feat: merge language persona channel into canonical app
This commit is contained in:
parent
3f64889639
commit
b70e092e28
18 changed files with 2658 additions and 37 deletions
|
|
@ -12,7 +12,9 @@ The first visible body uses a Rust-owned SQLite kernel under the Tauri app-data
|
|||
|
||||
HoloLake embeds a non-visual zero-point nucleus client runtime beneath the human surface. It is the minimum controlled projection of the BingShuo system controller, whose private body remains on the JD primary node; the public repository records evolution checkpoints rather than containing that private body. At application start, the Rust runtime loads the local protocol, compares the registered remote protocol version in the background, keeps a minimal local receipt, and leaves any unverified update unapplied. User-number verification runs before any future persona-loading path.
|
||||
|
||||
This system runtime is not Zhuyuan or another persona subject, and it is not the current model carrier. A valid number does not prove persona binding and does not grant execution or server authority. The current source implements deterministic protocol comparison, explicit-positive number verification and a fail-closed update skeleton. Signed protocol-payload installation, private registry distribution and persona loading are not yet implemented. Stage one does not expose an internal AI chat, model API configuration or arbitrary remote-code channel.
|
||||
This system runtime is not Zhuyuan or another persona subject, and it is not the current model carrier. A valid number does not prove persona binding and does not grant execution or server authority. The current source implements deterministic protocol comparison, explicit-positive number verification and a fail-closed update skeleton. Signed protocol-payload installation and private registry distribution are not yet implemented.
|
||||
|
||||
The native product now contains a language-persona conversation slice. Human conversation is the primary surface; model configuration stays behind secondary settings, secrets remain in the operating-system keychain, and models remain replaceable inference resources rather than persona identity or authority. The same channel can run beside the knowledge workspace with the exact active page path and content hash attached to each knowledge receipt. It still does not expose an arbitrary remote-code channel or unscoped tool execution.
|
||||
|
||||
## Native knowledge workspace
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue