yacht-eval 0.2.0__tar.gz

yacht_eval-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+Apache License
+Version 2.0, January 2004
+https://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 2026 codyw912
+
+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
+
+    https://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.

yacht_eval-0.2.0/PKG-INFO

@@ -0,0 +1,196 @@
+Metadata-Version: 2.4
+Name: yacht-eval
+Version: 0.2.0
+Summary: Yet Another Coding Harness Testbed
+Author: codyw912
+Author-email: codyw912 <32690983+codyw912@users.noreply.github.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Dist: datasets>=4.8.5
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+
+# YACHT
+
+Yet Another Coding Harness Testbed.
+
+YACHT is an evaluation control plane for agentic coding systems. It runs the
+same coding course across different agents, models, tools, prompts, memory
+systems, and runtime environments, then records the evidence needed to decide
+whether a change actually helped.
+
+The goal is not only to produce benchmark scores. A useful YACHT run should
+also answer:
+
+- Did the setup solve the task?
+- Was the runtime available, isolated, and configured as claimed?
+- Which tools were actually used?
+- How many tokens did the run spend?
+- What did it cost?
+- How long did it take?
+- Which artifacts prove the result?
+
+YACHT is designed as open-source infrastructure for reproducible, inspectable
+coding-agent evaluation.
+
+## Current Status
+
+YACHT now has a real end-to-end benchmark smoke path:
+
+- containerized Pi baseline vs containerized Pi+fff
+- explicit secret injection
+- runtime and rigging preflight
+- SWE-bench Lite task context loading
+- per-task repository checkout at the benchmark base commit
+- agent task attempts and transcripts
+- candidate patch extraction
+- native SWE-bench Docker grading
+- benchmark scorecards with outcome, token, cost, duration, and tool-use metrics
+
+The first verified real benchmark smoke used `django__django-11099`; both
+baseline and fff vessels resolved the task. A two-task smoke using
+`django__django-11099` and `django__django-11179` has also completed end to
+end. That is a foundation, not a final tool. The next phase is making this
+easier for humans to run, inspect, and extend.
+
+## Core Concepts
+
+| Concept | Meaning |
+| ------- | ------- |
+| Course | A benchmark suite, task set, or evaluation route. |
+| Vessel | An agent, model, runtime, or full coding setup being evaluated. |
+| Rigging | Tools, prompts, skills, MCP servers, memory systems, and policies added to a vessel. |
+| Runtime | The reproducible environment used to run a vessel. |
+| Preflight | Machine evidence that a runtime and its rigging are available, configured, and isolated before spending task tokens. |
+| Wake | The artifacts left by a run: transcripts, metrics, logs, tool calls, patches, reports. |
+| Logbook | The persisted directory containing a run's wake and scorecards. |
+| Scorecard | The final comparison view across vessels. |
+
+The nautical vocabulary is part of the project identity, but the artifacts stay
+plain JSON so other tools can consume them.
+
+## First Real Benchmark
+
+Prerequisites:
+
+- Python 3.12 or newer available to `uv`
+- `uv`
+- Git on `PATH`
+- Docker installed, running, and usable by the current user
+- network access for the first `uv` dependency sync, SWE-bench metadata, and
+  Docker image build
+- no manual SWE-bench install: uv resolves the `swebench` harness on demand
+  for native benchmark launches, and `yacht doctor` performs and verifies the
+  first resolution
+- an Anthropic API key exported as `ANTHROPIC_API_KEY`
+- the repo-local Pi runtime image built with the command below
+
+Build the Pi runtime image:
+
+```sh
+docker build -t yacht/pi-agent-runtime:pi-0.74.0 containers/pi-agent-runtime
+```
+
+Run the benchmark smoke:
+
+```sh
+LOGBOOK=/private/tmp/yacht-real-benchmark-$(date +%Y%m%d-%H%M%S)
+
+uv run yacht doctor examples/container-pi-fff-real-benchmark-smoke.toml
+
+uv run yacht run examples/container-pi-fff-real-benchmark-smoke.toml \
+  --logbook "$LOGBOOK" \
+  --workspace . \
+  --secret anthropic=@env:ANTHROPIC_API_KEY
+
+uv run yacht status --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK" --vessel pi-container-fff
+```
+
+The default smoke config runs one SWE-bench Lite instance to keep iteration
+cheap. For a slightly broader two-instance check, use
+`examples/container-pi-fff-real-benchmark-small.toml` with the same commands.
+
+Fish shell:
+
+```fish
+set -x LOGBOOK /private/tmp/yacht-real-benchmark-(date +%Y%m%d-%H%M%S)
+
+uv run yacht doctor examples/container-pi-fff-real-benchmark-smoke.toml
+
+uv run yacht run examples/container-pi-fff-real-benchmark-smoke.toml \
+  --logbook "$LOGBOOK" \
+  --workspace . \
+  --secret anthropic=@env:ANTHROPIC_API_KEY
+
+uv run yacht status --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK"
+```
+
+The status report is the first thing to inspect after a run. It shows which
+benchmark artifacts exist, what is missing, and the next recommended command.
+The benchmark report then summarizes benchmark outcome, agent usage metrics,
+notable deltas, per-task outcomes, per-task usage, and the relevant per-vessel
+artifact paths. Use `--vessel` and `--task` to narrow the detailed sections
+when inspecting a specific run. After a scorecard exists, `yacht status`
+recommends a filtered inspection command for the first challenger/task outcome.
+For example:
+
+```text
+Benchmark scorecard: container-pi-fff-real-benchmark-small / swe-bench-lite
+Status: complete
+Comparisons: 1 | Vessels: 2 | Measured: 2 | Missing: 0
+Usage: Attempts: 4 | Failed: 0 | Tool calls: 15 | Tokens: 63084 | Cost: 0.020688 | Duration: 210.332s
+Artifacts: logbook=/private/tmp/yacht-real-benchmark-... | scorecard=/private/tmp/yacht-real-benchmark-.../benchmark-scorecard.json | attempts=/private/tmp/yacht-real-benchmark-.../task-attempt-scorecard.json | launch=/private/tmp/yacht-real-benchmark-.../benchmark-launch-result.json | grading=/private/tmp/yacht-real-benchmark-.../benchmark-grading-collection.json
+
+Notable deltas:
+container-pi-vs-pi-fff-benchmark-small: pi-container-fff vs pi-container-baseline | resolved +0 | rate +0.000 | tokens +10988 | cost +0.001650 | duration +7.792s | tool_calls +3
+
+comparison | baseline | challenger | resolved_delta | rate_delta | measured | missing | eligible | preflight
+container-pi-vs-pi-fff-benchmark-small | pi-container-baseline | pi-container-fff | +0 | +0.000 | 2/2 | 0 | 2 | preflight-passed:2
+
+Agent usage by task:
+comparison | vessel | task | tools | tokens | cost | duration | attempt_artifact
+container-pi-vs-pi-fff-benchmark-small | pi-container-fff | django__django-11179 | fffind:1, read:1, bash:1, edit:1 | 25492 | 0.006795 | 75.793s | /private/tmp/yacht-real-benchmark-.../task-attempts/.../django__django-11179.json
+```
+
+## Development Smoke
+
+For a no-token local harness check:
+
+```sh
+uv run yacht validate examples/local-agent-preflight-smoke.toml
+uv run yacht run examples/local-agent-preflight-smoke.toml --logbook logbook
+uv run yacht status --logbook logbook
+uv run yacht report --logbook logbook
+```
+
+This validates the control-plane path without Pi, SWE-bench, Docker grading, or
+provider credentials.
+
+## Documentation
+
+- [Project vision](docs/project/vision.md)
+- [Roadmap](docs/project/roadmap.md)
+- [Audit-backed plan](docs/project/audit-backed-plan.md)
+- [Codebase structure](docs/project/codebase-structure.md)
+- [Command reference](docs/reference/commands.md)
+- [Release checklist](docs/reference/release.md)
+- [Schema contract](docs/reference/schemas.md)
+- [Architecture decisions](docs/adr/)
+- [Changelog](CHANGELOG.md)
+
+## License
+
+YACHT is licensed under the [Apache License 2.0](LICENSE).
+
+## Design Principles
+
+- Prefer reproducible, inspectable evidence over agent attestation.
+- Keep runtime provisioning separate from benchmark task grading.
+- Make secrets explicit and never copy user-home auth state implicitly.
+- Treat benchmarks, smoke tests, and future evaluators as adapters.
+- Keep public artifacts language-neutral and stable enough for other tools to
+  consume.
+- Report success together with cost, tokens, time, tool use, and failure modes.

yacht_eval-0.2.0/README.md

@@ -0,0 +1,184 @@
+# YACHT
+
+Yet Another Coding Harness Testbed.
+
+YACHT is an evaluation control plane for agentic coding systems. It runs the
+same coding course across different agents, models, tools, prompts, memory
+systems, and runtime environments, then records the evidence needed to decide
+whether a change actually helped.
+
+The goal is not only to produce benchmark scores. A useful YACHT run should
+also answer:
+
+- Did the setup solve the task?
+- Was the runtime available, isolated, and configured as claimed?
+- Which tools were actually used?
+- How many tokens did the run spend?
+- What did it cost?
+- How long did it take?
+- Which artifacts prove the result?
+
+YACHT is designed as open-source infrastructure for reproducible, inspectable
+coding-agent evaluation.
+
+## Current Status
+
+YACHT now has a real end-to-end benchmark smoke path:
+
+- containerized Pi baseline vs containerized Pi+fff
+- explicit secret injection
+- runtime and rigging preflight
+- SWE-bench Lite task context loading
+- per-task repository checkout at the benchmark base commit
+- agent task attempts and transcripts
+- candidate patch extraction
+- native SWE-bench Docker grading
+- benchmark scorecards with outcome, token, cost, duration, and tool-use metrics
+
+The first verified real benchmark smoke used `django__django-11099`; both
+baseline and fff vessels resolved the task. A two-task smoke using
+`django__django-11099` and `django__django-11179` has also completed end to
+end. That is a foundation, not a final tool. The next phase is making this
+easier for humans to run, inspect, and extend.
+
+## Core Concepts
+
+| Concept | Meaning |
+| ------- | ------- |
+| Course | A benchmark suite, task set, or evaluation route. |
+| Vessel | An agent, model, runtime, or full coding setup being evaluated. |
+| Rigging | Tools, prompts, skills, MCP servers, memory systems, and policies added to a vessel. |
+| Runtime | The reproducible environment used to run a vessel. |
+| Preflight | Machine evidence that a runtime and its rigging are available, configured, and isolated before spending task tokens. |
+| Wake | The artifacts left by a run: transcripts, metrics, logs, tool calls, patches, reports. |
+| Logbook | The persisted directory containing a run's wake and scorecards. |
+| Scorecard | The final comparison view across vessels. |
+
+The nautical vocabulary is part of the project identity, but the artifacts stay
+plain JSON so other tools can consume them.
+
+## First Real Benchmark
+
+Prerequisites:
+
+- Python 3.12 or newer available to `uv`
+- `uv`
+- Git on `PATH`
+- Docker installed, running, and usable by the current user
+- network access for the first `uv` dependency sync, SWE-bench metadata, and
+  Docker image build
+- no manual SWE-bench install: uv resolves the `swebench` harness on demand
+  for native benchmark launches, and `yacht doctor` performs and verifies the
+  first resolution
+- an Anthropic API key exported as `ANTHROPIC_API_KEY`
+- the repo-local Pi runtime image built with the command below
+
+Build the Pi runtime image:
+
+```sh
+docker build -t yacht/pi-agent-runtime:pi-0.74.0 containers/pi-agent-runtime
+```
+
+Run the benchmark smoke:
+
+```sh
+LOGBOOK=/private/tmp/yacht-real-benchmark-$(date +%Y%m%d-%H%M%S)
+
+uv run yacht doctor examples/container-pi-fff-real-benchmark-smoke.toml
+
+uv run yacht run examples/container-pi-fff-real-benchmark-smoke.toml \
+  --logbook "$LOGBOOK" \
+  --workspace . \
+  --secret anthropic=@env:ANTHROPIC_API_KEY
+
+uv run yacht status --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK" --vessel pi-container-fff
+```
+
+The default smoke config runs one SWE-bench Lite instance to keep iteration
+cheap. For a slightly broader two-instance check, use
+`examples/container-pi-fff-real-benchmark-small.toml` with the same commands.
+
+Fish shell:
+
+```fish
+set -x LOGBOOK /private/tmp/yacht-real-benchmark-(date +%Y%m%d-%H%M%S)
+
+uv run yacht doctor examples/container-pi-fff-real-benchmark-smoke.toml
+
+uv run yacht run examples/container-pi-fff-real-benchmark-smoke.toml \
+  --logbook "$LOGBOOK" \
+  --workspace . \
+  --secret anthropic=@env:ANTHROPIC_API_KEY
+
+uv run yacht status --logbook "$LOGBOOK"
+uv run yacht report --logbook "$LOGBOOK"
+```
+
+The status report is the first thing to inspect after a run. It shows which
+benchmark artifacts exist, what is missing, and the next recommended command.
+The benchmark report then summarizes benchmark outcome, agent usage metrics,
+notable deltas, per-task outcomes, per-task usage, and the relevant per-vessel
+artifact paths. Use `--vessel` and `--task` to narrow the detailed sections
+when inspecting a specific run. After a scorecard exists, `yacht status`
+recommends a filtered inspection command for the first challenger/task outcome.
+For example:
+
+```text
+Benchmark scorecard: container-pi-fff-real-benchmark-small / swe-bench-lite
+Status: complete
+Comparisons: 1 | Vessels: 2 | Measured: 2 | Missing: 0
+Usage: Attempts: 4 | Failed: 0 | Tool calls: 15 | Tokens: 63084 | Cost: 0.020688 | Duration: 210.332s
+Artifacts: logbook=/private/tmp/yacht-real-benchmark-... | scorecard=/private/tmp/yacht-real-benchmark-.../benchmark-scorecard.json | attempts=/private/tmp/yacht-real-benchmark-.../task-attempt-scorecard.json | launch=/private/tmp/yacht-real-benchmark-.../benchmark-launch-result.json | grading=/private/tmp/yacht-real-benchmark-.../benchmark-grading-collection.json
+
+Notable deltas:
+container-pi-vs-pi-fff-benchmark-small: pi-container-fff vs pi-container-baseline | resolved +0 | rate +0.000 | tokens +10988 | cost +0.001650 | duration +7.792s | tool_calls +3
+
+comparison | baseline | challenger | resolved_delta | rate_delta | measured | missing | eligible | preflight
+container-pi-vs-pi-fff-benchmark-small | pi-container-baseline | pi-container-fff | +0 | +0.000 | 2/2 | 0 | 2 | preflight-passed:2
+
+Agent usage by task:
+comparison | vessel | task | tools | tokens | cost | duration | attempt_artifact
+container-pi-vs-pi-fff-benchmark-small | pi-container-fff | django__django-11179 | fffind:1, read:1, bash:1, edit:1 | 25492 | 0.006795 | 75.793s | /private/tmp/yacht-real-benchmark-.../task-attempts/.../django__django-11179.json
+```
+
+## Development Smoke
+
+For a no-token local harness check:
+
+```sh
+uv run yacht validate examples/local-agent-preflight-smoke.toml
+uv run yacht run examples/local-agent-preflight-smoke.toml --logbook logbook
+uv run yacht status --logbook logbook
+uv run yacht report --logbook logbook
+```
+
+This validates the control-plane path without Pi, SWE-bench, Docker grading, or
+provider credentials.
+
+## Documentation
+
+- [Project vision](docs/project/vision.md)
+- [Roadmap](docs/project/roadmap.md)
+- [Audit-backed plan](docs/project/audit-backed-plan.md)
+- [Codebase structure](docs/project/codebase-structure.md)
+- [Command reference](docs/reference/commands.md)
+- [Release checklist](docs/reference/release.md)
+- [Schema contract](docs/reference/schemas.md)
+- [Architecture decisions](docs/adr/)
+- [Changelog](CHANGELOG.md)
+
+## License
+
+YACHT is licensed under the [Apache License 2.0](LICENSE).
+
+## Design Principles
+
+- Prefer reproducible, inspectable evidence over agent attestation.
+- Keep runtime provisioning separate from benchmark task grading.
+- Make secrets explicit and never copy user-home auth state implicitly.
+- Treat benchmarks, smoke tests, and future evaluators as adapters.
+- Keep public artifacts language-neutral and stable enough for other tools to
+  consume.
+- Report success together with cost, tokens, time, tool use, and failure modes.

yacht_eval-0.2.0/pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "yacht-eval"
+version = "0.2.0"
+description = "Yet Another Coding Harness Testbed"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [
+    { name = "codyw912", email = "32690983+codyw912@users.noreply.github.com" }
+]
+requires-python = ">=3.12"
+dependencies = [
+    "datasets>=4.8.5",
+]
+
+[project.scripts]
+yacht = "yacht.cli:main"
+
+[tool.ruff]
+src = ["src"]
+
+[build-system]
+requires = ["uv_build>=0.11.4,<0.12.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-name = "yacht"
+
+[dependency-groups]
+dev = [
+    "coverage>=7.15.1",
+    "ruff>=0.15.21",
+]

yacht_eval-0.2.0/src/yacht/__init__.py

@@ -0,0 +1,3 @@
+"""YACHT: Yet Another Coding Harness Testbed."""
+
+__version__ = "0.2.0"

yacht_eval-0.2.0/src/yacht/cli/__init__.py

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+from yacht.cli.app import build_parser, main
+
+__all__ = ["build_parser", "main"]

yacht_eval-0.2.0/src/yacht/cli/app.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+
+import argparse
+from typing import Sequence
+
+from yacht.cli.commands import COMMAND_MODULES
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="yacht",
+        description="Run reproducible agentic coding harness regattas.",
+    )
+    subcommands = parser.add_subparsers(dest="command", required=True)
+    for module in COMMAND_MODULES:
+        module.register(subcommands)
+    return parser
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = build_parser()
+    args = parser.parse_args(argv)
+    return args.handler(args)

yacht_eval-0.2.0/src/yacht/cli/commands/__init__.py

@@ -0,0 +1,13 @@
+from __future__ import annotations
+
+from yacht.cli.commands import doctor
+from yacht.cli.commands import inspect
+from yacht.cli.commands import internals
+from yacht.cli.commands import regatta
+
+COMMAND_MODULES = (
+    doctor,
+    regatta,
+    inspect,
+    internals,
+)