refactor: consolidate LLM JSON parsing into shared llm_utils module

Extracted duplicate _strip_markdown_fences / _parse_llm_json functions
from 7 files into app/services/llm_utils.py. Two shared functions:
- strip_markdown_fences(): fence stripping only
- parse_llm_json(): fence stripping + JSON parse + error logging

Files updated: flowpilot_engine, knowledge_flywheel, session_to_flow_service,
ai_tree_generator_service, ai_fix_service, ai_chat_service, kb_conversion_service

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

backend/app/core/kb_conversion_service.py

@@ -24,13 +24,7 @@ COST_PER_INPUT_TOKEN = 3.0 / 1_000_000
 COST_PER_OUTPUT_TOKEN = 15.0 / 1_000_000
 
 
-def _strip_markdown_fences(text: str) -> str:
-    """Strip markdown code fences if the model wrapped its JSON response."""
-    text = text.strip()
-    match = re.match(r"^```(?:json)?\s*([\s\S]*?)```$", text)
-    if match:
-        return match.group(1).strip()
-    return text
+from app.services.llm_utils import strip_markdown_fences as _strip_markdown_fences
 
 
 def _try_repair_json(text: str) -> dict | None: