agentic-dev-loop 0.15.7__tar.gz → 1.0.0b1__tar.gz

agentic_dev_loop-1.0.0b1/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.4
+Name: agentic-dev-loop
+Version: 1.0.0b1
+Summary: Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
+Author: Luke Wilson
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/lukedawilson/agentic-dev-loop
+Project-URL: Documentation, https://lukedawilson.github.io/agentic-dev-loop/
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Security
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: openhands-sdk~=1.17.0
+Requires-Dist: openhands-tools~=1.17.0
+Requires-Dist: browser-use==0.11.13
+Requires-Dist: pillow>=13.0.0
+Requires-Dist: agent-client-protocol<1.0.0
+Requires-Dist: langgraph>=1.2
+Requires-Dist: langgraph-checkpoint-sqlite>=3.0
+Requires-Dist: msgpack>=1.0
+Requires-Dist: filelock>=4.2.1
+Requires-Dist: pyasn1>=0.6.5
+Requires-Dist: pypdf>=6.21.4
+Provides-Extra: dev
+Requires-Dist: hypothesis>=6.0; extra == "dev"
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pip-audit>=2.0; extra == "dev"
+Requires-Dist: pre-commit>=3.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material~=9.6; extra == "docs"
+Requires-Dist: pymdown-extensions~=10.0; extra == "docs"
+Dynamic: license-file
+
+# agentic-dev-loop
+
+> **Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.**
+
+Describe your pipeline in one YAML file - agent steps, mechanical test gates, and
+trusted actions - and `agentic-dev-loop` runs it end to end: agent and command steps get
+kernel-level sandboxing via Docker, verdicts route the graph, every boundary is
+checkpointed, and nothing gets committed until every gate passes.
+
+![The live graph view - pipeline graph with fail loopbacks, summary tiles, per-stage consoles, and event log](https://raw.githubusercontent.com/lukedawilson/agentic-dev-loop/main/docs/viz-pipeline.png)
+
+## Key features
+
+- **A tool, not a wiring project.** One CLI entry point, opinionated defaults,
+  fixed safety policies. You write the pipeline and the agent definitions -
+  nothing else.
+- **Deterministic.** Same pipeline + same state means the same routing.
+  Verdicts are parsed from files and validated tool calls, retries are
+  bounded, nothing is best-effort.
+- **Sandboxed by default.** The agent's shell and every command step run
+  inside an always-on Docker sandbox: network off by default, writes only to
+  declared `mounts:`, no `.git`. If no sandbox is available, the run stops
+  instead of degrading.
+- **Crash-safe and resumable.** Every boundary is checkpointed; interrupt a
+  run and resume it from the exact checkpoint with `--resume`, notes intact.
+- **Watchable.** A live browser graph view with per-stage consoles and an
+  event log, a browsable run history, and markdown reports.
+- **Gated commits.** A single commit point that fires only when every gate
+  passed and the worktree was clean at start.
+- **Supply-chain careful.** A digest-pinned dev image, a locked-by-default
+  dependency policy, and a CVE-audited restore step.
+- **Secret-safe.** Secrets are refs in config, values in the host environment,
+  opted in per step, and scrubbed from every engine-written output; the
+  workspace may not contain `.env*` files.
+- **Onboarding that stays honest.** `init` scaffolds a working loop for your
+  repo, `doctor` probes the host before every run, `upgrade` converges the
+  install and the pinned version.
+- **Extensible.** Plugins add your own actions, tools, and document loaders,
+  loaded from outside the workspace only.
+
+## Supported platforms
+
+The engine is plain Linux under the hood and runs wherever a compliant
+Docker engine does:
+
+| Platform | Support |
+| --- | --- |
+| **Linux** | Native. Docker Engine, OrbStack, Colima, or podman with docker compat. |
+| **macOS** | Native. Docker Desktop, OrbStack, or Colima. |
+| **Windows** | Via **WSL2** (Ubuntu distro). Enable Docker Desktop's WSL integration (or run Docker Engine inside the distro) and keep the repo on the WSL filesystem (`~/dev/...`), not `/mnt/c` - bind-mounting a 9p path into containers breaks permissions and is slow. |
+
+## Quickstart
+
+### Prerequisites
+
+| Requirement | Detail |
+| --- | --- |
+| Python | >= 3.12 |
+| Docker engine | Engine API >= 1.43 (Engine 24). Any compliant engine works - Docker Desktop, OrbStack, Colima, Rancher Desktop, podman docker-compat. On Windows, run under WSL2: the repo must live on the WSL filesystem, not /mnt/c. |
+| LLM API key | The env var named by your pipeline's `api_key_env` (e.g. `OPENAI_API_KEY`) must be set - a missing key fails fast, naming it. Alternatively, `agentic-dev-loop copilot-login` authenticates a Copilot subscription (see [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/)). |
+
+### Installation
+
+```bash
+pipx install agentic-dev-loop
+agentic-dev-loop --version
+```
+
+Install with **pipx**: the engine's venv lives outside the workspace, so it
+is unmounted from the sandbox and never agent-writable. On the first run the
+engine pulls the digest-pinned dev image and verifies its digest. Setup
+details and troubleshooting live in the [setup guide](https://lukedawilson.github.io/agentic-dev-loop/setup/).
+
+### Your first loop
+
+```bash
+cd <your-repo>
+agentic-dev-loop init --profile python                     # writes the pipeline + agents
+export OPENAI_API_KEY=...                                  # whatever api_key_env names
+agentic-dev-loop agentic-dev-loop/pipeline.yaml --dry-run  # validate - no LLM, no Docker
+agentic-dev-loop agentic-dev-loop/pipeline.yaml            # run it
+```
+
+`init` scaffolds `agentic-dev-loop/pipeline.yaml` plus the agent files it
+names; `--dry-run` loads and validates with no LLM, no Docker, and no state
+writes. A minimal pipeline looks like:
+
+```yaml
+name: my-construction-loop
+
+llm:
+  model: openai/deepseek-v4-pro
+  base_url: https://api.deepseek.com
+  api_key_env: OPENAI_API_KEY
+
+max_attempts: 10
+agents_dir: sdk_agents
+
+steps:
+  - name: dev
+    agent: dev
+    produces: implementation-summary.md
+    on_pass: test
+
+  - name: test
+    command: .venv-sandbox/bin/python -m pytest tests/ -q
+    on_pass: review
+    on_fail: { goto: dev, retry: true }
+
+  - name: review
+    agent: review
+    artifact: review-findings.md
+    verdicts: { pass: APPROVED, fail: NEEDS CHANGES }
+    on_pass: commit
+    on_fail: { goto: dev, retry: true }
+
+  - name: commit
+    action: commit
+    params: { message: "feat: construct {subject}" }
+```
+
+Every field - per-step isolation, mounts and egress, secrets, dependency
+policy, named LLM profiles - is in the
+[pipeline.yaml reference](https://lukedawilson.github.io/agentic-dev-loop/pipeline/).
+
+## Documentation
+
+| Page | What it covers |
+| --- | --- |
+| [Architecture](https://lukedawilson.github.io/agentic-dev-loop/architecture/) | The five layers, one full run end to end, and the host-boundary security model |
+| [CLI](https://lukedawilson.github.io/agentic-dev-loop/cli/) | Run flags, resuming, the live view, reports, container management, and onboarding commands |
+| [pipeline.yaml](https://lukedawilson.github.io/agentic-dev-loop/pipeline/) | The complete configuration reference: steps, isolation, secrets, networking, dependency policy |
+| [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/) | OpenAI-compatible endpoints (OpenAI, DeepSeek, and others) and the GitHub Copilot subscription |
+| [Authoring a loop](https://lukedawilson.github.io/agentic-dev-loop/authoring/) | From `init` to a committed pipeline: agent files, stage lineup, adaptation checklist |
+| [Setup and troubleshooting](https://lukedawilson.github.io/agentic-dev-loop/setup/) | Docker engines, the dev image, caching, error codes |
+| [Browser sandbox](https://lukedawilson.github.io/agentic-dev-loop/browser-sandbox/) | Running a browser inside the sandbox |
+| [Known issues](https://lukedawilson.github.io/agentic-dev-loop/known-issues/) | Container lifecycle edge cases |
+
+## Contributing
+
+Read [AGENTS.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/AGENTS.md) first -
+it is the instruction set for both human and agent contributors - then see
+[CONTRIBUTING.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/CONTRIBUTING.md)
+for the development workflow and the OpenCode commands.
+
+---
+
+Built on [OpenHands SDK](https://github.com/OpenHands/software-agent-sdk) and
+[LangGraph](https://github.com/langchain-ai/langgraph).

agentic_dev_loop-1.0.0b1/README.md

@@ -0,0 +1,149 @@
+# agentic-dev-loop
+
+> **Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.**
+
+Describe your pipeline in one YAML file - agent steps, mechanical test gates, and
+trusted actions - and `agentic-dev-loop` runs it end to end: agent and command steps get
+kernel-level sandboxing via Docker, verdicts route the graph, every boundary is
+checkpointed, and nothing gets committed until every gate passes.
+
+![The live graph view - pipeline graph with fail loopbacks, summary tiles, per-stage consoles, and event log](https://raw.githubusercontent.com/lukedawilson/agentic-dev-loop/main/docs/viz-pipeline.png)
+
+## Key features
+
+- **A tool, not a wiring project.** One CLI entry point, opinionated defaults,
+  fixed safety policies. You write the pipeline and the agent definitions -
+  nothing else.
+- **Deterministic.** Same pipeline + same state means the same routing.
+  Verdicts are parsed from files and validated tool calls, retries are
+  bounded, nothing is best-effort.
+- **Sandboxed by default.** The agent's shell and every command step run
+  inside an always-on Docker sandbox: network off by default, writes only to
+  declared `mounts:`, no `.git`. If no sandbox is available, the run stops
+  instead of degrading.
+- **Crash-safe and resumable.** Every boundary is checkpointed; interrupt a
+  run and resume it from the exact checkpoint with `--resume`, notes intact.
+- **Watchable.** A live browser graph view with per-stage consoles and an
+  event log, a browsable run history, and markdown reports.
+- **Gated commits.** A single commit point that fires only when every gate
+  passed and the worktree was clean at start.
+- **Supply-chain careful.** A digest-pinned dev image, a locked-by-default
+  dependency policy, and a CVE-audited restore step.
+- **Secret-safe.** Secrets are refs in config, values in the host environment,
+  opted in per step, and scrubbed from every engine-written output; the
+  workspace may not contain `.env*` files.
+- **Onboarding that stays honest.** `init` scaffolds a working loop for your
+  repo, `doctor` probes the host before every run, `upgrade` converges the
+  install and the pinned version.
+- **Extensible.** Plugins add your own actions, tools, and document loaders,
+  loaded from outside the workspace only.
+
+## Supported platforms
+
+The engine is plain Linux under the hood and runs wherever a compliant
+Docker engine does:
+
+| Platform | Support |
+| --- | --- |
+| **Linux** | Native. Docker Engine, OrbStack, Colima, or podman with docker compat. |
+| **macOS** | Native. Docker Desktop, OrbStack, or Colima. |
+| **Windows** | Via **WSL2** (Ubuntu distro). Enable Docker Desktop's WSL integration (or run Docker Engine inside the distro) and keep the repo on the WSL filesystem (`~/dev/...`), not `/mnt/c` - bind-mounting a 9p path into containers breaks permissions and is slow. |
+
+## Quickstart
+
+### Prerequisites
+
+| Requirement | Detail |
+| --- | --- |
+| Python | >= 3.12 |
+| Docker engine | Engine API >= 1.43 (Engine 24). Any compliant engine works - Docker Desktop, OrbStack, Colima, Rancher Desktop, podman docker-compat. On Windows, run under WSL2: the repo must live on the WSL filesystem, not /mnt/c. |
+| LLM API key | The env var named by your pipeline's `api_key_env` (e.g. `OPENAI_API_KEY`) must be set - a missing key fails fast, naming it. Alternatively, `agentic-dev-loop copilot-login` authenticates a Copilot subscription (see [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/)). |
+
+### Installation
+
+```bash
+pipx install agentic-dev-loop
+agentic-dev-loop --version
+```
+
+Install with **pipx**: the engine's venv lives outside the workspace, so it
+is unmounted from the sandbox and never agent-writable. On the first run the
+engine pulls the digest-pinned dev image and verifies its digest. Setup
+details and troubleshooting live in the [setup guide](https://lukedawilson.github.io/agentic-dev-loop/setup/).
+
+### Your first loop
+
+```bash
+cd <your-repo>
+agentic-dev-loop init --profile python                     # writes the pipeline + agents
+export OPENAI_API_KEY=...                                  # whatever api_key_env names
+agentic-dev-loop agentic-dev-loop/pipeline.yaml --dry-run  # validate - no LLM, no Docker
+agentic-dev-loop agentic-dev-loop/pipeline.yaml            # run it
+```
+
+`init` scaffolds `agentic-dev-loop/pipeline.yaml` plus the agent files it
+names; `--dry-run` loads and validates with no LLM, no Docker, and no state
+writes. A minimal pipeline looks like:
+
+```yaml
+name: my-construction-loop
+
+llm:
+  model: openai/deepseek-v4-pro
+  base_url: https://api.deepseek.com
+  api_key_env: OPENAI_API_KEY
+
+max_attempts: 10
+agents_dir: sdk_agents
+
+steps:
+  - name: dev
+    agent: dev
+    produces: implementation-summary.md
+    on_pass: test
+
+  - name: test
+    command: .venv-sandbox/bin/python -m pytest tests/ -q
+    on_pass: review
+    on_fail: { goto: dev, retry: true }
+
+  - name: review
+    agent: review
+    artifact: review-findings.md
+    verdicts: { pass: APPROVED, fail: NEEDS CHANGES }
+    on_pass: commit
+    on_fail: { goto: dev, retry: true }
+
+  - name: commit
+    action: commit
+    params: { message: "feat: construct {subject}" }
+```
+
+Every field - per-step isolation, mounts and egress, secrets, dependency
+policy, named LLM profiles - is in the
+[pipeline.yaml reference](https://lukedawilson.github.io/agentic-dev-loop/pipeline/).
+
+## Documentation
+
+| Page | What it covers |
+| --- | --- |
+| [Architecture](https://lukedawilson.github.io/agentic-dev-loop/architecture/) | The five layers, one full run end to end, and the host-boundary security model |
+| [CLI](https://lukedawilson.github.io/agentic-dev-loop/cli/) | Run flags, resuming, the live view, reports, container management, and onboarding commands |
+| [pipeline.yaml](https://lukedawilson.github.io/agentic-dev-loop/pipeline/) | The complete configuration reference: steps, isolation, secrets, networking, dependency policy |
+| [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/) | OpenAI-compatible endpoints (OpenAI, DeepSeek, and others) and the GitHub Copilot subscription |
+| [Authoring a loop](https://lukedawilson.github.io/agentic-dev-loop/authoring/) | From `init` to a committed pipeline: agent files, stage lineup, adaptation checklist |
+| [Setup and troubleshooting](https://lukedawilson.github.io/agentic-dev-loop/setup/) | Docker engines, the dev image, caching, error codes |
+| [Browser sandbox](https://lukedawilson.github.io/agentic-dev-loop/browser-sandbox/) | Running a browser inside the sandbox |
+| [Known issues](https://lukedawilson.github.io/agentic-dev-loop/known-issues/) | Container lifecycle edge cases |
+
+## Contributing
+
+Read [AGENTS.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/AGENTS.md) first -
+it is the instruction set for both human and agent contributors - then see
+[CONTRIBUTING.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/CONTRIBUTING.md)
+for the development workflow and the OpenCode commands.
+
+---
+
+Built on [OpenHands SDK](https://github.com/OpenHands/software-agent-sdk) and
+[LangGraph](https://github.com/langchain-ai/langgraph).

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentic-dev-loop"
-version = "0.15.7"
+version = "1.0.0b1"
 description = "Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase."
 readme = "README.md"
 requires-python = ">=3.12"
@@ -73,6 +73,7 @@ dependencies = [
 
 [project.urls]
 Homepage = "https://github.com/lukedawilson/agentic-dev-loop"
+Documentation = "https://lukedawilson.github.io/agentic-dev-loop/"
 
 [project.scripts]
 agentic-dev-loop = "agentic_dev_loop.engine.cli:main"
@@ -84,6 +85,10 @@ dev = [
     "pip-audit>=2.0",
     "pre-commit>=3.0",
 ]
+docs = [
+    "mkdocs-material~=9.6",
+    "pymdown-extensions~=10.0",
+]
 
 [tool.setuptools.packages.find]
 where = ["src"]

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/src/agentic_dev_loop/engine/isolation.py

@@ -728,7 +728,8 @@ def _guard_git(request: SandboxExecutionRequest,
         name = " ".join(request.argv[:2])
         raise SandboxError(
             f"AE-SBX-008: git mutation {name!r} blocked - set "
-            "isolation.allow_git_mutations: true to allow (docs/setup.md §3)")
+            "isolation.allow_git_mutations: true to allow "
+            "(see the pipeline reference: docs/pipeline.md)")
 
 
 def _request_digest(argv: list[str], cwd: str, env: dict[str, str]) -> str:
@@ -974,7 +975,7 @@ class DockerBackend(Sandbox):
             raise SandboxError(
                 "AE-SBX-013: networked execution requested but no networked "
                 "container is running - declare `network: true` on the step "
-                "(docs/setup.md §3)")
+                "(see the pipeline reference: docs/pipeline.md)")
         return self._exec(request, container)
 
     def _run_profile(self, request: SandboxExecutionRequest) -> SandboxExecutionResult:

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/src/agentic_dev_loop/engine/onboarding/templates/dev.agent.md

@@ -9,7 +9,7 @@ opinionated LangGraph + OpenHands SDK pipeline engine written in Python.
 
 ## WORKFLOW
 
-1. Read the plan documents and README.md in the context below.
+1. Read the plan documents, README.md, and docs/pipeline.md in the context below.
 2. If the context contains a *Previous attempt feedback* section or a
    *Mechanical gate output* section, treat every issue listed there as a
    required fix from the pipeline's earlier stages - address each one before
@@ -128,7 +128,7 @@ opinionated LangGraph + OpenHands SDK pipeline engine written in Python.
 
 ## CONVENTIONS
 
-- Follow README.md strictly - the fixed policies are binding (file-artifact
+- Follow README.md and docs/pipeline.md strictly - the fixed policies are binding (file-artifact
   verdicts, per-attempt artifact hygiene, single gated commit point,
   fail-fast config and secrets).
 - Tests never touch the network: agents are stubbed via the FakeAgents

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/src/agentic_dev_loop/engine/onboarding/templates/qa.agent.md

@@ -160,7 +160,7 @@ turns building synthetic fixtures or debugging the harness.
   probe and report it as the check. Fabricated checks are a QA failure in
   themselves.
 - Reality beats the docs. If live behaviour has legitimately drifted from the
-  README, note the deviation; fail only when the code is at fault.
+  README or the pipeline reference, note the deviation; fail only when the code is at fault.
 - **Investigation budget.** If a probe failure cannot be diagnosed after a
   few attempts, STOP and write the report. Mark the probe as `INCONCLUSIVE`
   with the symptom and whatever you found. The pipeline will surface the

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/src/agentic_dev_loop/engine/onboarding/templates/review.agent.md

@@ -4,16 +4,16 @@ tools: [terminal, record_verdict]
 ---
 # Review Agent
 
-You are reviewing code for a unit of work against its plan documents and the
-repo's README.
+You are reviewing code for a unit of work against its plan documents, the
+repo's README, and the pipeline reference.
 
 ## WORKFLOW
 
-1. Read the plan documents and README.md in the context below.
+1. Read the plan documents, README.md, and docs/pipeline.md in the context below.
 2. Read the diff - understand what changed.
 3. Check:
    - Does the implementation match the plan?
-   - Are the README's fixed policies respected (file-artifact verdicts,
+   - Are the README's and the pipeline reference's fixed policies respected (file-artifact verdicts,
      artifact hygiene, single gated commit point, fail-fast config)?
    - Do the tests pin the new behavior without touching the network
      (FakeAgents in tests/conftest.py is the only permitted stub)?

agentic_dev_loop-1.0.0b1/src/agentic_dev_loop.egg-info/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.4
+Name: agentic-dev-loop
+Version: 1.0.0b1
+Summary: Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
+Author: Luke Wilson
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/lukedawilson/agentic-dev-loop
+Project-URL: Documentation, https://lukedawilson.github.io/agentic-dev-loop/
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Security
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: openhands-sdk~=1.17.0
+Requires-Dist: openhands-tools~=1.17.0
+Requires-Dist: browser-use==0.11.13
+Requires-Dist: pillow>=13.0.0
+Requires-Dist: agent-client-protocol<1.0.0
+Requires-Dist: langgraph>=1.2
+Requires-Dist: langgraph-checkpoint-sqlite>=3.0
+Requires-Dist: msgpack>=1.0
+Requires-Dist: filelock>=4.2.1
+Requires-Dist: pyasn1>=0.6.5
+Requires-Dist: pypdf>=6.21.4
+Provides-Extra: dev
+Requires-Dist: hypothesis>=6.0; extra == "dev"
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pip-audit>=2.0; extra == "dev"
+Requires-Dist: pre-commit>=3.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material~=9.6; extra == "docs"
+Requires-Dist: pymdown-extensions~=10.0; extra == "docs"
+Dynamic: license-file
+
+# agentic-dev-loop
+
+> **Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.**
+
+Describe your pipeline in one YAML file - agent steps, mechanical test gates, and
+trusted actions - and `agentic-dev-loop` runs it end to end: agent and command steps get
+kernel-level sandboxing via Docker, verdicts route the graph, every boundary is
+checkpointed, and nothing gets committed until every gate passes.
+
+![The live graph view - pipeline graph with fail loopbacks, summary tiles, per-stage consoles, and event log](https://raw.githubusercontent.com/lukedawilson/agentic-dev-loop/main/docs/viz-pipeline.png)
+
+## Key features
+
+- **A tool, not a wiring project.** One CLI entry point, opinionated defaults,
+  fixed safety policies. You write the pipeline and the agent definitions -
+  nothing else.
+- **Deterministic.** Same pipeline + same state means the same routing.
+  Verdicts are parsed from files and validated tool calls, retries are
+  bounded, nothing is best-effort.
+- **Sandboxed by default.** The agent's shell and every command step run
+  inside an always-on Docker sandbox: network off by default, writes only to
+  declared `mounts:`, no `.git`. If no sandbox is available, the run stops
+  instead of degrading.
+- **Crash-safe and resumable.** Every boundary is checkpointed; interrupt a
+  run and resume it from the exact checkpoint with `--resume`, notes intact.
+- **Watchable.** A live browser graph view with per-stage consoles and an
+  event log, a browsable run history, and markdown reports.
+- **Gated commits.** A single commit point that fires only when every gate
+  passed and the worktree was clean at start.
+- **Supply-chain careful.** A digest-pinned dev image, a locked-by-default
+  dependency policy, and a CVE-audited restore step.
+- **Secret-safe.** Secrets are refs in config, values in the host environment,
+  opted in per step, and scrubbed from every engine-written output; the
+  workspace may not contain `.env*` files.
+- **Onboarding that stays honest.** `init` scaffolds a working loop for your
+  repo, `doctor` probes the host before every run, `upgrade` converges the
+  install and the pinned version.
+- **Extensible.** Plugins add your own actions, tools, and document loaders,
+  loaded from outside the workspace only.
+
+## Supported platforms
+
+The engine is plain Linux under the hood and runs wherever a compliant
+Docker engine does:
+
+| Platform | Support |
+| --- | --- |
+| **Linux** | Native. Docker Engine, OrbStack, Colima, or podman with docker compat. |
+| **macOS** | Native. Docker Desktop, OrbStack, or Colima. |
+| **Windows** | Via **WSL2** (Ubuntu distro). Enable Docker Desktop's WSL integration (or run Docker Engine inside the distro) and keep the repo on the WSL filesystem (`~/dev/...`), not `/mnt/c` - bind-mounting a 9p path into containers breaks permissions and is slow. |
+
+## Quickstart
+
+### Prerequisites
+
+| Requirement | Detail |
+| --- | --- |
+| Python | >= 3.12 |
+| Docker engine | Engine API >= 1.43 (Engine 24). Any compliant engine works - Docker Desktop, OrbStack, Colima, Rancher Desktop, podman docker-compat. On Windows, run under WSL2: the repo must live on the WSL filesystem, not /mnt/c. |
+| LLM API key | The env var named by your pipeline's `api_key_env` (e.g. `OPENAI_API_KEY`) must be set - a missing key fails fast, naming it. Alternatively, `agentic-dev-loop copilot-login` authenticates a Copilot subscription (see [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/)). |
+
+### Installation
+
+```bash
+pipx install agentic-dev-loop
+agentic-dev-loop --version
+```
+
+Install with **pipx**: the engine's venv lives outside the workspace, so it
+is unmounted from the sandbox and never agent-writable. On the first run the
+engine pulls the digest-pinned dev image and verifies its digest. Setup
+details and troubleshooting live in the [setup guide](https://lukedawilson.github.io/agentic-dev-loop/setup/).
+
+### Your first loop
+
+```bash
+cd <your-repo>
+agentic-dev-loop init --profile python                     # writes the pipeline + agents
+export OPENAI_API_KEY=...                                  # whatever api_key_env names
+agentic-dev-loop agentic-dev-loop/pipeline.yaml --dry-run  # validate - no LLM, no Docker
+agentic-dev-loop agentic-dev-loop/pipeline.yaml            # run it
+```
+
+`init` scaffolds `agentic-dev-loop/pipeline.yaml` plus the agent files it
+names; `--dry-run` loads and validates with no LLM, no Docker, and no state
+writes. A minimal pipeline looks like:
+
+```yaml
+name: my-construction-loop
+
+llm:
+  model: openai/deepseek-v4-pro
+  base_url: https://api.deepseek.com
+  api_key_env: OPENAI_API_KEY
+
+max_attempts: 10
+agents_dir: sdk_agents
+
+steps:
+  - name: dev
+    agent: dev
+    produces: implementation-summary.md
+    on_pass: test
+
+  - name: test
+    command: .venv-sandbox/bin/python -m pytest tests/ -q
+    on_pass: review
+    on_fail: { goto: dev, retry: true }
+
+  - name: review
+    agent: review
+    artifact: review-findings.md
+    verdicts: { pass: APPROVED, fail: NEEDS CHANGES }
+    on_pass: commit
+    on_fail: { goto: dev, retry: true }
+
+  - name: commit
+    action: commit
+    params: { message: "feat: construct {subject}" }
+```
+
+Every field - per-step isolation, mounts and egress, secrets, dependency
+policy, named LLM profiles - is in the
+[pipeline.yaml reference](https://lukedawilson.github.io/agentic-dev-loop/pipeline/).
+
+## Documentation
+
+| Page | What it covers |
+| --- | --- |
+| [Architecture](https://lukedawilson.github.io/agentic-dev-loop/architecture/) | The five layers, one full run end to end, and the host-boundary security model |
+| [CLI](https://lukedawilson.github.io/agentic-dev-loop/cli/) | Run flags, resuming, the live view, reports, container management, and onboarding commands |
+| [pipeline.yaml](https://lukedawilson.github.io/agentic-dev-loop/pipeline/) | The complete configuration reference: steps, isolation, secrets, networking, dependency policy |
+| [LLM providers](https://lukedawilson.github.io/agentic-dev-loop/llm-providers/) | OpenAI-compatible endpoints (OpenAI, DeepSeek, and others) and the GitHub Copilot subscription |
+| [Authoring a loop](https://lukedawilson.github.io/agentic-dev-loop/authoring/) | From `init` to a committed pipeline: agent files, stage lineup, adaptation checklist |
+| [Setup and troubleshooting](https://lukedawilson.github.io/agentic-dev-loop/setup/) | Docker engines, the dev image, caching, error codes |
+| [Browser sandbox](https://lukedawilson.github.io/agentic-dev-loop/browser-sandbox/) | Running a browser inside the sandbox |
+| [Known issues](https://lukedawilson.github.io/agentic-dev-loop/known-issues/) | Container lifecycle edge cases |
+
+## Contributing
+
+Read [AGENTS.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/AGENTS.md) first -
+it is the instruction set for both human and agent contributors - then see
+[CONTRIBUTING.md](https://github.com/lukedawilson/agentic-dev-loop/blob/main/CONTRIBUTING.md)
+for the development workflow and the OpenCode commands.
+
+---
+
+Built on [OpenHands SDK](https://github.com/OpenHands/software-agent-sdk) and
+[LangGraph](https://github.com/langchain-ai/langgraph).

{agentic_dev_loop-0.15.7 → agentic_dev_loop-1.0.0b1}/src/agentic_dev_loop.egg-info/requires.txt

@@ -17,3 +17,7 @@ hypothesis>=6.0
 pytest>=8.0
 pip-audit>=2.0
 pre-commit>=3.0
+
+[docs]
+mkdocs-material~=9.6
+pymdown-extensions~=10.0