Quell reads your docstrings, Pydantic models, and type annotations, extracts every testable requirement, finds which ones have no test, generates pytest tests via a rule engine, verifies each test through a 5-gate pipeline, and writes only proven tests to disk.

Does Quell require an LLM API key?

The rule engine runs entirely in-process — no source code is ever transmitted. ~75% of edge cases are handled with no network call and no API key. LLM fallback is opt-in and only sends the function signature, never the full body.

What is the 5-gate pipeline?

Every generated test must pass: Gate 1 (AST valid Python), Gate 2 (not already in a test file), Gate 3 (no shell calls or file writes), Gate 4 (passes against original code), Gate 5 (fails when the requirement is violated). Only gate-5-verified tests are written to disk.

What is the Production Readiness Score (PRS)?

PRS = (WRITTEN × 1.0 + SCAFFOLDED × 0.5) / total_requirements × 100. Tiers: 80-100 Production Ready, 60-79 Review Needed, 0-59 Needs Work.

How is Quell different from GitHub Copilot or Qodo for test generation?

Quell reads specifications that already exist in your code — it does not generate tests from scratch. It finds requirements already documented in your docstrings, Pydantic models, and type annotations that have no test. The 5-gate pipeline, especially Gate 5 (violation injection), verifies each test actually catches the bug it claims to catch. This verification step is not present in Copilot, Qodo, or Hypothesis.

Can Quell be used in CI pipelines?

Yes. Run quell ci src/ --threshold 80 to fail CI if PRS falls below 80. Set prs_threshold in pyproject.toml under [tool.quell]. Works with GitHub Actions, GitLab CI, and any system that checks exit codes.

Claude Connector

Connect Quell to Claude.ai and ask about your production readiness in plain English — no terminal required.

What it does

Once connected, Claude can answer questions like:

"What's my PRS for the payments module?"
"Why can't those two edge cases be auto-tested?"
"Which tests should I review before merging?"
"Give me the README badge for this project."

Claude reads your synced Quell reports. It never sees your source code.

Requirements

Quell v2.0.1+ — pip install --upgrade quelltest
Pro or Team plan — cloud sync and the connector are Pro/Team features
quell auth login — authenticate your account first

Setup in 4 steps

Step 1 — Authenticate

quell auth login

This opens a browser and saves your token to ~/.config/quell/auth.json.

Step 2 — Sync your first report

quell find src/ --fix --sync

This scans your code, writes tests, and pushes a privacy-safe report to api.quelltest.com. You should see:

Report synced → quelltest.com/dashboard/your-project

Step 3 — Connect in Claude.ai

Open claude.ai
Go to Settings → Connectors
Search for "Quell"
Click Connect and complete the OAuth flow (under 30 seconds)

Step 4 — Ask Claude

Once connected, start a new conversation and ask:

What is my production readiness score for payments-service?

Claude will call the get_prs_report tool and reply with your PRS, test counts, and any flagged items.

Configuration

Add to pyproject.toml to enable sync automatically:

[tool.quell]
sync = true                        # opt-in (default: false)
sync_project_alias = "my-service"  # human-readable name in Claude

Or use the flag explicitly each time:

quell find src/ --sync
quell score .  --sync

Verify what was sent

quell sync status --privacy

Output:

Sync enabled: yes (Pro tier)
Project: my-service
Last push: 2026-06-07 10:00:00
What gets sent: test names, confidence scores, flagged reasons, PRS, file:line
What stays local: all source code, all test bodies, all docstrings
View full schema: https://quelltest.com/docs/sync-payload

Remove your data

quell sync unlink

This deletes all synced data from api.quelltest.com. Claude will no longer be able to answer questions about this project.

Next steps

MCP Tool Reference — all 8 tools Claude can call
Privacy & Security — exactly what gets sent