providers now per-agent: z.ai rides, bifrost stays home
Vanguard gets his own inference pipe. z.ai GLM Coding Plan, /paas/v4. BifrostClient learned to leave versioned URLs alone. ProviderRegistry dispatches per agent; every engine asks who it's talking to before dialing. Annie and Hal none the wiser.
This commit is contained in:
parent
19b8566e4d
commit
80bfb3a599
15 changed files with 326 additions and 57 deletions
7
.gitignore
vendored
7
.gitignore
vendored
|
|
@ -58,3 +58,10 @@ souveraine.log.prev
|
|||
|
||||
# Config (use souveraine.example.toml as template)
|
||||
souveraine.toml
|
||||
|
||||
# Local-only project scaffolding — kept on disk, never committed to any remote
|
||||
.superpowers/
|
||||
saf/
|
||||
journal/
|
||||
scripts/
|
||||
website/
|
||||
|
|
|
|||
Loading…
Reference in a new issue