Add image support in tool results across all providers

Tool results now use content blocks and can include both text and images.
All providers (Anthropic, Google, OpenAI Completions, OpenAI Responses)
correctly pass images from tool results to LLMs.

- Update ToolResultMessage type to use content blocks
- Add placeholder text for image-only tool results in Google/Anthropic
- OpenAI providers send tool result + follow-up user message with images
- Fix Anthropic JSON parsing for empty tool arguments
- Add comprehensive tests for image-only and text+image tool results
- Update README with tool result content blocks API

packages/coding-agent/src/tools/bash.ts

@@ -95,7 +95,7 @@ export const bashTool: AgentTool<typeof bashSchema> = {
 					if (output) output += "\n\n";
 					reject(new Error(`${output}Command exited with code ${code}`));
 				} else {
-					resolve({ output: output || "(no output)", details: undefined });
+					resolve({ content: [{ type: "text", text: output || "(no output)" }], details: undefined });
 				}
 			});