feat(agent-loop): run safe tool calls in parallel

docs/architecture.md

@@ -81,11 +81,13 @@ forever:
         'assistant/chunk'
       agent/step-result
       'assistant/message'
-      each tool call:
-        'tool/call'
-        tools/pre-execute -> tools/execute -> tools/post-execute
-        'tool/result'
-      append post-tool context and steering
+      schedule tool calls by ctx.tools.executionMode (exclusive = barrier;
+        consecutive parallel-safe = one rolling-pool group, <= maxParallelToolCalls in flight):
+        each started call:
+          'tool/call'
+          tools/pre-execute -> tools/execute -> tools/post-execute
+        'tool/result' committed in model order (slot-buffered)
+      append post-tool context (model order) and steering
       'step/end'
       agent/turn-continuation
       stop unless tools or continuation policy ask for another step
@@ -97,6 +99,8 @@ Prompt assembly is single-path: `renderPrompt(assemble({ agent }))` IS the syste
 
 Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; leftover steering after a turn is re-queued as ordinary input.
 
+Tool-call scheduling groups exclusive barriers and bounded parallel-safe runs while preserving ordered results ([the parallel tool-call RFC](rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)).
+
 ### Failure Boundaries
 
 The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain.