Merge remote-tracking branch 'upstream/master'

open-sse/config/providerModels.js

@@ -3,7 +3,8 @@ 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, modelSupportedFormats, normalizeModelId } from "../providers/models/schema.js";
-import { CODEX_REVIEW_SUFFIX } from "../providers/models/helpers.js";
+import { CODEX_REVIEW_SUFFIX, isMuseSparkModel } from "../providers/models/helpers.js";
+import { FORMATS } from "../translator/formats.js";
 export { PROVIDER_MODELS };
 
 
@@ -49,6 +50,9 @@ export function findModelName(aliasOrId, modelId) {
 }
 
 export function getModelTargetFormat(aliasOrId, modelId) {
+  if ((!aliasOrId || aliasOrId === "oc" || aliasOrId === "opencode") && isMuseSparkModel(modelId)) {
+    return FORMATS.OPENAI_RESPONSES;
+  }
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return null;
   return modelTargetFormat(findModel(models, modelId, aliasOrId));

open-sse/executors/opencode.js

@@ -4,10 +4,14 @@ import { PROVIDERS } from "../config/providers.js";
 import { getThinkingLevels } from "../providers/thinkingLevels.js";
 import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
 import { resolveSessionId } from "../utils/sessionManager.js";
+import { isMuseSparkModel } from "../providers/models/helpers.js";
 
 const OPENCODE_UA = "opencode";
 // Models served by /zen/v1/responses; every other model stays on /chat/completions.
-const RESPONSES_MODELS = new Set(["muse-spark-1.2-contributor-free"]);
+const RESPONSES_MODELS = new Set([
+  "muse-spark-1.2-contributor-free",
+  "muse-spark-1.3-contributor-free",
+]);
 
 function generateRequestId() {
   return `msg_${crypto.randomUUID().replace(/-/g, "")}`;
@@ -23,7 +27,8 @@ function baseModelId(model) {
 }
 
 function isResponsesModel(model) {
-  return RESPONSES_MODELS.has(baseModelId(model));
+  const base = baseModelId(model);
+  return RESPONSES_MODELS.has(base) || isMuseSparkModel(base);
 }
 
 function resolveOpencodeSession(body, credentials) {

open-sse/handlers/chatCore/requestDetail.js

@@ -25,10 +25,16 @@ export function extractUsageFromResponse(responseBody) {
   if (!responseBody || typeof responseBody !== "object") return null;
 
   // Claude format
+  // Note: OpenAI Responses usage ({input_tokens, input_tokens_details:{cached_tokens}})
+  // also matches this branch. Its prompt is cache-INCLUSIVE and its cache rides in
+  // input_tokens_details, so emit it as cached_tokens — the convention
+  // canonicalizeUsage() passes through without folding. Reading it here keeps
+  // cache accounting correct for /v1/responses and codex traffic.
   if (responseBody.usage?.input_tokens !== undefined) {
     return {
       prompt_tokens: responseBody.usage.input_tokens || 0,
       completion_tokens: responseBody.usage.output_tokens || 0,
+      cached_tokens: responseBody.usage.cached_tokens ?? responseBody.usage.input_tokens_details?.cached_tokens,
       cache_read_input_tokens: responseBody.usage.cache_read_input_tokens,
       cache_creation_input_tokens: responseBody.usage.cache_creation_input_tokens
     };
@@ -39,7 +45,7 @@ export function extractUsageFromResponse(responseBody) {
     return {
       prompt_tokens: responseBody.usage.prompt_tokens || 0,
       completion_tokens: responseBody.usage.completion_tokens || 0,
-      cached_tokens: responseBody.usage.prompt_tokens_details?.cached_tokens,
+      cached_tokens: responseBody.usage.cached_tokens ?? responseBody.usage.prompt_tokens_details?.cached_tokens,
       reasoning_tokens: responseBody.usage.completion_tokens_details?.reasoning_tokens
     };
   }

open-sse/handlers/fetch/index.js

@@ -1,4 +1,4 @@
-// Web Fetch handler — dispatches to firecrawl, jina-reader, tavily, exa
+// Web Fetch handler — dispatches to firecrawl, jina-reader, tavily, exa, ollama
 // Returns normalized shape across all providers
 
 const DEFAULT_TIMEOUT_MS = 15000;
@@ -56,8 +56,8 @@ function parseJinaTitle(text) {
   return m ? m[1].trim() : null;
 }
 
-function buildData({ provider, url, title, format, text, costUsd, responseMs, upstreamMs }) {
-  return {
+function buildData({ provider, url, title, format, text, links, costUsd, responseMs, upstreamMs }) {
+  const data = {
     provider,
     url,
     title: title || null,
@@ -66,6 +66,8 @@ function buildData({ provider, url, title, format, text, costUsd, responseMs, up
     usage: { fetch_cost_usd: costUsd ?? null },
     metrics: { response_time_ms: responseMs, upstream_latency_ms: upstreamMs }
   };
+  if (Array.isArray(links)) data.links = links;
+  return data;
 }
 
 async function readJsonOrText(res) {
@@ -115,6 +117,18 @@ export async function handleFetchCore({ url, format, maxCharacters, provider, pr
     if (provider === "exa") {
       return await runExa({ url, fmt, timeoutMs, apiKey, maxCharacters, costPerQuery, startedAt });
     }
+    if (provider === "ollama") {
+      return await runOllama({
+        url,
+        fmt,
+        timeoutMs,
+        apiKey,
+        maxCharacters,
+        costPerQuery,
+        startedAt,
+        baseUrl: providerConfig?.baseUrl,
+      });
+    }
     return { success: false, status: 400, error: `Unsupported provider: ${provider}` };
   } catch (err) {
     log?.("fetch handler error:", err?.message || err);
@@ -241,3 +255,56 @@ async function runExa({ url, fmt, timeoutMs, apiKey, maxCharacters, costPerQuery
     })
   };
 }
+
+async function runOllama({
+  url,
+  fmt,
+  timeoutMs,
+  apiKey,
+  maxCharacters,
+  costPerQuery,
+  startedAt,
+  baseUrl,
+}) {
+  const upstreamStart = Date.now();
+  const r = await tryFetch(baseUrl, {
+    method: "POST",
+    headers: {
+      "content-type": "application/json",
+      ...(apiKey ? { authorization: `Bearer ${apiKey}` } : {})
+    },
+    body: JSON.stringify({ url })
+  }, timeoutMs);
+
+  if (!r.ok) {
+    return { success: false, status: r.timeout ? 504 : 502, error: r.error };
+  }
+  const upstreamMs = Date.now() - upstreamStart;
+  const { json, text: responseText } = await readJsonOrText(r.res);
+  if (!r.res.ok) {
+    const error = json?.error
+      || json?.message
+      || responseText?.slice(0, 500)
+      || `Ollama error: ${r.res.status}`;
+    return { success: false, status: r.res.status, error };
+  }
+  if (!json || typeof json.content !== "string") {
+    return { success: false, status: 502, error: "Ollama returned an empty or invalid web fetch response" };
+  }
+
+  const text = truncate(json.content, maxCharacters);
+  return {
+    success: true,
+    data: buildData({
+      provider: "ollama",
+      url,
+      title: json.title || null,
+      format: fmt,
+      text,
+      links: json.links,
+      costUsd: costPerQuery,
+      responseMs: Date.now() - startedAt,
+      upstreamMs
+    })
+  };
+}

open-sse/handlers/search/index.js

@@ -10,6 +10,7 @@
 import { buildSearchRequest } from "./callers.js";
 import { normalizeSearchResponse } from "./normalizers.js";
 import { handleChatSearch } from "./chatSearch.js";
+import { fetchPublic } from "../../../src/shared/utils/ssrfGuard.js";
 
 const GLOBAL_TIMEOUT_MS = 15000;
 const NON_RETRIABLE = new Set([400, 401, 403, 404]);
@@ -100,7 +101,7 @@ async function tryDedicatedProvider({ provider, providerConfig, body, credential
   log?.info?.("SEARCH", `${provider.id} | "${params.query.slice(0, 80)}" | type=${params.searchType}`);
 
   try {
-    const resp = await fetch(url, { ...init, headers: sanitizeHeaders(init.headers), signal: controller.signal });
+    const resp = await fetchPublic(url, { ...init, headers: sanitizeHeaders(init.headers), signal: controller.signal });
     clearTimeout(timer);
     if (!resp.ok) {
       const errText = await resp.text().catch(() => "");

open-sse/providers/capabilities.js

@@ -83,7 +83,8 @@ export function capabilitiesFromServiceKind(kind) {
  * otherwise mis-match. Only declare deltas vs DEFAULT.
  */
 export const MODEL_CAPABILITIES = {
-  // Claude Opus 5, 4.6/4.7/4.8, and Kiro Sonnet 5 have 1M context + adaptive thinking (override generic claude pattern)
+  // Claude Fable 5.1, Opus 5, 4.6/4.7/4.8, and Kiro Sonnet 5 have 1M context + adaptive thinking (override generic claude pattern)
+  "claude-fable-5-1": { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 128000 },
   "claude-opus-5":     { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
   "claude-opus-5-thinking": { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
   "claude-opus-5-agentic": { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
@@ -126,8 +127,10 @@ export const MODEL_CAPABILITIES = {
   "kimi-for-coding-highspeed": { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
   "kimi-k2.7-code":    { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
   "kimi-k2.7-code-highspeed": { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
-  // OpenCode Free Muse Spark — OpenAI Responses reasoning supports up to xhigh.
-  "muse-spark-1.2-contributor-free": { reasoning: true, thinkingFormat: "openai", contextWindow: 1048576, maxOutput: 131072 },
+  // OpenCode Free Muse Spark — multimodal (text+image per models.dev meta/muse-spark)
+  // via OpenAI Responses input_image; reasoning supports up to xhigh.
+  "muse-spark-1.2-contributor-free": { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 1048576, maxOutput: 131072 },
+  "muse-spark-1.3-contributor-free": { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 1048576, maxOutput: 131072 },
 };
 
 const KIRO_GPT_5_6_CAPABILITIES = { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 272000, maxOutput: 128000 };
@@ -190,6 +193,15 @@ export const PROVIDER_CAPABILITIES = {
     "kimi-k2.6":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
     "kimi-k2.5":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 164000, maxOutput: 32000 },
     "hy3-preview":        { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
+    // hy3/hy3-x: 256K official (192K conservative, matches hy3-preview); hy4-preview: 1M official.
+    // glm-5.3: 1M (GLM-5.x gen); glm-5.3-flash window unverified (200K conservative).
+    "hy3":                { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
+    "hy3-x":              { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
+    "hy4-preview":        { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 64000 },
+    "hy4-preview-x":      { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 64000 },
+    "glm-5.3":            { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 48000 },
+    "glm-5.3-flash":      { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
+    "kimi-k3-1":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
     "deepseek-v4-pro":    { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
     "deepseek-v4-flash":  { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
     "deepseek-v3-2-volc": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 96000, maxOutput: 32000 },
@@ -225,6 +237,7 @@ export const PATTERN_CAPABILITIES = [
 
   // ── Gemini (all 2.0+ multimodal + google_search grounding, 1M ctx) ─
   { pattern: "*gemini*image*",  caps: { vision: true, imageOutput: true, contextWindow: 1048576 } },
+  { pattern: "*gemini-3.8*",    caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
   { pattern: "*gemini-3.7*",    caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
   { pattern: "*gemini-3*pro*",  caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65535 } },
   { pattern: "*gemini-3*",      caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
@@ -335,6 +348,9 @@ export const PATTERN_CAPABILITIES = [
   { pattern: "*laguna-s-2.1*",  caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 1000000, maxOutput: 32000 } },
   { pattern: "*laguna*",        caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 32000 } },
 
+
+  // ── OpenCode Free Muse Spark (multimodal text+image; OpenAI Responses reasoning supports up to xhigh) ─
+  { pattern: "*muse*spark*",    caps: { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 1048576, maxOutput: 131072 } },
   // ── Others ───────────────────────────────────────────────────────
   { pattern: "*hunyuan*",       caps: { reasoning: true, thinkingFormat: "hunyuan", contextWindow: 262144, maxOutput: 262144 } },
   { pattern: "hy3*",            caps: { reasoning: true, thinkingFormat: "hunyuan", contextWindow: 262144, maxOutput: 262144 } },

open-sse/providers/models/helpers.js

@@ -18,3 +18,10 @@ export function withCodexReviewModels(models) {
     ];
   });
 }
+
+export function isMuseSparkModel(modelId) {
+  if (!modelId || typeof modelId !== "string") return false;
+  const clean = modelId.replace(/\([^()]+\)\s*$/, "").trim();
+  const base = clean.includes("/") ? clean.split("/").pop() : clean;
+  return /^muse[-_]?spark(?:$|[-_:.\s])/i.test(base);
+}

open-sse/providers/pricing.js

@@ -57,6 +57,10 @@ export const MODEL_PRICING = {
   "o1-mini":                      { input: 3.00,  output: 12.00, cached: 1.50,  reasoning: 18.00,  cache_creation: 3.00  },
 
   // === Gemini ===
+  "gemini-3.8-flash":              { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
+  "gemini-3.8-flash-high":         { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
+  "gemini-3.8-flash-medium":       { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
+  "gemini-3.8-flash-low":          { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.7-flash":              { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.7-flash-high":         { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.7-flash-medium":       { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
@@ -260,6 +264,7 @@ export const PROVIDER_PRICING = {
     "z-ai/glm-5-turbo": { input: 1.2, output: 4.0, cached: 0.24, reasoning: 4.0 },
     "z-ai/glm-5.1": { input: 1.05, output: 3.5, cached: 0.525, reasoning: 3.5 },
     "z-ai/glm-5.2": { input: 1.4, output: 4.4, cached: 0.26, reasoning: 4.4 },
+    "z-ai/glm-5.3-free": { input: 0, output: 0, cached: 0, reasoning: 0 },
   },
 };
 

open-sse/providers/registry/antigravity.js

@@ -36,8 +36,7 @@ export default {
       },
     },
     usage: {
-      // Discovery (quota/project) on PROD; daily host rejects these.
-      quotaApiUrl: "https://cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels",
+      quotaApiUrl: `${ANTIGRAVITY_IDE_BASE_URL}/v1internal:fetchAvailableModels`,
       loadProjectApiUrl: "https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist",
       tokenUrl: "https://oauth2.googleapis.com/token",
     },
@@ -45,6 +44,10 @@ export default {
     clientSecret: "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",
   },
   models: [
+    { id: "gemini-3.8-flash-high", name: "Gemini 3.8 Flash (High)", upstreamModelId: "gemini-3.8-flash-high(high)" },
+    { id: "gemini-3.8-flash-medium", name: "Gemini 3.8 Flash (Medium)", upstreamModelId: "gemini-3.8-flash-medium(medium)" },
+    { id: "gemini-3.8-flash-low", name: "Gemini 3.8 Flash (Low)", upstreamModelId: "gemini-3.8-flash-low(low)" },
+    { id: "gemini-3.8-flash", name: "Gemini 3.8 Flash", upstreamModelId: "gemini-3.8-flash-medium(medium)" },
     { id: "gemini-3.7-flash-high", name: "Gemini 3.7 Flash (High)", upstreamModelId: "gemini-3.7-flash-tiered(high)" },
     { id: "gemini-3.7-flash-medium", name: "Gemini 3.7 Flash (Medium)", upstreamModelId: "gemini-3.7-flash-tiered(medium)" },
     { id: "gemini-3.7-flash-low", name: "Gemini 3.7 Flash (Low)", upstreamModelId: "gemini-3.7-flash-tiered(low)" },

open-sse/providers/registry/claude.js

@@ -1,4 +1,4 @@
-import { CLAUDE_CLI_SPOOF_HEADERS } from "../shared.js";
+import { CLAUDE_CLI_VERSION } from "../shared.js";
 
 export default {
   id: "claude",
@@ -25,7 +25,7 @@ export default {
       "Anthropic-Version": "2023-06-01",
       "Anthropic-Beta": "claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,advanced-tool-use-2025-11-20,effort-2025-11-24,structured-outputs-2025-12-15,fast-mode-2026-02-01,redact-thinking-2026-02-12,token-efficient-tools-2026-03-28",
       "Anthropic-Dangerous-Direct-Browser-Access": "true",
-      "User-Agent": "claude-cli/2.1.92 (external, sdk-cli)",
+      "User-Agent": `claude-cli/${CLAUDE_CLI_VERSION} (external, sdk-cli)`,
       "X-App": "cli",
       "X-Stainless-Helper-Method": "stream",
       "X-Stainless-Retry-Count": "0",
@@ -58,6 +58,7 @@ export default {
   },
   models: [
     { id: "claude-opus-5", name: "Claude Opus 5" },
+    { id: "claude-fable-5-1", name: "Claude Fable 5.1" },
     { id: "claude-fable-5", name: "Claude Fable 5" },
     { id: "claude-sonnet-5", name: "Claude Sonnet 5" },
     { id: "claude-haiku-4-5-20251001", name: "Claude 4.5 Haiku" },

open-sse/providers/registry/codebuddy-cn.js

@@ -47,16 +47,24 @@ export default {
   models: [
     { id: "glm-5.2", name: "GLM-5.2" },
     { id: "glm-5.1", name: "GLM-5.1" },
-    { id: "glm-5.0", name: "GLM-5.0" },
     { id: "glm-5.0-turbo", name: "GLM-5.0-Turbo" },
     { id: "glm-5v-turbo", name: "GLM-5v-Turbo" },
-    { id: "glm-4.7", name: "GLM-4.7" },
     { id: "minimax-m3", name: "MiniMax-M3" },
     { id: "minimax-m2.7", name: "MiniMax-M2.7" },
     { id: "kimi-k2.7", name: "Kimi-K2.7-Code" },
     { id: "kimi-k2.6", name: "Kimi-K2.6" },
     { id: "kimi-k2.5", name: "Kimi-K2.5" },
+    // "-x" suffix = paid tier of the same model (free id rides the promo quota:
+    // hy3 free until 2026-08-31, hy4-preview until 2026-09-10). Server model table
+    // seen in client logs 2026-08-30; glm-5.0 / glm-4.7 removed (API 11102 dead).
     { id: "hy3-preview", name: "Hy3 Preview" },
+    { id: "hy3", name: "Hy3" },
+    { id: "hy3-x", name: "Hy3 (Paid)" },
+    { id: "hy4-preview", name: "Hy4-Preview" },
+    { id: "hy4-preview-x", name: "Hy4-Preview (Paid)" },
+    { id: "glm-5.3", name: "GLM-5.3" },
+    { id: "glm-5.3-flash", name: "GLM-5.3-Flash" },
+    { id: "kimi-k3-1", name: "Kimi-K3" },
     { id: "deepseek-v4-pro", name: "DeepSeek-V4-Pro" },
     { id: "deepseek-v4-flash", name: "DeepSeek-V4-Flash" },
     { id: "deepseek-v3-2-volc", name: "DeepSeek-V3.2" },

open-sse/providers/registry/gemini.js

@@ -36,6 +36,7 @@ export default {
     },
   },
   models: [
+    { id: "gemini-3.8-flash", name: "Gemini 3.8 Flash" },
     { id: "gemini-3.7-flash", name: "Gemini 3.7 Flash" },
     { id: "gemini-3.6-flash", name: "Gemini 3.6 Flash" },
     { id: "gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite" },

open-sse/providers/registry/groq.js

@@ -17,6 +17,12 @@ export default {
   transport: {
     baseUrl: "https://api.groq.com/openai/v1/chat/completions",
     validateUrl: "https://api.groq.com/openai/v1/models",
+    // No dedicated quota endpoint; rate-limit info rides on x-ratelimit-*
+    // response headers, always included. Reuse the models list (already
+    // used as validateUrl) so reading usage never costs tokens.
+    usage: {
+      url: "https://api.groq.com/openai/v1/models",
+    },
   },
   models: [
     { id: "llama-3.3-70b-versatile", name: "Llama 3.3 70B" },
@@ -34,4 +40,8 @@ export default {
     authHeader: "bearer",
     format: "openai",
   },
+  features: {
+    usage: true,
+    usageApikey: true,
+  },
 };

open-sse/providers/registry/ollama.js

@@ -31,7 +31,16 @@ export default {
     { id: "qwen3.5", name: "Qwen3.5" },
     { id: "minimax-m3", name: "MiniMax M3" },
   ],
-  serviceKinds: ["llm"],
+  serviceKinds: ["llm", "webFetch"],
+  fetchConfig: {
+    baseUrl: "https://ollama.com/api/web_fetch",
+    method: "POST",
+    authType: "apikey",
+    authHeader: "bearer",
+    formats: ["markdown"],
+    maxCharacters: 200000,
+    timeoutMs: 30000,
+  },
   features: {
     usage: true,
     usageApikey: true,

open-sse/providers/registry/opencode.js

@@ -20,9 +20,10 @@ export default {
     noAuth: true,
   },
   models: [
-    // Only this model is served by /zen/v1/responses; the rest stay on
+    // Muse Spark models are served by /zen/v1/responses; the rest stay on
     // /chat/completions, so the format is declared per-model, not per-provider.
     { id: "muse-spark-1.2-contributor-free", name: "Muse Spark 1.2 Contributor Free", targetFormat: "openai-responses" },
+    { id: "muse-spark-1.3-contributor-free", name: "Muse Spark 1.3 Contributor Free", targetFormat: "openai-responses" },
   ],
   modelsFetcher: { url: "https://opencode.ai/zen/v1/models", type: "opencode-free" },
   passthroughModels: true,

open-sse/providers/registry/tokenrouter.js

@@ -24,129 +24,31 @@ export default {
     validateUrl: "https://api.tokenrouter.com/v1/models",
     thinkingFormat: "tokenrouter",
   },
-  // Seed snapshot from live /v1/models (120 entries). Latest catalogue is
+  // Seed snapshot from live /v1/models. Latest catalogue is
   // fetched via modelsFetcher; other ids still accepted via passthroughModels.
   models: [
-    { id: "MiniMax-Hailuo-2.3", name: "Minimax Hailuo 2.3", kind: "video" },
-    { id: "MiniMax-M3", name: "Minimax M3" },
-    { id: "anthropic/claude-fable-5", name: "Claude Fable 5" },
     { id: "anthropic/claude-haiku-4.5", name: "Claude Haiku 4.5" },
-    { id: "anthropic/claude-opus-4.5", name: "Claude Opus 4.5" },
-    { id: "anthropic/claude-opus-4.6", name: "Claude Opus 4.6" },
-    { id: "anthropic/claude-opus-4.7", name: "Claude Opus 4.7" },
-    { id: "anthropic/claude-opus-4.7-fast", name: "Claude Opus 4.7 Fast" },
+    { id: "anthropic/claude-sonnet-4.6", name: "Claude Sonnet 4.6" },
     { id: "anthropic/claude-opus-4.8", name: "Claude Opus 4.8" },
     { id: "anthropic/claude-opus-4.8-fast", name: "Claude Opus 4.8 Fast" },
-    { id: "anthropic/claude-opus-5", name: "Claude Opus 5" },
-    { id: "anthropic/claude-opus-5-fast", name: "Claude Opus 5 Fast" },
-    { id: "anthropic/claude-sonnet-4", name: "Claude Sonnet 4" },
-    { id: "anthropic/claude-sonnet-4.5", name: "Claude Sonnet 4.5" },
-    { id: "anthropic/claude-sonnet-4.6", name: "Claude Sonnet 4.6" },
-    { id: "anthropic/claude-sonnet-5", name: "Claude Sonnet 5" },
-    { id: "bytedance-seed/seedream-4.5", name: "Seedream 4.5", kind: "image" },
-    { id: "bytedance-seed/seedream-5.0-lite", name: "Seedream 5.0 Lite", kind: "image" },
-    { id: "bytedance-seed/seedream-5.0-pro", name: "Seedream 5.0 Pro", kind: "image" },
-    { id: "claude-haiku-4-5", name: "Claude Haiku 4 5" },
-    { id: "claude-opus-4-8-m-aws", name: "Claude Opus 4 8 M Aws" },
-    { id: "deepseek/deepseek-v3.2", name: "Deepseek V3.2" },
-    { id: "deepseek/deepseek-v4-flash", name: "Deepseek V4 Flash" },
-    { id: "deepseek/deepseek-v4-flash-0731", name: "Deepseek V4 Flash 0731" },
-    { id: "deepseek/deepseek-v4-pro", name: "Deepseek V4 Pro" },
-    { id: "ex/gpt-5.4", name: "Gpt 5.4" },
-    { id: "google/gemini-2.5-flash-image", name: "Gemini 2.5 Flash Image" },
-    { id: "google/gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
-    { id: "google/gemini-3-pro-image-preview", name: "Gemini 3 Pro Image Preview" },
-    { id: "google/gemini-3.1-flash-image-preview", name: "Gemini 3.1 Flash Image Preview" },
-    { id: "google/gemini-3.1-flash-lite-image", name: "Gemini 3.1 Flash Lite Image" },
-    { id: "google/gemini-3.1-pro-preview", name: "Gemini 3.1 Pro Preview" },
-    { id: "google/gemini-3.5-flash", name: "Gemini 3.5 Flash" },
-    { id: "google/gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite" },
-    { id: "google/gemini-3.6-flash", name: "Gemini 3.6 Flash" },
-    { id: "google/gemini-embedding-2", name: "Gemini Embedding 2" },
-    { id: "google/gemma-4-26b-a4b-it", name: "Gemma 4 26B A4B It" },
-    { id: "happyhorse-1.0-t2v", name: "Happyhorse 1.0 T2V", kind: "video" },
-    { id: "kling-3.0-turbo", name: "Kling 3.0 Turbo", kind: "video" },
-    { id: "kling-v2-6", name: "Kling V2 6", kind: "video" },
-    { id: "kling-v3", name: "Kling V3", kind: "video" },
-    { id: "kling-v3-omni", name: "Kling V3 Omni", kind: "video" },
-    { id: "microsoft/mai-image-2.5", name: "Mai Image 2.5" },
-    { id: "minimax/minimax-m2-her", name: "Minimax M2 Her" },
-    { id: "minimax/minimax-m2.1", name: "Minimax M2.1" },
-    { id: "minimax/minimax-m2.1-highspeed", name: "Minimax M2.1 Highspeed" },
-    { id: "minimax/minimax-m2.5", name: "Minimax M2.5" },
-    { id: "minimax/minimax-m2.7", name: "Minimax M2.7" },
-    { id: "minimax/minimax-m2.7-highspeed", name: "Minimax M2.7 Highspeed" },
-    { id: "miromind/mirothinker-1-7-deepresearch", name: "Mirothinker 1 7 Deepresearch" },
-    { id: "miromind/mirothinker-1-7-deepresearch-mini", name: "Mirothinker 1 7 Deepresearch Mini" },
-    { id: "mistralai/devstral-2512", name: "Devstral 2512" },
-    { id: "mistralai/mistral-medium-3-5", name: "Mistral Medium 3 5" },
-    { id: "mistralai/mistral-small-2603", name: "Mistral Small 2603" },
-    { id: "mistralai/voxtral-small-24b-2507", name: "Voxtral Small 24B 2507" },
-    { id: "moonshotai/kimi-k2.5", name: "Kimi K2.5" },
-    { id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
-    { id: "moonshotai/kimi-k2.7-code", name: "Kimi K2.7 Code" },
-    { id: "moonshotai/kimi-k3", name: "Kimi K3" },
-    { id: "moonshotai/kimi-k3-free", name: "Kimi K3 Free" },
-    { id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", name: "Nemotron 3 Nano Omni 30B A3B Reasoning:Free" },
-    { id: "nvidia/nemotron-3-super-120b-a12b", name: "Nemotron 3 Super 120B A12B" },
-    { id: "openai/gpt-4o-mini", name: "Gpt 4O Mini" },
-    { id: "openai/gpt-5", name: "Gpt 5" },
-    { id: "openai/gpt-5-image", name: "Gpt 5 Image" },
-    { id: "openai/gpt-5-image-mini", name: "Gpt 5 Image Mini" },
-    { id: "openai/gpt-5-mini", name: "Gpt 5 Mini" },
-    { id: "openai/gpt-5.2", name: "Gpt 5.2" },
     { id: "openai/gpt-5.4", name: "Gpt 5.4" },
-    { id: "openai/gpt-5.4-image-2", name: "Gpt 5.4 Image 2", kind: "image" },
     { id: "openai/gpt-5.4-mini", name: "Gpt 5.4 Mini" },
-    { id: "openai/gpt-5.4-nano", name: "Gpt 5.4 Nano" },
     { id: "openai/gpt-5.4-pro", name: "Gpt 5.4 Pro" },
     { id: "openai/gpt-5.5", name: "Gpt 5.5" },
-    { id: "openai/gpt-5.5-pro", name: "Gpt 5.5 Pro" },
-    { id: "openai/gpt-5.6-luna", name: "Gpt 5.6 Luna" },
     { id: "openai/gpt-5.6-sol", name: "Gpt 5.6 Sol" },
-    { id: "openai/gpt-5.6-terra", name: "Gpt 5.6 Terra" },
-    { id: "openai/gpt-audio", name: "Gpt Audio", kind: "audio" },
-    { id: "openai/gpt-audio-mini", name: "Gpt Audio Mini", kind: "audio" },
-    { id: "openai/gpt-oss-120b", name: "Gpt Oss 120B" },
+    { id: "google/gemini-3.5-flash", name: "Gemini 3.5 Flash" },
+    { id: "google/gemini-3.6-flash", name: "Gemini 3.6 Flash" },
+    { id: "deepseek/deepseek-v4-flash", name: "Deepseek V4 Flash" },
+    { id: "deepseek/deepseek-v4-pro", name: "Deepseek V4 Pro" },
     { id: "qwen/qwen3-coder-next", name: "Qwen3 Coder Next" },
-    { id: "qwen/qwen3.5-122b-a10b", name: "Qwen3.5 122B A10B" },
-    { id: "qwen/qwen3.5-35b-a3b", name: "Qwen3.5 35B A3B" },
-    { id: "qwen/qwen3.5-397b-a17b", name: "Qwen3.5 397B A17B" },
-    { id: "qwen/qwen3.5-9b", name: "Qwen3.5 9B" },
-    { id: "qwen/qwen3.5-flash", name: "Qwen3.5 Flash" },
-    { id: "qwen/qwen3.5-plus-02-15", name: "Qwen3.5 Plus 02 15" },
-    { id: "qwen/qwen3.6-plus", name: "Qwen3.6 Plus" },
     { id: "qwen/qwen3.7-max", name: "Qwen3.7 Max" },
-    { id: "qwen/qwen3.7-plus", name: "Qwen3.7 Plus" },
     { id: "qwen/qwen3.8-max", name: "Qwen3.8 Max" },
-    { id: "qwen3.5-omni-plus", name: "Qwen3.5 Omni Plus" },
-    { id: "qwen3.6-flash", name: "Qwen3.6 Flash" },
-    { id: "sakana/fugu-ultra", name: "Fugu Ultra" },
-    { id: "seed-2-0-code-preview-260328", name: "Seed 2 0 Code Preview 260328" },
-    { id: "seed-2-0-lite-260428", name: "Seed 2 0 Lite 260428" },
-    { id: "seed-2-0-mini-260428", name: "Seed 2 0 Mini 260428" },
-    { id: "seed-2-0-pro-260328", name: "Seed 2 0 Pro 260328" },
-    { id: "stepfun/step-3.5-flash", name: "Step 3.5 Flash" },
-    { id: "stepfun/step-3.7-flash", name: "Step 3.7 Flash" },
-    { id: "tencent/hy3-preview", name: "Hy3 Preview" },
-    { id: "x-ai/grok-4.1-fast", name: "Grok 4.1 Fast" },
-    { id: "x-ai/grok-4.20-beta", name: "Grok 4.20 Beta" },
-    { id: "x-ai/grok-4.3", name: "Grok 4.3" },
-    { id: "x-ai/grok-4.5", name: "Grok 4.5" },
-    { id: "x-ai/grok-build-0.1", name: "Grok Build 0.1" },
-    { id: "xiaomi/mimo-v2-flash", name: "Mimo V2 Flash" },
-    { id: "xiaomi/mimo-v2-omni", name: "Mimo V2 Omni" },
-    { id: "xiaomi/mimo-v2-pro", name: "Mimo V2 Pro" },
-    { id: "xiaomi/mimo-v2.5", name: "Mimo V2.5" },
-    { id: "xiaomi/mimo-v2.5-pro", name: "Mimo V2.5 Pro" },
-    { id: "z-ai/glm-4.5-air", name: "Glm 4.5 Air" },
-    { id: "z-ai/glm-4.6", name: "Glm 4.6" },
-    { id: "z-ai/glm-4.6v", name: "Glm 4.6V" },
-    { id: "z-ai/glm-4.7", name: "Glm 4.7" },
-    { id: "z-ai/glm-5", name: "Glm 5" },
-    { id: "z-ai/glm-5-turbo", name: "Glm 5 Turbo" },
-    { id: "z-ai/glm-5.1", name: "Glm 5.1" },
+    { id: "moonshotai/kimi-k2.7-code", name: "Kimi K2.7 Code" },
+    { id: "moonshotai/kimi-k3-free", name: "Kimi K3 Free" },
+    { id: "z-ai/glm-5.3-free", name: "Glm 5.3 Free" },
     { id: "z-ai/glm-5.2", name: "Glm 5.2" },
+    { id: "z-ai/glm-5-turbo", name: "Glm 5 Turbo" },
+    { id: "x-ai/grok-4.5", name: "Grok 4.5" },
   ],
   serviceKinds: ["llm", "embedding", "image"],
   embeddingConfig: {

open-sse/providers/shared.js

@@ -22,6 +22,7 @@ export function mapStainlessArch() {
 
 // Anthropic API version (single source — reused across claude-format providers/executors)
 export const ANTHROPIC_API_VERSION = "2023-06-01";
+export const CLAUDE_CLI_VERSION = "2.1.258";
 
 // Shared Claude-compatible API headers (reused across claude-format providers)
 export const CLAUDE_API_HEADERS = {
@@ -34,7 +35,7 @@ export const CLAUDE_CLI_SPOOF_HEADERS = {
   "Anthropic-Version": ANTHROPIC_API_VERSION,
   "Anthropic-Beta": "claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,context-management-2025-06-27,prompt-caching-scope-2026-01-05,advanced-tool-use-2025-11-20,effort-2025-11-24,structured-outputs-2025-12-15,fast-mode-2026-02-01,redact-thinking-2026-02-12,token-efficient-tools-2026-03-28",
   "Anthropic-Dangerous-Direct-Browser-Access": "true",
-  "User-Agent": "claude-cli/2.1.92 (external, sdk-cli)",
+  "User-Agent": `claude-cli/${CLAUDE_CLI_VERSION} (external, sdk-cli)`,
   "X-App": "cli",
   "X-Stainless-Helper-Method": "stream",
   "X-Stainless-Retry-Count": "0",
@@ -74,10 +75,10 @@ export const KIMI_CODING_BASE_URL = "https://api.kimi.com/coding/v1/messages";
 export const OPENAI_COMPAT_BASE = "https://api.openai.com/v1";
 export const ANTHROPIC_COMPAT_BASE = "https://api.anthropic.com/v1";
 
-// Official Antigravity IDE Desktop 2.1.1 fingerprint captured from macOS arm64.
+// Official Antigravity IDE Desktop 2.11.0 fingerprint captured from macOS arm64.
 // Keep this static even when 9router runs on Linux: the provider profile is
 // intentionally matching the IDE client, not the server host.
-export const ANTIGRAVITY_IDE_VERSION = "2.1.1";
+export const ANTIGRAVITY_IDE_VERSION = "2.11.0";
 export const ANTIGRAVITY_IDE_BASE_URL = "https://daily-cloudcode-pa.googleapis.com";
 export const ANTIGRAVITY_IDE_USER_AGENT = `antigravity/ide/${ANTIGRAVITY_IDE_VERSION} darwin/arm64`;
 

open-sse/providers/thinkingLevels.js

@@ -39,6 +39,13 @@ const PATTERN_THINKING = [
   { provider: "codex", pattern: "*gpt-5.6-terra*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
   { provider: "codex", pattern: "*gpt-5.6-luna*", levels: CODEX_GPT_5_6_LEVELS },
   { pattern: "*codex*", levels: ["low", "medium", "high", "xhigh"] }, // codex cannot disable thinking
+  // codebuddy-cn per-model effort sets — read off the client picker (server-
+  // delivered supportedEfforts), 2026-08-30. Gateway uses thinkingFormat "openai"
+  // but rejects levels outside each model's set.
+  { provider: "codebuddy-cn", pattern: "glm-5.3*",     levels: ["low", "high", "max"] },
+  { provider: "codebuddy-cn", pattern: "deepseek-v4*", levels: ["low", "high", "xhigh"] },
+  { provider: "codebuddy-cn", pattern: "hy3*",         levels: ["low", "high"] },
+  { provider: "codebuddy-cn", pattern: "hy4*",         levels: ["high"] },
 ];
 
 // Returns valid thinking levels for a model, or null when the model has no reasoning.

open-sse/services/usage.js

@@ -15,6 +15,7 @@ import { getGrokCliUsage } from "./usage/grok-cli.js";
 import { getKimiUsage } from "./usage/kimi.js";
 import { getDeepseekUsage } from "./usage/deepseek.js";
 import { getFreebuffUsage } from "./usage/freebuff.js";
+import { getGroqUsage } from "./usage/groq.js";
 import { getZedUsage } from "./usage/zed.js";
 import { resolveQoderCredentials } from "./qoderModels.js";
 import { getGlmUsage } from "./usage/glm.js";
@@ -57,6 +58,7 @@ const USAGE_HANDLERS = {
   kimi: (c) => getKimiUsage(c.accessToken, c.apiKey, c.proxyOptions, c.providerSpecificData),
   deepseek: (c) => getDeepseekUsage(c.apiKey, c.proxyOptions),
   freebuff: (c) => getFreebuffUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
+  groq: (c) => getGroqUsage(c.apiKey, c.proxyOptions),
   zed: (c) => getZedUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
 };
 

open-sse/services/usage/google.js

@@ -161,6 +161,9 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
     if (data.models) {
       // Filter only recommended/important models (must match PROVIDER_MODELS ag ids)
       const importantModels = [
+        'gemini-3.8-flash-high',
+        'gemini-3.8-flash-medium',
+        'gemini-3.8-flash-low',
         'gemini-3.7-flash-high',
         'gemini-3.7-flash-medium',
         'gemini-3.7-flash-low',

open-sse/services/usage/groq.js

@@ -0,0 +1,133 @@
+/**
+ * Groq usage — no dedicated quota endpoint. Rate-limit info instead rides on
+ * every API response as x-ratelimit-* headers (requests + tokens, always
+ * included). We piggyback on the models list (already used as
+ * transport.validateUrl) so reading usage never costs tokens.
+ *
+ * Headers:
+ *   x-ratelimit-limit-requests / x-ratelimit-remaining-requests
+ *   x-ratelimit-limit-tokens   / x-ratelimit-remaining-tokens
+ *   x-ratelimit-reset-requests / x-ratelimit-reset-tokens (duration strings, e.g. "2m59.56s")
+ *
+ * Docs: https://console.groq.com/docs/rate-limits
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { U } from "./shared.js";
+
+const MODELS_URL = U("groq").url;
+
+// Groq reset headers are Go-style duration strings ("2m59.56s", "7.66s"), not
+// timestamps — parse the h/m/s/ms components and add them to now().
+function parseGroqDurationMs(value) {
+  if (typeof value !== "string" || !value.trim()) return null;
+
+  const re = /(\d+(?:\.\d+)?)(ms|s|m|h)/g;
+  let match;
+  let totalMs = 0;
+  let matched = false;
+  while ((match = re.exec(value))) {
+    matched = true;
+    const amount = Number(match[1]);
+    const unit = match[2];
+    const unitMs = unit === "h" ? 3600000 : unit === "m" ? 60000 : unit === "ms" ? 1 : 1000;
+    totalMs += amount * unitMs;
+  }
+  return matched ? totalMs : null;
+}
+
+function resetAtFromDuration(value) {
+  const ms = parseGroqDurationMs(value);
+  return ms === null ? null : new Date(Date.now() + ms).toISOString();
+}
+
+function buildRateLimitQuota(headers, limitKey, remainingKey, resetKey) {
+  // headers.get() returns null when absent, and Number(null) is 0 (a finite
+  // number) — check presence explicitly so a missing header can't masquerade
+  // as a real "0 remaining" quota.
+  const limitRaw = headers.get(limitKey);
+  const remainingRaw = headers.get(remainingKey);
+  if (limitRaw === null || remainingRaw === null) return null;
+
+  const limit = Number(limitRaw);
+  const remaining = Number(remainingRaw);
+  if (!Number.isFinite(limit) || !Number.isFinite(remaining)) return null;
+
+  return {
+    used: Math.max(0, limit - remaining),
+    total: limit,
+    resetAt: resetAtFromDuration(headers.get(resetKey)),
+    unlimited: false,
+  };
+}
+
+/**
+ * @param {string|null|undefined} apiKey
+ * @param {object|null} proxyOptions
+ */
+export async function getGroqUsage(apiKey, proxyOptions = null) {
+  if (!apiKey || typeof apiKey !== "string" || !apiKey.trim()) {
+    return { message: "Groq API key not available. Add a key to view usage." };
+  }
+
+  try {
+    const response = await proxyAwareFetch(
+      MODELS_URL,
+      {
+        method: "GET",
+        headers: {
+          Authorization: `Bearer ${apiKey.trim()}`,
+          Accept: "application/json",
+        },
+      },
+      proxyOptions,
+    );
+
+    if (response.status === 401 || response.status === 403) {
+      return { plan: "Groq", message: "Groq authentication failed. Check the API key." };
+    }
+
+    if (!response.ok) {
+      const errText = await response.text().catch(() => "");
+      return {
+        plan: "Groq",
+        message: `Groq usage API error (${response.status})${errText ? `: ${errText.slice(0, 120)}` : ""}`,
+      };
+    }
+
+    // The quota data lives in headers, not the body — drain it so the
+    // connection can be released without needing the payload.
+    await response.text().catch(() => {});
+
+    const requests = buildRateLimitQuota(
+      response.headers,
+      "x-ratelimit-limit-requests",
+      "x-ratelimit-remaining-requests",
+      "x-ratelimit-reset-requests",
+    );
+    const tokens = buildRateLimitQuota(
+      response.headers,
+      "x-ratelimit-limit-tokens",
+      "x-ratelimit-remaining-tokens",
+      "x-ratelimit-reset-tokens",
+    );
+
+    if (!requests && !tokens) {
+      // Key is valid (request succeeded) but no rate-limit bucket reported —
+      // distinguish "not tracked yet" from an auth/error state.
+      return {
+        plan: "Groq",
+        message: "Groq connected. No rate-limit data reported for this key yet.",
+        quotas: {},
+      };
+    }
+
+    const quotas = {};
+    if (requests) quotas["Requests"] = requests;
+    if (tokens) quotas["Tokens"] = tokens;
+
+    return { plan: "Groq", quotas };
+  } catch (error) {
+    return { message: `Groq error: ${error.message}` };
+  }
+}

open-sse/translator/concerns/thinkingUnified.js

@@ -105,12 +105,16 @@ export function extractThinking(body) {
 // at the call-site where intent is snapshotted before format translation.
 export const captureThinking = extractThinking;
 
-// Resolve thinking format: provider override > capability > derive(targetFormat).
+const NATIVE_ONLY_FORMATS = new Set(["gemini-level", "gemini-budget", "claude-budget", "claude-adaptive", "kiro"]);
+
 function resolveFormat(targetFormat, model, provider) {
   const providerFmt = provider ? PROVIDERS[provider]?.thinkingFormat : null;
   if (providerFmt) return providerFmt;
   const caps = getCapabilitiesForModel(provider, model);
-  if (caps.thinkingFormat) return caps.thinkingFormat;
+  const isOpenAIWire = targetFormat === "openai" || targetFormat === "openai-responses";
+  if (caps.thinkingFormat && !(isOpenAIWire && NATIVE_ONLY_FORMATS.has(caps.thinkingFormat))) {
+    return caps.thinkingFormat;
+  }
   return FORMAT_TO_NATIVE[targetFormat] || "openai";
 }
 
@@ -237,12 +241,10 @@ function applyFormat(fmt, body, cfg, caps, supportedLevels) {
     }
     case "claude-adaptive": {
       if (none && canDisable) { body.thinking = { type: "disabled" }; break; }
-      // output_config.effort alone does NOT turn thinking on: Anthropic requires
-      // an explicit thinking:{type:"adaptive"} on Opus 4.6/4.7/4.8 and Sonnet 4.6
-      // ("thinking is off unless you explicitly set it"), and Anthropic-compatible
-      // shims (e.g. GitHub Copilot /v1/messages) default thinking off even for
-      // Sonnet 5. Send both fields — the documented adaptive-thinking shape.
-      body.thinking = { type: "adaptive" };
+      // Models that can disable thinking need the explicit adaptive switch.
+      // Permanently adaptive models such as Fable 5.1 accept effort directly.
+      if (canDisable) body.thinking = { type: "adaptive" };
+      else delete body.thinking;
       const level = toLevel(eff);
       body.output_config = { effort: level === "xhigh" ? "high" : level };
       break;

open-sse/translator/formats/claude.js

@@ -12,6 +12,18 @@ import { DEFAULT_MAX_TOKENS } from "../../config/runtimeConfig.js";
 const CACHE_CONTROL_5M = { type: "ephemeral" };
 const CACHE_CONTROL_1H = { type: "ephemeral", ttl: "1h" };
 
+// Anthropic rejects a tool carrying BOTH defer_loading:true and cache_control
+// ("Tools defer_loading cannot use prompt caching", #3567). MCP clients put
+// deferred tools at the tail, which is exactly where the cache anchor lands.
+// Anchor on the last tool that CAN be cached instead of dropping caching.
+export function lastCacheableToolIndex(tools) {
+  if (!Array.isArray(tools)) return -1;
+  for (let i = tools.length - 1; i >= 0; i--) {
+    if (tools[i]?.defer_loading !== true) return i;
+  }
+  return -1;
+}
+
 // Check if message has valid non-empty content
 export function hasValidContent(msg) {
   if (typeof msg.content === "string" && msg.content.trim()) return true;
@@ -108,11 +120,24 @@ function buildThinkingPlaceholder(provider) {
   return block;
 }
 
+// Anthropic validates server_tool_use ids against this pattern and rejects the
+// whole request with a 400 when one does not match. A combo that falls back to a
+// provider with its own built-in tools (z.ai/glm emits OpenAI-style `call_` ids for
+// its analyze_image tool) leaves such blocks in the history, so every later Claude
+// turn carries a poisoned id.
+const CLAUDE_SERVER_TOOL_USE_ID = /^srvtoolu_[a-zA-Z0-9_]+$/;
+
+function hasForeignServerToolUseId(block) {
+  return block?.type === CLAUDE_BLOCK.SERVER_TOOL_USE
+    && !CLAUDE_SERVER_TOOL_USE_ID.test(String(block.id ?? ""));
+}
+
 // Normalize a native Claude passthrough body to match Anthropic Messages API spec.
 // Newer Cowork/Claude Code clients emit beta-only shapes that OAuth endpoints reject:
 // 1. thinking.type "adaptive" → unsupported on Haiku
 // 2. output_config.effort → unsupported on Haiku
 // 3. role "system" messages (mid-conversation-system beta) → only top-level system is allowed
+// 4. server_tool_use blocks carrying a foreign (non-srvtoolu_) id → rejected outright
 export function normalizeClaudePassthrough(body, model = "") {
   if (!body || typeof body !== "object") return body;
 
@@ -164,6 +189,7 @@ export function normalizeClaudePassthrough(body, model = "") {
   // 3. Drop thinking blocks whose signature is not Claude's (combo mixes models,
   // so foreign signatures leak into history and Anthropic rejects them).
   const thinkingEnabled = body.thinking?.type === "enabled";
+  const droppedServerToolUseIds = new Set();
   if (Array.isArray(body.messages)) {
     for (const msg of body.messages) {
       if (msg.role !== ROLE.ASSISTANT || !Array.isArray(msg.content)) continue;
@@ -178,6 +204,10 @@ export function normalizeClaudePassthrough(body, model = "") {
           }
           continue;
         }
+        if (hasForeignServerToolUseId(block)) {
+          if (block.id != null) droppedServerToolUseIds.add(String(block.id));
+          continue;
+        }
         if (block.type === CLAUDE_BLOCK.TOOL_USE) hasToolUse = true;
         kept.push(block);
       }
@@ -188,6 +218,35 @@ export function normalizeClaudePassthrough(body, model = "") {
     }
   }
 
+  // A dropped server_tool_use leaves its result behind; Anthropic rejects a
+  // tool_result that references an id no block declares, so both halves must go.
+  if (droppedServerToolUseIds.size > 0 && Array.isArray(body.messages)) {
+    for (const msg of body.messages) {
+      if (!Array.isArray(msg.content)) continue;
+      const kept = msg.content.filter(block => !(
+        (block?.type === CLAUDE_BLOCK.TOOL_RESULT || block?.type === CLAUDE_BLOCK.WEB_SEARCH_TOOL_RESULT)
+        && droppedServerToolUseIds.has(String(block.tool_use_id ?? ""))
+      ));
+      if (kept.length !== msg.content.length) {
+        msg.content = kept;
+      }
+    }
+  }
+
+  // 5. Drop empty text blocks and any message left with no content at all.
+  // Anthropic rejects `messages.N.content` blocks with empty text (400
+  // "text content blocks must be non-empty"); a message whose blocks were all
+  // stripped above must be dropped, not padded with an empty placeholder.
+  if (Array.isArray(body.messages)) {
+    body.messages = body.messages.filter(msg => {
+      if (typeof msg.content === "string") return msg.content.trim().length > 0;
+      if (!Array.isArray(msg.content)) return true;
+      msg.content = msg.content.filter(block =>
+        !(block?.type === CLAUDE_BLOCK.TEXT && !String(block.text ?? "").trim()));
+      return msg.content.length > 0;
+    });
+  }
+
   return body;
 }
 
@@ -223,7 +282,7 @@ export function anchorClaudeCache(body) {
   }
 
   if (Array.isArray(body.tools)) {
-    const last = body.tools.length - 1;
+    const last = lastCacheableToolIndex(body.tools);
     body.tools.forEach((tool, i) => {
       if (i === last) tool.cache_control = { ...CACHE_CONTROL_1H };
       else delete tool.cache_control;
@@ -417,9 +476,10 @@ export function prepareClaudeRequest(body, provider = null, apiKey = null, conne
         });
     }
 
+    const lastCacheable = lastCacheableToolIndex(body.tools);
     body.tools = body.tools.map((tool, i) => {
       const { cache_control, ...rest } = tool;
-      if (i === body.tools.length - 1) {
+      if (i === lastCacheable) {
         return { ...rest, cache_control: { type: "ephemeral", ttl: "1h" } };
       }
       return rest;

open-sse/translator/formats/gemini.js

@@ -14,6 +14,8 @@ export const UNSUPPORTED_SCHEMA_CONSTRAINTS = [
   "uniqueItems", "contains",
   // 2020-12 keywords with no Gemini equivalent
   "unevaluatedProperties", "unevaluatedItems", "contentSchema",
+  // Tuple-array keywords; converted to items first, leftovers stripped
+  "prefixItems", "additionalItems",
   // Claude rejects these in VALIDATED mode
   "default", "examples",
   // JSON Schema meta keywords
@@ -308,6 +310,37 @@ function ensureObjectType(obj) {
   for (const v of Object.values(obj)) if (v && typeof v === "object") ensureObjectType(v);
 }
 
+// Convert prefixItems (tuple validation) to items — Gemini cannot express tuples,
+// and a type:"array" schema without items is rejected with "missing field"
+function convertPrefixItems(obj) {
+  if (!obj || typeof obj !== "object") return;
+
+  if (Array.isArray(obj.prefixItems) && obj.prefixItems.length > 0) {
+    const variants = obj.prefixItems.filter(s => s && s.type !== "null");
+    if (!obj.items && variants.length === 1) {
+      obj.items = variants[0];
+    } else if (!obj.items && variants.length > 1) {
+      obj.items = { anyOf: variants };
+    }
+    delete obj.prefixItems;
+  }
+
+  for (const value of Object.values(obj)) {
+    if (value && typeof value === "object") {
+      convertPrefixItems(value);
+    }
+  }
+}
+
+// Gemini requires items on every type:"array" schema — fill a permissive placeholder
+function ensureArrayItems(obj) {
+  if (!obj || typeof obj !== "object") return;
+  if (obj.type === "array" && !obj.items) {
+    obj.items = { type: "string" };
+  }
+  for (const v of Object.values(obj)) if (v && typeof v === "object") ensureArrayItems(v);
+}
+
 // Clean JSON Schema for Antigravity API compatibility - removes unsupported keywords recursively
 export function cleanJSONSchemaForAntigravity(schema) {
   if (!schema || typeof schema !== "object") return schema;
@@ -321,11 +354,13 @@ export function cleanJSONSchemaForAntigravity(schema) {
 
   // Phase 2: Flatten complex structures
   mergeAllOf(cleaned);
+  convertPrefixItems(cleaned);
   flattenAnyOfOneOf(cleaned);
   flattenTypeArrays(cleaned);
 
   // Phase 2.5: Infer missing type=object when properties exist (Gemini requirement)
   ensureObjectType(cleaned);
+  ensureArrayItems(cleaned);
 
   // Phase 3: Remove all unsupported keywords at ALL levels (including inside arrays)
   removeUnsupportedKeywords(cleaned, UNSUPPORTED_SCHEMA_CONSTRAINTS);

open-sse/translator/request/claude-to-kiro.js

@@ -327,7 +327,6 @@ export function claudeToKiroRequest(model, body, stream, credentials) {
   };
 
   if (profileArn) payload.profileArn = profileArn;
-  if (systemPrompt) payload.systemPrompt = systemPrompt;
   if (additionalModelRequestFields) {
     payload.additionalModelRequestFields = additionalModelRequestFields;
   }

open-sse/translator/request/openai-to-kiro.js

@@ -420,7 +420,6 @@ export function openaiToKiroRequest(model, body, stream, credentials) {
   if (profileArn) {
     payload.profileArn = profileArn;
   }
-  if (systemPrompt) payload.systemPrompt = systemPrompt;
   if (additionalModelRequestFields) {
     payload.additionalModelRequestFields = additionalModelRequestFields;
   }

open-sse/translator/schema/blocks.js

@@ -20,6 +20,8 @@ export const CLAUDE_BLOCK = {
   TOOL_RESULT: "tool_result",
   THINKING: "thinking",
   REDACTED_THINKING: "redacted_thinking",
+  SERVER_TOOL_USE: "server_tool_use",
+  WEB_SEARCH_TOOL_RESULT: "web_search_tool_result",
 };
 
 // OpenAI Responses API item types.

open-sse/utils/claudeCloaking.js

@@ -1,16 +1,16 @@
 import { createHash, randomBytes, randomUUID } from "crypto";
 import { CLAUDE_TOOL_SUFFIX, CC_DEFAULT_TOOLS } from "../config/appConstants.js";
+import { CLAUDE_CLI_VERSION } from "../providers/shared.js";
 
-const CLAUDE_VERSION = "2.1.92";
 const CC_ENTRYPOINT = "sdk-cli";
 
-// Generate billing header matching real Claude Code 2.1.92+ format:
+// Generate the billing header expected from current Claude Code clients.
 // x-anthropic-billing-header: cc_version=<ver>.<build>; cc_entrypoint=sdk-cli; cch=<hash>;
 function generateBillingHeader(payload) {
   const content = JSON.stringify(payload);
   const cch = createHash("sha256").update(content).digest("hex").slice(0, 5);
   const buildHash = randomBytes(2).toString("hex").slice(0, 3);
-  return `x-anthropic-billing-header: cc_version=${CLAUDE_VERSION}.${buildHash}; cc_entrypoint=${CC_ENTRYPOINT}; cch=${cch};`;
+  return `x-anthropic-billing-header: cc_version=${CLAUDE_CLI_VERSION}.${buildHash}; cc_entrypoint=${CC_ENTRYPOINT}; cch=${cch};`;
 }
 
 // Derive a deterministic UUID-v4-shaped string from a seed (stable per account)
@@ -19,7 +19,7 @@ function deriveUuid(seed) {
   return `${h.slice(0, 8)}-${h.slice(8, 12)}-4${h.slice(13, 16)}-${((parseInt(h[16], 16) & 0x3) | 0x8).toString(16)}${h.slice(17, 20)}-${h.slice(20, 32)}`;
 }
 
-// Generate fake user ID in Claude Code 2.1.92+ JSON format:
+// Generate fake user ID in the current Claude Code JSON format:
 // {"device_id":"<64hex>","account_uuid":"<uuid>","session_id":"<uuid>"}
 // device_id/account_uuid derive from apiKey (stable per account), session_id per-conversation
 function generateFakeUserID(sessionId, apiKey) {

open-sse/utils/modelMarkers.js

@@ -0,0 +1,20 @@
+// Claude Code appends a bracketed context marker to the model name when the
+// 1M-context beta is toggled on: `claude-opus-5` becomes `claude-opus-5[1m]`.
+// The marker is a client-side annotation, not part of any model id: it never
+// matches a combo name, an alias or a `provider/model` pair, so a request that
+// carries it dies at model resolution with "Invalid model format".
+//
+// The capability itself travels in the `anthropic-beta: context-1m-2025-08-07`
+// header, which is forwarded untouched — stripping the marker is enough to let
+// the request route normally and still reach the upstream as a 1M request.
+
+const CONTEXT_MARKER = /\[1m\]$/i;
+
+// Returns { model, contextMarker } — contextMarker is null when there is none.
+export function stripModelContextMarker(modelStr) {
+  if (typeof modelStr !== "string") return { model: modelStr, contextMarker: null };
+  const trimmed = modelStr.trim();
+  const match = trimmed.match(CONTEXT_MARKER);
+  if (!match) return { model: modelStr, contextMarker: null };
+  return { model: trimmed.slice(0, -match[0].length), contextMarker: match[0].slice(1, -1).toLowerCase() };
+}