Add full decision writing pipeline: classify, extract, brainstorm, write, QA, export

New services (11 files):
- classifier.py: auto doc-type classification + party identification (Claude Haiku)
- claims_extractor.py: claim extraction from pleadings (Claude Sonnet + regex)
- references_extractor.py: plan/case-law/legislation detection (regex)
- brainstorm.py: direction generation with 2-3 options (Claude Sonnet)
- block_writer.py: 12-block decision writer (template + Claude Sonnet/Opus)
- docx_exporter.py: DOCX export with David font, RTL, headings
- qa_validator.py: 6 QA checks with export blocking on critical failure
- learning_loop.py: draft vs final comparison + lesson extraction
- metrics.py: KPIs dashboard per case and global
- audit.py: action audit log
- cli.py: standalone CLI with 11 commands

Updated pipeline: extract → classify → chunk → embed → store → extract_references
New MCP tools: 29 total (was 16)
New DB tables: audit_log, decisions CRUD, claims CRUD
Config: Infisical support, external service allowlist

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

mcp-server/src/legal_mcp/models.py

@@ -19,10 +19,16 @@ class CaseStatus(str, enum.Enum):
 
 class DocType(str, enum.Enum):
     APPEAL = "appeal"           # כתב ערר
-    RESPONSE = "response"       # תשובה
-    DECISION = "decision"       # החלטה
-    REFERENCE = "reference"     # מסמך עזר
-    EXHIBIT = "exhibit"         # נספח
+    RESPONSE = "response"       # תשובה / כתב תשובה
+    PROTOCOL = "protocol"       # פרוטוקול דיון
+    PLAN = "plan"               # תכנית (תב"ע)
+    PERMIT = "permit"           # היתר בנייה
+    COURT_DECISION = "court_decision"  # פסק דין / החלטת בית משפט
+    DECISION = "decision"       # החלטת ועדה
+    APPRAISAL = "appraisal"     # שומה / חוות דעת שמאית
+    OBJECTION = "objection"     # התנגדות
+    EXHIBIT = "exhibit"         # נספח / מסמך תומך
+    REFERENCE = "reference"     # מסמך עזר אחר
 
 
 class SectionType(str, enum.Enum):