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

Major changes across parallel sessions:

- Add orchestrator SFT & GRPO training subpackage (learning/orchestrator/)
  with episode types, multi-objective reward, prompt registry, policy model,
  RL environment, and registered learning policies
- Add structured THOUGHT/TOOL/INPUT/FINAL_ANSWER mode to OrchestratorAgent
- Add 15 channel backends (Discord, Slack, Telegram, Email, Webhook, IRC,
  Matrix, Teams, WhatsApp, Signal, Mattermost, BlueBubbles, Feishu,
  Google Chat, Webchat) with channel tools and config
- Add LiteLLM engine backend for unified LLM provider access
- Add RLM agent and REPL tool
- Remove ToolLearningPolicy — learning taxonomy now only targets
  Intelligence (LM weights/routing) and Agents (logic/ICL/tool strategies)
- Rename SFTPolicy to SFTRouterPolicy (backward-compat alias kept)
- Remove OpenClaw agent infrastructure (openclaw*.py, openclaw_bridge.py)
- Fix async streaming tests (asyncio.run vs deprecated get_event_loop)
- Fix server channel route tests (pytest.importorskip for optional fastapi)
- Track uv.lock for reproducibility
- Update CLAUDE.md and docs to reflect all changes

1676 tests pass, 37 skipped.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jon Saad-Falcon
2026-02-23 18:32:32 +00:00
co-authored by Claude Opus 4.6
parent a0961633a3
commit 8d538cd1b0
105 changed files with 16486 additions and 1858 deletions
+3 -4
View File
@@ -39,8 +39,7 @@ The learning system defines a hierarchy of learning policy ABCs:
- **`LearningPolicy`** -- base ABC for all learning policies
- **`IntelligenceLearningPolicy`** -- specialization for model routing decisions
- **`AgentLearningPolicy`** -- specialization for agent behavior advice
- **`ToolLearningPolicy`** -- specialization for tool selection/configuration
- **`AgentLearningPolicy`** -- specialization for agent behavior advice (ICL examples, tool-use strategies)
---
@@ -59,9 +58,9 @@ The learning system defines a hierarchy of learning policy ABCs:
options:
show_source: true
### SFTPolicy
### SFTRouterPolicy
::: openjarvis.learning.sft_policy.SFTPolicy
::: openjarvis.learning.sft_policy.SFTRouterPolicy
options:
show_source: true
members_order: source