Note editor sidebar, full-doc assist, persistent drafts, version history

NoteEditorView: two-column sidebar layout (project/milestone/tags/assist
always visible), removed assist toggle button, InlineAssistPanel removed.

Writing assist: whole_doc mode rewrites entire document; DiffView.vue
replaces editor during review showing full-document diff. Scope dropdown
in sidebar switches between whole-document and section modes.

Persistent drafts: migration 0022 adds note_drafts (UNIQUE per note+user)
and note_versions (max 20, auto-pruned) tables. Draft saved after generation
completes, restored on editor mount, cleared on accept/reject. Version
snapshot created automatically whenever note body changes on save.

HistoryPanel.vue: version list + DiffView modal, restore button writes
body back to editor.

Config: OLLAMA_NUM_CTX default raised to 65536; assist num_predict now
tracks Config.OLLAMA_NUM_CTX instead of a hardcoded 4096.

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

src/fabledassistant/config.py

@@ -24,8 +24,9 @@ class Config:
     )
     OLLAMA_URL: str = os.environ.get("OLLAMA_URL", "http://localhost:11434")
     OLLAMA_MODEL: str = os.environ.get("OLLAMA_MODEL", "qwen3:latest")
-    # KV cache context window for generation. Lower = less VRAM, less throughput impact.
-    OLLAMA_NUM_CTX: int = int(os.environ.get("OLLAMA_NUM_CTX", "16384"))
+    # KV cache context window for generation. Higher = more RAM usage but longer inputs/outputs.
+    # 131072 is the practical maximum for most models. Lower this on RAM-constrained hosts.
+    OLLAMA_NUM_CTX: int = int(os.environ.get("OLLAMA_NUM_CTX", "65536"))
     SECRET_KEY: str = _read_secret("SECRET_KEY", "SECRET_KEY_FILE", "dev-secret-change-me")
     SECURE_COOKIES: bool = os.environ.get("SECURE_COOKIES", "").lower() in ("1", "true", "yes")
     LOG_LEVEL: str = os.environ.get("LOG_LEVEL", "INFO")