BACKLOG: N8 half done, ctl model context takes Strata and the longest answer alone

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

BACKLOG.md

@@ -1890,6 +1890,10 @@ served only from a definition written by hand. In order:
   a large MoE that fits no card is not "fits nowhere". Done 2026-10-30, without a speed (one measurement so far).
 - N7. The web serve page, the explorer's fit, the console's serve form: the same choice. Done 2026-10-30.
 - N8. `--context`/`--parallel` tied to `context_length`/`max_output`; `ctl model context` takes Strata.
+  `ctl model context` takes Strata (setup's `--context`), and `--max-output` changes the longest answer alone,
+  in place, with no restart: done 2026-11-01 (31f440a). Open: a Strata model served without `--context` still runs
+  at what Strata's setup picks (4096 on cuda01) while the catalog says the model's trained context (32768), so
+  serve should write `--context` from `context_length`; and `--parallel`.
 
 - N7b. The mirror page's Strata tab: every family and size, fetch (GGUF) or serve (packs Strata fetches itself:
   NVFP4, DeepSeek V4.1). Done 2026-10-30. Community `strata-ple` packs Strata 0.2.7 does not list stay unservable;