Skip to main content

Module autonomy

Module autonomy 

Source
Expand description

The session wake-up briefing and one-shot efficiency hints. The read-path drivers (session-start preload, related hints, silent import preload, prefetch, auto-dedup) were retired on 2026-10-17: an A/B on the retrieval corpus returned byte-identical responses and equal R@5/MRR with them off, while the session start cost 2-14 s more.

Structs§

AutonomyState
Tracks autonomous action state independently of the MCP tool layer.
SearchHistory
Per-key stats for progressive search hints (ctx_search / ctx_semantic_search).

Constants§

AUTO_CONTEXT_MAX_TOKENS
The largest --- AUTO CONTEXT --- block a reply carries; larger blocks are dropped, so the briefing is fitted to it.

Functions§

apply_auto_load_packages_once
Applies the auto-load context packages silently on the first call of a session that does not deliver the briefing; the result text is unchanged and the briefing names them later.
delivers_session_briefing
Whether this call is the one that may carry the session briefing and the shared-context hint: ctx_session with load, status or show, also through ctx_call. Every other tool result stays a deterministic function of its inputs (#498); the briefing carries per-run peer ids and memory.
session_wakeup_briefing
The wake-up briefing (last task, recent decisions, project facts, active peers), as --- AUTO CONTEXT ---, on the first briefing-delivering call of a session (see delivers_session_briefing).
shell_efficiency_hint
Suggests a more token-efficient lean-ctx tool when shell compression is low.
should_auto_consolidate
Returns true if enough tool calls have elapsed to trigger auto-consolidation.