chore(release): v2.7.9

"fix: safe crypto fallback for MITM on windows (#456)"

CHANGELOG.md

@@ -4,6 +4,36 @@
 
 ---
 
+## [2.7.9] — 2026-03-18
+
+> Sprint: Codex responses subpath passthrough natively supported, Windows MITM crash fixed, and Combos agent schemas adjusted.
+
+### ✨ Features
+
+- **feat(codex)**: Native responses subpath passthrough for Codex — natively routes `POST /v1/responses/compact` to Codex upstream, maintaining Claude Code compatibility without stripping the `/compact` suffix (#457)
+
+### 🐛 Bug Fixes
+
+- **fix(combos)**: Zod schemas (`updateComboSchema` and `createComboSchema`) now include `system_message`, `tool_filter_regex`, and `context_cache_protection`. Fixes bug where agent-specific settings created via the dashboard were silently discarded by the backend validation layer (#458)
+- **fix(mitm)**: Kiro MITM profile crash on Windows fixed — `node-machine-id` failed due to missing `REG.exe` env, and the fallback threw a fatal `crypto is not defined` error. Fallback now safely and correctly imports crypto (#456)
+
+---
+
+## [2.7.8] — 2026-03-18
+
+> Sprint: Budget save bug + combo agent features UI + omniModel tag security fix.
+
+### 🐛 Bug Fixes
+
+- **fix(budget)**: "Save Limits" no longer returns 422 — `warningThreshold` is now correctly sent as fraction (0–1) instead of percentage (0–100) (#451)
+- **fix(combos)**: `<omniModel>` internal cache tag is now stripped before forwarding requests to providers, preventing cache session breaks (#454)
+
+### ✨ Features
+
+- **feat(combos)**: Agent Features section added to combo create/edit modal — expose `system_message` override, `tool_filter_regex`, and `context_cache_protection` directly from the dashboard (#454)
+
+---
+
 ## [2.7.7] — 2026-03-18
 
 > Sprint: Docker pino crash, Codex CLI responses worker fix, package-lock sync.

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 2.7.7
+  version: 2.7.9
   description: |
     OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
     endpoint that routes requests to multiple AI providers with load balancing,

next.config.mjs

@@ -121,6 +121,10 @@ const nextConfig = {
         source: "/responses",
         destination: "/api/v1/responses",
       },
+      {
+        source: "/responses/:path*",
+        destination: "/api/v1/responses/:path*",
+      },
       {
         source: "/models",
         destination: "/api/v1/models",

open-sse/executors/base.ts

@@ -26,6 +26,7 @@ export type ProviderCredentials = {
   expiresAt?: string;
   connectionId?: string; // T07: used for API key rotation index
   providerSpecificData?: JsonRecord;
+  requestEndpointPath?: string;
 };
 
 export type ExecutorLog = {

open-sse/executors/codex.ts

@@ -9,6 +9,17 @@ type EffortLevel = (typeof EFFORT_ORDER)[number];
 const CODEX_FAST_WIRE_VALUE = "priority";
 let defaultFastServiceTierEnabled = false;
 
+function getResponsesSubpath(endpointPath: unknown): string | null {
+  const normalizedEndpoint = String(endpointPath || "").replace(/\/+$/, "");
+  const match = normalizedEndpoint.match(/(?:^|\/)responses(?:(\/.*))?$/i);
+  if (!match) return null;
+  return match[1] || "";
+}
+
+function isCompactResponsesEndpoint(endpointPath: unknown): boolean {
+  return getResponsesSubpath(endpointPath)?.toLowerCase() === "/compact";
+}
+
 function normalizeServiceTierValue(value: unknown): string | undefined {
   if (typeof value !== "string") return undefined;
   const normalized = value.trim().toLowerCase();
@@ -60,13 +71,31 @@ export class CodexExecutor extends BaseExecutor {
     super("codex", PROVIDERS.codex);
   }
 
+  buildUrl(model, stream, urlIndex = 0, credentials = null) {
+    void model;
+    void stream;
+    void urlIndex;
+
+    const responsesSubpath = getResponsesSubpath(credentials?.requestEndpointPath);
+    if (responsesSubpath !== null) {
+      const baseUrl = String(this.config.baseUrl || "").replace(/\/$/, "");
+      if (baseUrl.endsWith("/responses")) {
+        return `${baseUrl}${responsesSubpath}`;
+      }
+      return `${baseUrl}/responses${responsesSubpath}`;
+    }
+
+    return super.buildUrl(model, stream, urlIndex, credentials);
+  }
+
   /**
    * Codex Responses endpoint is SSE-first.
    * Always request event-stream from upstream, even when client requested stream=false.
    * Includes chatgpt-account-id header for strict workspace binding.
    */
   buildHeaders(credentials, stream = true) {
-    const headers = super.buildHeaders(credentials, true);
+    const isCompactRequest = isCompactResponsesEndpoint(credentials?.requestEndpointPath);
+    const headers = super.buildHeaders(credentials, isCompactRequest ? false : true);
 
     // Add workspace binding header if workspaceId is persisted
     const workspaceId = credentials?.providerSpecificData?.workspaceId;
@@ -107,9 +136,15 @@ export class CodexExecutor extends BaseExecutor {
    */
   transformRequest(model, body, stream, credentials) {
     const nativeCodexPassthrough = body?._nativeCodexPassthrough === true;
+    const isCompactRequest = isCompactResponsesEndpoint(credentials?.requestEndpointPath);
 
-    // Codex /responses rejects stream=false; we aggregate SSE back to JSON when needed.
-    body.stream = true;
+    // Codex /responses rejects stream=false, but /responses/compact rejects the stream field entirely.
+    if (isCompactRequest) {
+      delete body.stream;
+      delete body.stream_options;
+    } else {
+      body.stream = true;
+    }
     delete body._nativeCodexPassthrough;
 
     const requestServiceTier = normalizeServiceTierValue(body.service_tier);

open-sse/handlers/chatCore.ts

@@ -60,9 +60,8 @@ export function shouldUseNativeCodexPassthrough({
 }): boolean {
   if (provider !== "codex") return false;
   if (sourceFormat !== FORMATS.OPENAI_RESPONSES) return false;
-  return String(endpointPath || "")
-    .toLowerCase()
-    .endsWith("/responses");
+  const normalizedEndpoint = String(endpointPath || "").replace(/\/+$/, "");
+  return /(?:^|\/)responses(?:\/.*)?$/i.test(normalizedEndpoint);
 }
 
 /**
@@ -140,8 +139,8 @@ export async function handleChatCore({
   }
 
   const sourceFormat = detectFormat(body);
-  const endpointPath = (clientRawRequest?.endpoint || "").toLowerCase();
-  const isResponsesEndpoint = endpointPath.endsWith("/responses");
+  const endpointPath = String(clientRawRequest?.endpoint || "");
+  const isResponsesEndpoint = /(?:^|\/)responses(?:\/.*)?$/i.test(endpointPath);
   const nativeCodexPassthrough = shouldUseNativeCodexPassthrough({
     provider,
     sourceFormat,
@@ -385,6 +384,8 @@ export async function handleChatCore({
 
   // Get executor for this provider
   const executor = getExecutor(provider);
+  const getExecutionCredentials = () =>
+    nativeCodexPassthrough ? { ...credentials, requestEndpointPath: endpointPath } : credentials;
 
   // Create stream controller for disconnect detection
   const streamController = createStreamController({ onDisconnect, log, provider, model });
@@ -405,7 +406,7 @@ export async function handleChatCore({
           model: modelToCall,
           body: bodyToSend,
           stream,
-          credentials,
+          credentials: getExecutionCredentials(),
           signal: streamController.signal,
           log,
           extendedContext,
@@ -545,7 +546,7 @@ export async function handleChatCore({
           model,
           body: translatedBody,
           stream,
-          credentials,
+          credentials: getExecutionCredentials(),
           signal: streamController.signal,
           log,
           extendedContext,

open-sse/services/comboAgentMiddleware.ts

@@ -123,6 +123,20 @@ export function applyToolFilter(
   });
 }
 
+/**
+ * Strip all <omniModel> tags from message content before forwarding to the provider.
+ * The tag is an internal OmniRoute marker; providers must never see it or their
+ * cache will treat every tagged request as a new session (#454).
+ */
+export function stripModelTags(messages: Message[]): Message[] {
+  return messages.map((msg) => {
+    if (typeof msg.content === "string" && CACHE_TAG_PATTERN.test(msg.content)) {
+      return { ...msg, content: msg.content.replace(CACHE_TAG_PATTERN, "").trimEnd() };
+    }
+    return msg;
+  });
+}
+
 // ── Main Middleware ──────────────────────────────────────────────────────────
 
 /**
@@ -158,6 +172,11 @@ export function applyComboAgentMiddleware(
     comboConfig.tool_filter_regex
   );
 
+  // 4. Strip internal <omniModel> tags before forwarding to provider (#454)
+  //    These tags are OmniRoute-internal markers and must never reach the provider
+  //    since providers would treat each tagged request as a new cache session.
+  messages = stripModelTags(messages);
+
   return {
     body: {
       ...body,

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.7.7",
+  "version": "2.7.9",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/app/(dashboard)/dashboard/combos/page.tsx

@@ -1181,6 +1181,12 @@ function ComboFormModal({ isOpen, combo, onClose, onSave, activeProviders }) {
   const [config, setConfig] = useState(combo?.config || {});
   const [showStrategyNudge, setShowStrategyNudge] = useState(false);
   const strategyChangeMountedRef = useRef(false);
+  // Agent features (#399 / #401 / #454)
+  const [agentSystemMessage, setAgentSystemMessage] = useState<string>(combo?.system_message || "");
+  const [agentToolFilter, setAgentToolFilter] = useState<string>(combo?.tool_filter_regex || "");
+  const [agentContextCache, setAgentContextCache] = useState<boolean>(
+    !!combo?.context_cache_protection
+  );
 
   // DnD state
   const hasPricingForModel = useCallback(
@@ -1532,6 +1538,14 @@ function ComboFormModal({ isOpen, combo, onClose, onSave, activeProviders }) {
       saveData.config = configToSave;
     }
 
+    // Agent features (#399 / #401 / #454)
+    if (agentSystemMessage.trim()) saveData.system_message = agentSystemMessage.trim();
+    else delete saveData.system_message;
+    if (agentToolFilter.trim()) saveData.tool_filter_regex = agentToolFilter.trim();
+    else delete saveData.tool_filter_regex;
+    if (agentContextCache) saveData.context_cache_protection = true;
+    else delete saveData.context_cache_protection;
+
     await onSave(saveData);
     setSaving(false);
   };
@@ -2052,6 +2066,72 @@ function ComboFormModal({ isOpen, combo, onClose, onSave, activeProviders }) {
             </div>
           )}
 
+          {/* Agent Features (#399 / #401 / #454) */}
+          <div className="flex flex-col gap-2 p-3 bg-black/[0.02] dark:bg-white/[0.02] rounded-lg border border-black/5 dark:border-white/5">
+            <div className="flex items-center gap-1.5 mb-1">
+              <span className="material-symbols-outlined text-[14px] text-primary">smart_toy</span>
+              <p className="text-xs font-medium">Agent Features</p>
+              <span className="text-[10px] text-text-muted">
+                — optional, for agent/tool workflows
+              </span>
+            </div>
+
+            {/* System Message Override */}
+            <div>
+              <label className="text-[11px] font-medium text-text-muted block mb-0.5">
+                System Message Override
+              </label>
+              <textarea
+                rows={2}
+                value={agentSystemMessage}
+                onChange={(e) => setAgentSystemMessage(e.target.value)}
+                placeholder="Override the system prompt for all requests routed through this combo…"
+                className="w-full text-xs py-1.5 px-2 rounded border border-black/10 dark:border-white/10 bg-transparent focus:border-primary focus:outline-none resize-none"
+              />
+              <p className="text-[10px] text-text-muted mt-0.5">
+                Replaces any system message sent by the client. Leave empty to pass through client
+                system messages.
+              </p>
+            </div>
+
+            {/* Tool Filter Regex */}
+            <div>
+              <label className="text-[11px] font-medium text-text-muted block mb-0.5">
+                Tool Filter Regex
+              </label>
+              <input
+                type="text"
+                value={agentToolFilter}
+                onChange={(e) => setAgentToolFilter(e.target.value)}
+                placeholder="e.g. ^(bash|computer)$"
+                className="w-full text-xs py-1.5 px-2 rounded border border-black/10 dark:border-white/10 bg-transparent focus:border-primary focus:outline-none font-mono"
+              />
+              <p className="text-[10px] text-text-muted mt-0.5">
+                Only tools whose name matches this regex are forwarded to the provider. Leave empty
+                to forward all tools.
+              </p>
+            </div>
+
+            {/* Context Cache Protection */}
+            <div className="flex items-center justify-between gap-2">
+              <div>
+                <label className="text-[11px] font-medium text-text-muted block">
+                  Context Cache Protection
+                </label>
+                <p className="text-[10px] text-text-muted">
+                  Pins the provider/model across turns to preserve cache sessions. Internal tags are
+                  stripped before forwarding to the provider.
+                </p>
+              </div>
+              <input
+                type="checkbox"
+                checked={agentContextCache}
+                onChange={(e) => setAgentContextCache(e.target.checked)}
+                className="accent-primary shrink-0"
+              />
+            </div>
+          </div>
+
           {/* Actions */}
           <div className="flex gap-2 pt-1">
             <Button onClick={onClose} variant="ghost" fullWidth size="sm">

src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx

@@ -83,7 +83,11 @@ export default function BudgetTab() {
         if (data.monthlyLimitUsd)
           setForm((f) => ({ ...f, monthlyLimitUsd: String(data.monthlyLimitUsd) }));
         if (data.warningThreshold)
-          setForm((f) => ({ ...f, warningThreshold: String(data.warningThreshold) }));
+          // stored as fraction (0–1), display as percentage (0–100)
+          setForm((f) => ({
+            ...f,
+            warningThreshold: String(Math.round(data.warningThreshold * 100)),
+          }));
       }
     } catch {
       // silent
@@ -104,7 +108,8 @@ export default function BudgetTab() {
           apiKeyId: selectedKey,
           dailyLimitUsd: form.dailyLimitUsd ? parseFloat(form.dailyLimitUsd) : null,
           monthlyLimitUsd: form.monthlyLimitUsd ? parseFloat(form.monthlyLimitUsd) : null,
-          warningThreshold: parseInt(form.warningThreshold) || 80,
+          // schema expects a fraction (0–1); UI shows percentage (0–100)
+          warningThreshold: (parseInt(form.warningThreshold) || 80) / 100,
         }),
       });
       if (res.ok) {

src/app/api/v1/responses/[...path]/route.ts

@@ -0,0 +1,33 @@
+import { CORS_ORIGIN } from "@/shared/utils/cors";
+import { handleChat } from "@/sse/handlers/chat";
+import { initTranslators } from "@omniroute/open-sse/translator/index.ts";
+
+let initialized = false;
+
+async function ensureInitialized() {
+  if (!initialized) {
+    await initTranslators();
+    initialized = true;
+    console.log("[SSE] Translators initialized for /v1/responses/*");
+  }
+}
+
+export async function OPTIONS() {
+  return new Response(null, {
+    headers: {
+      "Access-Control-Allow-Origin": CORS_ORIGIN,
+      "Access-Control-Allow-Methods": "GET, POST, OPTIONS",
+      "Access-Control-Allow-Headers": "*",
+    },
+  });
+}
+
+/**
+ * POST /v1/responses/:path* - OpenAI Responses subpaths
+ * Reuses the shared chat handler so native Codex passthrough can keep
+ * arbitrary Responses suffixes all the way to the upstream provider.
+ */
+export async function POST(request) {
+  await ensureInitialized();
+  return await handleChat(request);
+}

src/shared/utils/machineId.ts

@@ -23,13 +23,16 @@ export async function getConsistentMachineId(salt = null) {
   } catch (error) {
     console.log("Error getting machine ID:", error);
     // Fallback to random ID if node-machine-id fails
-    return crypto.randomUUID
-      ? crypto.randomUUID()
-      : "xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx".replace(/[xy]/g, function (c) {
-          const r = (Math.random() * 16) | 0;
-          const v = c == "x" ? r : (r & 0x3) | 0x8;
-          return v.toString(16);
-        });
+    try {
+      const cryptoFallback = await import("crypto");
+      return cryptoFallback.randomUUID();
+    } catch {
+      return "xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx".replace(/[xy]/g, function (c) {
+        const r = (Math.random() * 16) | 0;
+        const v = c == "x" ? r : (r & 0x3) | 0x8;
+        return v.toString(16);
+      });
+    }
   }
 }
 
@@ -44,13 +47,16 @@ export async function getRawMachineId() {
   } catch (error) {
     console.log("Error getting raw machine ID:", error);
     // Fallback to random ID if node-machine-id fails
-    return crypto.randomUUID
-      ? crypto.randomUUID()
-      : "xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx".replace(/[xy]/g, function (c) {
-          const r = (Math.random() * 16) | 0;
-          const v = c == "x" ? r : (r & 0x3) | 0x8;
-          return v.toString(16);
-        });
+    try {
+      const cryptoFallback = await import("crypto");
+      return cryptoFallback.randomUUID();
+    } catch {
+      return "xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx".replace(/[xy]/g, function (c) {
+        const r = (Math.random() * 16) | 0;
+        const v = c == "x" ? r : (r & 0x3) | 0x8;
+        return v.toString(16);
+      });
+    }
   }
 }
 

src/shared/validation/schemas.ts

@@ -80,6 +80,9 @@ export const createComboSchema = z.object({
   strategy: comboStrategySchema.optional().default("priority"),
   config: comboConfigSchema,
   allowedProviders: z.array(z.string().max(200)).optional(),
+  system_message: z.string().max(50000).optional(),
+  tool_filter_regex: z.string().max(1000).optional(),
+  context_cache_protection: z.boolean().optional(),
 });
 
 // ──── Auto-Combo Schemas ────
@@ -813,6 +816,9 @@ export const updateComboSchema = z
     config: comboRuntimeConfigSchema.optional(),
     isActive: z.boolean().optional(),
     allowedProviders: z.array(z.string().max(200)).optional(),
+    system_message: z.string().max(50000).optional(),
+    tool_filter_regex: z.string().max(1000).optional(),
+    context_cache_protection: z.boolean().optional(),
   })
   .superRefine((value, ctx) => {
     if (
@@ -821,7 +827,10 @@ export const updateComboSchema = z
       value.strategy === undefined &&
       value.config === undefined &&
       value.isActive === undefined &&
-      value.allowedProviders === undefined
+      value.allowedProviders === undefined &&
+      value.system_message === undefined &&
+      value.tool_filter_regex === undefined &&
+      value.context_cache_protection === undefined
     ) {
       ctx.addIssue({
         code: z.ZodIssueCode.custom,

tests/unit/plan3-p0.test.mjs

@@ -108,6 +108,24 @@ test("shouldUseNativeCodexPassthrough only enables responses-native Codex reques
     false
   );
 
+  assert.equal(
+    shouldUseNativeCodexPassthrough({
+      provider: "codex",
+      sourceFormat: FORMATS.OPENAI_RESPONSES,
+      endpointPath: "/v1/responses/compact",
+    }),
+    true
+  );
+
+  assert.equal(
+    shouldUseNativeCodexPassthrough({
+      provider: "codex",
+      sourceFormat: FORMATS.OPENAI_RESPONSES,
+      endpointPath: "/v1/responses/items/history",
+    }),
+    true
+  );
+
   assert.equal(
     shouldUseNativeCodexPassthrough({
       provider: "codex",
@@ -140,6 +158,18 @@ test("CodexExecutor always requests SSE accept header", () => {
   assert.equal(headers.Accept, "text/event-stream");
 });
 
+test("CodexExecutor does not request SSE accept header for compact requests", () => {
+  const executor = new CodexExecutor();
+  const headers = executor.buildHeaders(
+    {
+      accessToken: "test-token",
+      requestEndpointPath: "/v1/responses/compact",
+    },
+    false
+  );
+  assert.equal(headers.Accept, undefined);
+});
+
 test("CodexExecutor preserves native responses payloads for Codex passthrough", () => {
   const executor = new CodexExecutor();
   const transformed = executor.transformRequest(
@@ -167,6 +197,41 @@ test("CodexExecutor preserves native responses payloads for Codex passthrough",
   assert.ok(!("_nativeCodexPassthrough" in transformed));
 });
 
+test("CodexExecutor strips streaming fields for compact passthrough", () => {
+  const executor = new CodexExecutor();
+  const transformed = executor.transformRequest(
+    "gpt-5.1-codex",
+    {
+      model: "gpt-5.1-codex",
+      input: "compact this session",
+      stream: false,
+      stream_options: { include_usage: true },
+      _nativeCodexPassthrough: true,
+    },
+    false,
+    {
+      requestEndpointPath: "/v1/responses/compact",
+    }
+  );
+
+  assert.equal("stream" in transformed, false);
+  assert.equal("stream_options" in transformed, false);
+  assert.ok(!("_nativeCodexPassthrough" in transformed));
+});
+
+test("CodexExecutor routes responses subpaths to matching upstream paths", () => {
+  const executor = new CodexExecutor();
+  const compactUrl = executor.buildUrl("gpt-5.1-codex", true, 0, {
+    requestEndpointPath: "/v1/responses/compact",
+  });
+  assert.match(compactUrl, /\/responses\/compact$/);
+
+  const genericSubpathUrl = executor.buildUrl("gpt-5.1-codex", true, 0, {
+    requestEndpointPath: "/v1/responses/items/history",
+  });
+  assert.match(genericSubpathUrl, /\/responses\/items\/history$/);
+});
+
 test("translateNonStreamingResponse converts Responses API payload to OpenAI chat.completion", () => {
   const responseBody = {
     id: "resp_123",