministic unit layer + test-masking on PR->release (not just PR->main), G2 a modularization-parity gate (would have caught the #3988 drop at its PR), G3 flake quarantine. Env flakes (LiveWS startup timeout, integration server-startup cascade) are pre-existing/CI-env, triaged separately. --------- Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Veier04 <118300867+Veier04@users.noreply.github.com> Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com> Co-authored-by: WormAlien <164898390+WormAlien@users.noreply.github.com> Co-authored-by: thezukiru <121331256+thezukiru@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: NOXX - Commiter <artur1992123@mail.ru> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Demiurge The Single <megamen932@gmail.com> Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
576 lines
18 KiB
TypeScript
576 lines
18 KiB
TypeScript
/**
|
|
* Tests for VisionBridgeGuardrail.
|
|
* Uses dependency injection to avoid SQLite dependency.
|
|
*/
|
|
|
|
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
|
|
const { VisionBridgeGuardrail } = await import("../../../src/lib/guardrails/visionBridge.ts");
|
|
const { resetGuardrailsForTests } = await import("../../../src/lib/guardrails/registry.ts");
|
|
const { getResolvedModelCapabilities } = await import("../../../src/lib/modelCapabilities.ts");
|
|
import type { GuardrailContext } from "../../../src/lib/guardrails/base.ts";
|
|
import type { VisionModelConfig } from "../../../src/lib/guardrails/visionBridgeHelpers.ts";
|
|
|
|
// ── Mock state ──────────────────────────────────────────────────────────────
|
|
|
|
let mockSettings: Record<string, unknown> = {
|
|
visionBridgeEnabled: true,
|
|
visionBridgeModel: "openai/gpt-4o-mini",
|
|
visionBridgePrompt: "Describe this image concisely.",
|
|
visionBridgeTimeout: 30000,
|
|
visionBridgeMaxImages: 10,
|
|
};
|
|
|
|
let mockVisionResponse = "A beautiful sunset over the ocean";
|
|
let shouldVisionFail = false;
|
|
let visionCallCount = 0;
|
|
|
|
function createGuardrail(options?: Parameters<typeof VisionBridgeGuardrail>[0]) {
|
|
return new VisionBridgeGuardrail({
|
|
...options,
|
|
deps: {
|
|
getSettings: async () => mockSettings,
|
|
callVisionModel: async (_imageDataUri: string, _config: VisionModelConfig) => {
|
|
visionCallCount++;
|
|
if (shouldVisionFail) {
|
|
throw new Error("Vision model failed");
|
|
}
|
|
return mockVisionResponse;
|
|
},
|
|
...(options?.deps ?? {}),
|
|
},
|
|
});
|
|
}
|
|
|
|
test.beforeEach(() => {
|
|
resetGuardrailsForTests({ registerDefaults: false });
|
|
visionCallCount = 0;
|
|
shouldVisionFail = false;
|
|
mockSettings = {
|
|
visionBridgeEnabled: true,
|
|
visionBridgeModel: "openai/gpt-4o-mini",
|
|
visionBridgePrompt: "Describe this image concisely.",
|
|
visionBridgeTimeout: 30000,
|
|
visionBridgeMaxImages: 10,
|
|
};
|
|
});
|
|
|
|
// ── Helpers ─────────────────────────────────────────────────────────────────
|
|
|
|
function createContext(overrides: Partial<GuardrailContext> = {}): GuardrailContext {
|
|
return {
|
|
model: "minimax/minimax-01",
|
|
log: console,
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function createPayload(overrides: Record<string, unknown> = {}): Record<string, unknown> {
|
|
return {
|
|
model: "minimax/minimax-01",
|
|
messages: [{ role: "user", content: "Hello" }],
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
// ── Basic Properties ────────────────────────────────────────────────────────
|
|
|
|
test("VisionBridgeGuardrail has correct name and priority", () => {
|
|
const guardrail = createGuardrail();
|
|
assert.strictEqual(guardrail.name, "vision-bridge");
|
|
assert.strictEqual(guardrail.priority, 5);
|
|
});
|
|
|
|
test("VisionBridgeGuardrail is enabled by default", () => {
|
|
const guardrail = createGuardrail();
|
|
assert.strictEqual(guardrail.enabled, true);
|
|
});
|
|
|
|
test("VisionBridgeGuardrail can be disabled via constructor", () => {
|
|
const guardrail = createGuardrail({ enabled: false });
|
|
assert.strictEqual(guardrail.enabled, false);
|
|
});
|
|
|
|
// ── VB-S05: Vision Bridge disabled via settings ────────────────────────────
|
|
|
|
test("VB-S05: passthroughs when visionBridgeEnabled is false", async () => {
|
|
mockSettings.visionBridgeEnabled = false;
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is in this image?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext());
|
|
assert.strictEqual(result.block, false);
|
|
assert.strictEqual(result.modifiedPayload, undefined);
|
|
});
|
|
|
|
// ── VB-S06: Disabled via context ────────────────────────────────────────────
|
|
|
|
test("VB-S06: skips when disabledGuardrails includes vision-bridge", async () => {
|
|
const guardrail = createGuardrail();
|
|
const payload = createPayload();
|
|
const context = createContext({ disabledGuardrails: ["vision-bridge"] });
|
|
|
|
const result = await guardrail.preCall(payload, context);
|
|
assert.strictEqual(result.block, false);
|
|
assert.strictEqual(result.modifiedPayload, undefined);
|
|
});
|
|
|
|
// ── VB-S02: Vision-capable model passthrough ────────────────────────────────
|
|
|
|
test("VB-S02: passthroughs for vision-capable model (gpt-4o)", async () => {
|
|
const guardrail = createGuardrail();
|
|
const payload = createPayload({
|
|
model: "openai/gpt-4o",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "openai/gpt-4o" }));
|
|
|
|
// If supportsVision is true, it should passthrough (no modification)
|
|
// If supportsVision is null/undefined (no sync data), it will process — that's correct behavior
|
|
const capabilities = getResolvedModelCapabilities("openai/gpt-4o");
|
|
if (capabilities.supportsVision === true) {
|
|
assert.strictEqual(result.block, false);
|
|
assert.strictEqual(result.modifiedPayload, undefined);
|
|
} else {
|
|
// Without sync data, supportsVision is null — guardrail processes the image
|
|
// This is correct fail-open behavior for unknown model capabilities
|
|
assert.strictEqual(result.block, false);
|
|
}
|
|
});
|
|
|
|
test("VB-S02b: respects native vision support for GPT-family models", async () => {
|
|
const guardrail = createGuardrail();
|
|
|
|
for (const model of ["gpt-5.5", "gpt-5.5-high", "codex/gpt-5.5", "openai/gpt-4o-mini"]) {
|
|
visionCallCount = 0;
|
|
|
|
const payload = createPayload({
|
|
model,
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model }));
|
|
|
|
assert.strictEqual(result.block, false, `expected passthrough for ${model}`);
|
|
assert.strictEqual(
|
|
result.modifiedPayload,
|
|
undefined,
|
|
`expected unmodified payload for ${model}`
|
|
);
|
|
assert.strictEqual(visionCallCount, 0, `expected no bridge call for ${model}`);
|
|
}
|
|
});
|
|
|
|
test("VB-S02: model capabilities returns supportsVision for known models", () => {
|
|
const gpt4oCaps = getResolvedModelCapabilities("openai/gpt-4o");
|
|
// supportsVision may be true (if sync data exists) or null (if not synced)
|
|
assert.ok(gpt4oCaps.supportsVision === true || gpt4oCaps.supportsVision === null);
|
|
});
|
|
|
|
// ── VB-S04: No images passthrough ──────────────────────────────────────────
|
|
|
|
test("VB-S04: passthroughs when no images in messages", async () => {
|
|
const guardrail = createGuardrail();
|
|
const payload = createPayload({
|
|
messages: [{ role: "user", content: "Hello, how are you?" }],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext());
|
|
assert.strictEqual(result.block, false);
|
|
assert.strictEqual(result.modifiedPayload, undefined);
|
|
});
|
|
|
|
test("VB-S04: passthroughs when messages array is empty", async () => {
|
|
const guardrail = createGuardrail();
|
|
const payload = createPayload({ messages: [] });
|
|
const result = await guardrail.preCall(payload, createContext());
|
|
assert.strictEqual(result.block, false);
|
|
});
|
|
|
|
// ── VB-S01: Single image processing ─────────────────────────────────────────
|
|
|
|
test("VB-S01: replaces image with description for non-vision model", async () => {
|
|
mockVisionResponse = "A beautiful sunset over the ocean";
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is in this image?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
assert.strictEqual(result.block, false);
|
|
assert.ok(result.modifiedPayload);
|
|
|
|
const modified = result.modifiedPayload as {
|
|
messages: Array<{ content: unknown[] }>;
|
|
};
|
|
const content = modified.messages[0].content as Array<{
|
|
type: string;
|
|
text?: string;
|
|
}>;
|
|
|
|
const imagePart = content.find((p) => p.type === "image_url");
|
|
assert.strictEqual(imagePart, undefined);
|
|
|
|
const descriptionPart = content.find((p) => p.type === "text" && p.text?.includes("sunset"));
|
|
assert.ok(descriptionPart);
|
|
});
|
|
|
|
// ── VB-S04: Multiple images ─────────────────────────────────────────────────
|
|
|
|
test("VB-S04: processes multiple images and concatenates descriptions", async () => {
|
|
let callIdx = 0;
|
|
const descriptions = ["A cute cat", "A playful dog", "A colorful bird"];
|
|
|
|
const guardrail = new VisionBridgeGuardrail({
|
|
deps: {
|
|
getSettings: async () => mockSettings,
|
|
callVisionModel: async () => {
|
|
const desc = descriptions[callIdx] || "Unknown image";
|
|
callIdx++;
|
|
return desc;
|
|
},
|
|
},
|
|
});
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "Describe these images" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/cat.png" },
|
|
},
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/dog.png" },
|
|
},
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/bird.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
assert.strictEqual(result.block, false);
|
|
assert.ok(result.modifiedPayload);
|
|
assert.strictEqual(callIdx, 3);
|
|
|
|
const modified = result.modifiedPayload as {
|
|
messages: Array<{ content: unknown[] }>;
|
|
};
|
|
const content = modified.messages[0].content as Array<{
|
|
type: string;
|
|
text?: string;
|
|
}>;
|
|
|
|
assert.ok(content.some((p) => p.type === "text" && p.text?.includes("[Image 1]")));
|
|
assert.ok(content.some((p) => p.type === "text" && p.text?.includes("[Image 2]")));
|
|
assert.ok(content.some((p) => p.type === "text" && p.text?.includes("[Image 3]")));
|
|
});
|
|
|
|
// ── VB-S03: Fail-open on vision error ──────────────────────────────────────
|
|
|
|
test("VB-S03: preserves the original image when the vision API fails (#4012)", async () => {
|
|
shouldVisionFail = true;
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
assert.strictEqual(result.block, false);
|
|
|
|
const modified = (result.modifiedPayload ?? payload) as {
|
|
messages: Array<{ content: unknown[] }>;
|
|
};
|
|
const content = modified.messages[0].content as Array<{
|
|
type: string;
|
|
text?: string;
|
|
}>;
|
|
|
|
// #4012: a failed describe must NOT replace the image with an "(unavailable)"
|
|
// stub — the original image is preserved so a vision-capable upstream can see it.
|
|
const imagePart = content.find((p) => p.type === "image_url");
|
|
assert.ok(imagePart, "original image_url part must be preserved on describe failure");
|
|
const unavailPart = content.find((p) => p.type === "text" && p.text?.includes("unavailable"));
|
|
assert.strictEqual(unavailPart, undefined);
|
|
});
|
|
|
|
test("VB-S03: logs warning when vision API fails", async () => {
|
|
shouldVisionFail = true;
|
|
let warningLogged = false;
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const mockLog = {
|
|
warn: (_tag: string, msg: string) => {
|
|
if (msg.includes("Failed to get description")) {
|
|
warningLogged = true;
|
|
}
|
|
},
|
|
};
|
|
|
|
await guardrail.preCall(
|
|
payload,
|
|
createContext({
|
|
model: "minimax/minimax-01",
|
|
log: mockLog as GuardrailContext["log"],
|
|
})
|
|
);
|
|
|
|
assert.strictEqual(warningLogged, true);
|
|
});
|
|
|
|
// ── VB-S07: Base64 image format ─────────────────────────────────────────────
|
|
|
|
test("VB-S07: handles base64 image format", async () => {
|
|
mockVisionResponse = "An image description";
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "image",
|
|
source: {
|
|
type: "base64",
|
|
media_type: "image/png",
|
|
data: "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==",
|
|
},
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
assert.strictEqual(result.block, false);
|
|
assert.ok(result.modifiedPayload);
|
|
});
|
|
|
|
// ── VB-S09: Image count limit ───────────────────────────────────────────────
|
|
|
|
test("VB-S09: respects maxImages setting", async () => {
|
|
mockSettings.visionBridgeMaxImages = 2;
|
|
const guardrail = createGuardrail();
|
|
|
|
const images = Array.from({ length: 5 }, (_, i) => ({
|
|
type: "image_url" as const,
|
|
image_url: { url: `https://example.com/image${i}.png` },
|
|
}));
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [{ type: "text", text: "Describe these" }, ...images],
|
|
},
|
|
],
|
|
});
|
|
|
|
await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
// Should only call vision API for 2 images (maxImages=2)
|
|
assert.strictEqual(visionCallCount, 2);
|
|
});
|
|
|
|
// ── VB-S10: Meta information returned ───────────────────────────────────────
|
|
|
|
test("VB-S10: returns meta with imagesProcessed count", async () => {
|
|
mockVisionResponse = "A test description";
|
|
const guardrail = createGuardrail();
|
|
|
|
const payload = createPayload({
|
|
model: "minimax/minimax-01",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/a.png" },
|
|
},
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/b.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "minimax/minimax-01" }));
|
|
|
|
assert.ok(result.meta);
|
|
assert.ok(typeof result.meta === "object");
|
|
|
|
const meta = result.meta as Record<string, unknown>;
|
|
assert.strictEqual(meta.imagesProcessed, 2);
|
|
assert.ok(Array.isArray(meta.descriptions));
|
|
assert.strictEqual((meta.descriptions as string[]).length, 2);
|
|
assert.strictEqual(typeof meta.processingTimeMs, "number");
|
|
assert.strictEqual(meta.visionModel, "openai/gpt-4o-mini");
|
|
});
|
|
|
|
// ── VB-S11: Combo mapping forces vision processing despite vision-capable model ──
|
|
|
|
test("VB-S11: processes images when vision-capable model has combo mapping", async () => {
|
|
mockVisionResponse = "A description from combo-mapped vision bridge";
|
|
const guardrail = createGuardrail({
|
|
deps: {
|
|
checkModelHasComboMapping: async (_model: string) => true,
|
|
},
|
|
});
|
|
|
|
const payload = createPayload({
|
|
model: "openai/gpt-4o",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const startCallCount = visionCallCount;
|
|
const result = await guardrail.preCall(payload, createContext({ model: "openai/gpt-4o" }));
|
|
|
|
// Vision bridge should have processed the image
|
|
assert.strictEqual(result.block, false);
|
|
assert.ok(visionCallCount > startCallCount, "Expected vision model to be called");
|
|
assert.ok(
|
|
result.modifiedPayload !== undefined,
|
|
"Expected modifiedPayload when combo mapping forces vision bridge"
|
|
);
|
|
});
|
|
|
|
test("VB-S11b: passthroughs when vision-capable model has NO combo mapping", async () => {
|
|
const guardrail = createGuardrail({
|
|
deps: {
|
|
checkModelHasComboMapping: async (_model: string) => false,
|
|
},
|
|
});
|
|
|
|
const payload = createPayload({
|
|
model: "openai/gpt-4o",
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{ type: "text", text: "What is this?" },
|
|
{
|
|
type: "image_url",
|
|
image_url: { url: "https://example.com/image.png" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
});
|
|
|
|
const result = await guardrail.preCall(payload, createContext({ model: "openai/gpt-4o" }));
|
|
|
|
// Vision bridge should skip (passthrough) since model supports vision and no combo mapping
|
|
assert.strictEqual(result.block, false);
|
|
assert.strictEqual(result.modifiedPayload, undefined);
|
|
assert.strictEqual(visionCallCount, 0);
|
|
});
|