feat(batch-agent): add Langfuse prompt management

- _get_system_prompt helper: fetches managed prompts from Langfuse
  with hardcoded fallback (same pattern as chat service)
- journey.py: journey_system prompt manageable via Langfuse
- agent_runner.py: batch_file_classifier, batch_processing,
  batch_cloud_processing prompts all manageable via Langfuse
- redis_consumer.py: link_prompt_to_trace for all three handlers

services/batch-agent/app/agent_runner.py

@@ -28,6 +28,7 @@ from app.agents.task_agent import TASK_TOOLS
 from app.agents.timeline_agent import TIMELINE_TOOLS
 from app.llm import get_llm
 from app.ws_context import execute_on_client, set_current_user, clear_current_user
+import app.tracing as tracing
 from shared.db import async_session
 from shared.models import AgentRunLog, CloudAgentConfig, LocalAgentConfig
 from shared.redis import redis_client, ws_out_channel
@@ -166,6 +167,12 @@ and what you created.
 """
 
 
+def _get_system_prompt(langfuse_name: str, fallback: str) -> str:
+    """Fetch a managed prompt from Langfuse, falling back to the hardcoded string."""
+    managed = tracing.get_prompt(langfuse_name, fallback=None)
+    return managed if managed is not None else fallback
+
+
 # ── LLM tool-calling loop ─────────────────────────────────────────────────
 
 
@@ -420,7 +427,7 @@ async def _classify_file(
         if d in _DOMAIN_DESCRIPTIONS
     )
 
-    system = _STEP1_SYSTEM_PROMPT.format(
+    system = _get_system_prompt("batch_file_classifier", _STEP1_SYSTEM_PROMPT).format(
         domain_definitions=domain_definitions,
         projects_list=projects_list,
     )
@@ -597,7 +604,9 @@ async def run_local_agent(user_id: str, trigger_data: dict[str, Any], *, langfus
 
                 existing_context = "\n\n".join(existing_blocks)
 
-                system_prompt = _PROCESSING_SYSTEM_PROMPT.format(
+                system_prompt = _get_system_prompt(
+                    "batch_processing", _PROCESSING_SYSTEM_PROMPT
+                ).format(
                     existing_context=existing_context,
                     project_context=project_context,
                     data_types=", ".join(domains),
@@ -781,7 +790,9 @@ async def run_cloud_agent(user_id: str, config_id: str, *, langfuse_handler: Any
                 continue
             items_processed += 1
 
-            processing_prompt = _CLOUD_PROCESSING_PROMPT.format(
+            processing_prompt = _get_system_prompt(
+                "batch_cloud_processing", _CLOUD_PROCESSING_PROMPT
+            ).format(
                 data_types=", ".join(config.data_types),
                 project_context="Determine the appropriate project from the message context.",
                 file_list=f"Message from {config.provider} (id: {msg.id})",