fix(fs-search): sample an over-cap glob result across the tree

Asked what a workspace contained, an agent described one subfolder as the
whole project. `glob {"pattern": "*"}` matched 10030 paths across 22
top-level entries and the inline page was the first 100 of them, all under a
single unpacked archive.

Three properties compose into that page: a pattern with no `/` matches
basenames at any depth, so `*` means the whole tree rather than its top
level; `--sort=modified` orders oldest first, and unpacking an archive
restores timestamps that predate everything the user wrote; and the page was
the head of that order. Each is defensible alone, and together they make the
most ordinary request an agent receives produce a confident wrong answer.

A result within `globMaxResults` is unchanged — shown whole, in
modification-time order. Beyond it the page is filled round-robin across the
complete result's top-level entries, so one subtree cannot own every slot,
and the footer states that the page was sampled rather than taken in
modification-time order. Measured on a 24-entry, 716-file reproduction, the
head of 100 reaches 7 top-level names and the sampled page reaches 21. The
spill artifact still holds the complete sorted list.

The guidance and schema stop steering away from `ls`, state the any-depth
pattern rule, say results are files and never directories, and point at
`list` for a directory's contents.
This commit is contained in:
NI0317
2026-07-28 12:05:36 +08:00
parent d4614f92d6
commit 9b9b45e65e
8 changed files with 208 additions and 38 deletions

View File

@@ -248,7 +248,7 @@ const TOOL_PACKAGES: ToolPackage[] = [
await ctx.plugin(ToolFsSearch)
},
note:
'glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.',
'glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. An over-cap glob result does not return the head of the sorted list: its inline page is taken round-robin across the top-level entries of the complete result and the footer states that basis, because modification-time order is ascending and the restored timestamps of an unpacked archive put one subtree in front of every broad match.',
},
{
pkg: '@deepseek-ai/dsh-tool-pty',