Skip to content

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust

prompt: remove reference to unshipped async bash() kernel helper (#1508)

Sebastian Mülleraa0bdfa6ad27
diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 3dc4d41ed1..379b4ced95 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -2,6 +2,7 @@
## [Unreleased]
+- Removed a system prompt paragraph referring to an async `bash()` kernel helper and managed jobs that do not exist in the runtime.
- Changed RLM guidance to orchestrate independent workers in parallel, use available async shell helpers safely, end the turn instead of sleeping, polling, or blocking on long awaits, provide proactive outcome-focused progress updates from root agents, and use simplified technical English for user-facing prose.
- Fixed new top-level daemon sessions inheriting an RLM child depth from the supervisor process.
diff --git a/packages/coding-agent/src/core/prompts/rlm.ts b/packages/coding-agent/src/core/prompts/rlm.ts
index 3bab46027d..4841138866 100644
--- a/packages/coding-agent/src/core/prompts/rlm.ts
+++ b/packages/coding-agent/src/core/prompts/rlm.ts
@@ -34,8 +34,6 @@ const IPYTHON_CONTROL_PROMPT = [
"",
"When running shell commands from IPython, use `%%bash` cells. If you use `%%bash`, it must be the first line of the code cell: no comments, spaces, blank lines, imports, or Python statements before it. Avoid `!cmd` shell escapes for project commands so shell behavior is explicit and multi-line commands share one shell context.",
"",
- "If the runtime provides a documented async `bash()` helper, use `await bash(...)` only for short, bounded work that completes in the current turn; do not wrap it in `asyncio.create_task`. For background work, or work that must survive a kernel restart, session rotation, or teardown, use a managed job with a durable receipt instead.",
- "",
"Important: do not install dependencies into the IPython kernel just to make an external project import or run there. If a project import, test, script, CLI, or dependency check is needed, run it through that project's own environment and normal command interface. For example, in a Python repo use its documented commands, `uv run ...`, `.venv/bin/python ...`, or the active project interpreter from the repo root. Treat failures from that native environment as the relevant result.",
"",
"Use Python for reading, searching, and editing files — it gives you reusable variables you can slice, filter, and act on without re-reading. Always assign read/search results to named variables so you can revisit them later.",