Andre Brait ae2035efa0 feat(hook): show the graph nodes behind a nudged call, and tighten its wording ...

Agents treated the soft nudge as noise: it was the same placeholder text on
every call, and "or to modify/debug specific lines" excused nearly any
targeted read. A firing nudge (and the strict-mode deny) now carries:

- a command built from the call: `graphify explain "<symbol>"` when the
  searched word is a node label, `graphify query "<terms>"` otherwise, or
  `graphify explain "<file>"` for a read;
- up to five matching graph nodes with file and line, so the nudge shows
  what the graph already knows instead of only asking for it.

The lookup scans graph.json labels and paths directly (0.1-0.5 s on 3k-15k
node graphs; the full query stack costs ~1.5 s per hook call), skips graphs
over 32 MiB, and falls back to the plain nudge on any failure or no match.

The escape clause now allows raw reads only once the exact file and lines
are known, and the always-on rule names the moment to query: before the
first grep, search or source-file read.

(cherry picked from commit b51314765c)

2026-10-13 10:26:57 +01:00

..

skillgen

feat(hook): show the graph nodes behind a nudged call, and tighten its wording

2026-10-13 10:26:57 +01:00

__init__.py

feat(skills): progressive-disclosure split for all platforms (generator + drift fence) (#1121)

2026-06-02 20:48:13 +01:00