Files
AutoGPT/autogpt_platform/backend
Bently 67405f7eb9 fix(copilot): ensure tool_call/tool_response pairs stay intact during context compaction (#11863)
## Summary

Fixes context compaction breaking tool_call/tool_response pairs, causing
API validation errors.

## Problem

When context compaction slices messages with `messages[-KEEP_RECENT:]`,
a naive slice can separate an assistant message containing `tool_calls`
from its corresponding tool response messages. This causes API
validation errors like:

```
messages.0.content.1: unexpected 'tool_use_id' found in 'tool_result' blocks: orphan_12345.
Each 'tool_result' block must have a corresponding 'tool_use' block in the previous message.
```

## Solution

Added `_ensure_tool_pairs_intact()` helper function that:
1. Detects orphan tool responses in a slice (tool messages whose
`tool_call_id` has no matching assistant message)
2. Extends the slice backwards to include the missing assistant messages
3. Falls back to removing orphan tool responses if the assistant cannot
be found (edge case)

Applied this safeguard to:
- The initial `KEEP_RECENT` slice (line ~990)
- The progressive fallback slices when still over token limit (line
~1079)

## Testing

- Syntax validated with `python -m py_compile`
- Logic reviewed for correctness

## Linear

Fixes SECRT-1839

---
*Debugged by Toran & Orion in #agpt Discord*
2026-01-28 00:21:54 +00:00
..