t-247: Add Provider abstraction for multi-backend LLM support

- Create Omni/Agent/Provider.hs with unified Provider interface
- Support OpenRouter (cloud), Ollama (local), Amp (subprocess stub)
- Add runAgentWithProvider to Engine.hs for Provider-based execution
- Add EngineType to Core.hs (EngineOpenRouter, EngineOllama, EngineAmp)
- Add --engine flag to 'jr work' command
- Worker.hs dispatches to appropriate provider based on engine type

Usage:
  jr work <task-id>                    # OpenRouter (default)
  jr work <task-id> --engine=ollama    # Local Ollama
  jr work <task-id> --engine=amp       # Amp CLI (stub)

1 files changed, 13 insertions, 1 deletions

diff --git a/Omni/Agent/Core.hs b/Omni/Agent/Core.hs
index 88f7237..fb4a4b3 100644
--- a/Omni/Agent/Core.hs
+++ b/Omni/Agent/Core.hs
@@ -6,6 +6,17 @@ module Omni.Agent.Core where
 import Alpha
 import Data.Aeson (FromJSON, ToJSON)
 
+-- | Engine/provider selection for agent
+data EngineType
+  = EngineOpenRouter
+  | EngineOllama
+  | EngineAmp
+  deriving (Show, Eq, Generic)
+
+instance ToJSON EngineType
+
+instance FromJSON EngineType
+
 -- | Status of a worker agent
 data WorkerStatus
   = Idle
@@ -28,7 +39,8 @@ data Worker = Worker
     workerPid :: Maybe Int,
     workerStatus :: WorkerStatus,
     workerPath :: FilePath,
-    workerQuiet :: Bool -- Disable ANSI status bar (for loop mode)
+    workerQuiet :: Bool, -- Disable ANSI status bar (for loop mode)
+    workerEngine :: EngineType -- Which LLM backend to use
   }
   deriving (Show, Eq, Generic)