mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-09 08:21:50 +00:00
feat(execute_code): add project/strict execution modes, default to project (#11971)
Weaker models (Gemma-class) repeatedly rediscover and forget that
execute_code uses a different CWD and Python interpreter than terminal(),
causing them to flip-flop on whether user files exist and to hit import
errors on project dependencies like pandas.
Adds a new 'code_execution.mode' config key (default 'project') that
brings execute_code into line with terminal()'s filesystem/interpreter:
project (new default):
- cwd = session's TERMINAL_CWD (falls back to os.getcwd())
- python = active VIRTUAL_ENV/bin/python or CONDA_PREFIX/bin/python
with a Python 3.8+ version check; falls back cleanly to
sys.executable if no venv or the candidate fails
- result : 'import pandas' works, '.env' resolves, matches terminal()
strict (opt-in):
- cwd = staging tmpdir (today's behavior)
- python = sys.executable (today's behavior)
- result : maximum reproducibility and isolation; project deps
won't resolve
Security-critical invariants are identical across both modes and covered by
explicit regression tests:
- env scrubbing (strips *_API_KEY, *_TOKEN, *_SECRET, *_PASSWORD,
*_CREDENTIAL, *_PASSWD, *_AUTH substrings)
- SANDBOX_ALLOWED_TOOLS whitelist (no execute_code recursion, no
delegate_task, no MCP from inside scripts)
- resource caps (5-min timeout, 50KB stdout, 50 tool calls)
Deliberately avoids 'sandbox'/'isolated'/'cloud' language in tool
descriptions (regression from commit 39b83f34 where agents on local
backends falsely believed they were sandboxed and refused networking).
Override via env var: HERMES_EXECUTE_CODE_MODE=strict|project
This commit is contained in:
parent
54e0eb24c0
commit
285bb2b915
5 changed files with 643 additions and 14 deletions
|
|
@ -771,6 +771,20 @@ DEFAULT_CONFIG = {
|
|||
"wrap_response": True,
|
||||
},
|
||||
|
||||
# execute_code settings — controls the tool used for programmatic tool calls.
|
||||
"code_execution": {
|
||||
# Execution mode:
|
||||
# project (default) — scripts run in the session's working directory
|
||||
# with the active virtualenv/conda env's python, so project deps
|
||||
# (pandas, torch, project packages) and relative paths resolve.
|
||||
# strict — scripts run in an isolated temp directory with
|
||||
# hermes-agent's own python (sys.executable). Maximum isolation
|
||||
# and reproducibility; project deps and relative paths won't work.
|
||||
# Env scrubbing (strips *_API_KEY, *_TOKEN, *_SECRET, ...) and the
|
||||
# tool whitelist apply identically in both modes.
|
||||
"mode": "project",
|
||||
},
|
||||
|
||||
# Logging — controls file logging to ~/.hermes/logs/.
|
||||
# agent.log captures INFO+ (all agent activity); errors.log captures WARNING+.
|
||||
"logging": {
|
||||
|
|
@ -788,7 +802,7 @@ DEFAULT_CONFIG = {
|
|||
},
|
||||
|
||||
# Config schema version - bump this when adding new required fields
|
||||
"_config_version": 18,
|
||||
"_config_version": 19,
|
||||
}
|
||||
|
||||
# =============================================================================
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue