coldpass

vedicreader/vishalakshi

GitHub ↗ · How this check works

Per-setup public labels: Linux / Haiku: Works

Static status badge · SVG · read-only JSON. Embed with ![Coldpass status](https://coldpass.dev/badge/vedicreader--vishalakshi.svg).

Works

Only older checks are saved; no current product test.

Answers apply to each recorded setup, revision and operation. Earlier observations remain in Run details.

Tested on Linux
PlatformHaikuLuna
Linuxyes

Linux / Haiku 5.5: yes · Oct 18, 2026 · d74a91306fcc · claude-code / 2.1.300 (Claude Code)
Recorded operation: /tmp/vv/bin/vishalakshi search 'late chunking' --limit 3

Needs keys or browser
None seen
Setup time
3 min 3 s to install, 3 s to first use
Issue
none found in recorded check

Safety: no observations were recorded for the selected revision. Functional results do not establish a safety result.

Run details

Haiku 5.5

Native agent · Checked operation passed

Checked operation /tmp/vv/bin/vishalakshi search 'late chunking' --limit 3

Agent-reported scope: Installed vishalakshi from the pinned checkout and ran the CLI `vishalakshi search` (chunk-level hybrid search) over a vault populated with `vishalakshi add_dir /workspace/nbs` in offline mode (VISHALAKSHI_OFFLINE=1). Search returned JSON hits with node_id, breadcrumb, score and snippet.

Run details
run
vedicreader--vishalakshi-claude-haiku-5-5-1792343842763977876
date
Oct 18, 2026
time to working
235.5s
product hosting / execution
Local command in the guest
recorded operation scope
product operation
model
claude-haiku-5-5
agent / version
claude-code / 2.1.300 (Claude Code)
platform
linux
reported cost
$0.012798
Recorded source
https://github.com/vedicreader/vishalakshi
Tool transport
mcp-assigned-vm
Test version
readme-e8f276743e13e2c45e947267e722fb5007f8ab05a3813d972332c57d739c7360
revision
d74a91306fccc976f5868ee0a4a46ccac52be77b
Whose fault: not assigned · resolved

What the agent did

Installed vishalakshi from the pinned checkout and ran the CLI `vishalakshi search` (chunk-level hybrid search) over a vault populated with `vishalakshi add_dir /workspace/nbs` in offline mode (VISHALAKSHI_OFFLINE=1). Search returned JSON hits with node_id, breadcrumb, score and snippet.

apt-get install python3-venv python3-pip (guest prerequisite)
python3 -m venv /tmp/vv
/tmp/vv/bin/pip install -e /workspace (README 'Development' install; the README's `pip install vishalakshi` equivalent)
VISHALAKSHI_VAULT=/tmp/vishalakshi-probe/vault.db VISHALAKSHI_OFFLINE=1 /tmp/vv/bin/vishalakshi add_dir /workspace/nbs
VISHALAKSHI_VAULT=... VISHALAKSHI_OFFLINE=1 /tmp/vv/bin/vishalakshi search 'late chunking' --limit 3

run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt