Re-exports§
pub use conversation_forks::ForkThreadOutcome;pub use conversation_forks::ForkThreadRequest;pub use bus::*;pub use dynamic_workflows::*;pub use runtime::*;pub use teams::*;
Modules§
- artifacts
- bus
- conversation_
forks - Conversation forks (roadmap phases 90 + 81).
- dynamic_
workflows - fake_
provider - forks
- Runtime fork manager (roadmap phase 81, Task 2): resolves configured
ForkProviders from the extension registry and applies path/policy checks before provider calls. Thread attachment lives inconversation_forks; these are the provider-facing primitives shared by conversation forks and theforks/*app-server surface. - inference_
routing - media_
artifacts - media_
generation - Provider-neutral image generation service.
- model_
profiles - policy_
gate - runtime
- teams
- tool_
search - Runtime tool-search catalog adapter (roadmap phase 79, Task 2).
Structs§
Constants§
Functions§
- apply_
model_ instruction_ overlay - apply_
plan_ mode - apply_
runtime_ profile - apply_
task_ ledger_ required - apply_
thread_ developer_ instructions - Prepends host-supplied thread instructions to the developer slot so they layer directly under the harness system prompt while harness addenda (runtime profile, plan mode, overlays) append after them.
- apply_
turn_ developer_ context - Sets the per-turn developer-context slot. Supplied on turn/start only and never persisted, so a context delivered on turn N is absent on turn N+1 unless the host sends it again. Providers render the slot after all stable instruction content — through a provider-native per-turn channel (e.g. a trailing system-role message) where available — so cached stable-prefix blocks survive per-turn changes.
- default_
instructions