Skip to content

RLM: make bash REPL default, keep Python REPL optional #758

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
snimu merged 9 commits into from
Jan 21, 2026
Merged

RLM: make bash REPL default, keep Python REPL optional #758

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
b8aa5e8
Add bash REPL mode (incomplete answer parsing)
snimu Jan 21, 2026
1d462dd
Fix bash REPL parsing and python venv typing
snimu Jan 21, 2026
9791796
Document bash default and remove spec
snimu Jan 21, 2026
df3f847
Add --json support for bash root tools
snimu Jan 21, 2026
31134aa
Use dedicated executor for RLM FIFO IO
snimu Jan 21, 2026
5b9100a
Improve bash llm_batch output formatting
snimu Jan 21, 2026
9f35f69
Unblock FIFO read on code timeout
snimu Jan 21, 2026
a587e98
Cleanup bash worker template quoting
snimu Jan 21, 2026
b22e91f
Add context limit warning to bash REPL
snimu Jan 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/environments.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -760,4 +760,4 @@ Newer and more experimental environment classes include:
- **`GymEnv`** — universal runner for Gym-compatible environments (OpenAI Gym / Gymnasium API)
- **`CliAgentEnv`** — runs custom agent code inside sandboxes, intercepting API requests
- **`HarborEnv`** — loads Harbor-format agent benchmark tasks
- **`RLMEnv`** — implements Recursive Language Models for unbounded context processing. Execution is local-only and uses a filesystem-based context: a provided `context_dir` is copied into the working directory, or legacy JSON-serializable `context` data is written to `context.json`/`context.txt`. User code runs in a Python REPL with a best-effort filesystem jail that restricts access to the working directory; customize additional guardrails via `disallowed_modules`/`disallowed_builtins`. Tooling can be split via `tools` (shared), `root_tools` (REPL-only), and `sub_tools` (sub-LLM tools). Fixed root tools like `llm_batch` are always present and cannot be overridden. Tool ordering is fixed tools → shared tools → role-specific tools, with per-list deduplication by name. Root tools are callable only inside the REPL; sub-LLM tools use standard tool-calling.
- **`RLMEnv`** — implements Recursive Language Models for unbounded context processing. Execution is local-only and uses a filesystem-based context: a provided `context_dir` is copied into the working directory, or legacy JSON-serializable `context` data is written to `context.json`/`context.txt`. The REPL language is configurable via `repl_language` (default: `bash`); use `repl_language="python"` to retain the Python REPL. Bash mode uses `call_bash_repl` and behaves like a terminal; Python mode uses `call_python_repl` with the best-effort filesystem jail that restricts access to the working directory. Customize additional guardrails via `disallowed_modules`/`disallowed_builtins`. Tooling can be split via `tools` (shared), `root_tools` (REPL-only), and `sub_tools` (sub-LLM tools). Fixed root tools like `llm_batch` are always present and cannot be overridden. Tool ordering is fixed tools → shared tools → role-specific tools, with per-list deduplication by name. Root tools are callable only inside the REPL; sub-LLM tools use standard tool-calling.
Loading
Loading