feat: smart approvals + /stop command (inspired by OpenAI Codex)

* feat: smart approvals — LLM-based risk assessment for dangerous commands

Adds a 'smart' approval mode that uses the auxiliary LLM to assess
whether a flagged command is genuinely dangerous or a false positive,
auto-approving low-risk commands without prompting the user.

Inspired by OpenAI Codex's Smart Approvals guardian subagent
(openai/codex#13860).

Config (config.yaml):
  approvals:
    mode: manual   # manual (default), smart, off

Modes:
- manual — current behavior, always prompt the user
- smart  — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block),
           or ESCALATE (fall through to manual prompt)
- off    — skip all approval prompts (equivalent to --yolo)

When smart mode auto-approves, the pattern gets session-level approval
so subsequent uses of the same pattern don't trigger another LLM call.
When it denies, the command is blocked without user prompt. When
uncertain, it escalates to the normal manual approval flow.

The LLM prompt is carefully scoped: it sees only the command text and
the flagged reason, assesses actual risk vs false positive, and returns
a single-word verdict.

* feat: make smart approval model configurable via config.yaml

Adds auxiliary.approval section to config.yaml with the same
provider/model/base_url/api_key pattern as other aux tasks (vision,
web_extract, compression, etc.).

Config:
  auxiliary:
    approval:
      provider: auto
      model: ''        # fast/cheap model recommended
      base_url: ''
      api_key: ''

Bridged to env vars in both CLI and gateway paths so the aux client
picks them up automatically.

* feat: add /stop command to kill all background processes

Adds a /stop slash command that kills all running background processes
at once. Currently users have to process(list) then process(kill) for
each one individually.

Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current
turn) from /stop (cleans up background processes). See openai/codex#14602.

Ctrl+C continues to only interrupt the active agent turn — background
dev servers, watchers, etc. are preserved. /stop is the explicit way
to clean them all up.
This commit is contained in:
Teknium
2026-03-16 06:20:11 -07:00
committed by GitHub
parent 2633272ea9
commit 57be18c026
6 changed files with 142 additions and 4 deletions

30
cli.py
View File

@@ -395,7 +395,13 @@ def load_cli_config() -> Dict[str, Any]:
"provider": "AUXILIARY_WEB_EXTRACT_PROVIDER",
"model": "AUXILIARY_WEB_EXTRACT_MODEL",
"base_url": "AUXILIARY_WEB_EXTRACT_BASE_URL",
"api_key": "AUXILIARY_WEB_EXTRACT_API_KEY",
"api_key": "AUXILI..._KEY",
},
"approval": {
"provider": "AUXILIARY_APPROVAL_PROVIDER",
"model": "AUXILIARY_APPROVAL_MODEL",
"base_url": "AUXILIARY_APPROVAL_BASE_URL",
"api_key": "AUXILIARY_APPROVAL_API_KEY",
},
}
@@ -1987,6 +1993,26 @@ class HermesCLI:
# Treat as a git hash
return ref
def _handle_stop_command(self):
"""Handle /stop — kill all running background processes.
Inspired by OpenAI Codex's separation of interrupt (stop current turn)
from /stop (clean up background processes). See openai/codex#14602.
"""
from tools.process_registry import get_registry
registry = get_registry()
processes = registry.list_processes()
running = [p for p in processes if p.get("status") == "running"]
if not running:
print(" No running background processes.")
return
print(f" Stopping {len(running)} background process(es)...")
killed = registry.kill_all()
print(f" ✅ Stopped {killed} process(es).")
def _handle_paste_command(self):
"""Handle /paste — explicitly check clipboard for an image.
@@ -3237,6 +3263,8 @@ class HermesCLI:
self._reload_mcp()
elif cmd_lower.startswith("/rollback"):
self._handle_rollback_command(cmd_original)
elif cmd_lower == "/stop":
self._handle_stop_command()
elif cmd_lower.startswith("/background"):
self._handle_background_command(cmd_original)
elif cmd_lower.startswith("/skin"):