Summary
Extensions registering hook handlers via joinSession({ hooks }) cannot observe non-success tool results. onPostToolUse only fires for resultType === "success" — failure / rejected / denied / timeout outcomes are silently invisible to extensions.
The underlying CLI does emit a postToolUseFailure hook event for failed tool calls, but the SDK never dispatches it: it is missing from both the SessionHooks interface and the runtime _handleHooksInvoke handler map.
Repro
-
In an extension, register a session via joinSession with handlers for both onPostToolUse and (attempting) onPostToolUseFailure:
import { joinSession } from "@github/copilot-sdk/extension";
const session = await joinSession({
hooks: {
onPostToolUse: async (input) => {
console.log("post:", input.toolName, input.toolResult?.resultType);
},
// Not declared on SessionHooks, but try anyway:
onPostToolUseFailure: async (input) => {
console.log("post-failure:", input.toolName);
},
},
});
-
Have Copilot run a tool that fails (e.g. a shell command that exits non-zero, then a tool that times out, then one that triggers a "rejected" / "denied" outcome).
-
Observe: onPostToolUse fires only for the successful tool calls. onPostToolUseFailure never fires for any of the failure modes.
Expected
Extensions should be able to observe all terminal tool outcomes — success, failure, rejected, denied, timeout — through the hooks system. Either:
- Add
onPostToolUseFailure to SessionHooks and dispatch it from _handleHooksInvoke, or
- Always fire
onPostToolUse regardless of resultType (with the resultType field on the input distinguishing outcomes).
Evidence in shipped CLI 1.0.43-0
Path: <copilot-pkg>/copilot-sdk/extension.js (the bundled SDK shipped with the Copilot CLI).
The runtime hook dispatcher exposes only 6 hook types:
async _handleHooksInvoke(hookType, input) {
if (!this.hooks) return void 0;
const handlerMap = {
preToolUse: this.hooks.onPreToolUse,
postToolUse: this.hooks.onPostToolUse,
userPromptSubmitted: this.hooks.onUserPromptSubmitted,
sessionStart: this.hooks.onSessionStart,
sessionEnd: this.hooks.onSessionEnd,
errorOccurred: this.hooks.onErrorOccurred,
};
const handler = handlerMap[hookType];
if (!handler) return void 0; // silently dropped
...
}
The matching TypeScript declaration in copilot-sdk/types.d.ts SessionHooks declares the same 6 handlers, so authors using TypeScript can't even discover the missing types.
Meanwhile, the host CLI (app.js in the same package) builds a hook proxy per connected extension that DOES include postToolUseFailure:
// createHooksProxy(sessionId, connection)
return {
preToolUse: [o => n("preToolUse", o)],
postToolUse: [o => n("postToolUse", o)],
postToolUseFailure: [o => n("postToolUseFailure", o)],
userPromptSubmitted: [o => n("userPromptSubmitted", o)],
sessionStart: [o => n("sessionStart", o)],
sessionEnd: [o => n("sessionEnd", o)],
errorOccurred: [o => n("errorOccurred", o)],
};
And the host's processToolExecutionResult explicitly gates postToolUse on success, routing failures elsewhere:
async processToolExecutionResult(toolName, toolArgs, toolResult) {
let s = (toolResult.resultType === "success"
? await h1(this.getEffectiveHooks()?.postToolUse, ...)
: void 0)?.modifiedResult ?? toolResult;
let a = s.resultType === "failure"
? await this.runPostToolUseFailureHooks(toolName, toolArgs, s)
: void 0;
...
}
So the CLI sends hooks.invoke requests with hookType: "postToolUseFailure" to the extension over IPC, but the SDK's _handleHooksInvoke doesn't recognize that hook type and returns undefined without invoking any handler.
The full set of hook types the CLI knows about (app.js):
new Set([
"sessionStart", "sessionEnd", "userPromptSubmitted",
"preToolUse", "postToolUse", "postToolUseFailure",
"errorOccurred",
"agentStop", "subagentStop", "subagentStart",
"preCompact", "permissionRequest", "notification",
])
The SDK's hooks API exposes 6 of these to extensions. Several of the missing ones (like permissionRequest) are intentionally exposed via different APIs (onPermissionRequest in the JoinSessionConfig), so this report intentionally focuses on the most clear-cut gap: postToolUseFailure.
Impact
Extensions that want to observe or react to tool failures — for telemetry, replay buffers, fault-injection tests, or UI that visualizes tool execution — have no reliable way to do so. Since post-only-on-success silently drops the failure cases, extensions can wrongly report "no result" or, if pairing pre with post, leak resources tracking calls whose post will never come.
Suggested fix
Add the missing handler to _handleHooksInvoke's map and to the SessionHooks TypeScript interface:
export interface SessionHooks {
onPreToolUse?: PreToolUseHandler;
onPostToolUse?: PostToolUseHandler;
+ onPostToolUseFailure?: PostToolUseFailureHandler;
onUserPromptSubmitted?: UserPromptSubmittedHandler;
onSessionStart?: SessionStartHandler;
onSessionEnd?: SessionEndHandler;
onErrorOccurred?: ErrorOccurredHandler;
}
const handlerMap = {
preToolUse: this.hooks.onPreToolUse,
postToolUse: this.hooks.onPostToolUse,
+ postToolUseFailure: this.hooks.onPostToolUseFailure,
userPromptSubmitted: this.hooks.onUserPromptSubmitted,
sessionStart: this.hooks.onSessionStart,
sessionEnd: this.hooks.onSessionEnd,
errorOccurred: this.hooks.onErrorOccurred,
};
The input shape can mirror PostToolUseHookInput (toolName + toolArgs + toolResult), since the CLI's emit site already provides the same payload.
Environment
@github/copilot 1.0.43-0 (Windows win32-x64 package).
- Bundled SDK at
<install>/copilot-sdk/extension.js.
- Confirmed by inspecting the shipped JS and the TypeScript declarations in the same package.
Summary
Extensions registering hook handlers via
joinSession({ hooks })cannot observe non-success tool results.onPostToolUseonly fires forresultType === "success"— failure / rejected / denied / timeout outcomes are silently invisible to extensions.The underlying CLI does emit a
postToolUseFailurehook event for failed tool calls, but the SDK never dispatches it: it is missing from both theSessionHooksinterface and the runtime_handleHooksInvokehandler map.Repro
In an extension, register a session via
joinSessionwith handlers for bothonPostToolUseand (attempting)onPostToolUseFailure:Have Copilot run a tool that fails (e.g. a shell command that exits non-zero, then a tool that times out, then one that triggers a "rejected" / "denied" outcome).
Observe:
onPostToolUsefires only for the successful tool calls.onPostToolUseFailurenever fires for any of the failure modes.Expected
Extensions should be able to observe all terminal tool outcomes — success, failure, rejected, denied, timeout — through the hooks system. Either:
onPostToolUseFailuretoSessionHooksand dispatch it from_handleHooksInvoke, oronPostToolUseregardless ofresultType(with theresultTypefield on the input distinguishing outcomes).Evidence in shipped CLI
1.0.43-0Path:
<copilot-pkg>/copilot-sdk/extension.js(the bundled SDK shipped with the Copilot CLI).The runtime hook dispatcher exposes only 6 hook types:
The matching TypeScript declaration in
copilot-sdk/types.d.tsSessionHooksdeclares the same 6 handlers, so authors using TypeScript can't even discover the missing types.Meanwhile, the host CLI (
app.jsin the same package) builds a hook proxy per connected extension that DOES includepostToolUseFailure:And the host's
processToolExecutionResultexplicitly gatespostToolUseon success, routing failures elsewhere:So the CLI sends
hooks.invokerequests withhookType: "postToolUseFailure"to the extension over IPC, but the SDK's_handleHooksInvokedoesn't recognize that hook type and returnsundefinedwithout invoking any handler.The full set of hook types the CLI knows about (
app.js):The SDK's hooks API exposes 6 of these to extensions. Several of the missing ones (like
permissionRequest) are intentionally exposed via different APIs (onPermissionRequestin theJoinSessionConfig), so this report intentionally focuses on the most clear-cut gap:postToolUseFailure.Impact
Extensions that want to observe or react to tool failures — for telemetry, replay buffers, fault-injection tests, or UI that visualizes tool execution — have no reliable way to do so. Since post-only-on-success silently drops the failure cases, extensions can wrongly report "no result" or, if pairing pre with post, leak resources tracking calls whose post will never come.
Suggested fix
Add the missing handler to
_handleHooksInvoke's map and to theSessionHooksTypeScript interface:export interface SessionHooks { onPreToolUse?: PreToolUseHandler; onPostToolUse?: PostToolUseHandler; + onPostToolUseFailure?: PostToolUseFailureHandler; onUserPromptSubmitted?: UserPromptSubmittedHandler; onSessionStart?: SessionStartHandler; onSessionEnd?: SessionEndHandler; onErrorOccurred?: ErrorOccurredHandler; }const handlerMap = { preToolUse: this.hooks.onPreToolUse, postToolUse: this.hooks.onPostToolUse, + postToolUseFailure: this.hooks.onPostToolUseFailure, userPromptSubmitted: this.hooks.onUserPromptSubmitted, sessionStart: this.hooks.onSessionStart, sessionEnd: this.hooks.onSessionEnd, errorOccurred: this.hooks.onErrorOccurred, };The input shape can mirror
PostToolUseHookInput(toolName+toolArgs+toolResult), since the CLI's emit site already provides the same payload.Environment
@github/copilot1.0.43-0(Windowswin32-x64package).<install>/copilot-sdk/extension.js.