@liustack/modlens 3.3.0 → 3.4.0

package/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## 3.4.0 - 2026-08-12
+
+- Vendor-specific request fields can now be passed through to the three API providers, which is how you turn thinking off (issue #12). `modlens config set openai.extraBody '{"thinking":{"type":"disabled"}}'` stores it per provider, `--extra-body '<json>'` overrides it for one run, and an empty value clears it. Reasoning models spend their budget re-deriving a transcription task that needs none, so on a thinking-by-default model this is the difference between a slow read and a fast one. There is deliberately no `--no-thinking` flag: every gateway spells the knob differently (`thinking.type` on the MiMo API, `reasoning.effort` on its Responses route, `chat_template_kwargs.enable_thinking` on a self-hosted vLLM, `thinkingConfig` inside `generationConfig` on Gemini), some ignore what they do not know and others reject it with a 400, so guessing on the user's behalf would fail silently about as often as it worked. `configure.md` carries the per-vendor recipes.
+- The passthrough deep-merges into the request body, so adding a knob to a nested block keeps what was already there (a Gemini `thinkingConfig` no longer wipes out the `responseJsonSchema` next to it). The fields that carry the image, the prompt, and the schema enforcement are reserved and rejected with a message naming the field. The two CLI providers take no request body: they warn in `meta.warnings` that the value was ignored rather than letting a run look configured when nothing was sent.
+
 ## 3.3.0 - 2026-08-07
 
 - Automatic provider failover. A run now tries every provider that is set up on this machine, in order, and the first good result wins: a provider that errors, times out, or returns a schema-violating result hands over to the next. A local image tries `antigravity-cli`, then `gemini-api`, `openai`, `anthropic`, `claude-cli`; a remote URL tries the inline API providers first and the agent last (only the inline download path runs the private-address guards, the magic-byte check, and the size cap), and `claude-cli` never joins the remote chain since it reads local files only. The result's `meta.attempts` records every provider tried with timings and failure reasons, and `meta.warnings` carries failover notices. `doctor` prints both chains. Availability (binary on PATH, required keys present) is one shared source of truth between the doctor's readiness report and the chain. The 3.2.0 remote-URL reroute is absorbed by the remote chain order.

package/README.md

@@ -16,6 +16,7 @@
 </p>
 
 <p align="center">
+  <a href="https://x.com/liustack"><img src="https://img.shields.io/badge/follow-%40liustack-black?style=flat-square&logo=x&logoColor=white" alt="Follow @liustack on X"></a>
   <a href="https://www.npmjs.com/package/@liustack/modlens"><img src="https://img.shields.io/npm/v/@liustack/modlens?style=flat-square&label=npm&color=cb3837" alt="npm"></a>
   <a href="https://nodejs.org"><img src="https://img.shields.io/node/v/@liustack/modlens?style=flat-square" alt="Node.js"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License"></a>
@@ -101,6 +102,16 @@ npx -y skills add liustack/liustack -g
 
 ⭐ If it helps, star [ModLens](https://github.com/liustack/modlens) and [liustack](https://github.com/liustack/liustack). Stars are how the next developer finds them.
 
+## Star History
+
+<a href="https://www.star-history.com/?repos=liustack%2Fmodlens&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=liustack/modlens&type=date&theme=dark&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=liustack/modlens&type=date&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=liustack/modlens&type=date&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+ </picture>
+</a>
+
 ## Disclaimer
 
 Provided as-is under the MIT License below. The author makes no warranty and gives no endorsement for any particular use, commercial use included. Your use of upstream engines (Antigravity CLI, the Gemini, OpenAI, and Anthropic APIs, and any OpenAI-compatible endpoint) is governed by their own terms and quotas, which you are responsible for.

package/README.zh-CN.md

@@ -16,6 +16,7 @@
 </p>
 
 <p align="center">
+  <a href="https://x.com/liustack"><img src="https://img.shields.io/badge/follow-%40liustack-black?style=flat-square&logo=x&logoColor=white" alt="Follow @liustack on X"></a>
   <a href="https://www.npmjs.com/package/@liustack/modlens"><img src="https://img.shields.io/npm/v/@liustack/modlens?style=flat-square&label=npm&color=cb3837" alt="npm"></a>
   <a href="https://nodejs.org"><img src="https://img.shields.io/node/v/@liustack/modlens?style=flat-square" alt="Node.js"></a>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License"></a>
@@ -101,6 +102,16 @@ Codex 桌面 App 中识别一张推文截图。配文、互动数据（2.9K 回
 
 ⭐ 如果它对你有用，请给 [ModLens](https://github.com/liustack/modlens) 一个 star，这是其他开发者找到它的方式。
 
+## Star History
+
+<a href="https://www.star-history.com/?repos=liustack%2Fmodlens&type=date&legend=top-left">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=liustack/modlens&type=date&theme=dark&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=liustack/modlens&type=date&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=liustack/modlens&type=date&legend=top-left&sealed_token=oQQAwrPffo9WRUsM6P4RnEu4ZdRART3ChPwIkavGtAfrMycGmLYdjuM2uJ4gjnoIyaF_MDwhOBkJlzmS8pT_W9IRDlsCqLafe7gwvw7Vcnr5MRTkczOasg" />
+ </picture>
+</a>
+
 ## 免责声明
 
 本项目依下方 MIT 协议按现状提供。作者不对任何特定用途（含商业使用）提供保证或背书。上游引擎（Antigravity CLI，Gemini、OpenAI、Anthropic 的 API，以及任何 OpenAI 兼容端点）的使用受各自条款和额度约束，由使用者负责。

package/dist/main.js

@@ -7,7 +7,7 @@ import { spawn } from "child_process";
 import * as os from "os";
 import require$$0$1 from "node:assert";
 import require$$1 from "node:net";
-import require$$2 from "node:http";
+import require$$2$1 from "node:http";
 import require$$0$2 from "node:stream";
 import require$$5 from "node:querystring";
 import require$$0 from "node:events";
@@ -18,21 +18,44 @@ import require$$0$4 from "node:buffer";
 import require$$0$5 from "node:zlib";
 import require$$5$1 from "node:perf_hooks";
 import require$$8 from "node:util/types";
-import require$$2$1 from "node:worker_threads";
-import require$$2$2 from "node:crypto";
-import require$$1$1 from "node:sqlite";
+import require$$2$2 from "node:worker_threads";
+import require$$2$3 from "node:crypto";
 import require$$11 from "node:stream/web";
 import require$$0$6 from "node:url";
-import require$$1$2 from "node:async_hooks";
-import require$$1$3 from "node:console";
+import require$$1$1 from "node:async_hooks";
+import require$$1$2 from "node:console";
 import require$$0$7 from "node:fs/promises";
-import require$$1$4 from "node:path";
-import require$$2$3 from "node:timers";
-import require$$1$5 from "node:dns";
+import require$$1$3 from "node:path";
+import require$$2$4 from "node:timers";
+import require$$1$4 from "node:dns";
 import * as dns$1 from "dns/promises";
 import { isIP } from "net";
 import { createRequire } from "module";
 import * as crypto from "crypto";
+function getAugmentedNamespace(n) {
+  if (Object.prototype.hasOwnProperty.call(n, "__esModule")) return n;
+  var f = n.default;
+  if (typeof f == "function") {
+    var a = function a2() {
+      if (this instanceof a2) {
+        return Reflect.construct(f, arguments, this.constructor);
+      }
+      return f.apply(this, arguments);
+    };
+    a.prototype = f.prototype;
+  } else a = {};
+  Object.defineProperty(a, "__esModule", { value: true });
+  Object.keys(n).forEach(function(k) {
+    var d = Object.getOwnPropertyDescriptor(n, k);
+    Object.defineProperty(a, k, d.get ? d : {
+      enumerable: true,
+      get: function() {
+        return n[k];
+      }
+    });
+  });
+  return a;
+}
 var undici = { exports: {} };
 var symbols;
 var hasRequiredSymbols;
@@ -1038,7 +1061,7 @@ function requireUtil$5() {
   hasRequiredUtil$5 = 1;
   const assert = require$$0$1;
   const { kDestroyed, kBodyUsed, kListeners, kBody } = requireSymbols();
-  const { IncomingMessage } = require$$2;
+  const { IncomingMessage } = require$$2$1;
   const stream = require$$0$2;
   const net = require$$1;
   const { stringify } = require$$5;
@@ -4286,7 +4309,7 @@ function requireWebidl() {
   hasRequiredWebidl = 1;
   const assert = require$$0$1;
   const { types, inspect } = require$$3;
-  const { markAsUncloneable } = require$$2$1;
+  const { markAsUncloneable } = require$$2$2;
   const UNDEFINED = 1;
   const BOOLEAN = 2;
   const STRING = 3;
@@ -5647,14 +5670,20 @@ function requireUtil$4() {
   return util$4;
 }
 var runtimeFeatures = {};
+const __viteBrowserExternal = {};
+const __viteBrowserExternal$1 = /* @__PURE__ */ Object.freeze(/* @__PURE__ */ Object.defineProperty({
+  __proto__: null,
+  default: __viteBrowserExternal
+}, Symbol.toStringTag, { value: "Module" }));
+const require$$2 = /* @__PURE__ */ getAugmentedNamespace(__viteBrowserExternal$1);
 var hasRequiredRuntimeFeatures;
 function requireRuntimeFeatures() {
   if (hasRequiredRuntimeFeatures) return runtimeFeatures;
   hasRequiredRuntimeFeatures = 1;
   const lazyLoaders = {
     __proto__: null,
-    "node:crypto": () => require$$2$2,
-    "node:sqlite": () => require$$1$1
+    "node:crypto": () => require$$2$3,
+    "node:sqlite": () => require$$2
   };
   function detectRuntimeFeatureByNodeModule(moduleName) {
     try {
@@ -5731,7 +5760,7 @@ function requireFormdata() {
   const { webidl } = requireWebidl();
   const nodeUtil = require$$3;
   const { runtimeFeatures: runtimeFeatures2 } = requireRuntimeFeatures();
-  const random = runtimeFeatures2.has("crypto") ? require$$2$2.randomInt : (max) => Math.floor(Math.random() * max);
+  const random = runtimeFeatures2.has("crypto") ? require$$2$3.randomInt : (max) => Math.floor(Math.random() * max);
   class FormData {
     #state = [];
     #boundary = null;
@@ -9083,7 +9112,7 @@ function requireClient() {
   hasRequiredClient = 1;
   const assert = require$$0$1;
   const net = require$$1;
-  const http = require$$2;
+  const http = require$$2$1;
   const util2 = requireUtil$5();
   const { ClientStats } = requireStats();
   const { channels } = requireDiagnostics();
@@ -12557,7 +12586,7 @@ function requireApiRequest() {
   if (hasRequiredApiRequest) return apiRequest.exports;
   hasRequiredApiRequest = 1;
   const assert = require$$0$1;
-  const { AsyncResource } = require$$1$2;
+  const { AsyncResource } = require$$1$1;
   const { Readable } = requireReadable();
   const { InvalidArgumentError, RequestAbortedError } = requireErrors();
   const util2 = requireUtil$5();
@@ -12810,7 +12839,7 @@ function requireApiStream() {
   if (hasRequiredApiStream) return apiStream;
   hasRequiredApiStream = 1;
   const assert = require$$0$1;
-  const { AsyncResource } = require$$1$2;
+  const { AsyncResource } = require$$1$1;
   const { InvalidArgumentError, InvalidReturnValueError } = requireErrors();
   const util2 = requireUtil$5();
   const { addSignal, removeSignal } = requireAbortSignal();
@@ -13025,7 +13054,7 @@ function requireApiPipeline() {
     PassThrough
   } = require$$0$2;
   const assert = require$$0$1;
-  const { AsyncResource } = require$$1$2;
+  const { AsyncResource } = require$$1$1;
   const {
     InvalidArgumentError,
     InvalidReturnValueError,
@@ -13227,7 +13256,7 @@ function requireApiUpgrade() {
   if (hasRequiredApiUpgrade) return apiUpgrade;
   hasRequiredApiUpgrade = 1;
   const { InvalidArgumentError, SocketError } = requireErrors();
-  const { AsyncResource } = require$$1$2;
+  const { AsyncResource } = require$$1$1;
   const assert = require$$0$1;
   const util2 = requireUtil$5();
   const { kHTTP2Stream } = requireSymbols();
@@ -13327,7 +13356,7 @@ function requireApiConnect() {
   if (hasRequiredApiConnect) return apiConnect;
   hasRequiredApiConnect = 1;
   const assert = require$$0$1;
-  const { AsyncResource } = require$$1$2;
+  const { AsyncResource } = require$$1$1;
   const { InvalidArgumentError, SocketError } = requireErrors();
   const util2 = requireUtil$5();
   const { addSignal, removeSignal } = requireAbortSignal();
@@ -13502,7 +13531,7 @@ function requireMockUtils() {
     kTotalDispatchCount
   } = requireMockSymbols();
   const { serializePathWithQuery, parseHeaders } = requireUtil$5();
-  const { STATUS_CODES } = require$$2;
+  const { STATUS_CODES } = require$$2$1;
   const {
     types: {
       isPromise
@@ -14543,7 +14572,7 @@ function requirePendingInterceptorsFormatter() {
   if (hasRequiredPendingInterceptorsFormatter) return pendingInterceptorsFormatter;
   hasRequiredPendingInterceptorsFormatter = 1;
   const { Transform } = require$$0$2;
-  const { Console } = require$$1$3;
+  const { Console } = require$$1$2;
   const PERSISTENT = process.versions.icu ? "✅" : "Y ";
   const NOT_PERSISTENT = process.versions.icu ? "❌" : "N ";
   pendingInterceptorsFormatter = class PendingInterceptorsFormatter {
@@ -14777,7 +14806,7 @@ function requireSnapshotUtils() {
       match: new Set(matchHeaders.map((header) => caseSensitive ? header : header.toLowerCase()))
     };
   }
-  const crypto2 = runtimeFeatures2.has("crypto") ? require$$2$2 : null;
+  const crypto2 = runtimeFeatures2.has("crypto") ? require$$2$3 : null;
   const hashId = crypto2?.hash ? (value) => crypto2.hash("sha256", value, "base64url") : (value) => Buffer.from(value).toString("base64url");
   function isUndiciHeaders(headers2) {
     return Array.isArray(headers2) && (headers2.length & 1) === 0;
@@ -14854,8 +14883,8 @@ function requireSnapshotRecorder() {
   if (hasRequiredSnapshotRecorder) return snapshotRecorder;
   hasRequiredSnapshotRecorder = 1;
   const { writeFile, readFile, mkdir } = require$$0$7;
-  const { dirname, resolve } = require$$1$4;
-  const { setTimeout: setTimeout2, clearTimeout: clearTimeout2 } = require$$2$3;
+  const { dirname, resolve } = require$$1$3;
+  const { setTimeout: setTimeout2, clearTimeout: clearTimeout2 } = require$$2$4;
   const { InvalidArgumentError, UndiciError } = requireErrors();
   const { hashId, isUrlExcludedFactory, normalizeHeaders, createHeaderFilters } = requireSnapshotUtils();
   function normalizeUrlForMatching(url, matchQuery, normalizeQuery) {
@@ -16040,7 +16069,7 @@ function requireDns() {
   if (hasRequiredDns) return dns;
   hasRequiredDns = 1;
   const { isIP: isIP2 } = require$$1;
-  const { lookup } = require$$1$5;
+  const { lookup } = require$$1$4;
   const DecoratorHandler = requireDecoratorHandler();
   const { InvalidArgumentError, InformationalError } = requireErrors();
   const maxInt = Math.pow(2, 31) - 1;
@@ -19506,7 +19535,7 @@ function requireSqliteCacheStore() {
         }
       }
       if (!DatabaseSync) {
-        DatabaseSync = require$$1$1.DatabaseSync;
+        DatabaseSync = require$$2.DatabaseSync;
       }
       this.#db = new DatabaseSync(opts?.location ?? ":memory:");
       this.#db.exec(`
@@ -21471,7 +21500,7 @@ function requireSubresourceIntegrity() {
   const validSRIHashAlgorithmTokenSet = /* @__PURE__ */ new Map([["sha256", 0], ["sha384", 1], ["sha512", 2]]);
   let crypto2;
   if (runtimeFeatures2.has("crypto")) {
-    crypto2 = require$$2$2;
+    crypto2 = require$$2$3;
     const cryptoHashes = crypto2.getHashes();
     if (cryptoHashes.length === 0) {
       validSRIHashAlgorithmTokenSet.clear();
@@ -21665,7 +21694,7 @@ function requireFetch() {
   const { dataURLProcessor, serializeAMimeType, minimizeSupportedMimeType } = requireDataUrl();
   const { getGlobalDispatcher } = requireGlobal();
   const { webidl } = requireWebidl();
-  const { STATUS_CODES } = require$$2;
+  const { STATUS_CODES } = require$$2$1;
   const { bytesMatch } = requireSubresourceIntegrity();
   const { isomorphicEncode } = requireInfra();
   const GET_OR_HEAD = ["GET", "HEAD"];
@@ -24425,7 +24454,7 @@ function requireFrame() {
   const BUFFER_SIZE = 8 * 1024;
   let buffer = null;
   let bufIdx = BUFFER_SIZE;
-  const randomFillSync = runtimeFeatures2.has("crypto") ? require$$2$2.randomFillSync : null;
+  const randomFillSync = runtimeFeatures2.has("crypto") ? require$$2$3.randomFillSync : null;
   function generateMask() {
     if (bufIdx === BUFFER_SIZE) {
       bufIdx = 0;
@@ -24530,7 +24559,7 @@ function requireConnection() {
   const { WebsocketFrameSend } = requireFrame();
   const assert = require$$0$1;
   const { runtimeFeatures: runtimeFeatures2 } = requireRuntimeFeatures();
-  const crypto2 = runtimeFeatures2.has("crypto") ? require$$2$2 : null;
+  const crypto2 = runtimeFeatures2.has("crypto") ? require$$2$3 : null;
   let warningEmitted = false;
   function establishWebSocketConnection(url, protocols, client2, handler, options) {
     const requestURL = url;
@@ -27508,6 +27537,54 @@ function schemaViolations(schema, value, path2) {
   }
   return [];
 }
+function parseExtraBody(raw, origin) {
+  let parsed;
+  try {
+    parsed = JSON.parse(raw);
+  } catch (error) {
+    throw new Error(`${origin} is not valid JSON: ${error.message}`);
+  }
+  if (!isPlainObject(parsed)) {
+    throw new Error(
+      `${origin} must be a JSON object, for example {"thinking":{"type":"disabled"}}`
+    );
+  }
+  return parsed;
+}
+function mergeExtraBody(body2, extra, reserved, providerName) {
+  if (!extra || Object.keys(extra).length === 0) {
+    return body2;
+  }
+  for (const path2 of reserved) {
+    if (hasPath(extra, path2)) {
+      throw new Error(
+        `extraBody cannot override "${path2}" for the ${providerName} provider: it carries the image, the prompt, or the schema this tool depends on. Remove that field from ${providerName}.extraBody (or --extra-body).`
+      );
+    }
+  }
+  return deepMerge(body2, extra);
+}
+function deepMerge(base, overlay) {
+  const merged = { ...base };
+  for (const [key, value] of Object.entries(overlay)) {
+    const current = merged[key];
+    merged[key] = isPlainObject(current) && isPlainObject(value) ? deepMerge(current, value) : value;
+  }
+  return merged;
+}
+function hasPath(value, dottedPath) {
+  let cursor = value;
+  for (const segment of dottedPath.split(".")) {
+    if (!isPlainObject(cursor) || !Object.hasOwn(cursor, segment)) {
+      return false;
+    }
+    cursor = cursor[segment];
+  }
+  return true;
+}
+function isPlainObject(value) {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
 function tryParseJson(text) {
   try {
     return JSON.parse(text);
@@ -27584,27 +27661,34 @@ Report your findings by calling the ${TOOL_NAME} tool.`;
       "anthropic-version": "2023-06-01",
       "Content-Type": "application/json"
     },
-    body: JSON.stringify({
-      model,
-      max_tokens: 4096,
-      tools: [
+    body: JSON.stringify(
+      mergeExtraBody(
         {
-          name: TOOL_NAME,
-          description: "Report the structured visual evidence extracted from the image.",
-          input_schema: VISION_RESULT_SCHEMA
-        }
-      ],
-      tool_choice: { type: "tool", name: TOOL_NAME },
-      messages: [
-        {
-          role: "user",
-          content: [
-            { type: "image", source: imageSource },
-            { type: "text", text: prompt }
+          model,
+          max_tokens: 4096,
+          tools: [
+            {
+              name: TOOL_NAME,
+              description: "Report the structured visual evidence extracted from the image.",
+              input_schema: VISION_RESULT_SCHEMA
+            }
+          ],
+          tool_choice: { type: "tool", name: TOOL_NAME },
+          messages: [
+            {
+              role: "user",
+              content: [
+                { type: "image", source: imageSource },
+                { type: "text", text: prompt }
+              ]
+            }
           ]
-        }
-      ]
-    }),
+        },
+        options.settings?.extraBody,
+        ["model", "messages", "tools", "tool_choice", "stream"],
+        "anthropic"
+      )
+    ),
     signal: AbortSignal.timeout(options.timeoutMs)
   });
   if (!response2.ok) {
@@ -27871,20 +27955,31 @@ async function executeGeminiApi(options) {
       "x-goog-api-key": apiKey,
       "Content-Type": "application/json"
     },
-    body: JSON.stringify({
-      contents: [
+    body: JSON.stringify(
+      mergeExtraBody(
         {
-          parts: [
-            { inline_data: { mime_type: image.mimeType, data: image.data } },
-            { text: prompt }
-          ]
-        }
-      ],
-      generationConfig: {
-        responseMimeType: "application/json",
-        responseJsonSchema: VISION_RESULT_SCHEMA
-      }
-    }),
+          contents: [
+            {
+              parts: [
+                { inline_data: { mime_type: image.mimeType, data: image.data } },
+                { text: prompt }
+              ]
+            }
+          ],
+          generationConfig: {
+            responseMimeType: "application/json",
+            responseJsonSchema: VISION_RESULT_SCHEMA
+          }
+        },
+        options.settings?.extraBody,
+        [
+          "contents",
+          "generationConfig.responseMimeType",
+          "generationConfig.responseJsonSchema"
+        ],
+        "gemini-api"
+      )
+    ),
     signal: AbortSignal.timeout(options.timeoutMs)
   });
   if (!response2.ok) {
@@ -27941,18 +28036,25 @@ Respond with ONE JSON object only, no markdown fences, no commentary. Fill this
       Authorization: `Bearer ${apiKey}`,
       "Content-Type": "application/json"
     },
-    body: JSON.stringify({
-      model,
-      messages: [
+    body: JSON.stringify(
+      mergeExtraBody(
         {
-          role: "user",
-          content: [
-            { type: "image_url", image_url: { url: imageUrl } },
-            { type: "text", text: prompt }
+          model,
+          messages: [
+            {
+              role: "user",
+              content: [
+                { type: "image_url", image_url: { url: imageUrl } },
+                { type: "text", text: prompt }
+              ]
+            }
           ]
-        }
-      ]
-    }),
+        },
+        options.settings?.extraBody,
+        ["model", "messages", "stream"],
+        "openai"
+      )
+    ),
     signal: AbortSignal.timeout(options.timeoutMs)
   });
   if (!response2.ok) {
@@ -28022,6 +28124,7 @@ function providerAliases() {
 function listProviders() {
   return [...new Set(Object.values(PROVIDERS).map((provider) => provider.name))];
 }
+const STRING_FIELDS = ["apiKey", "baseUrl", "model"];
 const CONFIG_DIR = path.join(os.homedir(), ".modlens");
 const CONFIG_PATH = path.join(CONFIG_DIR, "config.json");
 const ENV_BINDINGS = {
@@ -28077,17 +28180,31 @@ function setConfigValue(dottedKey, value, configPath = CONFIG_PATH) {
     const dot = dottedKey.indexOf(".");
     if (dot <= 0 || dot === dottedKey.length - 1) {
       throw new Error(
-        `Invalid config key: ${dottedKey}. Use "provider" or "<provider>.<apiKey|baseUrl|model>".`
+        `Invalid config key: ${dottedKey}. Use "provider" or "<provider>.<apiKey|baseUrl|model|extraBody>".`
       );
     }
     const providerName = dottedKey.slice(0, dot);
     const field = dottedKey.slice(dot + 1);
-    if (!["apiKey", "baseUrl", "model"].includes(field)) {
-      throw new Error(`Unknown config field: ${field}. Use apiKey, baseUrl, or model.`);
+    if (field === "extraBody") {
+      config2.providers ??= {};
+      config2.providers[providerName] ??= {};
+      if (value.trim() === "") {
+        delete config2.providers[providerName].extraBody;
+      } else {
+        config2.providers[providerName].extraBody = parseExtraBody(
+          value,
+          `${providerName}.extraBody`
+        );
+      }
+    } else if (!STRING_FIELDS.includes(field)) {
+      throw new Error(
+        `Unknown config field: ${field}. Use apiKey, baseUrl, model, or extraBody.`
+      );
+    } else {
+      config2.providers ??= {};
+      config2.providers[providerName] ??= {};
+      config2.providers[providerName][field] = value;
     }
-    config2.providers ??= {};
-    config2.providers[providerName] ??= {};
-    config2.providers[providerName][field] = value;
   }
   fs.mkdirSync(path.dirname(configPath), { recursive: true });
   fs.writeFileSync(configPath, `${JSON.stringify(config2, null, 2)}
@@ -28126,7 +28243,7 @@ function renderEffectiveConfig(config2, env = process.env) {
     const fileSettings = config2.providers?.[name] ?? {};
     const bindings = ENV_BINDINGS[name] ?? {};
     const fields = {};
-    for (const field of ["apiKey", "baseUrl", "model"]) {
+    for (const field of STRING_FIELDS) {
       const envName = bindings[field];
       const envValue = envName ? env[envName]?.trim() : void 0;
       const value = envValue ?? fileSettings[field];
@@ -28136,6 +28253,9 @@ function renderEffectiveConfig(config2, env = process.env) {
         fields[field] = `${shown} (${source})`;
       }
     }
+    if (fileSettings.extraBody !== void 0) {
+      fields.extraBody = `${JSON.stringify(fileSettings.extraBody)} (file)`;
+    }
     if (Object.keys(fields).length > 0) {
       providers[name] = fields;
     }
@@ -28273,7 +28393,8 @@ async function analyzeImage(options) {
         options,
         resolvedInput,
         timeoutMs,
-        config2
+        config2,
+        warnings
       );
       attempts.push({
         provider: provider.name,
@@ -28323,8 +28444,14 @@ async function analyzeImage(options) {
     `Every configured vision provider failed for this image. ${attempts.map((attempt) => `${attempt.provider}: ${attempt.error}`).join(" | ")}`
   );
 }
-async function runProvider(provider, model, options, resolvedInput, timeoutMs, config2) {
-  const settings = resolveProviderSettings(provider.name, config2);
+async function runProvider(provider, model, options, resolvedInput, timeoutMs, config2, warnings) {
+  const configured = resolveProviderSettings(provider.name, config2);
+  const settings = options.extraBody ? { ...configured, extraBody: options.extraBody } : configured;
+  if (settings.extraBody && !provider.execute) {
+    warnings.push(
+      `${provider.name} is a CLI provider and takes no request body, so extraBody was ignored for this run.`
+    );
+  }
   const providerOptions = {
     imageSource: resolvedInput.source,
     imageKind: resolvedInput.kind,
@@ -29207,8 +29334,11 @@ function recoverPastedImages(options = {}) {
   return result;
 }
 const program = new Command();
-program.name("modlens").description("Plug-in vision for text-only LLMs: image in, structured JSON evidence out").version("3.3.0");
-program.command("analyze", { isDefault: true }).description("Analyze an image into structured JSON evidence (default command)").requiredOption("-i, --input <path|url>", "Input image path or https URL").option("-o, --output <path>", "Write result JSON to a file").option("-m, --model <name>", "Provider model name").option("-p, --provider <name>", `Vision provider (${listProviders().join(", ")})`).option("--prompt <text>", "Extra focus for this image").option("--timeout <ms>", "Provider timeout in milliseconds", "180000").option("--provider-bin <path>", "Provider binary path (default: agy)").option("--workdir <path>", "Working directory for the provider").action(async (options) => {
+program.name("modlens").description("Plug-in vision for text-only LLMs: image in, structured JSON evidence out").version("3.4.0");
+program.command("analyze", { isDefault: true }).description("Analyze an image into structured JSON evidence (default command)").requiredOption("-i, --input <path|url>", "Input image path or https URL").option("-o, --output <path>", "Write result JSON to a file").option("-m, --model <name>", "Provider model name").option("-p, --provider <name>", `Vision provider (${listProviders().join(", ")})`).option("--prompt <text>", "Extra focus for this image").option("--timeout <ms>", "Provider timeout in milliseconds", "180000").option("--provider-bin <path>", "Provider binary path (default: agy)").option("--workdir <path>", "Working directory for the provider").option(
+  "--extra-body <json>",
+  `JSON merged into the API request body, e.g. '{"thinking":{"type":"disabled"}}'`
+).action(async (options) => {
   try {
     const timeoutMs = Number.parseInt(options.timeout, 10);
     if (!Number.isFinite(timeoutMs) || timeoutMs <= 0) {
@@ -29221,7 +29351,8 @@ program.command("analyze", { isDefault: true }).description("Analyze an image in
       prompt: options.prompt,
       timeoutMs,
       providerBin: options.providerBin,
-      workdir: options.workdir
+      workdir: options.workdir,
+      extraBody: options.extraBody ? parseExtraBody(options.extraBody, "--extra-body") : void 0
     });
     const output = JSON.stringify(result, null, 2);
     if (options.output) {
@@ -29302,6 +29433,7 @@ config.command("init").description(`Create a starter config at ${CONFIG_PATH}`).
         "Everything is optional. Two things you can set:",
         "  modlens config set provider <name>                      which provider analyzes images",
         "  modlens config set <provider>.<apiKey|baseUrl|model> <value>   provider credentials",
+        `  modlens config set <provider>.extraBody '{"thinking":{"type":"disabled"}}'   vendor request fields`,
         ""
       ].join("\n")
     );

package/docs/troubleshooting.md

@@ -127,6 +127,23 @@ antigravity-cli provider timed out after 210000 ms.
 
 Retry once with `--timeout 300000`. Dense images on agy legitimately take 15-40 seconds, and `-m gemini-3.1-pro-high` is slower still. Engines that ignore SIGTERM are escalated to SIGKILL, so a timeout returns promptly regardless.
 
+## Every read is slow on a reasoning model
+
+A model that thinks by default spends its budget before it starts transcribing, which a vision read does not need. There is no `--no-thinking` flag because each vendor names the switch differently, so pass the vendor's own field:
+
+```bash
+modlens config set openai.extraBody '{"thinking":{"type":"disabled"}}'
+modlens -i shot.png --extra-body '{"reasoning_effort":"low"}'    # one run only
+```
+
+The per-vendor spellings, which models cannot turn it off at all, and how to tell whether the field actually landed are in [Configuration](../skills/modlens/references/configure.md#turning-thinking-off).
+
+```
+extraBody cannot override "messages" for the openai provider
+```
+
+That field carries the image, the prompt, or the schema enforcement. Remove it and keep the vendor knobs. A 400 from the gateway naming a field you set means that endpoint uses a different spelling, and a run on `antigravity-cli` or `claude-cli` says in `meta.warnings` that it ignored the value, since a CLI provider has no request body.
+
 ## Windows
 
 ModLens runs on Windows. Three platform differences are worth knowing:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@liustack/modlens",
-  "version": "3.3.0",
+  "version": "3.4.0",
   "description": "Plug-in vision for text-only LLMs, powered by the free Antigravity CLI",
   "type": "module",
   "bin": {

package/skills/modlens/SKILL.md

@@ -33,11 +33,11 @@ The launcher finds a working way to run modlens and forwards your arguments to i
 
 ### If you cannot run the launcher script
 
-Some harnesses forbid running scripts. Reason through the same order by hand and run the first line that works (the pinned version is 3.3.0):
+Some harnesses forbid running scripts. Reason through the same order by hand and run the first line that works (the pinned version is 3.4.0):
 
-1. A `modlens` on `PATH` whose major version is 3 and is at least 3.3.0: `modlens <args>`.
-2. Otherwise, if `npx` exists: `npx --yes --package @liustack/modlens@3.3.0 modlens <args>`.
-3. Otherwise, if `bunx` exists: `bunx --bun @liustack/modlens@3.3.0 <args>`.
+1. A `modlens` on `PATH` whose major version is 3 and is at least 3.4.0: `modlens <args>`.
+2. Otherwise, if `npx` exists: `npx --yes --package @liustack/modlens@3.4.0 modlens <args>`.
+3. Otherwise, if `bunx` exists: `bunx --bun @liustack/modlens@3.4.0 <args>`.
 4. Otherwise none of these runtimes is here. Tell the user no JavaScript runtime was found and that installing Node 22.13+ (https://nodejs.org) or Bun (https://bun.sh) is the next step. Do not claim modlens itself failed.
 
 `references/runtime.md` documents the version pin, the compatibility rule, and the diagnostic fields.
@@ -78,6 +78,8 @@ modlens -i <image> -o <output.json> -m <model> --prompt "<extra focus>" --timeou
 
 Speed expectations: `gemini-api` typically 5-10 seconds, `antigravity-cli` 15-40 seconds and `claude-cli` 20-45 seconds (full agent loops), `openai`/`anthropic` depend on the endpoint. For dense or hard images on antigravity-cli, try `-m gemini-3.1-pro-high`.
 
+If every read is slow because the configured model thinks before answering, pass the vendor's own switch through the request body, for example `--extra-body '{"thinking":{"type":"disabled"}}'`, or store it with `modlens config set <provider>.extraBody '<json>'`. The spelling differs per endpoint, so read `references/configure.md` before guessing.
+
 ## Finding the image path in the chat
 
 Harnesses rarely hand you a clean path. First identify which harness you are in, then use its route. Never mix routes across harnesses.

package/skills/modlens/references/cli.md

@@ -51,6 +51,12 @@ Output is a fixed JSON shape:
 | `--timeout <ms>` | Provider timeout | `180000` |
 | `--provider-bin <path>` | Provider binary path | `agy` / `claude` |
 | `--workdir <path>` | Working directory for the provider | a fresh isolated directory per run |
+| `--extra-body <json>` | JSON merged into the API request body, e.g. `'{"thinking":{"type":"disabled"}}'` | the provider's `extraBody` from the config |
+
+`--extra-body` is how vendor-specific knobs get through, turning thinking off
+being the common one. It applies to the three API providers and replaces the
+configured `extraBody` for that run. Per-vendor spellings and the fields it
+refuses to touch are in [Configuration](configure.md).
 
 The default `-m` model depends on the provider:
 

package/skills/modlens/references/configure.md

@@ -10,7 +10,7 @@ Read this when the user asks how to set up, configure, or switch ModLens provide
 modlens config init                     # write a starter config (refuses to overwrite; --force to redo)
 modlens config show                     # effective file, API keys masked
 modlens config set provider <name>      # change the default provider
-modlens config set <provider>.<field> <value>   # fields: apiKey, baseUrl, model
+modlens config set <provider>.<field> <value>   # fields: apiKey, baseUrl, model, extraBody
 ```
 
 `config set` writes the file with 0600 permissions.
@@ -32,7 +32,8 @@ Everything lives under two top-level keys, both optional. A missing file means a
     "openai": {
       "apiKey": "sk-...",
       "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode/v1",
-      "model": "qwen3.6-27b"
+      "model": "qwen3.6-27b",
+      "extraBody": { "thinking": { "type": "disabled" } }
     },
     "anthropic": { "apiKey": "sk-ant-..." },
     "claude-cli": { "model": "haiku" }
@@ -43,7 +44,8 @@ Everything lives under two top-level keys, both optional. A missing file means a
 Field semantics:
 
 - `provider`: which provider runs when `-p` is not given. Canonical names or aliases both work (`agy`/`antigravity` for `antigravity-cli`, `gemini` for `gemini-api`, `openai-compat` for `openai`, `claude` for `anthropic`, `claude-code` for `claude-cli`). Empty or absent means `antigravity-cli`.
-- `providers.<name>.<field>`: only three fields exist, `apiKey`, `baseUrl`, `model`. Every provider entry is optional, and every field inside it is optional. Alias keys are read too (settings saved under `gemini` are found when `gemini-api` resolves), with the canonical key winning on conflict.
+- `providers.<name>.<field>`: four fields exist, `apiKey`, `baseUrl`, `model`, and `extraBody`. Every provider entry is optional, and every field inside it is optional. Alias keys are read too (settings saved under `gemini` are found when `gemini-api` resolves), with the canonical key winning on conflict.
+- `providers.<name>.extraBody`: a JSON object merged into the request body of the API providers (`gemini-api`, `openai`, `anthropic`), for whatever knobs that vendor has and modlens has no flag for. Turning thinking off is the usual reason, see the section below. Nested objects merge key by key, so adding one knob leaves the rest of that block alone. The fields carrying the image, the prompt, and the schema enforcement are refused with an error naming the field. The two CLI providers take no request body, so a run on `antigravity-cli` or `claude-cli` ignores it and says so in `meta.warnings`.
 - Environment variables override the file for these bindings: `GEMINI_API_KEY`, `OPENAI_API_KEY`, `OPENAI_BASE_URL`, `ANTHROPIC_API_KEY`, `ANTHROPIC_BASE_URL`. Nothing else is read from the environment except `MODLENS_HARNESS` (paste-recovery scope, unrelated to this file).
 - Unknown top-level keys and unknown provider names are ignored rather than rejected, so a typo fails quiet: run `modlens doctor` after hand-editing, it shows which file and env values are actually in effect.
 
@@ -105,6 +107,37 @@ Rides an existing `claude` sign-in, so it costs the user's Claude subscription q
 modlens config set provider claude-cli   # make it the default if the user wants
 ```
 
+## Turning thinking off
+
+A reasoning model spends its thinking budget before it answers. Reading text out of an image needs none of that, so on a model that thinks by default the run is slower and more expensive for nothing. Every vendor names the switch differently, and there is no portable one, so modlens sends whatever you put in `extraBody` and leaves the naming to the vendor's own docs.
+
+```bash
+modlens config set openai.extraBody '{"thinking":{"type":"disabled"}}'   # persist it
+modlens -i shot.png --extra-body '{"thinking":{"type":"disabled"}}'      # one run only
+modlens config set openai.extraBody ''                                   # clear it
+```
+
+`--extra-body` replaces the stored object for that run rather than merging into it.
+
+Known spellings, current as of August 2026:
+
+| Endpoint | Field to send |
+| :-- | :-- |
+| MiMo official API (`api.xiaomimimo.com/v1`) | `{"thinking":{"type":"disabled"}}` |
+| MiMo Responses-format route | `{"reasoning":{"effort":"none"}}` |
+| Qwen, GLM, MiMo and friends self-hosted on vLLM or SGLang | `{"chat_template_kwargs":{"enable_thinking":false}}` |
+| OpenAI-style gateways that accept an effort level | `{"reasoning_effort":"low"}` |
+| `gemini-api`, Gemini 3 family | `{"generationConfig":{"thinkingConfig":{"thinkingLevel":"LOW"}}}` |
+| `gemini-api`, Gemini 2.5 Flash and Flash Lite | `{"generationConfig":{"thinkingConfig":{"thinkingBudget":0}}}` |
+| `anthropic` | nothing to do, thinking is off unless it is asked for |
+
+Three things that bite:
+
+- Not every model can turn it off. Gemini 3 Pro and Gemini 2.5 Pro have no off switch, only a lower level. Some models ignore an effort field entirely and think anyway.
+- Strict clouds (Groq and Cerebras among them) reject fields they do not recognize with a 400. If a request that worked before now fails with a 400 naming your field, that gateway wants a different spelling, not this one.
+- Others accept an unknown field and quietly ignore it, so check that it took effect instead of assuming. Compare `meta.durationSeconds` and the token counts in `meta.usage` against a run without `extraBody`. If neither moved, the field did not land.
+- A weaker model may need its thinking to fill the schema. Measured on one flowchart: `gemini-3.6-flash` at `thinkingLevel: LOW` came back in 5.7s instead of 12s with the same regions and the same transcription, but `qwen3.6-27b` on DashScope with `enable_thinking: false` started omitting the required `type` on layout regions, which modlens rejects rather than passing off as evidence. If shape errors appear right after you turn thinking off, that is the trade, so turn it back on for that model or move to a route with server-side schema enforcement.
+
 ## Choosing a provider for the user
 
 - Wants zero setup and free: `antigravity-cli` (needs agy sign-in, 15-40s per image).
@@ -125,4 +158,6 @@ chains, and the result's `meta.attempts` shows what a run actually tried.
 - `Provider CLI not found: agy`: install Antigravity CLI or switch provider.
 - `Claude CLI reported ...` or empty result: check `claude` login state.
 - openai route `does not match the vision schema`: retry once, then switch to gemini-api or anthropic.
+- `extraBody cannot override "<field>"`: that field carries the image, the prompt, or the schema. Drop it from the object and keep the vendor knobs.
+- A 400 that names a field you set in `extraBody`: that gateway does not know it. See the thinking section above for the other spellings.
 - `config init` refusing to run: the file exists; use `modlens config show` first, `--force` only if the user agrees to overwrite.

package/skills/modlens/references/runtime.md

@@ -8,7 +8,7 @@ shell syntax.
 
 ## Pinned version
 
-- Pinned CLI version: 3.3.0
+- Pinned CLI version: 3.4.0
 - npm package: `@liustack/modlens`
 - CLI binary name: `modlens`
 

package/skills/modlens/scripts/run.ps1

@@ -24,7 +24,7 @@ $ErrorActionPreference = 'Stop'
 # package.json version, and the release script rewrites it on every bump.
 $Package = '@liustack/modlens'
 $Bin = 'modlens'
-$Pinned = '3.3.0'
+$Pinned = '3.4.0'
 # -------------------------------------------------------------------------------
 
 $NativeNote = 'no native artifact is published for this tool yet; phase A ships npm launch paths only'

package/skills/modlens/scripts/run.sh

@@ -22,7 +22,7 @@ set -eu
 # package.json version, and the release script rewrites it on every bump.
 PKG="@liustack/modlens"
 BIN="modlens"
-PINNED="3.3.0"
+PINNED="3.4.0"
 # -------------------------------------------------------------------------------
 
 NATIVE_NOTE="no native artifact is published for this tool yet; phase A ships npm launch paths only"