Merge remote-tracking branch 'upstream/master'

# Conflicts:
#	.gitignore
#	open-sse/handlers/chatCore.js

open-sse/config/appConstants.js

@@ -1,5 +1,6 @@
 import { platform, arch } from "os";
 import { PROVIDERS, PROVIDER_OAUTH } from "./providers.js";
+import { ANTIGRAVITY_IDE_USER_AGENT } from "../providers/shared.js";
 
 // === Gemini CLI === derive từ registry gemini-cli.transport
 export const GEMINI_CLI_VERSION = PROVIDERS["gemini-cli"]?.cliVersion;
@@ -59,7 +60,7 @@ export function getPlatformEnum() {
 }
 
 export function getPlatformUserAgent() {
-  return `antigravity/1.104.0 ${platform()}/${arch()}`;
+  return ANTIGRAVITY_IDE_USER_AGENT;
 }
 
 export const CLIENT_METADATA = {
@@ -129,7 +130,7 @@ export const AG_DEFAULT_TOOLS = new Set([
 
 // Antigravity chat/stream headers
 export const ANTIGRAVITY_HEADERS = {
-  "User-Agent": `antigravity/1.107.0 ${platform()}/${arch()}`
+  "User-Agent": ANTIGRAVITY_IDE_USER_AGENT
 };
 
 // Cloud Code Assist API

open-sse/config/providerModels.js

@@ -2,7 +2,7 @@ import { PROVIDERS } from "./providers.js";
 import REGISTRY from "../providers/registry/index.js";
 // PROVIDER_MODELS now built from providers/registry (transport + models co-located)
 import { PROVIDER_MODELS } from "../providers/index.js";
-import { modelQuotaFamily, modelStrip, modelTargetFormat } from "../providers/models/schema.js";
+import { modelQuotaFamily, modelStrip, modelTargetFormat, normalizeModelId } from "../providers/models/schema.js";
 import { CODEX_REVIEW_SUFFIX } from "../providers/models/helpers.js";
 
 export { PROVIDER_MODELS };
@@ -18,46 +18,69 @@ export function getDefaultModel(aliasOrId) {
   return models?.[0]?.id || null;
 }
 
+// Providers whose registry uses dots in version numbers (e.g. "claude-sonnet-4.5").
+// For these, we tolerate clients sending dashes ("claude-sonnet-4-5") by normalizing
+// digit-hyphen-digit to digit-dot-digit before lookup. Other providers are left untouched.
+const DOT_VERSION_PROVIDERS = new Set(["kr", "kiro"]);
+
+// Find a registry entry by id. For Kiro models, tolerates dash/dot version separators
+// ("claude-sonnet-4-5" ~= "claude-sonnet-4.5"). Other providers use exact match only.
+function findModel(models, modelId, aliasOrId) {
+  if (!models) return undefined;
+  const found = models.find(m => m.id === modelId);
+  if (found) return found;
+  if (!DOT_VERSION_PROVIDERS.has(aliasOrId)) return undefined;
+  const normalized = normalizeModelId(modelId);
+  if (normalized === modelId) return undefined;
+  return models.find(m => m.id === normalized);
+}
+
 export function isValidModel(aliasOrId, modelId, passthroughProviders = new Set()) {
   if (passthroughProviders.has(aliasOrId)) return true;
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return false;
-  return models.some(m => m.id === modelId);
+  return !!findModel(models, modelId, aliasOrId);
 }
 
 export function findModelName(aliasOrId, modelId) {
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return modelId;
-  const found = models.find(m => m.id === modelId);
+  const found = findModel(models, modelId, aliasOrId);
   return found?.name || modelId;
 }
 
 export function getModelTargetFormat(aliasOrId, modelId) {
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return null;
-  return modelTargetFormat(models.find(m => m.id === modelId));
+  return modelTargetFormat(findModel(models, modelId, aliasOrId));
 }
 
 export function getModelType(aliasOrId, modelId) {
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return null;
-  const found = models.find(m => m.id === modelId);
+  const found = findModel(models, modelId, aliasOrId);
   return found?.kind || found?.type || null;
 }
 
 export function getModelUpstreamId(aliasOrId, modelId) {
+  // Split off thinking suffix "(level)" so lookup hits the base id; re-append it to
+  // the result so downstream applyThinking still sees the suffix (body.model is stripped separately).
+  const sufMatch = typeof modelId === "string" ? modelId.match(/\([^()]+\)\s*$/) : null;
+  const suffix = sufMatch ? sufMatch[0] : "";
+  const baseId = suffix ? modelId.slice(0, sufMatch.index).trim() : modelId;
   const models = PROVIDER_MODELS[aliasOrId];
-  const found = models?.find(m => m.id === modelId);
-  if (found?.upstreamModelId) return found.upstreamModelId;
-  if (aliasOrId === "cx" && typeof modelId === "string" && modelId.endsWith(CODEX_REVIEW_SUFFIX)) {
-    return modelId.slice(0, -CODEX_REVIEW_SUFFIX.length);
+  const found = findModel(models, baseId, aliasOrId);
+  if (found?.upstreamModelId) return found.upstreamModelId + suffix;
+  if (found?.id) return found.id + suffix;
+  if (aliasOrId === "cx" && typeof baseId === "string" && baseId.endsWith(CODEX_REVIEW_SUFFIX)) {
+    return baseId.slice(0, -CODEX_REVIEW_SUFFIX.length) + suffix;
   }
-  return modelId;
+  return baseId + suffix;
 }
 
 export function getModelQuotaFamily(aliasOrId, modelId) {
   const models = PROVIDER_MODELS[aliasOrId];
-  return modelQuotaFamily(models?.find(m => m.id === modelId));
+  return modelQuotaFamily(findModel(models, modelId, aliasOrId));
 }
 
 // OAuth short aliases — derived from registry `alias` (single source). everything else: alias = id.
@@ -79,5 +102,5 @@ export function getModelsByProviderId(providerId) {
 // Get strip list for a model entry (explicit opt-in only)
 // Returns array of content types to strip, e.g. ["image", "audio"]
 export function getModelStrip(alias, modelId) {
-  return modelStrip(PROVIDER_MODELS[alias]?.find(m => m.id === modelId));
+  return modelStrip(findModel(PROVIDER_MODELS[alias], modelId, alias));
 }

open-sse/config/runtimeConfig.js

@@ -39,6 +39,15 @@ function envMs(name, def) {
   return Number.isFinite(n) && n > 0 ? n : def;
 }
 
+function envUrl(name, def) {
+  const raw = process.env[name]?.trim();
+  return raw || def;
+}
+
+// SearXNG endpoint used by the unauthenticated web-search provider.
+// Configure this for a separate Docker service or remote SearXNG instance.
+export const SEARXNG_URL = envUrl("SEARXNG_URL", "http://localhost:8888/search");
+
 // Inter-chunk stall timeout (once tokens are flowing). Generous headroom so
 // slow reasoning models aren't aborted mid-stream. Env: STREAM_STALL_TIMEOUT_MS.
 export const STREAM_STALL_TIMEOUT_MS = envMs("STREAM_STALL_TIMEOUT_MS", 360 * 1000);