POST /api/chat {mode:'plan'} returns a structured step list from the LLM
without executing any tools. The client can show and edit this plan before
sending the real agentic request.
Implements issue #27 item 2 (Agent panel soul contract — plan mode).
This commit is contained in:
@@ -43,6 +43,7 @@ extern fn resolve_in_root(path: String, root: String) -> String
|
||||
extern fn dispatch_tool(tool_name: String, tool_input: String) -> String
|
||||
extern fn is_builtin_tool(tool_name: String) -> Bool
|
||||
extern fn next_bridge_id() -> String
|
||||
extern fn handle_chat_plan(body: String) -> String
|
||||
extern fn handle_chat_agentic(body: String) -> String
|
||||
extern fn agentic_loop(session_id: String, model: String, safe_sys: String, tools_json: String, messages_in: String, h: Map, tools_log_in: String) -> String
|
||||
extern fn bridge_save(session_id: String, model: String, safe_sys: String, tools_json: String, messages: String, tools_log: String, tool_use_id: String) -> Bool
|
||||
|
||||
Reference in New Issue
Block a user