docs: clarify refreshable model catalog authority

This commit is contained in:
Shakker
2026-04-28 02:37:41 +01:00
parent 2c1be64d97
commit 197f95c94d
3 changed files with 7 additions and 5 deletions

View File

@@ -53,8 +53,9 @@ Notes:
unavailable until matching auth is configured.
- Broad `models list --all` merges manifest catalog rows over registry rows
without loading provider runtime supplement hooks. Provider-filtered manifest
fast paths use `static` and `refreshable` manifest rows; providers marked
`runtime` stay on registry/runtime discovery.
fast paths use only providers marked `static`; providers marked `refreshable`
stay registry/cache-backed and append manifest rows as supplements, while
providers marked `runtime` stay on registry/runtime discovery.
- `models list` keeps native model metadata and runtime caps distinct. In table
output, `Ctx` shows `contextTokens/contextWindow` when an effective runtime
cap differs from the native context window; JSON rows include `contextTokens`

View File

@@ -784,8 +784,9 @@ Suppression fields:
Do not put runtime-only data in `modelCatalog`. Use `static` only when manifest
rows are complete enough for provider-filtered list and picker surfaces to skip
registry/runtime discovery. Use `refreshable` when manifest rows are useful
seeds or supplements but a registry/cache refresh may add more rows. Use
`runtime` when OpenClaw must load provider runtime to know the list.
listable seeds or supplements but a refresh/cache can add more rows later;
refreshable rows are not authoritative by themselves. Use `runtime` when OpenClaw
must load provider runtime to know the list.
## modelIdNormalization reference