Skip to main content

Crate jevdev

Crate jevdev 

Source
Expand description

§jevdev

A coding-agent harness built around Jev, TypeSafe’s System One decision model.

The harness keeps all agent state as explicit, typed, content-addressed chunks (state) and asks Jev the per-turn questions a coding agent normally leaves to defaults (jev::questions):

Decision pointQuestionTyped answer
ContextHow visible should this chunk be for this query?hide / short / long / full
CacheReuse the cached prefix or rebuild?noul + probability
RoutingCan this subtask leave the frontier model?choice + cost estimate
ToolsWhich tool fits this intent?ranked choice, top-k
PermissionsShould this command run?allow / ask / deny
SecurityWhich files will this task touch?sensitivity score

Frontier models (llm), tools (tools), and deterministic code do the actual work. Context is assembled per query (context), never appended; routing is priced per context rebuild (router); commands pass a Cedar policy plus Jev deep inspection (policy); and the turn loop lives in runtime, with a terminal UI in tui.

Modules§

config
Harness configuration, loaded from jevdev.toml in the repository root.
context
Meta-attention: context as a per-query decision.
jev
The Jev client.
llm
Frontier and helper models.
policy
Programmable permissions.
router
Cost-priced, security-aware model routing.
runtime
The turn loop.
state
Explicit, typed, content-addressed state.
tools
Tools with tiered disclosure.
tui
Terminal UI.

Constants§

VERSION
Crate version, as compiled.