Skip to content

Agent Zero AI framework

Forward remote exec reset flag

Alessandrob48e31bead54
diff --git a/plugins/_a0_connector/prompts/agent.system.tool.code_execution_remote.md b/plugins/_a0_connector/prompts/agent.system.tool.code_execution_remote.md
index b8e7010c6..094d105ed 100644
--- a/plugins/_a0_connector/prompts/agent.system.tool.code_execution_remote.md
+++ b/plugins/_a0_connector/prompts/agent.system.tool.code_execution_remote.md
@@ -21,6 +21,8 @@ and retry.
## Arguments
- `runtime`: one of `terminal`, `python`, `nodejs`, `output`, `reset`
- `session`: integer session id (default `0`)
+- `reset`: optional boolean for `terminal`, `python`, or `nodejs`; when true,
+ the CLI resets the session before running the supplied code
Runtime-specific fields:
- `terminal`, `python`, `nodejs`: require `code`
@@ -28,7 +30,9 @@ Runtime-specific fields:
## Notes
- Reuse `session` when continuing a workflow.
-- Use `output` to poll a running session and `reset` for a stuck session.
+- Use `output` to poll a running session and `runtime=reset` for a stuck session.
+ Use `reset: true` on a new command when you need a clean session and want to
+ run the replacement command immediately.
- Paths and shell syntax are evaluated on the CLI host, not inside Agent Zero.
- When the user gives a relative path like `tmp/file.txt`, keep it relative to
the CLI host terminal. Do not prepend or `cd` to `/a0/usr/workdir`; that is the
diff --git a/plugins/_a0_connector/skills/host-code-execution/SKILL.md b/plugins/_a0_connector/skills/host-code-execution/SKILL.md
index 76938e8a3..448f63ba8 100644
--- a/plugins/_a0_connector/skills/host-code-execution/SKILL.md
+++ b/plugins/_a0_connector/skills/host-code-execution/SKILL.md
@@ -24,7 +24,8 @@ Browser boundary: do not use shell launchers such as `xdg-open`, `sensible-brows
- Use `runtime=terminal` for shell commands, `runtime=python` for Python snippets, and `runtime=nodejs` for Node.js snippets.
- Reuse the same integer `session` while continuing a workflow; session state is local to the CLI frontend.
- Use `runtime=output` when a previous command is still running or returned before the shell reached a prompt.
-- Use `runtime=reset` when a session is stuck or a clean shell is safer.
+- Use `runtime=reset` when a session is stuck and no replacement command needs to run yet.
+- Use `reset: true` with `runtime=terminal`, `python`, or `nodejs` when a session is stuck and the next command should run immediately in a clean shell.
- Match the remote host shell syntax. A Windows CLI may need PowerShell syntax even when Agent Zero runs on Linux.
## Failure Handling
diff --git a/plugins/_a0_connector/tools/code_execution_remote.py b/plugins/_a0_connector/tools/code_execution_remote.py
index 248b62e5c..45d68a3e4 100644
--- a/plugins/_a0_connector/tools/code_execution_remote.py
+++ b/plugins/_a0_connector/tools/code_execution_remote.py
@@ -30,6 +30,16 @@ class CodeExecutionRemote(Tool):
def _runtime_requires_write_access(runtime: str) -> bool:
return runtime in {"terminal", "python", "nodejs", "input"}
+ @staticmethod
+ def _coerce_bool(value: Any) -> bool:
+ if isinstance(value, bool):
+ return value
+ if isinstance(value, (int, float)):
+ return bool(value)
+ if isinstance(value, str):
+ return value.strip().lower() in {"1", "true", "yes", "on"}
+ return False
+
def get_log_object(self):
import uuid
@@ -118,6 +128,8 @@ class CodeExecutionRemote(Tool):
"session": session,
"context_id": context_id,
}
+ if runtime != "reset" and self._coerce_bool(self.args.get("reset")):
+ payload["reset"] = True
if runtime in {"terminal", "python", "nodejs"}:
code = self.args.get("code")