This repository was archived by the owner on May 24, 2026. It is now read-only.
Repository navigation
This repository was archived by the owner on May 24, 2026. It is now read-only.
Add Session Hooks support (PreToolUse, PostToolUse, UserPromptSubmitted, etc.) #680
Description
Summary
The SDK provides 6 hook types that allow customizing session behavior at key lifecycle points. PolyPilot does not use any of them.
SDK Hooks
| Hook | Input | Output | Purpose |
|---|---|---|---|
| OnPreToolUse | ToolName, ToolArgs, Cwd |
PermissionDecision, ModifiedArgs, AdditionalContext |
Block/modify tool calls before execution |
| OnPostToolUse | ToolName, ToolArgs, ToolResult |
ModifiedResult, AdditionalContext |
Filter/transform tool output after execution |
| OnUserPromptSubmitted | Prompt, Cwd |
ModifiedPrompt, AdditionalContext |
Rewrite prompts, inject context |
| OnSessionStart | Cwd, Source, InitialPrompt |
AdditionalContext, ModifiedConfig |
Custom initialization |
| OnSessionEnd | Reason, FinalMessage, Error |
CleanupActions, SessionSummary |
Custom cleanup |
| OnErrorOccurred | Error, ErrorContext, Recoverable |
ErrorHandling, RetryCount |
Custom error recovery |
Hook Events
HookStartEvent— hook invocation began (includesHookType,Input)HookEndEvent— hook invocation completed (includesOutput,Success,Error)
Proposed Implementation
- Hook configuration UI per session or per group (multi-agent preset)
- PreToolUse: Configurable tool approval policies (e.g., "always block
rm -rf", "require approval for write operations") - PostToolUse: Output filtering (e.g., redact secrets, collapse verbose output)
- UserPromptSubmitted: Auto-inject context like repo conventions, current task, or team decisions
- Hook activity log: Show when hooks fire and what they modified (via HookStart/HookEnd events)
Value
Power-user feature for customizing agent behavior. Enterprise users especially want tool approval policies and output filtering.
Activity
Keesan12 commentedon May 23, 2026
The HookStart/HookEnd events are worth exposing in the activity log, but I would redact and summarize by default.
PreToolUse and UserPromptSubmitted can carry sensitive prompt, args, and cwd data. A useful log row could show hook type, matcher, decision, modified yes/no, duration, error, and redacted input hash. Then users can answer "which hook changed this run?" without dumping prompt or tool payloads into the UI.
For enterprise approval policies, I would also keep the raw permission decision machine-readable: allow, deny, require_approval, modify. Display strings are useful, but typed decisions are what let retry/resume behavior stay predictable.