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.

quell find

The primary Quell command. Scans your code for untested edge cases across all available spec sources.

Usage

quell find [PATH]                   # Find and report gaps (no writes)
quell find [PATH] --fix             # Find + write tests for verified cases
quell find [PATH] --fix --auto      # Skip confirmation prompts (CI mode)

Arguments

Argument	Description
`PATH`	File or directory to scan. Defaults to current directory.

Options

Option	Description
`--fix`	Generate and write verified tests. Prompts for confirmation unless `--auto` is set.
`--auto`	Skip confirmation prompts. Use in CI pipelines.
`--source`	Comma-separated spec sources to use: `docstrings,pydantic,types`. Default: auto-detect.
`--output`	Test output file path. Default: auto-detect from existing test structure.
`--threshold`	Minimum PRS score required in `--auto` mode. Exit non-zero if below.

What it scans

Quell auto-detects every spec source available:

Function docstrings (raises, returns, constraints)
Pydantic model validators and Field() constraints
Type annotations (Optional, Literal, Union)
Guard clauses and assertion patterns

Example output

Scanning src/payments.py...

Found 4 edge cases:

✓  WRITTEN   test_payment_rejects_zero_amount        [5/5 gates]
✓  WRITTEN   test_payment_rejects_negative_amount    [5/5 gates]
~  SCAFFOLDED test_refund_idempotency                [1-3 gates — external state]
✗  FLAGGED   test_stripe_gateway_timeout             [side effect: stripe.Charge.create()]

Tests written to: tests/test_payments.py
PRS: 75 → 84 (+9)

Exit codes

Code	Meaning
0	Success
1	Error during scan
2	Score below threshold (with `--threshold`)