Token tracking y cálculo de costes por mensaje

- Config: COST_PER_1M_INPUT y COST_PER_1M_OUTPUT configurables via .env
- OpenAI adapter: stream_options include_usage para capturar tokens reales
- base.py: acumula input/output tokens de cada iteración del agente
- planner.py: devuelve usage junto con el plan
- engine.py: suma tokens de planner + steps + review, calcula coste USD
- Response incluye usage{input_tokens, output_tokens} y total_cost_usd

Formato compatible con el bridge de Claude Code CLI para integración
con el frontend y reporting a Acai webservice.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/orchestrator/agents/base.py

@@ -59,6 +59,8 @@ class BaseAgent:
         )
         tool_executions: list[ToolExecution] = []
         accumulated_content = ""
+        total_input_tokens = 0
+        total_output_tokens = 0
         # Real conversation history: assistant messages + tool results
         conversation: list[dict[str, Any]] = []
         tool_fingerprints: dict[str, ToolExecution] = {}
@@ -139,6 +141,11 @@ class BaseAgent:
                     tool["parsed_arguments"] = args
                     tool_calls.append(tool)
 
+                # Accumulate token usage from any chunk that has it
+                if chunk.usage:
+                    total_input_tokens += chunk.usage.get("input_tokens", 0)
+                    total_output_tokens += chunk.usage.get("output_tokens", 0)
+
                 if chunk.finish_reason == "end_turn":
                     break
 
@@ -234,6 +241,10 @@ class BaseAgent:
             "content": accumulated_content,
             "artifacts": artifacts,
             "tool_executions": tool_executions,
+            "usage": {
+                "input_tokens": total_input_tokens,
+                "output_tokens": total_output_tokens,
+            },
         }
 
     async def _execute_tool(