oh-my-opencode 1.0.2 → 1.1.0

package/dist/agents/multimodal-looker.d.ts

@@ -0,0 +1,2 @@
+import type { AgentConfig } from "@opencode-ai/sdk";
+export declare const multimodalLookerAgent: AgentConfig;

package/dist/agents/types.d.ts

@@ -1,4 +1,4 @@
 import type { AgentConfig } from "@opencode-ai/sdk";
-export type AgentName = "oracle" | "librarian" | "explore" | "frontend-ui-ux-engineer" | "document-writer";
+export type AgentName = "oracle" | "librarian" | "explore" | "frontend-ui-ux-engineer" | "document-writer" | "multimodal-looker";
 export type AgentOverrideConfig = Partial<AgentConfig>;
 export type AgentOverrides = Partial<Record<AgentName, AgentOverrideConfig>>;

package/dist/index.js

@@ -2358,6 +2358,47 @@ STOP HERE - DO NOT CONTINUE TO NEXT TASK
 You are a technical writer who creates documentation that developers actually want to read.
 </guide>`
 };
+
+// src/agents/multimodal-looker.ts
+var multimodalLookerAgent = {
+  description: "Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
+  mode: "subagent",
+  model: "google/gemini-2.5-flash",
+  temperature: 0.1,
+  tools: { Read: true },
+  prompt: `You interpret media files that cannot be read as plain text.
+
+Your job: examine the attached file and extract ONLY what was requested.
+
+When to use you:
+- Media files the Read tool cannot interpret
+- Extracting specific information or summaries from documents
+- Describing visual content in images or diagrams
+- When analyzed/extracted data is needed, not raw file contents
+
+When NOT to use you:
+- Source code or plain text files needing exact contents (use Read)
+- Files that need editing afterward (need literal content from Read)
+- Simple file reading where no interpretation is needed
+
+How you work:
+1. Receive a file path and a goal describing what to extract
+2. Read and analyze the file deeply
+3. Return ONLY the relevant extracted information
+4. The main agent never processes the raw file - you save context tokens
+
+For PDFs: extract text, structure, tables, data from specific sections
+For images: describe layouts, UI elements, text, diagrams, charts
+For diagrams: explain relationships, flows, architecture depicted
+
+Response rules:
+- Return extracted information directly, no preamble
+- If info not found, state clearly what's missing
+- Match the language of the request
+- Be thorough on the goal, concise on everything else
+
+Your output goes straight to the main agent for continued work.`
+};
 // src/shared/frontmatter.ts
 function parseFrontmatter(content) {
   const frontmatterRegex = /^---\r?\n([\s\S]*?)\r?\n---\r?\n([\s\S]*)$/;
@@ -2717,7 +2758,8 @@ var allBuiltinAgents = {
   librarian: librarianAgent,
   explore: exploreAgent,
   "frontend-ui-ux-engineer": frontendUiUxEngineerAgent,
-  "document-writer": documentWriterAgent
+  "document-writer": documentWriterAgent,
+  "multimodal-looker": multimodalLookerAgent
 };
 function mergeAgentConfig(base, override) {
   return deepMerge(base, override);
@@ -24168,6 +24210,97 @@ session_id: ${sessionID}
 `);
   return output;
 }
+// src/tools/look-at/constants.ts
+var MULTIMODAL_LOOKER_AGENT = "multimodal-looker";
+var LOOK_AT_DESCRIPTION = `Analyze media files (PDFs, images, diagrams) that require visual interpretation.
+
+Use this tool to extract specific information from files that cannot be processed as plain text:
+- PDF documents: extract text, tables, structure, specific sections
+- Images: describe layouts, UI elements, text content, diagrams
+- Charts/Graphs: explain data, trends, relationships
+- Screenshots: identify UI components, text, visual elements
+- Architecture diagrams: explain flows, connections, components
+
+Parameters:
+- file_path: Absolute path to the file to analyze
+- goal: What specific information to extract (be specific for better results)
+
+Examples:
+- "Extract all API endpoints from this OpenAPI spec PDF"
+- "Describe the UI layout and components in this screenshot"
+- "Explain the data flow in this architecture diagram"
+- "List all table data from page 3 of this PDF"
+
+This tool uses a separate context window with Gemini 2.5 Flash for multimodal analysis,
+saving tokens in the main conversation while providing accurate visual interpretation.`;
+// src/tools/look-at/tools.ts
+function createLookAt(ctx) {
+  return tool({
+    description: LOOK_AT_DESCRIPTION,
+    args: {
+      file_path: tool.schema.string().describe("Absolute path to the file to analyze"),
+      goal: tool.schema.string().describe("What specific information to extract from the file")
+    },
+    async execute(args, toolContext) {
+      log(`[look_at] Analyzing file: ${args.file_path}, goal: ${args.goal}`);
+      const prompt = `Analyze this file and extract the requested information.
+
+File path: ${args.file_path}
+Goal: ${args.goal}
+
+Read the file using the Read tool, then provide ONLY the extracted information that matches the goal.
+Be thorough on what was requested, concise on everything else.
+If the requested information is not found, clearly state what is missing.`;
+      log(`[look_at] Creating session with parent: ${toolContext.sessionID}`);
+      const createResult = await ctx.client.session.create({
+        body: {
+          parentID: toolContext.sessionID,
+          title: `look_at: ${args.goal.substring(0, 50)}`
+        }
+      });
+      if (createResult.error) {
+        log(`[look_at] Session create error:`, createResult.error);
+        return `Error: Failed to create session: ${createResult.error}`;
+      }
+      const sessionID = createResult.data.id;
+      log(`[look_at] Created session: ${sessionID}`);
+      log(`[look_at] Sending prompt to session ${sessionID}`);
+      await ctx.client.session.prompt({
+        path: { id: sessionID },
+        body: {
+          agent: MULTIMODAL_LOOKER_AGENT,
+          tools: {
+            task: false,
+            call_omo_agent: false,
+            look_at: false
+          },
+          parts: [{ type: "text", text: prompt }]
+        }
+      });
+      log(`[look_at] Prompt sent, fetching messages...`);
+      const messagesResult = await ctx.client.session.messages({
+        path: { id: sessionID }
+      });
+      if (messagesResult.error) {
+        log(`[look_at] Messages error:`, messagesResult.error);
+        return `Error: Failed to get messages: ${messagesResult.error}`;
+      }
+      const messages = messagesResult.data;
+      log(`[look_at] Got ${messages.length} messages`);
+      const lastAssistantMessage = messages.filter((m) => m.info.role === "assistant").sort((a, b) => (b.info.time?.created || 0) - (a.info.time?.created || 0))[0];
+      if (!lastAssistantMessage) {
+        log(`[look_at] No assistant message found`);
+        return `Error: No response from multimodal-looker agent`;
+      }
+      log(`[look_at] Found assistant message with ${lastAssistantMessage.parts.length} parts`);
+      const textParts = lastAssistantMessage.parts.filter((p) => p.type === "text");
+      const responseText = textParts.map((p) => p.text).join(`
+`);
+      log(`[look_at] Got response, length: ${responseText.length}`);
+      return responseText;
+    }
+  });
+}
 // src/tools/index.ts
 function createBackgroundTools(manager, client2) {
   return {
@@ -24685,13 +24818,15 @@ var OhMyOpenCodePlugin = async (ctx) => {
   const backgroundNotificationHook = isHookEnabled("background-notification") ? createBackgroundNotificationHook(backgroundManager) : null;
   const backgroundTools = createBackgroundTools(backgroundManager, ctx.client);
   const callOmoAgent = createCallOmoAgent(ctx, backgroundManager);
+  const lookAt = createLookAt(ctx);
   const googleAuthHooks = pluginConfig.google_auth ? await createGoogleAntigravityAuthPlugin(ctx) : null;
   return {
     ...googleAuthHooks ? { auth: googleAuthHooks.auth } : {},
     tool: {
       ...builtinTools,
       ...backgroundTools,
-      call_omo_agent: callOmoAgent
+      call_omo_agent: callOmoAgent,
+      look_at: lookAt
     },
     "chat.message": async (input, output) => {
       await claudeCodeHooks["chat.message"]?.(input, output);
@@ -24722,6 +24857,14 @@ var OhMyOpenCodePlugin = async (ctx) => {
           call_omo_agent: false
         };
       }
+      if (config3.agent["multimodal-looker"]) {
+        config3.agent["multimodal-looker"].tools = {
+          ...config3.agent["multimodal-looker"].tools,
+          task: false,
+          call_omo_agent: false,
+          look_at: false
+        };
+      }
       const mcpResult = pluginConfig.claude_code?.mcp ?? true ? await loadMcpConfigs() : { servers: {} };
       config3.mcp = {
         ...config3.mcp,

package/dist/tools/index.d.ts

@@ -2,6 +2,7 @@ import type { PluginInput } from "@opencode-ai/plugin";
 import type { BackgroundManager } from "../features/background-agent";
 type OpencodeClient = PluginInput["client"];
 export { createCallOmoAgent } from "./call-omo-agent";
+export { createLookAt } from "./look-at";
 export declare function createBackgroundTools(manager: BackgroundManager, client: OpencodeClient): {
     background_task: {
         description: string;

package/dist/tools/look-at/constants.d.ts

@@ -0,0 +1,2 @@
+export declare const MULTIMODAL_LOOKER_AGENT: "multimodal-looker";
+export declare const LOOK_AT_DESCRIPTION = "Analyze media files (PDFs, images, diagrams) that require visual interpretation.\n\nUse this tool to extract specific information from files that cannot be processed as plain text:\n- PDF documents: extract text, tables, structure, specific sections\n- Images: describe layouts, UI elements, text content, diagrams\n- Charts/Graphs: explain data, trends, relationships\n- Screenshots: identify UI components, text, visual elements\n- Architecture diagrams: explain flows, connections, components\n\nParameters:\n- file_path: Absolute path to the file to analyze\n- goal: What specific information to extract (be specific for better results)\n\nExamples:\n- \"Extract all API endpoints from this OpenAPI spec PDF\"\n- \"Describe the UI layout and components in this screenshot\"\n- \"Explain the data flow in this architecture diagram\"\n- \"List all table data from page 3 of this PDF\"\n\nThis tool uses a separate context window with Gemini 2.5 Flash for multimodal analysis,\nsaving tokens in the main conversation while providing accurate visual interpretation.";

package/dist/tools/look-at/index.d.ts

@@ -0,0 +1,3 @@
+export * from "./types";
+export * from "./constants";
+export { createLookAt } from "./tools";

package/dist/tools/look-at/tools.d.ts

@@ -0,0 +1,12 @@
+import { type PluginInput } from "@opencode-ai/plugin";
+export declare function createLookAt(ctx: PluginInput): {
+    description: string;
+    args: {
+        file_path: import("zod").ZodString;
+        goal: import("zod").ZodString;
+    };
+    execute(args: {
+        file_path: string;
+        goal: string;
+    }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+};

package/dist/tools/look-at/types.d.ts

@@ -0,0 +1,4 @@
+export interface LookAtArgs {
+    file_path: string;
+    goal: string;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "1.0.2",
+  "version": "1.1.0",
   "description": "OpenCode plugin - custom agents (oracle, librarian) and enhanced features",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",