vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: tighten favorite-tools head normalisation wording

Browse source 
Per damocles (capture-side owner): "argv[0] basename" undersells the
normalisation and misleads — the head is the basename of the first
*real* command, looking past `cd repo &&` prefixes, env-assignments,
and prefix-runners (sudo/env), so `cd /repo && cargo build` records
`cargo`, not `cd`. Match the persistence.md phrasing.
This commit is contained in:
iris 2026-06-06 08:08:12 +02:00 • committed by mara
commit a3e6585266
1 changed files with 8 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

13
docs/web-ui/agent.md
View file

@ -373,11 +373,14 @@ cost chart), doughnuts for tool / wake-source / result mix, and a
error / rate-limit / compaction outcomes are visible over time
(the doughnut shows only the window total).
A **favorite tools** doughnut shows the most-run shell commands —
normalised `bash_commands` heads (argv[0] basename) written per
bash task by the hive-bash-mcp capture, read via
`bash_breakdown`. Its card stays hidden until the agent has run a
bash command (a missing `bash_commands` table degrades to an empty
list), so it never renders an empty chart.
normalised `bash_commands` heads written per bash task by the
hive-bash-mcp capture: the basename of the *first real command*,
looking past `cd repo &&` prefixes, env-assignments, and
prefix-runners like `sudo` / `env` (so `cd /repo && cargo build`
records `cargo`, not `cd`). Read via `bash_breakdown`; the card
stays hidden until the agent has run a bash command (a missing
`bash_commands` table degrades to an empty list), so it never
renders an empty chart.
A summary chip row carries window totals, plus two
token-efficiency chips derived from the bucket sums: **cache
hit-rate** (`cache_read` over all input-side tokens) and