whetkit 0.1.0__tar.gz

whetkit-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

whetkit-0.1.0/PKG-INFO

@@ -0,0 +1,182 @@
+Metadata-Version: 2.4
+Name: whetkit
+Version: 0.1.0
+Summary: Measure and improve how well LLM agents select and use the tools exposed by an MCP server
+Keywords: mcp,model-context-protocol,llm,agents,evals,tool-use,tool-selection,benchmark
+Author: Mohammed Benlamlih
+License-Expression: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Testing
+Classifier: Typing :: Typed
+Requires-Dist: mcp==1.28.1
+Requires-Dist: anthropic==0.116.0
+Requires-Dist: openai==2.44.0
+Requires-Dist: pydantic==2.13.4
+Requires-Dist: pyyaml==6.0.3
+Requires-Dist: typer==0.26.8
+Requires-Python: >=3.13
+Project-URL: Changelog, https://github.com/benlamlih/whetkit/releases
+Project-URL: Documentation, https://github.com/benlamlih/whetkit#readme
+Project-URL: Homepage, https://github.com/benlamlih/whetkit
+Project-URL: Issues, https://github.com/benlamlih/whetkit/issues
+Project-URL: Repository, https://github.com/benlamlih/whetkit
+Description-Content-Type: text/markdown
+
+# whetkit
+
+**Measure — then improve — how well LLM agents pick and use the tools your MCP
+server exposes.**
+
+`whetkit` is a local-first CLI that runs an agent against your
+[MCP](https://modelcontextprotocol.io) server on a set of eval tasks, scores
+its **tool-selection hit-rate**, and then *curates* the tool set — renaming
+cryptic tools, rewriting vague descriptions, pruning noise, and merging
+duplicates — via a **reversible overlay proxy** that never modifies your
+server. It re-runs the eval through the overlay and hands you a before/after
+report.
+
+```text
+whetkit inspect  ──►  what does the agent actually see?
+whetkit run      ──►  how often does it pick the right tools?   (hit-rate)
+whetkit curate   ──►  fix the tool set, prove it helped          (before → after)
+```
+
+## Why tool curation matters
+
+Agents don't read your code — they read your tool names, descriptions, and
+schemas. A server that grew organically ends up with `data_query_1`,
+`proc_ord`, and `do_thing`: every one of them costs the model a guess, and
+every duplicate splits its attention. In practice a large share of agent
+failures on MCP servers are *tool-selection* failures — the model calls the
+wrong tool, loops through near-duplicates, or gives up — and they are fixable
+without touching a line of server code, because the fix is metadata.
+whetkit makes that loop measurable: score the failures, patch the metadata
+through an overlay, and show the hit-rate delta.
+
+## Install
+
+```sh
+uv tool install whetkit   # or: uvx whetkit / pipx install whetkit
+```
+
+(Releases are published to PyPI from tags — see [RELEASING.md](RELEASING.md).
+Until the first release, use the from-source quickstart below.)
+
+## Quickstart (5 minutes)
+
+Requires [uv](https://docs.astral.sh/uv/) and an Anthropic API key (or
+OpenAI — see `--model`). Python is pinned via `.python-version`; uv fetches
+it automatically.
+
+```sh
+git clone https://github.com/benlamlih/whetkit && cd whetkit
+uv sync
+export ANTHROPIC_API_KEY=sk-ant-...
+```
+
+**1. Inspect the bundled sample server** — a deliberately messy e-commerce
+server (14 tools: cryptic names, vague descriptions, duplicates, noise):
+
+```sh
+uv run whetkit inspect --server examples/sample-server
+```
+
+**2. Baseline eval** — run 5 tasks against it and score the hit-rate
+(deterministic tool-matching + LLM-judge on the final answers):
+
+```sh
+uv run whetkit run --server examples/sample-server --tasks examples/tasks
+```
+
+**3. Curate and prove it** — analyze the failures, generate a curation
+overlay, re-run the eval through it, and get the before/after:
+
+```sh
+uv run whetkit curate --server examples/sample-server --tasks examples/tasks
+```
+
+This writes:
+
+- `.whetkit/curation-plan.yaml` — the reviewable, hand-editable overlay plan
+- `.whetkit/report.html` — self-contained before/after report (open it in a browser)
+- `.whetkit/report.json` — the same data, machine-readable
+- `.whetkit/traces.sqlite3` — full reasoning-path traces of every run
+
+Because the sample server's tasks fail mostly on tool selection, the curated
+overlay typically flips several tasks from MISS to HIT — that delta is the
+whole point.
+
+**4. Use the curated view for real** — serve it to any MCP client:
+
+```sh
+uv run whetkit overlay --server examples/sample-server --plan .whetkit/curation-plan.yaml
+```
+
+Nothing about your origin server changes, ever. Delete the plan and you are
+back to the original world.
+
+## Pointing it at your own server
+
+- `--server` accepts a URL (streamable HTTP; `--http-mode stateless` for
+  2026-07-28-spec servers), a directory containing `server.json` or
+  `server.py`, or a `.py`/`.json` path directly.
+- Write tasks in YAML — format reference in
+  [docs/task-format.md](docs/task-format.md).
+- `--model` / `--judge-model` / `--optimizer-model` take
+  `provider:model_id`, e.g. `anthropic:claude-sonnet-5` or `openai:gpt-5.2`.
+  Keys come from `ANTHROPIC_API_KEY` / `OPENAI_API_KEY`.
+
+## Commands
+
+| Command | What it does |
+|---|---|
+| `whetkit inspect` | Tool inventory: names, params, description tokens, schema complexity. |
+| `whetkit run` | Agentic eval loop with real tool execution; scored results + traces. |
+| `whetkit curate` | Baseline → LLM-proposed overlay plan → curated eval → before/after report. |
+| `whetkit report` | Rebuild the HTML/JSON report from stored traces. |
+| `whetkit overlay` | Serve the curated view as a stdio MCP server. |
+
+## How scoring works
+
+- **Deterministic tool-match**: each task lists the expected tool calls
+  (with acceptable alternatives, optionally ordered). Order-tolerant by
+  default, `--match-mode exact` for strict grading. Reports
+  precision/recall, missing and extra calls.
+- **LLM-as-judge**: grades the agent's final answer against the task's
+  natural-language `success_criteria` with a strict calibrated prompt;
+  verdicts are cached in SQLite. `--judge auto|on|off`.
+- **Hit** = right tools *and* (when judged) task success. The headline
+  metric is the hit-rate across tasks.
+
+More docs: [docs/task-format.md](docs/task-format.md) ·
+[docs/curation.md](docs/curation.md) · [VERSIONS.md](VERSIONS.md) ·
+[MIGRATION.md](MIGRATION.md)
+
+## Development
+
+```sh
+uv sync
+uv run pytest        # 55+ tests, no API key needed (scripted fake provider)
+uv run ruff check .
+```
+
+Dependency versions are pinned exactly and documented with sources and check
+dates in [VERSIONS.md](VERSIONS.md). The MCP transport layer supports stdio,
+legacy stateful streamable-HTTP (2025 spec), and stateless streamable-HTTP
+(2026-07-28 spec); the SDK-facing code is isolated for the v1→v2 migration
+([MIGRATION.md](MIGRATION.md)).
+
+Scope note: whetkit is deliberately a local-first CLI. Hosting, dashboards,
+multi-tenancy, and security tooling are out of scope for Stage 1 — the
+architecture just leaves room for them.
+
+## License
+
+Apache-2.0 — see [LICENSE](LICENSE).

whetkit-0.1.0/README.md

@@ -0,0 +1,151 @@
+# whetkit
+
+**Measure — then improve — how well LLM agents pick and use the tools your MCP
+server exposes.**
+
+`whetkit` is a local-first CLI that runs an agent against your
+[MCP](https://modelcontextprotocol.io) server on a set of eval tasks, scores
+its **tool-selection hit-rate**, and then *curates* the tool set — renaming
+cryptic tools, rewriting vague descriptions, pruning noise, and merging
+duplicates — via a **reversible overlay proxy** that never modifies your
+server. It re-runs the eval through the overlay and hands you a before/after
+report.
+
+```text
+whetkit inspect  ──►  what does the agent actually see?
+whetkit run      ──►  how often does it pick the right tools?   (hit-rate)
+whetkit curate   ──►  fix the tool set, prove it helped          (before → after)
+```
+
+## Why tool curation matters
+
+Agents don't read your code — they read your tool names, descriptions, and
+schemas. A server that grew organically ends up with `data_query_1`,
+`proc_ord`, and `do_thing`: every one of them costs the model a guess, and
+every duplicate splits its attention. In practice a large share of agent
+failures on MCP servers are *tool-selection* failures — the model calls the
+wrong tool, loops through near-duplicates, or gives up — and they are fixable
+without touching a line of server code, because the fix is metadata.
+whetkit makes that loop measurable: score the failures, patch the metadata
+through an overlay, and show the hit-rate delta.
+
+## Install
+
+```sh
+uv tool install whetkit   # or: uvx whetkit / pipx install whetkit
+```
+
+(Releases are published to PyPI from tags — see [RELEASING.md](RELEASING.md).
+Until the first release, use the from-source quickstart below.)
+
+## Quickstart (5 minutes)
+
+Requires [uv](https://docs.astral.sh/uv/) and an Anthropic API key (or
+OpenAI — see `--model`). Python is pinned via `.python-version`; uv fetches
+it automatically.
+
+```sh
+git clone https://github.com/benlamlih/whetkit && cd whetkit
+uv sync
+export ANTHROPIC_API_KEY=sk-ant-...
+```
+
+**1. Inspect the bundled sample server** — a deliberately messy e-commerce
+server (14 tools: cryptic names, vague descriptions, duplicates, noise):
+
+```sh
+uv run whetkit inspect --server examples/sample-server
+```
+
+**2. Baseline eval** — run 5 tasks against it and score the hit-rate
+(deterministic tool-matching + LLM-judge on the final answers):
+
+```sh
+uv run whetkit run --server examples/sample-server --tasks examples/tasks
+```
+
+**3. Curate and prove it** — analyze the failures, generate a curation
+overlay, re-run the eval through it, and get the before/after:
+
+```sh
+uv run whetkit curate --server examples/sample-server --tasks examples/tasks
+```
+
+This writes:
+
+- `.whetkit/curation-plan.yaml` — the reviewable, hand-editable overlay plan
+- `.whetkit/report.html` — self-contained before/after report (open it in a browser)
+- `.whetkit/report.json` — the same data, machine-readable
+- `.whetkit/traces.sqlite3` — full reasoning-path traces of every run
+
+Because the sample server's tasks fail mostly on tool selection, the curated
+overlay typically flips several tasks from MISS to HIT — that delta is the
+whole point.
+
+**4. Use the curated view for real** — serve it to any MCP client:
+
+```sh
+uv run whetkit overlay --server examples/sample-server --plan .whetkit/curation-plan.yaml
+```
+
+Nothing about your origin server changes, ever. Delete the plan and you are
+back to the original world.
+
+## Pointing it at your own server
+
+- `--server` accepts a URL (streamable HTTP; `--http-mode stateless` for
+  2026-07-28-spec servers), a directory containing `server.json` or
+  `server.py`, or a `.py`/`.json` path directly.
+- Write tasks in YAML — format reference in
+  [docs/task-format.md](docs/task-format.md).
+- `--model` / `--judge-model` / `--optimizer-model` take
+  `provider:model_id`, e.g. `anthropic:claude-sonnet-5` or `openai:gpt-5.2`.
+  Keys come from `ANTHROPIC_API_KEY` / `OPENAI_API_KEY`.
+
+## Commands
+
+| Command | What it does |
+|---|---|
+| `whetkit inspect` | Tool inventory: names, params, description tokens, schema complexity. |
+| `whetkit run` | Agentic eval loop with real tool execution; scored results + traces. |
+| `whetkit curate` | Baseline → LLM-proposed overlay plan → curated eval → before/after report. |
+| `whetkit report` | Rebuild the HTML/JSON report from stored traces. |
+| `whetkit overlay` | Serve the curated view as a stdio MCP server. |
+
+## How scoring works
+
+- **Deterministic tool-match**: each task lists the expected tool calls
+  (with acceptable alternatives, optionally ordered). Order-tolerant by
+  default, `--match-mode exact` for strict grading. Reports
+  precision/recall, missing and extra calls.
+- **LLM-as-judge**: grades the agent's final answer against the task's
+  natural-language `success_criteria` with a strict calibrated prompt;
+  verdicts are cached in SQLite. `--judge auto|on|off`.
+- **Hit** = right tools *and* (when judged) task success. The headline
+  metric is the hit-rate across tasks.
+
+More docs: [docs/task-format.md](docs/task-format.md) ·
+[docs/curation.md](docs/curation.md) · [VERSIONS.md](VERSIONS.md) ·
+[MIGRATION.md](MIGRATION.md)
+
+## Development
+
+```sh
+uv sync
+uv run pytest        # 55+ tests, no API key needed (scripted fake provider)
+uv run ruff check .
+```
+
+Dependency versions are pinned exactly and documented with sources and check
+dates in [VERSIONS.md](VERSIONS.md). The MCP transport layer supports stdio,
+legacy stateful streamable-HTTP (2025 spec), and stateless streamable-HTTP
+(2026-07-28 spec); the SDK-facing code is isolated for the v1→v2 migration
+([MIGRATION.md](MIGRATION.md)).
+
+Scope note: whetkit is deliberately a local-first CLI. Hosting, dashboards,
+multi-tenancy, and security tooling are out of scope for Stage 1 — the
+architecture just leaves room for them.
+
+## License
+
+Apache-2.0 — see [LICENSE](LICENSE).

whetkit-0.1.0/pyproject.toml

@@ -0,0 +1,75 @@
+[project]
+name = "whetkit"
+version = "0.1.0"
+description = "Measure and improve how well LLM agents select and use the tools exposed by an MCP server"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Mohammed Benlamlih" }]
+requires-python = ">=3.13"
+keywords = [
+    "mcp",
+    "model-context-protocol",
+    "llm",
+    "agents",
+    "evals",
+    "tool-use",
+    "tool-selection",
+    "benchmark",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Software Development :: Quality Assurance",
+    "Topic :: Software Development :: Testing",
+    "Typing :: Typed",
+]
+dependencies = [
+    "mcp==1.28.1",
+    "anthropic==0.116.0",
+    "openai==2.44.0",
+    "pydantic==2.13.4",
+    "pyyaml==6.0.3",
+    "typer==0.26.8",
+]
+
+[project.urls]
+Homepage = "https://github.com/benlamlih/whetkit"
+Repository = "https://github.com/benlamlih/whetkit"
+Issues = "https://github.com/benlamlih/whetkit/issues"
+Documentation = "https://github.com/benlamlih/whetkit#readme"
+Changelog = "https://github.com/benlamlih/whetkit/releases"
+
+[project.scripts]
+whetkit = "whetkit.cli:app"
+
+[dependency-groups]
+dev = [
+    "pytest==9.1.1",
+    "pytest-asyncio==1.4.0",
+    "ruff==0.15.20",
+    "pre-commit==4.6.0",
+]
+
+[build-system]
+requires = ["uv_build>=0.8.17,<0.9.0"]
+build-backend = "uv_build"
+
+[tool.ruff]
+line-length = 100
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM"]
+
+[tool.ruff.lint.per-file-ignores]
+# HTML template module: markup lines stay readable at their natural length
+"src/whetkit/report/html.py" = ["E501"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

whetkit-0.1.0/src/whetkit/__init__.py

@@ -0,0 +1,3 @@
+"""whetkit: measure and improve LLM agent tool selection on MCP servers."""
+
+__version__ = "0.1.0"