chore(release): v3.1.10 — OmniRoute v3.1.9 remaining bug fixes sprint (#720)

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>

CHANGELOG.md

@@ -4,6 +4,15 @@
 
 ---
 
+## [3.1.10] — 2026-03-28
+
+### 🐛 Bug Fixes
+
+- **Fix #706** — Fixed icon fallback rendering caused by Tailwind V4 `font-sans` override by applying `!important` to `.material-symbols-outlined`.
+- **Fix #703** — Fixed GitHub Copilot broken streams by enabling `responses` to `openai` format translation for any custom models leveraging `apiFormat: "responses"`.
+- **Fix #702** — Replaced flat-rate usage tracking with accurate DB pricing calculations for both streaming and non-streaming responses.
+- **Fix #716** — Cleaned up Claude tool-call translation state, correctly parsing streaming arguments and preventing OpenAI `tool_calls` chunks from repeating the `id` field.
+
 ## [3.1.9] — 2026-03-28
 
 ### ✨ New Features
@@ -31,12 +40,12 @@
 
 ### 📁 New Files
 
-| File | Purpose |
-|------|---------|
-| `open-sse/translator/helpers/schemaCoercion.ts` | Schema coercion and tool description sanitization utilities |
-| `tests/unit/schema-coercion.test.mjs` | Unit tests for schema coercion |
-| `tests/unit/t40-opencode-cli-tools-integration.test.mjs` | CLI tool integration tests |
-| `COVERAGE_PLAN.md` | Test coverage planning document |
+| File                                                     | Purpose                                                     |
+| -------------------------------------------------------- | ----------------------------------------------------------- |
+| `open-sse/translator/helpers/schemaCoercion.ts`          | Schema coercion and tool description sanitization utilities |
+| `tests/unit/schema-coercion.test.mjs`                    | Unit tests for schema coercion                              |
+| `tests/unit/t40-opencode-cli-tools-integration.test.mjs` | CLI tool integration tests                                  |
+| `COVERAGE_PLAN.md`                                       | Test coverage planning document                             |
 
 ## [3.1.8] - 2026-03-27
 

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 3.1.9
+  version: 3.1.10
   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,

open-sse/handlers/chatCore.ts

@@ -27,6 +27,8 @@ import {
   saveCallLog,
 } from "@/lib/usageDb";
 import { getLoggedInputTokens, getLoggedOutputTokens } from "@/lib/usage/tokenAccounting";
+import { recordCost } from "@/domain/costRules";
+import { calculateCost } from "@/lib/usage/costCalculator";
 import { CLAUDE_OAUTH_TOOL_PREFIX } from "../translator/request/openai-to-claude.ts";
 import {
   getModelNormalizeToolCallId,
@@ -1315,6 +1317,11 @@ export async function handleChatCore({
       });
     }
 
+    if (apiKeyInfo?.id && usage) {
+      const estimatedCost = await calculateCost(provider, model, usage);
+      if (estimatedCost > 0) recordCost(apiKeyInfo.id, estimatedCost);
+    }
+
     // Translate response to client's expected format (usually OpenAI)
     // Pass toolNameMap so Claude OAuth proxy_ prefix is stripped in tool_use blocks (#605)
     let translatedResponse = needsTranslation(targetFormat, sourceFormat)
@@ -1447,22 +1454,29 @@ export async function handleChatCore({
       apiKeyName: apiKeyInfo?.name || null,
       noLog: apiKeyInfo?.noLog === true,
     }).catch(() => {});
+
+    if (apiKeyInfo?.id && streamUsage) {
+      calculateCost(provider, model, streamUsage)
+        .then((estimatedCost) => {
+          if (estimatedCost > 0) recordCost(apiKeyInfo.id, estimatedCost);
+        })
+        .catch(() => {});
+    }
   };
 
-  // For Codex provider, translate response from openai-responses to openai (Chat Completions) format
+  // For providers using Responses API format, translate stream back to openai (Chat Completions) format
   // UNLESS client is Droid CLI which expects openai-responses format back
   const isDroidCLI =
     userAgent?.toLowerCase().includes("droid") || userAgent?.toLowerCase().includes("codex-cli");
-  const needsCodexTranslation =
-    provider === "codex" &&
+  const needsResponsesTranslation =
     targetFormat === FORMATS.OPENAI_RESPONSES &&
     sourceFormat === FORMATS.OPENAI &&
     !isResponsesEndpoint &&
     !isDroidCLI;
 
-  if (needsCodexTranslation) {
-    // Codex returns openai-responses, translate to openai (Chat Completions) that clients expect
-    log?.debug?.("STREAM", `Codex translation mode: openai-responses → openai`);
+  if (needsResponsesTranslation) {
+    // Provider returns openai-responses, translate to openai (Chat Completions) that clients expect
+    log?.debug?.("STREAM", `Responses translation mode: openai-responses → openai`);
     transformStream = createSSETransformStreamWithLogger(
       "openai-responses",
       "openai",

open-sse/translator/response/claude-to-openai.ts

@@ -90,7 +90,6 @@ export function claudeToOpenAIResponse(chunk, state) {
               tool_calls: [
                 {
                   index: toolCall.index,
-                  id: toolCall.id,
                   function: { arguments: delta.partial_json },
                 },
               ],

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "3.1.9",
+  "version": "3.1.10",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "3.1.9",
+      "version": "3.1.10",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "3.1.9",
+  "version": "3.1.10",
   "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/globals.css

@@ -219,7 +219,7 @@ body {
 
 /* Material Symbols */
 .material-symbols-outlined {
-  font-family: "Material Symbols Outlined", sans-serif;
+  font-family: "Material Symbols Outlined", sans-serif !important;
   font-weight: normal;
   font-style: normal;
   font-size: 24px;

src/sse/handlers/chat.ts

@@ -42,7 +42,6 @@ import {
 import { markAccountExhaustedFrom429 } from "../../domain/quotaCache";
 import { RequestTelemetry, recordTelemetry } from "../../shared/utils/requestTelemetry";
 import { generateRequestId } from "../../shared/utils/requestId";
-import { recordCost } from "../../domain/costRules";
 import { logAuditEvent } from "../../lib/compliance/index";
 import { enforceApiKeyPolicy } from "../../shared/utils/apiKeyPolicy";
 import {
@@ -421,7 +420,6 @@ async function handleSingleModelChat(
 
     if (result.success) {
       clearModelUnavailability(provider, model);
-      recordCostIfNeeded(apiKeyInfo, result);
       if (telemetry) telemetry.startPhase("finalize");
       if (telemetry) telemetry.endPhase();
       return result.response;
@@ -670,18 +668,6 @@ async function executeChatWithBreaker({
   }
 }
 
-/**
- * Record cost if API key has budget tracking enabled.
- */
-function recordCostIfNeeded(apiKeyInfo: any, result: any) {
-  if (!apiKeyInfo?.id) return;
-  try {
-    const usage = result.usage || {};
-    const estimatedCost = ((usage.prompt_tokens || 0) + (usage.completion_tokens || 0)) * 0.000001;
-    if (estimatedCost > 0) recordCost(apiKeyInfo.id, estimatedCost);
-  } catch {}
-}
-
 // ──── Extracted helpers (T-28) ────
 
 function handleNoCredentials(

tests/unit/model-combo-mappings-db.test.mjs

@@ -79,6 +79,8 @@ test("updateModelComboMapping merges fields and returns the refreshed mapping",
     priority: 1,
   });
 
+  await new Promise((r) => setTimeout(r, 10));
+
   const updated = await mappingsDb.updateModelComboMapping(created.id, {
     pattern: "claude-*",
     comboId: comboB.id,