Merge origin/master (v0.5.69) into gitea/new_feature

2026-09-07 14:10:11 +07:00
parent 86112cee6d eb712ca821
commit a835771c97
222 changed files with 12285 additions and 3371 deletions
--- a/open-sse/providers/capabilities.js
+++ b/open-sse/providers/capabilities.js
@@ -6,6 +6,16 @@
 //   3. PATTERN_CAPABILITIES                     — glob match, ordered specific -> generic
 //   4. DEFAULT_CAPABILITIES                     — safe floor (always returned)
 //
+// Two extra layers then refine the result, and neither can override the hand
+// written tables above (steps 1-2 short-circuit before they are consulted):
+//   • the synced catalog — modalities keyed by model, limits keyed by provider
+//     + model, refreshed from models.dev in the background. It reads a file, so
+//     the server installs it via setCatalogSource(); this module stays free of
+//     node:fs because the dashboard bundles it into the browser too.
+//   • visionPatterns.js — name-based vision detection, last resort so a model
+//     nobody has catalogued yet still accepts images.
+// Both only ever turn a capability ON.
+//
 // ── HOW TO ADD / UPDATE A MODEL ──────────────────────────────────────
 // Authoritative data source: https://models.dev/api.json (145 providers, 4000+
 // models, MIT). Each model exposes the exact fields we map below:
@@ -23,6 +33,7 @@
 // 2.0+, Grok, Perplexity). Verify with: curl -s https://models.dev/api.json

 import { matchPattern } from "./pricing.js";
+import { looksLikeVisionModel } from "./visionPatterns.js";

 /**
 * Safe floor — every resolved result is merged over this so consumers
@@ -46,6 +57,7 @@ export const DEFAULT_CAPABILITIES = {
  thinkingFormat: null,
  thinkingCanDisable: true,  // false → model cannot turn thinking off (clamp to min instead of disable)
  thinkingRange: null,       // { min, max } for budget formats; null = no clamp
+  thinkingEffortSupported: false, // zai format only: model accepts a reasoning_effort level (GLM-5.2+; older GLM ignores it)
  // limits (tokens)
  contextWindow: 200000,
  maxOutput: 64000,
@@ -71,7 +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 },
@@ -94,8 +107,14 @@ export const MODEL_CAPABILITIES = {
  // Gemini image-gen / OpenAI image / xai image variants
  "gpt-image-1":       { imageOutput: true, tools: false },

-  // GLM vision variant (text GLM has no vision)
-  "glm-4.6v":          { vision: true, reasoning: true, thinkingFormat: "zai", contextWindow: 128000 },
+  // GLM vision variants (text GLM has no vision) — 5.3-Flash and 5V-Turbo are
+  // natively multimodal per z.ai, and 5.3-Flash carries the full 1M window.
+  "glm-5.3-flash":     { vision: true, videoInput: true, pdf: true, reasoning: true, thinkingFormat: "zai", contextWindow: 1000000, maxOutput: 131072 },
+  "glm-4.6v":          { vision: true, videoInput: true, reasoning: true, thinkingFormat: "zai", contextWindow: 128000, maxOutput: 32768 },
+  "glm-4.5v":          { vision: true, videoInput: true, reasoning: true, thinkingFormat: "zai", contextWindow: 64000, maxOutput: 16384 },
+
+  // DeepSeek's first V4 model with image input; text limits match V4-Flash.
+  "deepseek-v4-flash-vision-exp": { vision: true, reasoning: true, thinkingFormat: "deepseek", contextWindow: 1000000, maxOutput: 384000 },

  // Qwen plain coder/text (no vision) — registry "vision-model" / "coder-model" aliases
  "vision-model":      { vision: true, reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000 },
@@ -108,6 +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 — 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 };
@@ -131,6 +154,7 @@ export const PROVIDER_CAPABILITIES = {
    "deepseek-ai/deepseek-v4-flash": { reasoning: true, thinkingFormat: "openai", contextWindow: 1000000, maxOutput: 65536 },
  },
  "codex": {
+    "gpt-6-astra":               { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 272000, maxOutput: 128000 },
    "gpt-5.6-sol":               CODEX_GPT_56_SOL_CAPS,
    "gpt-5.6-sol-review":        CODEX_GPT_56_SOL_CAPS,
    "gpt-5.6-terra":             CODEX_GPT_56_DEFAULT_CAPS,
@@ -155,24 +179,69 @@ export const PROVIDER_CAPABILITIES = {
  // CodeBuddy.cn — authoritative per-model metadata from the gateway's model
  // config (contextWindow=maxInputTokens, maxOutput=maxOutputTokens, vision=
  // supportsImages). Every model reasons via OpenAI-style reasoning_effort
-  // (see registry thinkingFormat). `onlyReasoning` models can't turn thinking
-  // off → thinkingCanDisable:false (clamped to minimal instead of disabled).
+  // (see registry thinkingFormat). For thinkingCanDisable use the server's
+  // reasoning.canDisableThinking flag — see the note in the codebuddy-cn block
+  // below; it is NOT the inverse of onlyReasoning.
  "codebuddy-cn": {
-    "glm-5.2":            { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 48000 },
-    "glm-5.1":            { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
+    "glm-5.2":            { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 48000 },
+    "glm-5.1":            { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
    "glm-5.0":            { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
-    "glm-5.0-turbo":      { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
-    "glm-5v-turbo":       { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 38000 },
+    // maxOutput 64000 per both the plugin-baked fallback and the live server
+    // table (the old 38000 had no source and truncated output).
+    "glm-5v-turbo":       { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 64000 },
    "glm-4.7":            { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
-    "minimax-m3":         { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 48000 },
-    "minimax-m2.7":       { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
+    "minimax-m3":         { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 128000 },
    "kimi-k2.7":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
    "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 },
-    "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 },
+    // Per-model values mirror the server's product-config payload (the plugin
+    // fetches it from copilot.tencent.com; the `models[]` entries carry
+    // maxInputTokens/maxOutputTokens/supportsImages). contextWindow =
+    // maxInputTokens, maxOutput = maxOutputTokens. Where the server and the
+    // plugin-baked fallback disagree, the server table wins.
+    // ⚠️ thinkingCanDisable maps to the server's reasoning.canDisableThinking —
+    // it is NOT the inverse of onlyReasoning. onlyReasoning means "thinking is
+    // on by default"; canDisableThinking means "it CAN be turned off". glm-5.3
+    // and glm-5.3-flash are onlyReasoning:true BUT canDisableThinking:true, so
+    // their thinking is switchable; the hy* models are forced always-on.
+    "hy3":                { 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 },
+    "glm-5.3":            { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 48000 },
+    "glm-5.3-flash":      { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 32000 },
+    "kimi-k3-1":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 32000 },
+    "deepseek-v4-pro":    { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 50000 },
+    "deepseek-v4-flash":  { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 50000 },
+  },
+  // Qoder — upstream exposes opaque internal ids (dfmodel, kmodel, …); the
+  // registry `name` is display-only and capability lookup matches on the raw
+  // id, so every qoder model would fall through to DEFAULT_CAPABILITIES
+  // (200K) without this map. contextWindow follows the real model family's
+  // spec: the /algo/api/v2/model/list max_input_tokens under-reports some
+  // windows (GLM-5.3 / Kimi-K3 / Qwen3.8-Max claim 180K but accept more).
+  // max_output_tokens arrives as 0 for every model, so outputs are
+  // best-guess from the real model family. Vision tags below follow the
+  // upstream is_vl flag per explicit request, even though the executor
+  // currently sends image_urls:null (image pass-through over the agent_chat
+  // SSE protocol is unverified). reasoning:true on all of them — every model can
+  // reason; the upstream is_reasoning flag only drives model_config selection.
+  // thinkingFormat keeps the true-model family for documentation/UI, but
+  // thinkingCanDisable:false everywhere: the executor only forwards
+  // messages/tools/max_tokens, and thinking is fixed upstream via
+  // modelConfig.is_reasoning — client thinking intent is dropped, so "none"
+  // must never be offered as an option.
+  "qoder": {
+    "ultimate":       { vision: true, reasoning: true, thinkingFormat: "claude-adaptive", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 128000 }, // Claude Opus 5
+    "performance":    { vision: true, reasoning: true, thinkingFormat: "claude-adaptive", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 128000 }, // Claude Sonnet 5
+    "dmodel":         { reasoning: true, thinkingFormat: "deepseek", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },  // DeepSeek-V4-Pro
+    "dfmodel":        { reasoning: true, thinkingFormat: "deepseek", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },  // DeepSeek-V4-Flash
+    "gmodel":         { reasoning: true, thinkingFormat: "zai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 128000 },      // GLM-5.3
+    "gfmodel":        { vision: true, reasoning: true, thinkingFormat: "zai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 128000 }, // GLM-5.3-Flash
+    "kmodel_latest":  { vision: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },      // Kimi-K3
+    "kmodel":         { vision: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 65536 },  // Kimi-K2.7-Code
+    "mmodel":         { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 512000 }, // MiniMax-M3
+    "qmodel_latest":  { vision: true, reasoning: true, thinkingFormat: "qwen", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },  // Qwen3.7-Max
+    "qmodel":         { vision: true, reasoning: true, thinkingFormat: "qwen", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },  // Qwen3.7-Plus
+    "qfmodel":        { vision: true, reasoning: true, thinkingFormat: "qwen", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },  // Qwen3.8-Flash
+    "qmodel_38max":   { vision: true, reasoning: true, thinkingFormat: "qwen", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 65536 },      // Qwen3.8-Max
  },
  // Poolside Laguna — OpenAI-compatible, all reasoning-capable (32K max output).
  "poolside": {
@@ -205,6 +274,7 @@ 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 } },
@@ -214,6 +284,9 @@ export const PATTERN_CAPABILITIES = [
  { pattern: "*gemma*",         caps: { vision: true, contextWindow: 128000 } },
  { pattern: "*nanobanana*",    caps: { vision: true, imageOutput: true } },

+  // ── OpenAI GPT-6.x (vision + thinking + web search) ──────────────
+  { pattern: "*gpt-6*",         caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 272000, maxOutput: 128000 } },
+
  // ── OpenAI GPT-5.x (vision + thinking + web search) ──────────────
  { pattern: "*gpt-5*image*",   caps: { imageOutput: true } },
  { pattern: "*gpt-5*codex*",   caps: { reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 400000, maxOutput: 128000 } },
@@ -234,6 +307,8 @@ export const PATTERN_CAPABILITIES = [
  // ── Grok (vision + Live Search) ──────────────────────────────────
  { pattern: "*grok*image*",    caps: { imageOutput: true } },
  { pattern: "*grok-code*",     caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 256000 } },
+  // Grok 4.6: 500k context, no text output limit (docs.x.ai/developers/grok-4-6)
+  { pattern: "*grok-4.6*",      caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 500000, maxOutput: 500000 } },
  // Grok 4.5 (Grok CLI / Grok Build): 500k context per cli-chat-proxy /v1/models
  { pattern: "*grok-4.5*",      caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 500000, maxOutput: 64000 } },
  { pattern: "*grok-4*",        caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 256000 } },
@@ -261,6 +336,10 @@ export const PATTERN_CAPABILITIES = [
  { pattern: "*kimi*",          caps: { reasoning: true, thinkingFormat: "kimi", contextWindow: 262144 } },

  // ── GLM / Z.ai (thinking.enabled; disable via enable_thinking:false) ─
+  // reasoning_effort is only read by z.ai from GLM-5.2 onward (docs.z.ai/guides/capabilities/thinking) —
+  // older GLM (4.x, 5.0, 5.1, 5-turbo, 5v-turbo) ignore it, so gate it per exact version, not the "*glm-5*" catch-all.
+  { pattern: "*glm-5.3*",       caps: { reasoning: true, thinkingFormat: "zai", thinkingEffortSupported: true, contextWindow: 200000, maxOutput: 128000 } },
+  { pattern: "*glm-5.2*",       caps: { reasoning: true, thinkingFormat: "zai", thinkingEffortSupported: true, contextWindow: 200000, maxOutput: 128000 } },
  { pattern: "*glm-5*",         caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000, maxOutput: 128000 } },
  { pattern: "*glm-4.7*",       caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000, maxOutput: 128000 } },
  { pattern: "*glm-4*",         caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000 } },
@@ -309,6 +388,9 @@ 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 } },
@@ -330,6 +412,46 @@ const TRUST_UPSTREAM_VISION = new Set(["openrouter"]);
 * @param {string} model
 * @returns {object} full capabilities object
 */
+const MODALITY_KEYS = ["vision", "pdf", "audioInput", "videoInput"];
+
+// Catalog lookups, installed by the server at startup. Left as no-ops in the
+// browser bundle, where there is no file to read.
+let catalogSource = null;
+
+/**
+ * Install the synced catalog reader (server only).
+ * @param {{ getModalities: Function, getLimits: Function } | null} source
+ */
+export function setCatalogSource(source) {
+  catalogSource = source;
+}
+
+// Apply the synced catalog + name heuristic on top of a table-resolved result.
+// Strictly additive: a capability already true stays true, and a false one only
+// flips when an outside source positively declares support.
+function refine(base, provider, model) {
+  const result = { ...DEFAULT_CAPABILITIES, ...base };
+
+  if (catalogSource) {
+    const modalities = catalogSource.getModalities(model);
+    if (modalities) {
+      for (const key of MODALITY_KEYS) {
+        if (modalities[key] === true) result[key] = true;
+      }
+    }
+
+    const limits = catalogSource.getLimits(provider, model);
+    if (limits) {
+      if (limits.contextWindow > 0) result.contextWindow = limits.contextWindow;
+      if (limits.maxOutput > 0) result.maxOutput = limits.maxOutput;
+    }
+  }
+
+  if (!result.vision && looksLikeVisionModel(model)) result.vision = true;
+
+  return result;
+}
+
 export function getCapabilitiesForModel(provider, model) {
  if (!model) return { ...DEFAULT_CAPABILITIES };

@@ -347,16 +469,13 @@ export function getCapabilitiesForModel(provider, model) {
  if (MODEL_CAPABILITIES[baseModel]) return { ...DEFAULT_CAPABILITIES, ...MODEL_CAPABILITIES[baseModel] };
  if (MODEL_CAPABILITIES[model]) return { ...DEFAULT_CAPABILITIES, ...MODEL_CAPABILITIES[model] };

-  // 3. Pattern match (first match wins)
+  // 3. Pattern match (first match wins), refined by catalog + name heuristic
  for (const { pattern, caps } of PATTERN_CAPABILITIES) {
    if (matchPattern(pattern, baseModel) || matchPattern(pattern, model)) {
-      return { ...DEFAULT_CAPABILITIES, ...caps };
+      return refine(caps, provider, model);
    }
  }

-  // 4. Floor (upstream-validated gateways keep vision on for unknown models)
-  if (provider && TRUST_UPSTREAM_VISION.has(provider)) {
-    return { ...DEFAULT_CAPABILITIES, vision: true };
-  }
-  return { ...DEFAULT_CAPABILITIES };
+  // 4. Floor
+  return refine(null, provider, model);
 }
--- a/open-sse/providers/catalogOverride.js
+++ b/open-sse/providers/catalogOverride.js
@@ -0,0 +1,72 @@
+// Read side of the model catalog synced from models.dev.
+//
+// The file is the source of truth; the only thing held in memory is a parsed
+// copy dropped as soon as the file's mtime changes. getCapabilitiesForModel is
+// synchronous and runs per request, so the hot path is one stat (~1us) and the
+// parse (~0.1ms on a ~18KB file) only reruns after a sync.
+
+import fs from "node:fs";
+import path from "node:path";
+import { DATA_DIR } from "@/lib/dataDir.js";
+
+export const CATALOG_FILE = path.join(DATA_DIR, "model-catalog.json");
+// Trimmed upstream catalog, read by the add-models skill (not by the router).
+export const CATALOG_RAW_FILE = path.join(DATA_DIR, "model-catalog-raw.json");
+
+const EMPTY = { models: {}, providers: {} };
+let cache = EMPTY;
+let cachedMtime = -1;
+
+// "zai-org/GLM-4.6V:free" -> "glm-4.6v"
+function baseId(model) {
+  if (!model) return "";
+  const withoutVendor = model.includes("/") ? model.split("/").pop() : model;
+  return withoutVendor.toLowerCase().split(":")[0];
+}
+
+function load() {
+  let mtime;
+  try {
+    mtime = fs.statSync(CATALOG_FILE).mtimeMs;
+  } catch {
+    cache = EMPTY;
+    cachedMtime = -1;
+    return cache;
+  }
+  if (mtime === cachedMtime) return cache;
+
+  cachedMtime = mtime;
+  try {
+    const parsed = JSON.parse(fs.readFileSync(CATALOG_FILE, "utf8"));
+    cache = { models: parsed?.models || {}, providers: parsed?.providers || {} };
+  } catch {
+    cache = EMPTY;
+  }
+  return cache;
+}
+
+// Modality is a property of the model itself — any gateway serving it inherits
+// the same image/video/pdf support, so this is keyed by model id alone.
+export function getCatalogModalities(model) {
+  return load().models[baseId(model)] || null;
+}
+
+// Context and output limits are a property of the gateway, not the model: each
+// one truncates differently, so these stay keyed by provider + model.
+export function getCatalogLimits(provider, model) {
+  const byProvider = provider && load().providers[provider];
+  if (!byProvider) return null;
+  return byProvider[model] || byProvider[baseId(model)] || null;
+}
+
+// Force a re-read on the next lookup (called right after a sync writes the file).
+export function invalidateCatalog() {
+  cachedMtime = -1;
+}
+
+// Hand the reader to capabilities.js. That module is bundled into the browser
+// too, so it cannot import this file directly — the server pushes it in.
+export async function installCatalogSource() {
+  const { setCatalogSource } = await import("./capabilities.js");
+  setCatalogSource({ getModalities: getCatalogModalities, getLimits: getCatalogLimits });
+}
--- a/open-sse/providers/models/helpers.js
+++ b/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);
+}
--- a/open-sse/providers/pricing.js
+++ b/open-sse/providers/pricing.js
@@ -53,10 +53,15 @@ export const MODEL_PRICING = {
  "gpt-5.6-luna":                 { input: 1.00,  output: 6.00,  cached: 0.10,  reasoning: 6.00,   cache_creation: 1.00  },
  "gpt-5.6-terra":                { input: 2.50,  output: 15.00, cached: 0.25,  reasoning: 15.00,  cache_creation: 2.50  },
  "gpt-5.6-sol":                  { input: 5.00,  output: 30.00, cached: 0.50,  reasoning: 30.00,  cache_creation: 5.00  },
+  "gpt-6-astra":                  { input: 5.00,  output: 30.00, cached: 0.50,  reasoning: 30.00,  cache_creation: 5.00  },
  "o1":                           { input: 15.00, output: 60.00, cached: 7.50,  reasoning: 90.00,  cache_creation: 15.00 },
  "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 +265,7 @@ 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 },
  },
 };

--- a/open-sse/providers/registry/antigravity.js
+++ b/open-sse/providers/registry/antigravity.js
@@ -17,7 +17,7 @@ export default {
    deprecationNotice: "RISK_NOTICE",
  },
  category: "oauth",
-  serviceKinds: ["llm", "image"],
+  serviceKinds: ["llm", "image", "webSearch"],
  transport: {
    baseUrls: [ANTIGRAVITY_IDE_BASE_URL],
    format: "antigravity",
@@ -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: `${ANTIGRAVITY_IDE_BASE_URL}/v1internal:fetchAvailableModels`,
      loadProjectApiUrl: "https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist",
      tokenUrl: "https://oauth2.googleapis.com/token",
    },
@@ -45,6 +44,10 @@ export default {
    clientSecret: "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",
  },
  models: [
+    { id: "gemini-3.8-flash-high", name: "Gemini 3.8 Flash (High)", upstreamModelId: "gemini-3.8-flash-high(high)" },
+    { id: "gemini-3.8-flash-medium", name: "Gemini 3.8 Flash (Medium)", upstreamModelId: "gemini-3.8-flash-medium(medium)" },
+    { id: "gemini-3.8-flash-low", name: "Gemini 3.8 Flash (Low)", upstreamModelId: "gemini-3.8-flash-low(low)" },
+    { id: "gemini-3.8-flash", name: "Gemini 3.8 Flash", upstreamModelId: "gemini-3.8-flash-medium(medium)" },
    { id: "gemini-3.7-flash-high", name: "Gemini 3.7 Flash (High)", upstreamModelId: "gemini-3.7-flash-tiered(high)" },
    { id: "gemini-3.7-flash-medium", name: "Gemini 3.7 Flash (Medium)", upstreamModelId: "gemini-3.7-flash-tiered(medium)" },
    { id: "gemini-3.7-flash-low", name: "Gemini 3.7 Flash (Low)", upstreamModelId: "gemini-3.7-flash-tiered(low)" },
@@ -82,6 +85,11 @@ export default {
    loadCodeAssistUserAgent: ANTIGRAVITY_IDE_USER_AGENT,
    refreshLeadMs: 300000,
  },
+  searchViaChat: {
+    defaultModel: "gemini-2.5-flash",
+    endpoint: `${ANTIGRAVITY_IDE_BASE_URL}/v1internal:generateContent`,
+    freeTier: "Free — Google Search grounding through an Antigravity OAuth account.",
+  },
  features: {
    usage: true,
  },
--- a/open-sse/providers/registry/claude.js
+++ b/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" },
--- a/open-sse/providers/registry/codebuddy-cn.js
+++ b/open-sse/providers/registry/codebuddy-cn.js
@@ -47,19 +47,26 @@ 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" },
-    { id: "hy3-preview", name: "Hy3 Preview" },
+    // Catalog mirrors the server's product-config payload (the plugin fetches
+    // it from copilot.tencent.com). Models the server no longer publishes are
+    // removed even when the chat endpoint still answers them — the published
+    // list is the contract. Drop log: glm-5.0 / glm-4.7 and hy4-preview-x
+    // (endpoint returns 11102 "model service info not found"), plus
+    // glm-5.0-turbo / minimax-m2.7 / kimi-k2.5 / hy3-preview /
+    // deepseek-v3-2-volc (absent from the server list, though still answering
+    // 200) and hy3-x (paid tier, not used here).
+    // "-x" suffix = paid tier of the same model (free id rides the promo quota).
+    { id: "hy3", name: "Hy3" },
+    { id: "hy4-preview", name: "Hy4-Preview" },
+    { 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" },
  ],
  oauth: {
    baseUrl: "https://copilot.tencent.com",
--- a/open-sse/providers/registry/codex.js
+++ b/open-sse/providers/registry/codex.js
@@ -45,6 +45,7 @@ export default {
    },
  },
  models: [
+    { id: "gpt-6-astra", name: "GPT 6.0 Astra" },
    { id: "gpt-5.6-sol", name: "GPT 5.6 Sol" },
    { id: "gpt-5.6-sol-review", name: "GPT 5.6 Sol Review", upstreamModelId: "gpt-5.6-sol", quotaFamily: "review" },
    { id: "gpt-5.6-terra", name: "GPT 5.6 Terra" },
@@ -59,6 +60,9 @@ export default {
    { id: "gpt-5.4-mini-review", name: "GPT 5.4 Mini Review", upstreamModelId: "gpt-5.4-mini", quotaFamily: "review" },
    { id: "gpt-5.3-codex-spark", name: "GPT 5.3 Codex Spark" },
    { id: "gpt-5.3-codex-spark-review", name: "GPT 5.3 Codex Spark Review", upstreamModelId: "gpt-5.3-codex-spark", quotaFamily: "review" },
+    { id: "gpt-5.6-sol-image", name: "GPT 5.6 Sol Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
+    { id: "gpt-5.6-terra-image", name: "GPT 5.6 Terra Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
+    { id: "gpt-5.6-luna-image", name: "GPT 5.6 Luna Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
    { id: "gpt-5.5-image", name: "GPT 5.5 Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
    { id: "gpt-5.4-image", name: "GPT 5.4 Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
    { id: "gpt-5.3-image", name: "GPT 5.3 Image", capabilities: ["text2img","edit"], params: ["size","quality","background","image_detail","output_format"], kind: "image" },
--- a/open-sse/providers/registry/deepseek.js
+++ b/open-sse/providers/registry/deepseek.js
@@ -45,6 +45,7 @@ export default {
    { id: "deepseek-v4-pro-max", name: "DeepSeek V4 Pro Max", upstreamModelId: "deepseek-v4-pro" },
    { id: "deepseek-v4-pro-none", name: "DeepSeek V4 Pro No Thinking", upstreamModelId: "deepseek-v4-pro" },
    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash" },
+    { id: "deepseek-v4-flash-vision-exp", name: "DeepSeek V4 Flash Vision (Exp)" },
    { id: "deepseek-chat", name: "DeepSeek V3.2 Chat" },
    { id: "deepseek-reasoner", name: "DeepSeek V3.2 Reasoner" },
  ],
--- a/open-sse/providers/registry/gemini.js
+++ b/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" },
--- a/open-sse/providers/registry/glm-cn.js
+++ b/open-sse/providers/registry/glm-cn.js
@@ -22,10 +22,13 @@ export default {
  },
  models: [
    { id: "glm-5.3", name: "GLM 5.3" },
+    { id: "glm-5.3-flash", name: "GLM 5.3 Flash (Vision)" },
    { id: "glm-5.2", name: "GLM 5.2" },
    { id: "glm-5.1", name: "GLM 5.1" },
+    { id: "glm-5-turbo", name: "GLM 5 Turbo" },
    { id: "glm-5", name: "GLM 5" },
    { id: "glm-4.7", name: "GLM-4.7" },
+    { id: "glm-4.6v", name: "GLM 4.6V (Vision)" },
    { id: "glm-4.6", name: "GLM-4.6" },
    { id: "glm-4.5-air", name: "GLM-4.5-Air" },
  ],
--- a/open-sse/providers/registry/glm.js
+++ b/open-sse/providers/registry/glm.js
@@ -46,12 +46,28 @@ export default {
  ],
  models: [
    { id: "glm-5.3", name: "GLM 5.3" },
+    { id: "glm-5.3-flash", name: "GLM 5.3 Flash (Vision)" },
    { id: "glm-5.2", name: "GLM 5.2" },
    { id: "glm-5.1", name: "GLM 5.1" },
+    { id: "glm-5-turbo", name: "GLM 5 Turbo" },
    { id: "glm-5", name: "GLM 5" },
    { id: "glm-4.7", name: "GLM 4.7" },
    { id: "glm-4.6v", name: "GLM 4.6V (Vision)" },
  ],
+  serviceKinds: ["llm", "webSearch"],
+  // Coding plan bundles web search on the same API key as chat.
+  searchConfig: {
+    baseUrl: "https://api.z.ai/api/mcp/web_search_prime/mcp",
+    method: "POST",
+    authType: "apikey",
+    authHeader: "bearer",
+    costPerQuery: 0,
+    searchTypes: ["web"],
+    defaultMaxResults: 5,
+    maxMaxResults: 50,
+    timeoutMs: 10000,
+    cacheTTLMs: 300000,
+  },
  features: {
    usage: true,
    usageApikey: true,
--- a/open-sse/providers/registry/groq.js
+++ b/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,
+  },
 };
--- a/open-sse/providers/registry/index.js
+++ b/open-sse/providers/registry/index.js
@@ -66,6 +66,7 @@ import p63 from "./nebius.js";
 import p64 from "./nvidia.js";
 import p65 from "./ollama-local.js";
 import p66 from "./ollama.js";
+import p123 from "./ollama-search.js";
 import p67 from "./openai.js";
 import p68 from "./opencode-go.js";
 import p69 from "./opencode.js";
@@ -121,6 +122,7 @@ import p118 from "./selfhosted-tts.js";
 import p119 from "./selfhosted-embedding.js";
 import p120 from "./fish-audio.js";
 import p121 from "./alitp-intl.js";
+import p122 from "./xquik.js";

 export default [
  p0,
@@ -190,6 +192,7 @@ export default [
  p64,
  p65,
  p66,
+  p123,
  p67,
  p68,
  p69,
@@ -243,4 +246,5 @@ export default [
  p119,
  p120,
  p121,
+  p122,
 ];
--- a/open-sse/providers/registry/ollama-search.js
+++ b/open-sse/providers/registry/ollama-search.js
@@ -0,0 +1,35 @@
+export default {
+  id: "ollama-search",
+  alias: "ollama-search",
+  display: {
+    name: "Ollama Search",
+    icon: "cloud",
+    color: "#ffffff",
+    textIcon: "OL",
+    website: "https://ollama.com",
+    notice: {
+      text: "Web search via Ollama Cloud subscription. Reuses the API key from the Ollama (chat) provider.",
+      apiKeyUrl: "https://ollama.com/settings/keys",
+    },
+  },
+  category: "apikey",
+  authType: "apikey",
+  authModes: ["apikey"],
+  serviceKinds: ["webSearch"],
+  // Credential fallback: reuses the API key registered under the `ollama`
+  // chat provider — one key, chat + search.
+  credentialFallback: "ollama",
+  searchConfig: {
+    baseUrl: "https://ollama.com/api/web_search",
+    method: "POST",
+    authType: "apikey",
+    authHeader: "bearer",
+    costPerQuery: 0,
+    freeMonthlyQuota: 1000,
+    searchTypes: ["web"],
+    defaultMaxResults: 5,
+    maxMaxResults: 10,
+    timeoutMs: 10000,
+    cacheTTLMs: 300000,
+  },
+};
--- a/open-sse/providers/registry/ollama.js
+++ b/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,
--- a/open-sse/providers/registry/opencode-go.js
+++ b/open-sse/providers/registry/opencode-go.js
@@ -21,6 +21,9 @@ export default {
  transport: {
    baseUrl: "https://opencode.ai/zen/go/v1/chat/completions",
    headers: {},
+    usage: {
+      url: "https://opencode.ai/zen/go/v1/usage",
+    },
  },
  // Multi-endpoint: pick the transport matching the client sourceFormat to skip
  // translation. Guarded per-model by `supportedFormats` (see chatCore) because
@@ -31,12 +34,14 @@ export default {
    { format: "openai-responses", baseUrl: "https://opencode.ai/zen/go/v1/responses", auth: { combined: true, header: "Authorization", scheme: "bearer" } },
  ],
  models: [
+    { id: "glm-5.3-flash", name: "GLM 5.3 Flash (Vision)", supportedFormats: ["openai"] },
    { id: "glm-5.2", name: "GLM 5.2", supportedFormats: ["openai"] },
    { id: "glm-5.1", name: "GLM 5.1", supportedFormats: ["openai"] },
    { id: "kimi-k2.7-code", name: "Kimi K2.7 Code", supportedFormats: ["openai"] },
    { id: "kimi-k2.6", name: "Kimi K2.6", supportedFormats: ["openai"] },
    { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", supportedFormats: ["openai", "claude", "openai-responses"] },
    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", supportedFormats: ["openai", "claude", "openai-responses"] },
+    { id: "deepseek-v4-flash-vision-exp", name: "DeepSeek V4 Flash Vision (Exp)", supportedFormats: ["openai", "claude", "openai-responses"] },
    { id: "mimo-v2.5", name: "MiMo V2.5", supportedFormats: ["openai"] },
    { id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro", supportedFormats: ["openai"] },
    { id: "minimax-m3", name: "MiniMax M3", supportedFormats: ["openai", "claude"] },
@@ -45,5 +50,13 @@ export default {
    { id: "qwen3.7-max", name: "Qwen 3.7 Max", supportedFormats: ["openai", "claude"] },
    { id: "qwen3.7-plus", name: "Qwen 3.7 Plus", supportedFormats: ["openai", "claude"] },
    { id: "qwen3.6-plus", name: "Qwen 3.6 Plus", supportedFormats: ["openai", "claude"] },
+    // Muse Spark is served by /zen/go/v1/responses only — responses-only entry forces
+    // chatCore past the sourceFormat-matched transports into translation (see chatCore guard).
+    { id: "muse-spark-1.2-contributor", name: "Muse Spark 1.2 Contributor", targetFormat: "openai-responses", supportedFormats: ["openai-responses"] },
+    { id: "muse-spark-1.3-contributor", name: "Muse Spark 1.3 Contributor", targetFormat: "openai-responses", supportedFormats: ["openai-responses"] },
  ],
+  features: {
+    usage: true,
+    usageApikey: true,
+  },
 };
--- a/open-sse/providers/registry/opencode.js
+++ b/open-sse/providers/registry/opencode.js
@@ -19,7 +19,12 @@ export default {
    },
    noAuth: true,
  },
-  models: [],
+  models: [
+    // 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,
 };
--- a/open-sse/providers/registry/qoder.js
+++ b/open-sse/providers/registry/qoder.js
@@ -30,12 +30,15 @@ export default {
    { id: "auto", name: "Auto" },
    { id: "performance", name: "Performance" },
    { id: "efficient", name: "Efficient" },
-    { id: "qmodel_preview", name: "Qwen3.8-Max-Preview" },
+    { id: "lite", name: "Lite" },
+    { id: "qmodel_38max", name: "Qwen3.8-Max" },
    { id: "qmodel_latest", name: "Qwen3.7-Max" },
    { id: "qmodel", name: "Qwen3.7-Plus" },
+    { id: "qfmodel", name: "Qwen3.8-Flash" },
    { id: "kmodel_latest", name: "Kimi-K3" },
    { id: "kmodel", name: "Kimi-K2.7-Code" },
-    { id: "gm51model", name: "GLM-5.2" },
+    { id: "gmodel", name: "GLM-5.3" },
+    { id: "gfmodel", name: "GLM-5.3-Flash" },
    { id: "dmodel", name: "DeepSeek-V4-Pro" },
    { id: "dfmodel", name: "DeepSeek-V4-Flash" },
    { id: "mmodel", name: "MiniMax-M3" },
--- a/open-sse/providers/registry/tokenrouter.js
+++ b/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: {
--- a/open-sse/providers/registry/xai.js
+++ b/open-sse/providers/registry/xai.js
@@ -36,6 +36,8 @@ export default {
    },
  },
  models: [
+    { id: "grok-4.6", name: "Grok 4.6" },
+    { id: "grok-4.5", name: "Grok 4.5" },
    { id: "grok-4", name: "Grok 4" },
    { id: "grok-4-fast-reasoning", name: "Grok 4 Fast Reasoning" },
    { id: "grok-code-fast-1", name: "Grok Code Fast" },
--- a/open-sse/providers/registry/xquik.js
+++ b/open-sse/providers/registry/xquik.js
@@ -0,0 +1,35 @@
+export default {
+  id: "xquik",
+  alias: "xquik",
+  display: {
+    name: "Xquik",
+    icon: "tag",
+    color: "#5C3327",
+    textIcon: "XQ",
+    website: "https://docs.xquik.com/api-reference/x/search-tweets",
+    notice: {
+      apiKeyUrl: "https://xquik.com",
+      text: "Searches public X posts. Billing uses 1 Xquik credit per returned post."
+    }
+  },
+  category: "apikey",
+  authType: "apikey",
+  serviceKinds: [
+    "webSearch"
+  ],
+  searchConfig: {
+    baseUrl: "https://xquik.com/api/v1/x/tweets/search",
+    validateUrl: "https://xquik.com/api/v1/credits",
+    method: "GET",
+    authType: "apikey",
+    authHeader: "x-api-key",
+    searchTypes: [
+      "x"
+    ],
+    defaultMaxResults: 5,
+    maxMaxResults: 100,
+    timeoutMs: 10000,
+    cacheTTLMs: 60000,
+    creditsPerResult: 1
+  }
+};
--- a/open-sse/providers/shared.js
+++ b/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`;

--- a/open-sse/providers/thinkingLevels.js
+++ b/open-sse/providers/thinkingLevels.js
@@ -35,10 +35,23 @@ const CODEX_GPT_5_6_LEVELS = ["none", "minimal", "low", "medium", "high", "xhigh

 // Model-name pattern overrides (glob, first match wins) — more precise than format default.
 const PATTERN_THINKING = [
+  { provider: "codex", pattern: "*gpt-6*", levels: CODEX_GPT_5_6_LEVELS },
  { provider: "codex", pattern: "*gpt-5.6-sol*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
  { 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 — the server's product-config payload
+  // publishes `reasoning.supportedEfforts` per model. NOTE: the chat endpoint
+  // accepts any level you send (probed none/minimal/low/medium/high/xhigh/max
+  // → all 200), but values outside a model's supportedEfforts are silently
+  // clamped, so the declared set stays authoritative for the picker. Models
+  // that publish no supportedEfforts (glm-5.1 / glm-5v-turbo / kimi-k2.x /
+  // kimi-k3-1 / minimax-m3) fall through to the openai format default.
+  { provider: "codebuddy-cn", pattern: "glm-5.3*",     levels: ["low", "high", "max"] },
+  { provider: "codebuddy-cn", pattern: "glm-5.2",      levels: ["high", "xhigh"] },
+  { 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.
--- a/open-sse/providers/visionPatterns.js
+++ b/open-sse/providers/visionPatterns.js
@@ -0,0 +1,42 @@
+// Name-based vision detection — last resort when neither the catalog file nor
+// the capability tables know a model. Vendors put the modality in the id
+// ("qwen3-vl-plus", "glm-4.6v", "deepseek-v4-flash-vision-exp"), so a custom or
+// freshly released model still gets image input instead of silently dropping it.
+//
+// Only ever turns vision ON. Never used to turn a declared capability off.
+
+const SEP = "[-_/:.]";
+
+// Image GENERATION, video generation, and non-chat models also carry these
+// words but take no image input — checked first so they can never match.
+const NOT_VISION = new RegExp(
+  [
+    `(^|${SEP})(image|img)(${SEP}|$)`,
+    "stable-image", "gen[0-9]_image", "nanobanana", "imagine",
+    "t2v", "i2v", "flux", "dall", "sdxl", "diffusion",
+    "embed", "rerank", "guard", "moderation",
+    "tts", "stt", "whisper", "voice", "speech", "audio",
+  ].join("|"),
+  "i"
+);
+
+// Explicit modality words, plus the "<digit>v" suffix vendors use for vision
+// variants (glm-4.6v, glm-5v-turbo). The digit-v branch requires a dotted
+// version so the never-shipped `gpt-4v` cannot match.
+const VISION_NAME = new RegExp(
+  [
+    `(^|${SEP})(vision|vl|vlm|multimodal|omni|visual)(${SEP}|$)`,
+    `[0-9]\\.[0-9]+v(${SEP}|$)`,
+    `(^|${SEP})glm-[0-9]+v(${SEP}|$)`,
+    "(^|[-_/:.])(llava|pixtral|internvl|cogvlm|minicpm-v|moondream|idefics|fuyu)",
+  ].join("|"),
+  "i"
+);
+
+// Does this model id look like a vision model? Name signal only.
+export function looksLikeVisionModel(modelId) {
+  if (!modelId) return false;
+  const id = String(modelId).toLowerCase();
+  if (NOT_VISION.test(id)) return false;
+  return VISION_NAME.test(id);
+}