Jon Saad-FalconandClaude Opus 4.6 62f2ea2252 fix: fix loop_guard role comparison for Python 3.10 compatibility ...

str(Role.SYSTEM) returns 'Role.SYSTEM' on Python 3.10, not 'system'.
Use getattr(m, 'role', None) == 'system' which works because Role
inherits from str. Also wires compress_context into operative agent.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-05 05:38:27 +00:00

..

__init__.py

Implement OpenJarvis v1.0 — all five pillars, SDK, benchmarks, Docker

2026-02-17 00:52:48 +00:00

test_agent_routing_matrix.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_backward_compat.py

Refactor agent hierarchy: extract BaseAgent/ToolUsingAgent helpers, add native ReAct/OpenHands

2026-02-24 03:59:24 +00:00

test_base_agent.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_claude_code.py

Add desktop distribution pipeline: rolling releases, auto-updates, code signing

2026-02-27 19:14:05 +00:00

test_continuation.py

Add desktop distribution pipeline: rolling releases, auto-updates, code signing

2026-02-27 19:14:05 +00:00

test_loop_guard.py

fix: fix loop_guard role comparison for Python 3.10 compatibility

2026-03-05 05:38:27 +00:00

test_native_openhands.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_native_react.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_openhands.py

Refactor agent hierarchy: extract BaseAgent/ToolUsingAgent helpers, add native ReAct/OpenHands

2026-02-24 03:59:24 +00:00

test_orchestrator.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_react.py

Enrich agent tool awareness, normalize engine tool_calls, add telemetry and eval config

2026-02-25 01:58:18 +00:00

test_rlm_repl.py

Add orchestrator training, channels, LiteLLM engine, and simplify learning taxonomy

2026-02-23 18:32:32 +00:00

test_rlm.py

fix: codebase cleanup — bug fixes, test hardening, and lint

2026-03-05 05:29:42 +00:00

test_simple.py

Restructure codebase into 5-pillar architecture with MCP tool management, composition layer, and structured learning

2026-02-22 05:57:13 +00:00