dcp-harness 0.1.0__tar.gz

dcp_harness-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.
+

dcp_harness-0.1.0/MANIFEST.in

@@ -0,0 +1,10 @@
+include README.md
+include LICENSE
+recursive-include src/dcp_harness *.py py.typed
+recursive-include tests *.py
+prune .pytest_cache
+prune build
+prune dist
+global-exclude *.py[cod]
+global-exclude __pycache__
+

dcp_harness-0.1.0/PKG-INFO

@@ -0,0 +1,106 @@
+Metadata-Version: 2.4
+Name: dcp-harness
+Version: 0.1.0
+Summary: Controlled evidence-producing harness for the Discovery Certification Protocol
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/cxcscmu/Discovery-Certification-Protocol
+Project-URL: Issues, https://github.com/cxcscmu/Discovery-Certification-Protocol/issues
+Classifier: Development Status :: 3 - Alpha
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: dcp-audit==0.4.2
+Provides-Extra: dev
+Requires-Dist: pytest<9,>=8; extra == "dev"
+Requires-Dist: ruff==0.15.20; extra == "dev"
+Requires-Dist: build<2,>=1.2; extra == "dev"
+Dynamic: license-file
+
+# DCP Harness
+
+`dcp-harness` is a lightweight evidence-producing shell for Auto Research. It
+wraps Claude Code CLI, controls the agent's external actions, records the run,
+performs the registered DCP ablations, and writes a Bundle that anyone can
+check offline with `dcp-audit`.
+
+The wrapper gives the agent only file tools. Claude's shell, Web, MCP, and
+subagent tools are disabled. The only external action is a strict JSON file.
+The harness can execute a task experiment or fetch an allowlisted HTTPS URL,
+then records the request, raw response, model-visible text, workspace change,
+model identity, and receipt hashes before starting a fresh model session.
+Only the main run may use live Web access. Challengers and Gate 3 branches get
+an exact replay of URLs observed by the main run.
+
+A small task adapter supplies task semantics, private evaluation, baseline,
+and truthful or neutral experiment feedback. Private scores are opened only
+after every candidate in a phase has committed. The adapter registers all
+thresholds and sample counts before the main run. It also supplies SHA-256
+digests for the private verifier, held-out units, baseline policy, and feedback
+policies; these materials are rechecked before every phase. The harness fills mechanical
+evidence from the frozen ledger, invokes the unchanged `dcp-audit` kernel, and
+immediately checks that the resulting Bundle replays exactly.
+
+## Quickstart
+
+```bash
+python -m pip install dcp-harness
+dcp-harness init my-audit
+# Complete task_adapter.py and configure the model and Docker image first.
+dcp-harness doctor --config my-audit/dcp-harness.json
+dcp-harness run --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp verify my-audit/run-001/bundle
+```
+
+`init --force` adds missing starter files without overwriting existing files.
+The commands can also be run separately. Resuming Gate 3 reuses its existing
+receipts and completed branches. An interrupted model call with no committed
+turn record remains unresolved rather than being silently retried.
+
+```bash
+dcp-harness capture   --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness challenge --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness gate3     --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness finalize  --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness status    --config my-audit/dcp-harness.json --run my-audit/run-001
+```
+
+## Trust boundary
+
+The harness owns agent execution, action mediation, Web capture and replay,
+randomization, checkpoints, receipts, and append-only ledgers. The Python task
+adapter is trusted only for the parts that necessarily depend on the task. It
+prepares public files, runs the private verifier, and defines truthful and
+neutral observations. `assemble_evidence()` derives scores, hashes, counts,
+and branch records mechanically. Its `AuditAttestations` input contains the
+small set of task-specific judgments that cannot be inferred from bytes. Every
+attestation defaults to false.
+
+Built-in positive controls check file delivery and response formatting by
+copying a canary. They do not independently establish the proposal's broader
+Memory, Web, and known-component calibration coverage. Assess that coverage
+separately when approving a new task's audit.
+
+The model API connection is infrastructure transport, not a research Web
+channel. In container mode the agent has no tool capable of starting an
+arbitrary network request. A task adapter that talks to another service must
+treat that service as a registered experiment and return its observation
+through the audited action channel.
+
+## Current scope
+
+The alpha supports one local auditor, Claude Code CLI, Docker isolation,
+allowlisted HTTPS capture, exact observed-URL replay, Gate 2 challenges, Gate 3
+paired feedback and sham branches, pre-action infrastructure replacement,
+resumable phases, and deterministic local Bundles. Host mode is available for
+development but cannot attest private isolation. Local Bundles always retain
+`formal_certificate_issued=false`; formal countersigning belongs to a future
+external registry rather than this package.
+
+See the repository [usage guide](../../README.md#run-a-prospective-audit) for
+the complete CLI and Python examples.
+
+Licensed under Apache-2.0.

dcp_harness-0.1.0/README.md

@@ -0,0 +1,84 @@
+# DCP Harness
+
+`dcp-harness` is a lightweight evidence-producing shell for Auto Research. It
+wraps Claude Code CLI, controls the agent's external actions, records the run,
+performs the registered DCP ablations, and writes a Bundle that anyone can
+check offline with `dcp-audit`.
+
+The wrapper gives the agent only file tools. Claude's shell, Web, MCP, and
+subagent tools are disabled. The only external action is a strict JSON file.
+The harness can execute a task experiment or fetch an allowlisted HTTPS URL,
+then records the request, raw response, model-visible text, workspace change,
+model identity, and receipt hashes before starting a fresh model session.
+Only the main run may use live Web access. Challengers and Gate 3 branches get
+an exact replay of URLs observed by the main run.
+
+A small task adapter supplies task semantics, private evaluation, baseline,
+and truthful or neutral experiment feedback. Private scores are opened only
+after every candidate in a phase has committed. The adapter registers all
+thresholds and sample counts before the main run. It also supplies SHA-256
+digests for the private verifier, held-out units, baseline policy, and feedback
+policies; these materials are rechecked before every phase. The harness fills mechanical
+evidence from the frozen ledger, invokes the unchanged `dcp-audit` kernel, and
+immediately checks that the resulting Bundle replays exactly.
+
+## Quickstart
+
+```bash
+python -m pip install dcp-harness
+dcp-harness init my-audit
+# Complete task_adapter.py and configure the model and Docker image first.
+dcp-harness doctor --config my-audit/dcp-harness.json
+dcp-harness run --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp verify my-audit/run-001/bundle
+```
+
+`init --force` adds missing starter files without overwriting existing files.
+The commands can also be run separately. Resuming Gate 3 reuses its existing
+receipts and completed branches. An interrupted model call with no committed
+turn record remains unresolved rather than being silently retried.
+
+```bash
+dcp-harness capture   --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness challenge --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness gate3     --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness finalize  --config my-audit/dcp-harness.json --run my-audit/run-001
+dcp-harness status    --config my-audit/dcp-harness.json --run my-audit/run-001
+```
+
+## Trust boundary
+
+The harness owns agent execution, action mediation, Web capture and replay,
+randomization, checkpoints, receipts, and append-only ledgers. The Python task
+adapter is trusted only for the parts that necessarily depend on the task. It
+prepares public files, runs the private verifier, and defines truthful and
+neutral observations. `assemble_evidence()` derives scores, hashes, counts,
+and branch records mechanically. Its `AuditAttestations` input contains the
+small set of task-specific judgments that cannot be inferred from bytes. Every
+attestation defaults to false.
+
+Built-in positive controls check file delivery and response formatting by
+copying a canary. They do not independently establish the proposal's broader
+Memory, Web, and known-component calibration coverage. Assess that coverage
+separately when approving a new task's audit.
+
+The model API connection is infrastructure transport, not a research Web
+channel. In container mode the agent has no tool capable of starting an
+arbitrary network request. A task adapter that talks to another service must
+treat that service as a registered experiment and return its observation
+through the audited action channel.
+
+## Current scope
+
+The alpha supports one local auditor, Claude Code CLI, Docker isolation,
+allowlisted HTTPS capture, exact observed-URL replay, Gate 2 challenges, Gate 3
+paired feedback and sham branches, pre-action infrastructure replacement,
+resumable phases, and deterministic local Bundles. Host mode is available for
+development but cannot attest private isolation. Local Bundles always retain
+`formal_certificate_issued=false`; formal countersigning belongs to a future
+external registry rather than this package.
+
+See the repository [usage guide](../../README.md#run-a-prospective-audit) for
+the complete CLI and Python examples.
+
+Licensed under Apache-2.0.

dcp_harness-0.1.0/pyproject.toml

@@ -0,0 +1,44 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dcp-harness"
+version = "0.1.0"
+description = "Controlled evidence-producing harness for the Discovery Certification Protocol"
+readme = { file = "README.md", content-type = "text/markdown" }
+requires-python = ">=3.11"
+license = "Apache-2.0"
+dependencies = ["dcp-audit==0.4.2"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+]
+
+[project.urls]
+Repository = "https://github.com/cxcscmu/Discovery-Certification-Protocol"
+Issues = "https://github.com/cxcscmu/Discovery-Certification-Protocol/issues"
+
+[project.optional-dependencies]
+dev = ["pytest>=8,<9", "ruff==0.15.20", "build>=1.2,<2"]
+
+[project.scripts]
+dcp-harness = "dcp_harness.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+packages = ["dcp_harness"]
+include-package-data = true
+
+[tool.setuptools.package-data]
+dcp_harness = ["py.typed"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 88
+target-version = "py311"

dcp_harness-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dcp_harness-0.1.0/src/dcp_harness/__init__.py

@@ -0,0 +1,33 @@
+"""Controlled evidence production for DCP audits."""
+
+from dcp_harness.adapter import (
+    AuditMaterials,
+    BaseTaskAdapter,
+    EpisodeContext,
+    EpisodeEvaluation,
+    EvidencePackage,
+    Phase,
+    RegistrationContext,
+    RunView,
+)
+from dcp_harness.config import HarnessConfig, load_config
+from dcp_harness.evidence import AuditAttestations, assemble_evidence
+from dcp_harness.runtime import Harness
+
+__all__ = [
+    "AuditMaterials",
+    "BaseTaskAdapter",
+    "AuditAttestations",
+    "EpisodeContext",
+    "EpisodeEvaluation",
+    "EvidencePackage",
+    "Harness",
+    "HarnessConfig",
+    "Phase",
+    "RegistrationContext",
+    "RunView",
+    "assemble_evidence",
+    "load_config",
+]
+
+__version__ = "0.1.0"

dcp_harness-0.1.0/src/dcp_harness/__main__.py

@@ -0,0 +1,4 @@
+from dcp_harness.cli import main
+
+raise SystemExit(main())
+

dcp_harness-0.1.0/src/dcp_harness/actions.py

@@ -0,0 +1,85 @@
+"""The only audited action channel exposed to the research agent."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any
+
+from dcp_harness.util import HarnessError, load_json_object, require_keys
+
+
+ACTION_SCHEMA = "dcp_action_v1"
+ACTION_PATH = Path(".dcp/action.json")
+OBSERVATION_PATH = Path(".dcp/observation.json")
+MAX_ACTION_BYTES = 128 * 1024
+
+
+@dataclass(frozen=True)
+class Action:
+    kind: str
+    payload: dict[str, Any]
+    raw: dict[str, Any]
+
+
+def instructions(*, live_web: bool, replay_web: bool) -> str:
+    web_text = (
+        "Web requests are available through the audited action channel."
+        if live_web
+        else "Only exact replay of URLs in WEB_PRIVILEGED.json is available."
+        if replay_web
+        else "No Web requests are available in this episode."
+    )
+    return f"""# DCP audited action channel
+
+Work only inside this workspace. Bash, direct Web tools, and subagents are not
+part of the registered interface. {web_text}
+
+When you need one external action, write `.dcp/action.json` with exactly one of
+these strict JSON objects and end the session.
+
+```json
+{{"schema":"{ACTION_SCHEMA}","action":"web_fetch","payload":{{"schema":"dcp_web_request_v1","requests":[{{"request_id":"doc-1","query":"what you seek","url":"https://allowed.example/page"}}]}}}}
+```
+
+```json
+{{"schema":"{ACTION_SCHEMA}","action":"experiment","payload":{{"task-defined":"request"}}}}
+```
+
+When the final artifact has been committed to the path required by the task,
+write the following object and end the session.
+
+```json
+{{"schema":"{ACTION_SCHEMA}","action":"finish","payload":{{}}}}
+```
+
+The next isolated session will receive `.dcp/observation.json`. One session may
+commit only one action. Private evaluation results are never returned here.
+"""
+
+
+def read_action(workspace: Path) -> Action:
+    path = workspace / ACTION_PATH
+    if not path.is_file() or path.is_symlink():
+        raise HarnessError("agent did not commit a regular .dcp/action.json")
+    if path.stat().st_size > MAX_ACTION_BYTES:
+        raise HarnessError("agent action exceeds the 128 KiB limit")
+    document = load_json_object(path)
+    require_keys(
+        document,
+        allowed={"schema", "action", "payload"},
+        required={"schema", "action", "payload"},
+        label="agent action",
+    )
+    if document["schema"] != ACTION_SCHEMA:
+        raise HarnessError(f"agent action schema must be {ACTION_SCHEMA!r}")
+    kind = document["action"]
+    if kind not in {"web_fetch", "experiment", "finish"}:
+        raise HarnessError("agent action must be web_fetch|experiment|finish")
+    payload = document["payload"]
+    if not isinstance(payload, dict):
+        raise HarnessError("agent action payload must be a JSON object")
+    if kind == "finish" and payload:
+        raise HarnessError("finish action payload must be empty")
+    return Action(kind=kind, payload=dict(payload), raw=document)
+