Changelog

Task #3 had a recurrence.pattern JSON object without a "type" field,

causing NotSupportedException with [JsonPolymorphic]. Replaced the

attribute-based approach with a custom RecurrencePatternConverter that

handles missing/unknown discriminators gracefully (defaults to daily).

This matches the pattern already used by RecurrenceEnd and is resilient

to data written by older versions or external sync sources.

Also added RustWeekdayConverter.TryParse for use by the converter.

Add right-click context menus to task items across all views (List,

Kanban, GTD Timeline, Calendar Timeline) with: Edit, Start Work, Mark

Complete/Reopen, Start/Stop Timer, Duplicate, Archive, Delete. Updated

the "..." button flyout to include the same expanded set of actions.

Added DuplicateTaskByItem and StartTaskByItem commands that accept a

TaskItem parameter for use from context menu bindings (the existing

DuplicateTask/StartTask operate on SelectedTask only).

Added StatusMessage feedback to AI Title and AI Rewrite commands so

failures are surfaced to the user instead of failing silently.

Cloud models use the user's own API key — they should speak freely.

The tier-based token ceilings (1024/4096/8192) and sentence-count

truncation were designed for local models that can't self-regulate.

Changes:

• CloudMaxTokensFor now returns a flat 16384 regardless of tier
• Sanitize() accepts isCloud flag: skips sentence truncation and

markdown stripping for cloud responses

• Local model path unchanged (still gets tight limits + cleanup)

Gemini 2.5 Pro tends to be verbose in its JSON responses, causing

truncation at 256 tokens which breaks JSON parsing. 512 gives enough

headroom for the memory extraction response without significant cost.

The note entity JSON nests blocks at content.content (PageDocument has

{ "type": "doc", "content": [...blocks...] }), not at content directly.

The previous fix checked content.ValueKind == Array which was Object

(the PageDocument), so it fell through to the else branch and returned

without finding any dataset references.

Now drills content → content.content to find the block array.