mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-12 13:52:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

fix(profile): gate bg-review memory tool on memory_enabled (#54937 layer 2)

Browse source 
background_review hardcoded enabled_toolsets=["memory", "skills"] in the
review fork's whitelist, so a skill-review fork on a profile with
memory_enabled: false still granted the LLM the built-in MEMORY.md read/write
tool — contaminating a profile that opted out of built-in memory. The flag was
already in scope (review_agent._memory_enabled). Include "memory" only when
_memory_enabled or _user_profile_enabled (USER.md also needs the tool).

Layer 1 of #54937 (the path leak) is fixed by this PR's thread-context
propagation: get_memory_dir() is already per-call on main, so once the
bg-review thread inherits the profile override its writes land in the right
profile (verified). This commit closes the remaining whitelist layer.
This commit is contained in:
Erosika 2026-06-30 21:18:12 +00:00 • committed by Teknium
parent 1f1d346ced
commit 437dcacbbf
2 changed files with 79 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

9
agent/background_review.py
View file

@ -725,10 +725,17 @@ def _run_review_in_thread(
clear_thread_tool_whitelist,
)
# Gate the built-in memory tool on the profile's memory_enabled flag.
# Hardcoding ["memory", "skills"] granted the review LLM the MEMORY.md
# read/write tool even when a profile set memory_enabled: false,
# contaminating a memory-disabled profile (#54937 layer 2).
review_toolsets = ["skills"]
if review_agent._memory_enabled or review_agent._user_profile_enabled:
review_toolsets.insert(0, "memory")
review_whitelist = {
t["function"]["name"]
for t in get_tool_definitions(
enabled_toolsets=["memory", "skills"],
enabled_toolsets=review_toolsets,
quiet_mode=True,
)
}