@luffysolution/omnischolar-pi 0.1.22 → 0.1.24

package/docs/IMAGE_PROVIDERS.en.md

@@ -111,6 +111,37 @@ Upload only images you may share with the selected service. After files are save
 - DashScope/Qwen supports the Qwen AI Platform native endpoint `https://dashscope.aliyuncs.com/api/v1` and regional Bailian workspace endpoints such as `https://<workspace>.cn-beijing.maas.aliyuncs.com/api/v1`. When `workspace` and `region` are supplied, the tool can derive the regional endpoint.
 - Gemini's `apiKeyEnv` must name an environment variable that exists.
 - Atlas Cloud uses `https://api.atlascloud.ai/api/v1`, submits to `model/generateImage`, and polls `model/prediction/{id}`. The built-in set includes official Nano Banana 2, GPT Image 2, and GPT Image 2.5 Flare/Sunburst IDs. Atlas image tasks are asynchronous and their `outputs` are saved locally.
-- Custom services automatically probe the standard OpenAI-compatible `/models` endpoint, or use `options.modelCatalogEndpoint` for a non-standard catalog URL. If the catalog lacks explicit `capabilities`/`supportedCapabilities`, declare `text-to-image`, `image-to-image`, or `edit` in `models` before calling it.
+- Custom services automatically probe the standard OpenAI-compatible `/models` endpoint, or use `options.modelCatalogEndpoint` for a non-standard catalog URL. If the catalog lacks explicit `capabilities`/`supportedCapabilities`, declare `text-to-image`, `image-to-image`, or `edit` in `models` before calling it. Custom image requests default to a 180-second timeout and can be adjusted with `options.imageTimeoutSeconds` up to 1800 seconds.
+
+Multiple custom profiles can be configured under `media.providers`. Profile names may differ, but each must set `providerType: "custom"`; every profile has its own `apiKeyEnv`, `baseUrl`, model capabilities, and `supportedParameters`. Select the profile by its provider name when calling the tool. Common OpenAI/Gemini-compatible image endpoints are `images/generations` and `images/edits`; override them with `generationEndpoint` and `editEndpoint` when needed.
+
+For example, keep separate keys for two model families:
+
+```json
+{
+  "custom-aixoras-openai": {
+    "providerType": "custom",
+    "apiKeyEnv": "OMNISCHOLAR_AIXORAS_OPENAI_API_KEY",
+    "baseUrl": "https://api.aixoras.com/v1",
+    "models": {
+      "gpt-image-2": {
+        "capabilities": ["text-to-image", "image-to-image", "edit"],
+        "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"]
+      }
+    }
+  },
+  "custom-aixoras-gemini": {
+    "providerType": "custom",
+    "apiKeyEnv": "OMNISCHOLAR_AIXORAS_GEMINI_API_KEY",
+    "baseUrl": "https://api.aixoras.com/v1",
+    "models": {
+      "gemini-3.1-flash-image": {
+        "capabilities": ["text-to-image", "image-to-image", "edit"],
+        "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"]
+      }
+    }
+  }
+}
+```
 
 Review text, structures, mechanisms, scale, and quantitative labels after generation. **AI images are illustrative drafts, not experimental data, real measurements, or scientific conclusions.**

package/docs/IMAGE_PROVIDERS.md

@@ -111,6 +111,37 @@ Atlas、fal、Vertex、DashScope/Qwen 和自定义服务的模型目录能力不
 - DashScope/Qwen 支持千问 AI 平台的通用原生地址 `https://dashscope.aliyuncs.com/api/v1`，也支持百炼按地域的 workspace 地址，例如 `https://<workspace>.cn-beijing.maas.aliyuncs.com/api/v1`。当填写 `workspace` 和 `region` 时，工具可以自动拼接地域地址。
 - Gemini 配置中的 `apiKeyEnv` 必须指向已存在的环境变量。
 - Atlas Cloud 使用 `https://api.atlascloud.ai/api/v1`、`model/generateImage` 提交和 `model/prediction/{id}` 轮询；默认内置 Nano Banana 2、GPT Image 2、GPT Image 2.5 Flare/Sunburst 的官方模型 ID。Atlas 的图片任务是异步的，结果中的 `outputs` 会保存到本地。
-- 自定义服务会自动探测标准 OpenAI 兼容的 `/models`；也可以用 `options.modelCatalogEndpoint` 指定非标准目录地址。目录结果缺少明确 `capabilities`/`supportedCapabilities` 时只展示为未绑定能力，必须在 `models` 中声明 `text-to-image`、`image-to-image` 或 `edit` 后才能调用。
+- 自定义服务会自动探测标准 OpenAI 兼容的 `/models`；也可以用 `options.modelCatalogEndpoint` 指定非标准目录地址。目录结果缺少明确 `capabilities`/`supportedCapabilities` 时只展示为未绑定能力，必须在 `models` 中声明 `text-to-image`、`image-to-image` 或 `edit` 后才能调用。custom 图片请求默认超时为 180 秒，可用 `options.imageTimeoutSeconds` 调整（上限 1800 秒）。
+
+可以在 `media.providers` 下配置多个 custom profile。profile 名称可以不同，但必须设置 `providerType: "custom"`；每个 profile 独立填写 `apiKeyEnv`、`baseUrl`、模型能力和 `supportedParameters`，调用时用对应 profile 名称选择服务。OpenAI/Gemini 兼容中转站常见的图片 endpoint 是 `images/generations` 和 `images/edits`，可通过 `generationEndpoint`、`editEndpoint` 调整。
+
+例如两个 API 分开配置：
+
+```json
+{
+  "custom-aixoras-openai": {
+    "providerType": "custom",
+    "apiKeyEnv": "OMNISCHOLAR_AIXORAS_OPENAI_API_KEY",
+    "baseUrl": "https://api.aixoras.com/v1",
+    "models": {
+      "gpt-image-2": {
+        "capabilities": ["text-to-image", "image-to-image", "edit"],
+        "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"]
+      }
+    }
+  },
+  "custom-aixoras-gemini": {
+    "providerType": "custom",
+    "apiKeyEnv": "OMNISCHOLAR_AIXORAS_GEMINI_API_KEY",
+    "baseUrl": "https://api.aixoras.com/v1",
+    "models": {
+      "gemini-3.1-flash-image": {
+        "capabilities": ["text-to-image", "image-to-image", "edit"],
+        "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"]
+      }
+    }
+  }
+}
+```
 
 生成后仍需人工检查文字、结构、机制、比例和定量描述。**AI 图片是示意草稿，不是实验数据、真实测量或科研结论。**

package/omnischolar.config.example.json

@@ -210,34 +210,41 @@
         "baseUrl": "https://images.example.edu/v1",
         "models": {
           "gpt-image-2": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           },
           "gpt-image-2.5-sunburst": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           },
           "gpt-image-2.5-flare": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           },
           "gemini-3.1-flash-image": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           },
           "gemini-3.1-flash-lite-image": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           },
           "gemini-3-pro-image": {
-            "capabilities": ["text-to-image"],
+            "capabilities": ["text-to-image", "image-to-image", "edit", "multi-reference"],
+            "supportedParameters": ["size", "resolution", "background", "outputFormat", "quality", "n"],
             "paid": true
           }
         },
         "options": {
           "modelCatalogEndpoint": null,
           "generationEndpoint": "images/generations",
-          "editEndpoint": "images/edits"
+          "editEndpoint": "images/edits",
+          "imageTimeoutSeconds": 180
         }
       }
     }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@luffysolution/omnischolar-pi",
-  "version": "0.1.22",
+  "version": "0.1.24",
   "description": "Pi MCP bridge for the OmniScholar research toolkit",
   "type": "module",
   "license": "MIT",

package/pi-extension/dist/index.js

@@ -1,7 +1,7 @@
 import { Client } from "@modelcontextprotocol/sdk/client/index.js";
 import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
 import { Type } from "typebox";
-const CLIENT_INFO = { name: "omnischolar-pi", version: "0.1.22" };
+const CLIENT_INFO = { name: "omnischolar-pi", version: "0.1.24" };
 export function resultText(result) {
     return result.content
         .map((item) => {