From 5a98ce59735ec4b06204157e39b01634236ee9fb Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Fri, 3 Apr 2026 20:43:01 -0700
Subject: [PATCH] fix: use clean user message for all memory provider
 operations (#4940)

When a skill is active, user_message contains the full SKILL.md content
injected by the skill system. This bloated string was being passed to
memory provider sync_all(), queue_prefetch_all(), and prefetch_all(),
causing providers with query size limits (e.g. Honcho's 10K char limit)
to fail.

Both call sites now use original_user_message (the clean user input,
already defined at line 6516) instead of the skill-inflated user_message:

- Pre-turn prefetch (line ~6695): prefetch_all() query
- Post-turn sync (line ~8672): sync_all() + queue_prefetch_all()

Fixes #4889
---
 run_agent.py | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/run_agent.py b/run_agent.py
index a2330f525..97f95d273 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -6689,10 +6689,12 @@ class AIAgent:
         # External memory provider: prefetch once before the tool loop.
         # Reuse the cached result on every iteration to avoid re-calling
         # prefetch_all() on each tool call (10 tool calls = 10x latency + cost).
+        # Use original_user_message (clean input) — user_message may contain
+        # injected skill content that bloats / breaks provider queries.
         _ext_prefetch_cache = ""
         if self._memory_manager:
             try:
-                _query = user_message if isinstance(user_message, str) else ""
+                _query = original_user_message if isinstance(original_user_message, str) else ""
                 _ext_prefetch_cache = self._memory_manager.prefetch_all(_query) or ""
             except Exception:
                 pass
@@ -8666,11 +8668,13 @@ class AIAgent:
             _should_review_skills = True
             self._iters_since_skill = 0
 
-        # External memory provider: sync the completed turn + queue next prefetch
-        if self._memory_manager and final_response and user_message:
+        # External memory provider: sync the completed turn + queue next prefetch.
+        # Use original_user_message (clean input) — user_message may contain
+        # injected skill content that bloats / breaks provider queries.
+        if self._memory_manager and final_response and original_user_message:
             try:
-                self._memory_manager.sync_all(user_message, final_response)
-                self._memory_manager.queue_prefetch_all(user_message)
+                self._memory_manager.sync_all(original_user_message, final_response)
+                self._memory_manager.queue_prefetch_all(original_user_message)
             except Exception:
                 pass