coldpass

grishahq/agentsql

GitHub ↗ · How this check works

Per-setup public labels: Linux / Luna: Didn’t work

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

mcp-server

Didn’t work

The recorded operation failed on the tested setups.

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

Tested on Linux
PlatformHaikuLuna
Linuxno

Linux / Luna: no · Oct 26, 2026 · 133f934dd5ab · codex / codex-cli 0.163.0
Recorded operation: <guest-path> demo --directory <guest-path>

Does what it says
0 of 1 claims checked out
  • The deterministic demo demonstrates stale input rejection and recomputation.: Real input did not produce the expected result: Demo passed: stale output rejected atomically, refreshed output accepted.

    Source: The deterministic demo uses **simulated agent workers**, runs locally, and needs

    Input: agentsql demo

    Expected: stale output rejected atomically, refreshed output accepted

    Command: <guest-path> demo --directory <guest-path>

    Observed: { "error": "ValueError", "message": "The demo directory must be new or empty" }

MCP
Documented only
Local or hosted
local
Local: runs on your machine
Maintained
Maintained
actively maintained: last commit 0 days ago; 12 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases

Last commit Oct 25, 2026

Issue
yes, not fixed yet
Our test was blocked; no repo verdict.
Examples
0 of 1 ran as expected
  • Run deterministic scenarios: command exited with code 1

    Source: README.md: Install and run

    Input: python examples/scenarios.py

    Expected: 11 deterministic scenarios

    Command: <guest-path> examples/scenarios.py --directory <guest-path>

    Observed: ERROR: The scenario directory must be new or empty and not a symlink

Evidence
some README behavior checked
Agent interfaces
CLI, MCP (documented only)
CLI, MCP (documented only)

Observed interfaces were exercised by the checker. Documentation alone does not confirm compatibility.

Tested with
Codex / Luna
  • Linux: Codex / Luna · agent codex-cli 0.163.0 · Recorded operation failed · Oct 26, 2026 on 133f934dd5ab

Each entry describes its recorded operation and source revision.

Safety
No unexpected network or file activity found in these checks

No problems traced to this repository code in these checks; a short run cannot prove safety.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

Full event, path and process lists for each observed setup:

Repair history and test corrections
Current diagnosis: unknown · pending

product invocation failed: {"argv": ["<guest-path>", "demo", "--directory", "<guest-path>"], "returncode": 1, "stdout": "", "stderr": "{\n \"error\": \"ValueError\",\n \"message\": \"The demo directory must be new or empty\"\n}\n", "needs_credentials": false, "needs_browser": false}

Repair record fix-7c00f9c2410d945e1f27 · current status JSON. Original run outcomes remain unchanged.

Failed run: grishahq/agentsql · Oct 26, 2026 · Recorded operation failed.

Run details

Luna

Native agent · Recorded operation failed

Operation / attempted scope <guest-path> demo --directory <guest-path>

Agent-reported scope: Run AgentSQL deterministic demo and scenarios

Run details
run
grishahq--agentsql-gpt-6-luna-1793019802651352815
date
Oct 26, 2026
time to working
not recorded
product hosting / execution
Local command in the guest
recorded operation scope
Python 3.12 venv; package installed from checkout; local SQLite only
model
gpt-6-luna
agent / version
codex / codex-cli 0.163.0
platform
linux
reported cost
not reported (not assumed free)
Recorded source
https://github.com/grishahq/agentsql
Backend
hyperv
Tool transport
mcp-assigned-vm
Requested source pin (not an observed revision)
{"commit": "133f934dd5abef00fff00a993a52cdb4a9e41649", "url": "https://github.com/grishahq/agentsql"}
Test version
readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56
revision
133f934dd5abef00fff00a993a52cdb4a9e41649
Current diagnosis: unknown · pending

product invocation failed: {"argv": ["<guest-path>", "demo", "--directory", "<guest-path>"], "returncode": 1, "stdout": "", "stderr": "{\n \"error\": \"ValueError\",\n \"message\": \"The demo directory must be new or empty\"\n}\n", "needs_credentials": false, "needs_browser": false}

Repair record fix-7c00f9c2410d945e1f27 · current status JSON. Original run outcomes remain unchanged.

Failed run: grishahq/agentsql · Oct 26, 2026 · Recorded operation failed.

Fix: fix-7c00f9c2410d945e1f27.

Recorded blocker / warning

Step: <guest-path> demo --directory <guest-path>

product invocation failed: {"argv": ["<guest-path>", "demo", "--directory", "<guest-path>"], "returncode": 1, "stdout": "", "stderr": "{\n \"error\": \"ValueError\",\n \"message\": \"The demo directory must be new or empty\"\n}\n", "needs

Safety: No problems traced to this repository code in these checks.

No problems traced to this repository code in these checks.

Reviewed as expected for a test run: attempted writes that failed, so nothing was written.

OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check.

A short run cannot establish that code is safe.

Connections show IP addresses; proxies can hide the final hostname.

Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing.

Full safety evidence →

Answers recorded for this run
  • The deterministic demo demonstrates stale input rejection and recomputation.: Real input did not produce the expected result: Demo passed: stale output rejected atomically, refreshed output accepted.

    Source: The deterministic demo uses **simulated agent workers**, runs locally, and needs

    Input: agentsql demo

    Expected: stale output rejected atomically, refreshed output accepted

    Command: <guest-path> demo --directory <guest-path>

    Observed: { "error": "ValueError", "message": "The demo directory must be new or empty" }

Examples

  • Run deterministic scenarios: command exited with code 1

    Source: README.md: Install and run

    Input: python examples/scenarios.py

    Expected: 11 deterministic scenarios

    Command: <guest-path> examples/scenarios.py --directory <guest-path>

    Observed: ERROR: The scenario directory must be new or empty and not a symlink

Local or hosted: local

Suggested next step (agent-reported): Inspect the recorded blocker and correct the README prerequisites or harness error.

What the agent did

Run AgentSQL deterministic demo and scenarios

pwd && ls -la && sed -n '1,240p' README.md && python3 --version && id -u
python3 -m venv .venv && .venv/bin/python -m pip install .
mkdir -p .coldpass && .venv/bin/agentsql demo --directory ./demo-output
sed -n '1,100p' examples/scenarios.py && find .coldpass -maxdepth 1 -type f -print
rg -n "schedule|cron|webhook|cycle|--once|--now|def main|agentsql" src README.md
find .coldpass -maxdepth 2 -type f -print; sed -n '1,160p' pyproject.toml
cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["<guest-path>","demo","--directory","<guest-path>"],"cwd":"<guest-path>","expected_text":"Demo passed: stale output rejected atomically, refreshed output accepted."}
EOF
cat > .coldpass/claims.json <<'EOF'
[{"kind":"claim","claim":"The deterministic demo demonstrates stale input rejection and recomputation.","source":"The deterministic demo uses **simulated agent workers**, runs locally, and needs","input":"agentsql demo","expected":"stale output rejected atomically, refreshed output accepted","probe_kind":"cli","argv":["<guest-path>","demo","--directory","<guest-path>"],"expected_text":"Demo passed: stale output rejected atomically, refreshed output accepted.","cwd":"<guest-path>"}]
EOF
cat > .coldpass/examples.json <<'EOF'
[{"kind":"example","claim":"Run deterministic scenarios","source":"README.md: Install and run","input":"python examples/scenarios.py","expected":"11 deterministic scenarios","argv":["<guest-path>","examples/scenarios.py","--directory","<guest-path>"],"cwd":"<guest-path>"}]
EOF
cat > .coldpass/cycles.json <<'EOF'
{"detected":false,"reason":"Inspected README product entry points and examples; AgentSQL is invoked per CLI/API operation and documents no scheduler, recurring loop, or webhook cycle.","checks":[]}
EOF
<env-var>=<guest-path> python3 -I <guest-path> --validate --replay
cat > .coldpass/report.json <<'EOF'
{"outcome":"working","fault_owner":null,"operation":"Run AgentSQL deterministic demo and scenarios","operation_scope":"Python 3.12 venv; package installed from checkout; local SQLite only","steps":["python3 -m venv .venv",".venv/bin/python -m pip install .",".venv/bin/agentsql demo --directory ./demo-output",".venv/bin/python examples/scenarios.py --directory .coldpass/scenarios"],"deviations":[],"stuck_step":null,"main_blocker":null,"plain_failure":null,"suggested_fix":null}
EOF
ls -la .coldpass