Commit Graph

6 Commits

Author SHA1 Message Date
Teknium
735ca9dfb2 refactor: replace swe-rex with native Modal SDK for Modal backend (#3538)
Drop the swe-rex dependency for Modal terminal backend and use the
Modal SDK directly (Sandbox.create + Sandbox.exec). This fixes:

- AsyncUsageWarning from synchronous App.lookup() in async context
- DeprecationError from unencrypted_ports / .url on unencrypted tunnels
  (deprecated 2026-03-05)

The new implementation:
- Uses modal.App.lookup.aio() for async-safe app creation
- Uses Sandbox.create.aio() with 'sleep infinity' entrypoint
- Uses Sandbox.exec.aio() for direct command execution (no HTTP server
  or tunnel needed)
- Keeps all existing features: persistent filesystem snapshots,
  configurable resources (CPU/memory/disk), sudo support, interrupt
  handling, _AsyncWorker for event loop safety

Consistent with the Docker backend precedent (PR #2804) where we
removed mini-swe-agent in favor of direct docker run.

Files changed:
- tools/environments/modal.py - core rewrite
- tools/terminal_tool.py - health check: modal instead of swerex
- hermes_cli/setup.py - install modal instead of swe-rex[modal]
- pyproject.toml - modal extra: modal>=1.0.0 instead of swe-rex[modal]
- scripts/kill_modal.sh - grep for hermes-agent instead of swe-rex
- tests/ - updated for new implementation
- environments/README.md - updated patches section
- website/docs - updated install command
2026-03-28 11:21:44 -07:00
Teknium
ad1bf16f28 chore: remove all remaining mini-swe-agent references
Complete cleanup after dropping the mini-swe-agent submodule (PR #2804):

- Remove MSWEA_SILENT_STARTUP and MSWEA_GLOBAL_CONFIG_DIR env var
  settings from cli.py, run_agent.py, hermes_cli/main.py, doctor.py
- Remove mini-swe-agent health check from hermes doctor
- Remove 'minisweagent' from logger suppression lists
- Remove litellm/typer/platformdirs from requirements.txt
- Remove mini-swe-agent install steps from install.ps1 (Windows)
- Remove mini-swe-agent install steps from website docs
- Update all stale comments/docstrings referencing mini-swe-agent
  in terminal_tool.py, tools/__init__.py, code_execution_tool.py,
  environments/README.md, environments/agent_loop.py
- Remove mini_swe_runner from pyproject.toml py-modules
  (still exists as standalone script for RL training use)
- Shrink test_minisweagent_path.py to empty stub

The orphaned mini-swe-agent/ directory on disk needs manual removal:
  rm -rf mini-swe-agent/
2026-03-24 08:19:23 -07:00
teknium1
55a21fe37b docs: add Environments, Benchmarks & Data Generation guide
Comprehensive developer guide covering:
- Architecture (BaseEnv → HermesAgentBaseEnv → concrete envs)
- All three benchmarks (TerminalBench2, TBLite, YC-Bench)
- Training environments (TerminalTestEnv, HermesSweEnv)
- Core components (AgentLoop, ToolContext, Tool Call Parsers)
- Two-phase operation (Phase 1 OpenAI, Phase 2 VLLM)
- Running environments (evaluate, process, serve modes)
- Creating new environments (training + eval-only)
- Configuration reference and prerequisites

Also updates environments/README.md directory tree to include
TBLite and YC-Bench benchmarks.
2026-03-06 23:31:45 -08:00
teknium1
8481fdcf08 docs: complete Daytona backend documentation coverage
Update all remaining files that enumerate terminal backends to include
Daytona. Covers security docs (bypass info, backend comparison table),
environment variables reference (DAYTONA_API_KEY, TERMINAL_DAYTONA_IMAGE,
container resources header), AGENTS.md (architecture tree, config keys),
environments/README.md, hermes_base_env.py field description, and various
module docstrings.

Follow-up to PR #451 merge.
2026-03-06 03:37:05 -08:00
teknium1
9018e9dd70 refactor: update tool registration and documentation
- Enhanced tool registration process by implementing a self-registering mechanism in each tool file via `tools/registry.py`.
- Updated `model_tools.py` to serve as a thin orchestration layer, simplifying tool discovery and registration.
- Revised documentation to clarify the steps for adding new tools, emphasizing the importance of schema, handler, and registration consistency.
- Improved dependency resolution in environments by ensuring toolsets are queried from `tools/registry.py`.
2026-02-21 21:03:40 -08:00
teknium
35ad3146a8 Add new environments and enhance tool context functionality
- Introduced new environments: Terminal Test Environment and SWE Environment, each with default configurations for testing and software engineering tasks.
- Added TerminalBench 2.0 evaluation environment with comprehensive setup for agentic LLMs, including task execution and verification.
- Enhanced ToolContext with methods for uploading and downloading files, ensuring binary-safe operations.
- Updated documentation across environments to reflect new features and usage instructions.
- Refactored existing environment configurations for consistency and clarity.
2026-02-10 19:39:05 +00:00