Fix hook tool_result event not emitted for tool errors

Tools are supposed to throw on error. What needs fixing is that we need to report tool_result for erroneous tool executions as well.

Fixes #374

packages/coding-agent/CHANGELOG.md

@@ -198,6 +198,7 @@ Total color count increased from 46 to 50. See [docs/theme.md](docs/theme.md) fo
 
 ### Fixed
 
+- **Hook `tool_result` event ignores errors from custom tools**: The `tool_result` hook event was never emitted when tools threw errors, and always had `isError: false` for successful executions. Now emits the event with correct `isError` value in both success and error cases. ([#374](https://github.com/badlogic/pi-mono/issues/374) by [@nicobailon](https://github.com/nicobailon))
 - **Edit tool fails on Windows due to CRLF line endings**: Files with CRLF line endings now match correctly when LLMs send LF-only text. Line endings are normalized before matching and restored to original style on write. ([#355](https://github.com/badlogic/pi-mono/issues/355) by [@Pratham-Dubey](https://github.com/Pratham-Dubey))
 - **Use bash instead of sh on Unix**: Fixed shell commands using `/bin/sh` instead of `/bin/bash` on Unix systems. ([#328](https://github.com/badlogic/pi-mono/pull/328) by [@dnouri](https://github.com/dnouri))
 - **OAuth login URL clickable**: Made OAuth login URLs clickable in terminal. ([#349](https://github.com/badlogic/pi-mono/pull/349) by [@Cursivez](https://github.com/Cursivez))

packages/coding-agent/src/core/hooks/tool-wrapper.ts

@@ -46,6 +46,7 @@ export function wrapToolWithHooks<T>(tool: AgentTool<any, T>, hookRunner: HookRu
 			}
 
 			// Execute the actual tool, forwarding onUpdate for progress streaming
+			try {
 				const result = await tool.execute(toolCallId, params, signal, onUpdate);
 
 				// Emit tool_result event - hooks can modify the result
@@ -70,6 +71,21 @@ export function wrapToolWithHooks<T>(tool: AgentTool<any, T>, hookRunner: HookRu
 				}
 
 				return result;
+			} catch (err) {
+				// Emit tool_result event for errors so hooks can observe failures
+				if (hookRunner.hasHandlers("tool_result")) {
+					await hookRunner.emit({
+						type: "tool_result",
+						toolName: tool.name,
+						toolCallId,
+						input: params,
+						content: [{ type: "text", text: err instanceof Error ? err.message : String(err) }],
+						details: undefined,
+						isError: true,
+					});
+				}
+				throw err; // Re-throw original error for agent-loop
+			}
 		},
 	};
 }