feat: integrate llm-connect FR-1/FR-3/FR-4 into IHF bridge

FR-3 (async_execute_prompt): CollectiveProposals now invokes all agents
concurrently via callAgentsBatch → single bridge subprocess with
asyncio.gather. Latency scales with slowest agent, not sum.

FR-4 (BudgetTracker): AgentDelegations passes tokenBudget to bridge;
llm-connect enforces it natively via BudgetTracker in RunConfig.
BudgetExceededError is a first-class BridgeError variant with total/
consumed/requested fields surfaced to the operator.

FR-1 (LLMServer passthrough): bridge accepts optional serverUrl field;
if present, calls POST {serverUrl}/execute instead of spawning a new
adapter. Infrastructure ready for hot-agent pre-warming (no schema
change required).

AgentBridge.hs: adds callAgentsBatch, callAgentWithBudget,
BudgetExceededError constructor, bridgeErrorMessage helper, defaultRequest,
requestToJson. All controllers updated to use bridgeErrorMessage.

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

Web/Controller/AgentDelegations.hs

@@ -1,11 +1,16 @@
 module Web.Controller.AgentDelegations where
 
 -- IHF Phase 11 — Advanced AI Federation (IHUB-WP-0012 T06)
+-- Updated: delegation token budget enforced natively by llm-connect BudgetTracker (FR-4).
 
 import Web.Controller.Prelude
 import Web.View.AgentDelegations.Index
 import Web.View.AgentDelegations.Show
-import Application.Helper.AgentBridge (callBridge, BridgeRequest(..))
+import Application.Helper.AgentBridge
+    ( callAgentWithBudget
+    , BridgeError(..)
+    , bridgeErrorMessage
+    )
 
 instance Controller AgentDelegationsController where
 
@@ -44,24 +49,32 @@ instance Controller AgentDelegationsController where
             |> set #status "pending"
             |> createRecord
 
-        result <- liftIO $ callBridge BridgeRequest
-            { provider     = receivingAgent.provider
-            , model        = receivingAgent.modelName
-            , systemPrompt = receivingAgent.systemPrompt
-            , prompt       = scope
-            , maxTokens    = tokenBudget
-            , temperature  = 0.7
-            }
+        -- FR-4: token budget passed to bridge → llm-connect BudgetTracker enforces it
+        -- natively, raising LLMBudgetExceededError if the call would exceed the cap.
+        result <- liftIO $ callAgentWithBudget receivingAgent scope tokenBudget 0
 
         now <- getCurrentTime
         case result of
+            Left BudgetExceededError { errorMessage, budgetTotal, budgetConsumed, budgetRequested } -> do
+                delegation
+                    |> set #status "failed"
+                    |> set #result (Just . A.toJSON $ A.object
+                        [ "error"            A..= errorMessage
+                        , "budgetTotal"      A..= budgetTotal
+                        , "budgetConsumed"   A..= budgetConsumed
+                        , "budgetRequested"  A..= budgetRequested
+                        ])
+                    |> set #completedAt (Just now)
+                    |> updateRecord
+                setErrorMessage ("Budget exceeded: requested " <> show budgetRequested
+                    <> " tokens but only " <> show (budgetTotal - budgetConsumed) <> " remain")
             Left err -> do
                 delegation
                     |> set #status "failed"
-                    |> set #result (Just . A.toJSON $ A.object ["error" A..= err.errorMessage])
+                    |> set #result (Just . A.toJSON $ A.object ["error" A..= bridgeErrorMessage err])
                     |> set #completedAt (Just now)
                     |> updateRecord
-                setErrorMessage ("Delegation failed: " <> err.errorMessage)
+                setErrorMessage ("Delegation failed: " <> bridgeErrorMessage err)
             Right resp -> do
                 delegation
                     |> set #status "completed"