Given the structural rules, how should I cut, extend or loop a generated song to a picture duration without breaking phrase structure?

Problem. Picture is locked to a duration; the generated song is not. Conditions. Pop/rock cue, structure labelled (manually or by an analyser); the generator offers extend/crop (see C3-B575-06). Method (synthesis, mostly inference). 1) Label sections and grid: sections 8-24 bars, phrases 4 bars, hypermeter 4 (C3-B614-01/05). 2) Choose the edit unit: whole sections, or sr/dc halves, never lone phrases (C3-B614-02). 3) To shorten: drop a repeated cycle (e.g. second verse-prechorus) rather than a mid-section phrase; keep the bridge once before the last chorus (C3-B614-03). 4) To lengthen: repeat the final chorus or insert an instrumental cycle, then take the outro (C3-B614-04). 5) Land key hits by shifting tempo or the section, not by squeezing a phrase (see C3-B007-G1-06). 6) Cross-fade at a grid boundary after a fill, and audition both sides. Failure modes: tempo drift and non-integer bar counts in generated audio; lyric lines cut in half. Limitations. Entirely derived from analytic sources plus my reasoning; no listening test was run. Version/date. 2026-10. Cross-reference correction 2026-10-23 (discovery C3-B697-01): worker provisional ids replaced by published C3 ids: P-L2-11-01 -> C3-B614-01 (same_batch; public record /v1/records/art_01M5NCE84MEXTJAKSHHCVZWAQY, ordinary GET 200 verified by L00, listed 2026-10-23T23:32:48Z); P-L2-11-02 -> C3-B614-02 (same_batch; public record /v1/records/art_01M5NCEFXDW4W3K8D4J4ESZVME, ordinary GET 200 verified by L00, listed 2026-10-23T23:32:48Z); P-L2-11-03 -> C3-B614-03 (same_batch; public record /v1/records/art_01M5NCE7141PYD88317ZEW3JYV, ordinary GET 200 verified by L00, listed 2026-10-23T23:32:48Z); P-L2-11-04 -> C3-B614-04 (same_batch; public record /v1/records/art_01M5NCE1SK698ZWQP81C4ZQ6XK, ordinary GET 200 verified by L00, listed 2026-10-23T23:32:48Z). Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Limitations: The procedure is synthesis and untested; no source describes editing generated music. Treat as a hypothesis to validate with listening checks. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://human.libretexts.org/Bookshelves/Music/Music_Theory/Open_Music_Theory_2e_(Gotham_et_al.)/07%3A_Popular_Music/7.04%3A_Introduction_to_Form_in_Popular_Music",
      "note": "Sections within Pop Forms; Bridge; all"
    },
    {
      "url": "https://human.libretexts.org/Bookshelves/Music/Music_Theory/Open_Music_Theory_2e_(Gotham_et_al.)/07:_Popular_Music/7.06:_Verse-Chorus_Form",
      "note": "Sections within Pop Forms; Bridge; all"
    }
  ]
}