Task work log, inline writing assistant, task editor sidebar layout

Backend:
- Migration 0021: task_logs table (FK → notes + users, CASCADE, indexed)
- models/task_log.py: SQLAlchemy model with to_dict()
- services/task_logs.py: CRUD with ownership checks, _UNSET sentinel for optional duration clear
- routes/task_logs.py: GET/POST/PATCH/DELETE /api/tasks/<id>/logs
- services/tools.py: log_work LLM tool (resolves task by title, creates log entry)
- services/generation_task.py: retry assist generation up to 3× on HTTP 500

Frontend:
- types/task.ts: TaskLog interface
- TaskLogSection.vue: chronological work log with date+time timestamps, duration badge, inline edit, autofocus
- InlineAssistPanel.vue: streaming preview + diff review rendered inline in editor column
- useAssist.ts: removed chatStore.chatReady gate; toast notifications for errors
- NoteEditorView.vue + TaskEditorView.vue: inline assist panel, aside restricted to idle state
- TaskEditorView.vue: two-column layout (editor+log left, metadata sidebar right), body defaults to Preview, sidebarOpen accordion for mobile
- editor-shared.css: .assist-active-hint style

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

src/fabledassistant/services/generation_task.py

@@ -409,18 +409,40 @@ async def run_assist_generation(
     messages: list[dict],
     model: str,
 ) -> None:
-    """Stream LLM response for assist into buffer. No DB persistence."""
-    try:
-        async for chunk in stream_chat(messages, model, options={"num_predict": 4096}):
-            buf.content_so_far += chunk
-            buf.append_event("chunk", {"chunk": chunk})
+    """Stream LLM response for assist into buffer. No DB persistence.
 
-        buf.state = GenerationState.COMPLETED
-        buf.finished_at = time.monotonic()
-        buf.append_event("done", {"done": True, "full_text": buf.content_so_far})
+    Retries up to 3 times on Ollama 500 errors (model still loading).
+    On each retry the accumulated content is reset so the done event
+    always reflects only the successful generation.
+    """
+    last_exc: BaseException | None = None
+    for attempt in range(3):
+        if attempt > 0:
+            delay = 3.0 * attempt
+            logger.warning(
+                "Ollama assist stream 500 (attempt %d/3), retrying in %.0fs", attempt, delay
+            )
+            await asyncio.sleep(delay)
+        try:
+            buf.content_so_far = ""
+            async for chunk in stream_chat(messages, model, options={"num_predict": 4096}):
+                buf.content_so_far += chunk
+                buf.append_event("chunk", {"chunk": chunk})
 
-    except Exception as e:
-        logger.exception("Error in assist generation task")
-        buf.state = GenerationState.ERRORED
-        buf.finished_at = time.monotonic()
-        buf.append_event("error", {"error": str(e)})
+            buf.state = GenerationState.COMPLETED
+            buf.finished_at = time.monotonic()
+            buf.append_event("done", {"done": True, "full_text": buf.content_so_far})
+            return
+
+        except httpx.HTTPStatusError as exc:
+            last_exc = exc
+            if exc.response.status_code != 500:
+                break
+        except Exception as exc:
+            last_exc = exc
+            break
+
+    logger.exception("Error in assist generation task")
+    buf.state = GenerationState.ERRORED
+    buf.finished_at = time.monotonic()
+    buf.append_event("error", {"error": str(last_exc)})