workflowval 0.1.0__tar.gz

workflowval-0.1.0/.gitignore

@@ -0,0 +1,15 @@
+.venv/
+__pycache__/
+*.pyc
+.mypy_cache/
+.ruff_cache/
+.pytest_cache/
+.coverage
+coverage.xml
+dist/
+build/
+.workflowval/
+.env
+.DS_Store
+.benchmark/
+reports/

workflowval-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 workflowval contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

workflowval-0.1.0/PKG-INFO

@@ -0,0 +1,215 @@
+Metadata-Version: 2.5
+Name: workflowval
+Version: 0.1.0
+Summary: Model-agnostic CLI agent that infers multi-step API workflows from an OpenAPI spec, tests them with pytest and triages every failure.
+Project-URL: Homepage, https://github.com/rkvf01/workflowval
+Project-URL: Documentation, https://github.com/rkvf01/workflowval/tree/main/docs
+Project-URL: Issues, https://github.com/rkvf01/workflowval/issues
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: httpx>=0.27
+Requires-Dist: jsonpatch>=1.41
+Requires-Dist: jsonpointer>=3.8
+Requires-Dist: litellm[mcp]>=1.83
+Requires-Dist: openapi-core>=0.19
+Requires-Dist: openapi-spec-validator>=0.7
+Requires-Dist: pydantic>=2.7
+Requires-Dist: pytest>=8
+Requires-Dist: ruff>=0.6
+Requires-Dist: typer>=0.12
+Description-Content-Type: text/markdown
+
+# workflowval
+
+Model-agnostic CLI agent that reads an OpenAPI spec, infers multi-step workflows, writes and runs
+pytest tests against a live API, and triages every failure as a test bug, an API bug or spec drift.
+
+**Status:** all six commands work: `test`, `plan`, `run`, `drift`, `inspect` and `report`.
+
+## Start here
+
+All the project's documents are in the [docs folder](https://github.com/rkvf01/workflowval/tree/main/docs).
+
+- **[Requirements](https://github.com/rkvf01/workflowval/blob/main/docs/requirements.md):** what workflowval was built to do.
+- **[Conclusions](https://github.com/rkvf01/workflowval/blob/main/docs/conclusions.md):** how it measured up, what helped and what didn't.
+- **[Model comparison](https://github.com/rkvf01/workflowval/blob/main/docs/model-comparison.md):** two models on the same benchmark, side by side.
+- **[Drift study](https://github.com/rkvf01/workflowval/blob/main/docs/drift-study.md):** the same tests against three implementations of one API.
+- **Build notes:** decisions in [M0](https://github.com/rkvf01/workflowval/blob/main/docs/m0-review.md), then changes and known limits in [M1](https://github.com/rkvf01/workflowval/blob/main/docs/m1-notes.md), [M2](https://github.com/rkvf01/workflowval/blob/main/docs/m2-notes.md) and [M3](https://github.com/rkvf01/workflowval/blob/main/docs/m3-notes.md).
+
+## Quickstart
+
+It needs Python 3.11 or later.
+
+```
+pip install workflowval
+```
+
+Then, from the folder where you want the tests written:
+
+```
+export OPENROUTER_API_KEY=...
+export WORKFLOWVAL_MODEL=openrouter/<vendor>/<model>
+workflowval inspect openapi.json
+workflowval test openapi.json --base-url http://localhost:8000 --max-cost-usd 2
+workflowval run tests/wf
+```
+
+This writes `workflows/<id>.json`, `tests/wf/test_<id>.py` and `results.json` in the current folder,
+plus `report.md`, `junit.xml`, bug reports and spec patches in `reports/`.
+If the API needs a login, pass `--auth auth.json` to both `test` and `run`, and set the env vars that
+file names. In a login config, a field like `user.email` nests the login body. See `benchmarks/targets.md` for
+the demo targets.
+
+## How it works
+
+`workflowval test` runs these steps, and saves its place after each one:
+
+1. **Plan.** The Planner reads the spec and any docs, and writes one workflow file per multi-step scenario,
+   each with the result it expects.
+2. **Review the plan.** The Reviewer looks for what the plan missed, as a user of the API would, and the
+   Planner adds workflows.
+3. **Write tests.** Code, not a model, renders each workflow into a pytest file, so this step is free and
+   repeatable.
+4. **Run and label.** The tests run against the live API. Only a result that doesn't match what the workflow
+   expected goes to the Reviewer, which labels it `TEST_BUG`, `API_BUG`, `SPEC_DRIFT`, `CONFLICT` or
+   `UNRESOLVED`.
+5. **Fix test bugs only.** The Planner corrects a wrong workflow and the Writer corrects test code. A real
+   failure is never changed to make it pass. It stays as a labeled expected failure.
+6. **Review the results.** The Reviewer sees the confirmed failures and asks for new workflows, including
+   ones that get past a known bug.
+7. **Report.** Bug reports, spec patches, `report.md` and `junit.xml` go in `reports/`.
+
+| Part | Where |
+| --- | --- |
+| Commands | `src/workflowval/cli.py`, `pipeline.py` |
+| Agent loop, budgets and stop rules | `src/workflowval/loop/` |
+| Model adapter, the only code that imports a provider library | `src/workflowval/models/` |
+| Tools the roles may call, limited per role | `src/workflowval/tools/` |
+| Data formats | `src/workflowval/schemas/` |
+| Spec reading and response checks | `src/workflowval/spec/` |
+| Test rendering | `src/workflowval/gen/` |
+| Role prompts | `src/workflowval/prompts/` |
+
+## What needs a model
+
+| Needs no model or key | Needs a model and its key |
+| --- | --- |
+| `workflowval inspect` | `workflowval plan` |
+| `workflowval run tests/wf` | `workflowval test` |
+| Plain `pytest tests/wf` | `workflowval drift` |
+| `workflowval report` | Labeling and fixing failures |
+| This repo's own lint and tests | `uv run pytest -m live`, and the benchmark |
+
+So you can generate tests once, commit them, and re-run them with no model cost. A failure already
+reviewed as real counts as expected, so it doesn't fail the run. Any other failure makes `run` exit 1,
+but nothing labels it; run `workflowval test` to get the diagnosis. `run` and `pytest` still need a
+reachable API and, for a login API, its credentials.
+
+## Reading the results
+
+| Result | Meaning | Fails the run? |
+| --- | --- | --- |
+| `PASSED` | The test passed | No |
+| `EXPECTED` | It hit the failure already reviewed as real, and only that failure | No |
+| `LOOKS FIXED` | A test marked as a known issue passed | No |
+| `MISMATCH` | A response breaks the spec, though the test may pass | No, except in `drift` |
+| `UNRESOLVED` | Fix attempts ran out, or the failure has no verdict | Yes |
+
+## Benchmark
+
+Scored against a seeded-bug app with 10 planted defects and one spec-docs conflict, for 3 rounds on one low-cost
+model. See `docs/m3-notes.md` for what the numbers mean, and `benchmarks/seeded/README.md` for who wrote the app,
+which affects how independent this score is.
+
+| Metric | Median (range) | Target |
+| --- | --- | --- |
+| Seeded bugs detected, of 10 | 10 (9 to 10) | 8 or more |
+| Label accuracy on detected bugs, % | 70 (67 to 90) | 80 or more |
+| Bugs a workflow could catch, of 10 | 10 (10 to 10) | 10 |
+| False API_BUG on the clean build | 1 (1 to 1) | 1 or fewer |
+| Tests green on the clean build, % | 98 (96 to 98) | 90 or more |
+| CONFLICT reports | 0 (0 to 0) | 1 |
+| Cost per round, USD | 0.31 (0.30 to 0.35) | reported only |
+
+Label accuracy and the conflict report still miss their targets on this model. A second model met them on
+the medians, at about 28 times the cost and with less steady detection: see `docs/model-comparison.md`.
+
+## Known limits
+
+- **Results vary by model and run,** since models choose the workflows and labels. Three rounds is a small sample.
+- **Labels are the weak spot.** About a quarter of detected bugs got the wrong label on both models tested. Check
+  a label before acting on it.
+- **A test stops at its first failure.** A bug in an early step can hide later bugs from every test that goes
+  through that step. This is deliberate: the failure stays a result, and getting further is the job of another test.
+- **Finding a conflict isn't reliable** on the low-cost model, which wrote no CONFLICT reports in the benchmark.
+- **The fix loop can be inconsistent.** On the same kind of edge case, it may rewrite what some tests expect and not
+  others. Rewrites that change what a test checks are printed as `CHANGED`, so review them.
+- **Edge cases get missed,** and a `204` can raise a false alarm. See `docs/drift-study.md`.
+- **Generated tests aren't sandboxed.** They run on your machine with your permissions, so use only specs and docs
+  you trust.
+- **The cost cap can go slightly over,** since it judges by the dearest call so far.
+- **A run resumes only after being killed.** One that stopped on a model error, a step limit or a cost limit doesn't
+  pick up where it stopped. Running it again starts a new run, which reuses a finished plan for the same spec.
+- **The benchmark isn't fully independent,** because of who wrote the seeded app. See `benchmarks/seeded/README.md`.
+
+## Safety and CI
+
+```
+workflowval test openapi.json --base-url https://staging.example.com --allow-remote --read-only
+workflowval run tests/wf --ci --ci-max-api-bugs 2
+```
+
+`--read-only` sends no writes. A non-local host needs `--allow-remote`, then `--yes`, `--ci` or `--read-only`.
+Generated tests refuse any other host. `--ci` fails on anything unresolved, or on bugs above the limits. A killed
+`workflowval test` picks up at its last step when run again. See `docs/m3-notes.md`.
+
+`--max-cost-usd 2` stops a run before a model call could pass that cost, judging by the dearest call so far, so a
+much larger call can still go slightly over. A call with no known price also stops the run, since the limit
+can't be kept. Temporary provider errors, such as rate limits, are retried up to 5 times.
+
+Secrets are hidden in everything saved or sent to a model: known values, auth headers and fields with names like
+`token`. A hidden value isn't checked against the spec. `--no-redact` keeps recorded response bodies exact, and works
+only with a local API, since those bodies may hold real secrets. Everything else stays hidden.
+
+## Develop
+
+This needs [uv](https://docs.astral.sh/uv/).
+
+```
+git clone https://github.com/rkvf01/workflowval.git && cd workflowval
+uv sync
+uv run ruff check . && uv run ruff format --check .
+uv run mypy --strict src
+uv run pytest --cov=workflowval.loop --cov=workflowval.spec --cov=workflowval.triage --cov-fail-under=80
+uv run workflowval --help
+```
+
+Unit tests use `FakeModel` and block network sockets, so they need no API key.
+
+## Models and API keys
+
+Live runs go through LiteLLM. Pick a model with `--model provider/name` or `WORKFLOWVAL_MODEL`, and
+override per role with `--role-model writer=provider/name`. Provider keys come from environment
+variables only, for example `OPENROUTER_API_KEY`. Local Ollama models (`ollama/<name>`) need no key.
+
+To check the adapter against a real provider:
+
+```
+export OPENROUTER_API_KEY=...
+WORKFLOWVAL_LIVE_MODEL=openrouter/<vendor>/<model> uv run pytest -m live
+```
+
+## Stats
+
+Every run writes model calls, tool calls and cost, per workflow and per role, to
+`.workflowval/stats.json`, and adds a line to `.workflowval/stats_history.jsonl`. After 5 usable runs,
+the run summary suggests a `--max-steps` value based on that history. It never changes the limit by
+itself. See `docs/m0-review.md`.
+
+Cost is the figure the provider returns with each reply, so tracking it adds no extra calls. To turn
+it off, use `--no-cost-tracking` or set `WORKFLOWVAL_COST_TRACKING=off`.
+
+## License
+
+MIT

workflowval-0.1.0/README.md

@@ -0,0 +1,193 @@
+# workflowval
+
+Model-agnostic CLI agent that reads an OpenAPI spec, infers multi-step workflows, writes and runs
+pytest tests against a live API, and triages every failure as a test bug, an API bug or spec drift.
+
+**Status:** all six commands work: `test`, `plan`, `run`, `drift`, `inspect` and `report`.
+
+## Start here
+
+All the project's documents are in the [docs folder](https://github.com/rkvf01/workflowval/tree/main/docs).
+
+- **[Requirements](https://github.com/rkvf01/workflowval/blob/main/docs/requirements.md):** what workflowval was built to do.
+- **[Conclusions](https://github.com/rkvf01/workflowval/blob/main/docs/conclusions.md):** how it measured up, what helped and what didn't.
+- **[Model comparison](https://github.com/rkvf01/workflowval/blob/main/docs/model-comparison.md):** two models on the same benchmark, side by side.
+- **[Drift study](https://github.com/rkvf01/workflowval/blob/main/docs/drift-study.md):** the same tests against three implementations of one API.
+- **Build notes:** decisions in [M0](https://github.com/rkvf01/workflowval/blob/main/docs/m0-review.md), then changes and known limits in [M1](https://github.com/rkvf01/workflowval/blob/main/docs/m1-notes.md), [M2](https://github.com/rkvf01/workflowval/blob/main/docs/m2-notes.md) and [M3](https://github.com/rkvf01/workflowval/blob/main/docs/m3-notes.md).
+
+## Quickstart
+
+It needs Python 3.11 or later.
+
+```
+pip install workflowval
+```
+
+Then, from the folder where you want the tests written:
+
+```
+export OPENROUTER_API_KEY=...
+export WORKFLOWVAL_MODEL=openrouter/<vendor>/<model>
+workflowval inspect openapi.json
+workflowval test openapi.json --base-url http://localhost:8000 --max-cost-usd 2
+workflowval run tests/wf
+```
+
+This writes `workflows/<id>.json`, `tests/wf/test_<id>.py` and `results.json` in the current folder,
+plus `report.md`, `junit.xml`, bug reports and spec patches in `reports/`.
+If the API needs a login, pass `--auth auth.json` to both `test` and `run`, and set the env vars that
+file names. In a login config, a field like `user.email` nests the login body. See `benchmarks/targets.md` for
+the demo targets.
+
+## How it works
+
+`workflowval test` runs these steps, and saves its place after each one:
+
+1. **Plan.** The Planner reads the spec and any docs, and writes one workflow file per multi-step scenario,
+   each with the result it expects.
+2. **Review the plan.** The Reviewer looks for what the plan missed, as a user of the API would, and the
+   Planner adds workflows.
+3. **Write tests.** Code, not a model, renders each workflow into a pytest file, so this step is free and
+   repeatable.
+4. **Run and label.** The tests run against the live API. Only a result that doesn't match what the workflow
+   expected goes to the Reviewer, which labels it `TEST_BUG`, `API_BUG`, `SPEC_DRIFT`, `CONFLICT` or
+   `UNRESOLVED`.
+5. **Fix test bugs only.** The Planner corrects a wrong workflow and the Writer corrects test code. A real
+   failure is never changed to make it pass. It stays as a labeled expected failure.
+6. **Review the results.** The Reviewer sees the confirmed failures and asks for new workflows, including
+   ones that get past a known bug.
+7. **Report.** Bug reports, spec patches, `report.md` and `junit.xml` go in `reports/`.
+
+| Part | Where |
+| --- | --- |
+| Commands | `src/workflowval/cli.py`, `pipeline.py` |
+| Agent loop, budgets and stop rules | `src/workflowval/loop/` |
+| Model adapter, the only code that imports a provider library | `src/workflowval/models/` |
+| Tools the roles may call, limited per role | `src/workflowval/tools/` |
+| Data formats | `src/workflowval/schemas/` |
+| Spec reading and response checks | `src/workflowval/spec/` |
+| Test rendering | `src/workflowval/gen/` |
+| Role prompts | `src/workflowval/prompts/` |
+
+## What needs a model
+
+| Needs no model or key | Needs a model and its key |
+| --- | --- |
+| `workflowval inspect` | `workflowval plan` |
+| `workflowval run tests/wf` | `workflowval test` |
+| Plain `pytest tests/wf` | `workflowval drift` |
+| `workflowval report` | Labeling and fixing failures |
+| This repo's own lint and tests | `uv run pytest -m live`, and the benchmark |
+
+So you can generate tests once, commit them, and re-run them with no model cost. A failure already
+reviewed as real counts as expected, so it doesn't fail the run. Any other failure makes `run` exit 1,
+but nothing labels it; run `workflowval test` to get the diagnosis. `run` and `pytest` still need a
+reachable API and, for a login API, its credentials.
+
+## Reading the results
+
+| Result | Meaning | Fails the run? |
+| --- | --- | --- |
+| `PASSED` | The test passed | No |
+| `EXPECTED` | It hit the failure already reviewed as real, and only that failure | No |
+| `LOOKS FIXED` | A test marked as a known issue passed | No |
+| `MISMATCH` | A response breaks the spec, though the test may pass | No, except in `drift` |
+| `UNRESOLVED` | Fix attempts ran out, or the failure has no verdict | Yes |
+
+## Benchmark
+
+Scored against a seeded-bug app with 10 planted defects and one spec-docs conflict, for 3 rounds on one low-cost
+model. See `docs/m3-notes.md` for what the numbers mean, and `benchmarks/seeded/README.md` for who wrote the app,
+which affects how independent this score is.
+
+| Metric | Median (range) | Target |
+| --- | --- | --- |
+| Seeded bugs detected, of 10 | 10 (9 to 10) | 8 or more |
+| Label accuracy on detected bugs, % | 70 (67 to 90) | 80 or more |
+| Bugs a workflow could catch, of 10 | 10 (10 to 10) | 10 |
+| False API_BUG on the clean build | 1 (1 to 1) | 1 or fewer |
+| Tests green on the clean build, % | 98 (96 to 98) | 90 or more |
+| CONFLICT reports | 0 (0 to 0) | 1 |
+| Cost per round, USD | 0.31 (0.30 to 0.35) | reported only |
+
+Label accuracy and the conflict report still miss their targets on this model. A second model met them on
+the medians, at about 28 times the cost and with less steady detection: see `docs/model-comparison.md`.
+
+## Known limits
+
+- **Results vary by model and run,** since models choose the workflows and labels. Three rounds is a small sample.
+- **Labels are the weak spot.** About a quarter of detected bugs got the wrong label on both models tested. Check
+  a label before acting on it.
+- **A test stops at its first failure.** A bug in an early step can hide later bugs from every test that goes
+  through that step. This is deliberate: the failure stays a result, and getting further is the job of another test.
+- **Finding a conflict isn't reliable** on the low-cost model, which wrote no CONFLICT reports in the benchmark.
+- **The fix loop can be inconsistent.** On the same kind of edge case, it may rewrite what some tests expect and not
+  others. Rewrites that change what a test checks are printed as `CHANGED`, so review them.
+- **Edge cases get missed,** and a `204` can raise a false alarm. See `docs/drift-study.md`.
+- **Generated tests aren't sandboxed.** They run on your machine with your permissions, so use only specs and docs
+  you trust.
+- **The cost cap can go slightly over,** since it judges by the dearest call so far.
+- **A run resumes only after being killed.** One that stopped on a model error, a step limit or a cost limit doesn't
+  pick up where it stopped. Running it again starts a new run, which reuses a finished plan for the same spec.
+- **The benchmark isn't fully independent,** because of who wrote the seeded app. See `benchmarks/seeded/README.md`.
+
+## Safety and CI
+
+```
+workflowval test openapi.json --base-url https://staging.example.com --allow-remote --read-only
+workflowval run tests/wf --ci --ci-max-api-bugs 2
+```
+
+`--read-only` sends no writes. A non-local host needs `--allow-remote`, then `--yes`, `--ci` or `--read-only`.
+Generated tests refuse any other host. `--ci` fails on anything unresolved, or on bugs above the limits. A killed
+`workflowval test` picks up at its last step when run again. See `docs/m3-notes.md`.
+
+`--max-cost-usd 2` stops a run before a model call could pass that cost, judging by the dearest call so far, so a
+much larger call can still go slightly over. A call with no known price also stops the run, since the limit
+can't be kept. Temporary provider errors, such as rate limits, are retried up to 5 times.
+
+Secrets are hidden in everything saved or sent to a model: known values, auth headers and fields with names like
+`token`. A hidden value isn't checked against the spec. `--no-redact` keeps recorded response bodies exact, and works
+only with a local API, since those bodies may hold real secrets. Everything else stays hidden.
+
+## Develop
+
+This needs [uv](https://docs.astral.sh/uv/).
+
+```
+git clone https://github.com/rkvf01/workflowval.git && cd workflowval
+uv sync
+uv run ruff check . && uv run ruff format --check .
+uv run mypy --strict src
+uv run pytest --cov=workflowval.loop --cov=workflowval.spec --cov=workflowval.triage --cov-fail-under=80
+uv run workflowval --help
+```
+
+Unit tests use `FakeModel` and block network sockets, so they need no API key.
+
+## Models and API keys
+
+Live runs go through LiteLLM. Pick a model with `--model provider/name` or `WORKFLOWVAL_MODEL`, and
+override per role with `--role-model writer=provider/name`. Provider keys come from environment
+variables only, for example `OPENROUTER_API_KEY`. Local Ollama models (`ollama/<name>`) need no key.
+
+To check the adapter against a real provider:
+
+```
+export OPENROUTER_API_KEY=...
+WORKFLOWVAL_LIVE_MODEL=openrouter/<vendor>/<model> uv run pytest -m live
+```
+
+## Stats
+
+Every run writes model calls, tool calls and cost, per workflow and per role, to
+`.workflowval/stats.json`, and adds a line to `.workflowval/stats_history.jsonl`. After 5 usable runs,
+the run summary suggests a `--max-steps` value based on that history. It never changes the limit by
+itself. See `docs/m0-review.md`.
+
+Cost is the figure the provider returns with each reply, so tracking it adds no extra calls. To turn
+it off, use `--no-cost-tracking` or set `WORKFLOWVAL_COST_TRACKING=off`.
+
+## License
+
+MIT

workflowval-0.1.0/pyproject.toml

@@ -0,0 +1,88 @@
+[project]
+name = "workflowval"
+version = "0.1.0"
+description = "Model-agnostic CLI agent that infers multi-step API workflows from an OpenAPI spec, tests them with pytest and triages every failure."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "MIT"
+license-files = ["LICENSE"]
+dependencies = [
+    "httpx>=0.27",
+    "jsonpatch>=1.41",
+    "jsonpointer>=3.8",
+    "litellm[mcp]>=1.83",  # Tool calls import mcp, which is only in this extra.
+    "openapi-core>=0.19",
+    "openapi-spec-validator>=0.7",
+    "pydantic>=2.7",
+    "pytest>=8",
+    "ruff>=0.6",
+    "typer>=0.12",
+]
+
+[project.urls]
+Homepage = "https://github.com/rkvf01/workflowval"
+Documentation = "https://github.com/rkvf01/workflowval/tree/main/docs"
+Issues = "https://github.com/rkvf01/workflowval/issues"
+
+[project.scripts]
+workflowval = "workflowval.cli:app"
+
+[dependency-groups]
+dev = [
+    "fastapi>=0.115",
+    "mypy>=1.10",
+    "pytest-cov>=5",
+    "pytest-socket>=0.7",
+    "uvicorn>=0.30",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/workflowval"]
+
+# A list of what ships, so nothing else in the folder can end up in the package.
+[tool.hatch.build.targets.sdist]
+only-include = ["src", "README.md", "LICENSE", "pyproject.toml"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "RUF", "S"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["S101", "S105", "S106"]
+"src/workflowval/gen/templates/**" = ["S101"]
+
+[tool.mypy]
+strict = true
+python_version = "3.11"
+mypy_path = "src"
+plugins = ["pydantic.mypy"]
+
+[[tool.mypy.overrides]]
+module = ["litellm", "litellm.*"]
+ignore_missing_imports = true
+follow_imports = "skip"
+
+[[tool.mypy.overrides]]
+module = ["jsonpatch", "jsonpointer"]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra --disable-socket --allow-unix-socket -m 'not live'"
+markers = ["live: calls a real model provider; needs an API key and is never run in CI"]
+
+[tool.coverage.run]
+branch = true
+source = ["workflowval"]
+
+[tool.coverage.report]
+show_missing = true
+exclude_also = ["if TYPE_CHECKING:", "\\.\\.\\.$"]

workflowval-0.1.0/src/workflowval/__init__.py

@@ -0,0 +1,3 @@
+"""workflowval: API workflow tests from an OpenAPI spec."""
+
+__version__ = "0.1.0"