v2.2.0

podcli v2.2.0

Highlights

• Horizontal (16:9) and square (1:1) clips alongside vertical 9:16, with per-format captions that scale to the canvas instead of floating mid-frame. Set the format in the studio (New episode → Settings → Format), via the create_clip / batch_create_clips MCP tools, or with podcli process --format. Defaults to vertical, so existing behavior is unchanged. (#37)
• Content studio — free-form "ask for anything" generation (LinkedIn post, thread, extra hooks, …) plus per-section Regenerate for titles, description, tags, and hashtags with optional guidance, and a live thumbnail preview. (#37)
• YouTube / direct-URL import — paste a link into the studio's video field to download it via yt-dlp and continue straight into the preview/transcription workflow. (#40)
• Thumbnail CLI flags — --thumbnails / --no-thumbnails on podcli process to force thumbnail generation on or off. (#38)

Studio UI

• Refreshed palette and a consistency pass: one low-opacity hairline border system, darker surfaces, depth from shadow, all-SVG icons, portaled modals, a sticky preview pane, tabular figures, and loading buttons that stay legible.
• Episode work now survives navigation — export results, energy analysis, suggestions, and selections persist when you leave and return to the page.

Under the hood

• New FormatSpec single source of truth (backend/services/formats.py) replaces scattered 1080×1920 hardcodes; format is threaded end to end with format-aware duration caps, and the render path forks on the format's reframe strategy (face-tracked crop for vertical/square, scale-and-pad letterbox for horizontal).

Full changelog: v2.1.2...v2.2.0