proseforge-agent 0.2.0__tar.gz → 0.3.0__tar.gz

{proseforge_agent-0.2.0 → proseforge_agent-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: proseforge-agent
-Version: 0.2.0
+Version: 0.3.0
 Summary: Agentic orchestration layer for long-form novel production on top of the ProseForge engine.
 Author: ProseForge Agent
 License: Apache-2.0
@@ -11,101 +11,127 @@ Requires-Dist: pyyaml>=6.0
 Requires-Dist: tomli>=2.0; python_version < "3.11"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
+Provides-Extra: ci
+Requires-Dist: pytest>=7.0; extra == "ci"
+Requires-Dist: pytest-rerunfailures>=13.0; extra == "ci"
+Requires-Dist: pytest-repeat>=0.9; extra == "ci"
 Dynamic: license-file
 
 > 🌐 [English](README.md) · [简体中文](README.zh-CN.md)
 
-# ProseForge Agent
+<p align="center">
+  <img src="assets/banner.png" alt="ProseForge Agent novel-writing command center" width="100%">
+</p>
 
-An agentic orchestration layer for long-form novel production. It wraps the
-canonical **ProseForge engine** (`$PROSEFORGE_ROOT`) with planning, retrieval,
-drafting, review, revision, deep memory, multi-provider model routing, daily
-workbooks, reports, extensions, an agent runtime, chat, an autonomous
-goal-directed loop, MCP integration, execution environments, skills, hosted
-cron, observability, middleware, and a real publish/binary/installer chain.
+<h1 align="center">ProseForge Agent</h1>
 
-ProseForge Agent does **not** reimplement the writing engine. The engine at
-`$PROSEFORGE_ROOT` remains the source of truth for project slots, pipeline
-actions, guards, reports, and exports. This package owns orchestration:
-model calls, provider routing, schedules, evidence packs, agent memory,
-workflow state, conversational agent loop, and background event processing.
+<p align="center">
+  <strong>An AI command layer for long-form novel production.</strong>
+</p>
+
+<p align="center">
+  <a href="README.zh-CN.md">简体中文</a> ·
+  <a href="https://pypi.org/project/proseforge-agent/">PyPI</a> ·
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/releases/tag/v0.2.0">Release v0.2.0</a> ·
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/pkgs/container/proseforge-agent">GHCR</a>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/proseforge-agent/"><img src="https://img.shields.io/pypi/v/proseforge-agent?style=for-the-badge&label=PyPI" alt="PyPI version"></a>
+  <a href="https://pypi.org/project/proseforge-agent/"><img src="https://img.shields.io/pypi/pyversions/proseforge-agent?style=for-the-badge" alt="Python versions"></a>
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/remacheybn408-boop/ProseForge-Agent/ci.yml?branch=main&style=for-the-badge&label=CI" alt="CI status"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-green?style=for-the-badge" alt="Apache-2.0 license"></a>
+</p>
+
+ProseForge Agent turns a novel project into a managed creative workflow:
+plan the book, retrieve canon, draft scenes, review prose, rewrite chapters,
+track memory, and run the whole process through your preferred model
+provider. It sits above the canonical **ProseForge engine**
+(`$PROSEFORGE_ROOT`) and handles orchestration rather than replacing the
+writing engine.
+
+Use it as a CLI, a full-screen terminal UI, a local HTTP service, a Docker
+image, or a background agent with gateway integrations.
 
-## Status
+<table>
+<tr><td><b>Plan the whole book</b></td><td>Turn a project goal into phase plans, daily workbooks, chapter tasks, and scene-level workflow.</td></tr>
+<tr><td><b>Draft with memory</b></td><td>Retrieve canon, timeline, character notes, prior scenes, and evidence packs before the model writes.</td></tr>
+<tr><td><b>Review and revise</b></td><td>Run a chapter lifecycle from draft to review, rewrite, and accept, with quality gates and rollback-friendly artifacts.</td></tr>
+<tr><td><b>Use the model you want</b></td><td>Profiles for OpenAI, Anthropic, Gemini, xAI/Grok, DeepSeek, Qwen, GLM, Mimo, MiniMax, Doubao, plus an offline fake provider.</td></tr>
+<tr><td><b>Run it like a real tool</b></td><td>Interactive REPL, full-screen TUI, local API, Docker image, Telegram gateway, MCP stdio, local execution, cron, and telemetry.</td></tr>
+<tr><td><b>Published now</b></td><td><code>v0.2.0</code> is live on PyPI, GHCR, and GitHub Releases. Release gate: <code>1358 tests passing</code> — 35 integration (real subprocess / HTTP / SQLite), the rest offline fakes.</td></tr>
+</table>
 
-**v0.2.0 — first public release.** 1301 tests passing on Python
-3.10/3.11/3.12 across Windows, macOS, and Linux. See `CHANGELOG.md` for
-release notes, and "What is production-ready and what is contract-only"
-below for exactly which surfaces are live.
+---
 
-## Installation
+## Quick Install
 
-From PyPI (recommended):
+### Python package
 
 ```bash
 pip install proseforge-agent
 pf-agent --help
 ```
 
-One-line installer (Linux / macOS / WSL2 — installs `uv` or uses `pipx`
-and puts `pf-agent` on your PATH):
+### Linux, macOS, WSL2
 
 ```bash
 curl -fsSL https://raw.githubusercontent.com/remacheybn408-boop/ProseForge-Agent/main/scripts/install.sh | sh
 ```
 
-Windows PowerShell:
+### Windows PowerShell
 
 ```powershell
 iex (irm https://raw.githubusercontent.com/remacheybn408-boop/ProseForge-Agent/main/scripts/install.ps1)
 ```
 
-Docker (runs the HTTP service on port 8765; a bearer token is required
-for the non-loopback bind):
+### Docker
 
 ```bash
 docker pull ghcr.io/remacheybn408-boop/proseforge-agent:latest
 PF_AGENT_SERVICE_TOKEN=<your-token> docker compose up
 ```
 
-From source:
+Install from source, or pass `--git main` to `install.sh`, only when you
+want unreleased changes from `main`.
 
-```bash
-git clone https://github.com/remacheybn408-boop/ProseForge-Agent.git
-cd ProseForge-Agent
-pip install -e ".[dev]"
-```
-
-> PyPI and GHCR artifacts are published by the tag-triggered release
-> workflow; if a brand-new version has not been tagged yet, install from
-> source or pass `--git main` to `install.sh`.
-
-## Quickstart
+## Getting Started
 
 ```bash
 pf-agent setup                 # guided wizard: providers, keys, workspace
-pf-agent                       # bare command opens the interactive chat REPL
+pf-agent                       # interactive chat REPL
+pf-agent tui                   # full-screen terminal UI
+pf-agent chat --message "draft an opening" --provider fake
+pf-agent run --goal "draft a one-line opening" --max-iterations 5
+pf-agent service serve         # local HTTP API on 127.0.0.1:8765
 ```
 
 The bare `pf-agent` command works like other coding agents' CLIs: the
 first run bootstraps a workspace, and after `pf-agent setup` it talks to
-your configured default model (the REPL banner shows which provider and
-model are active). Without setup it runs against the offline fake
-provider so you can tour the CLI with no keys.
-
-More entry points:
-
-```bash
-pf-agent doctor                # verify the installation and wiring
-pf-agent chat --message "draft an opening"        # one-shot chat turn
-pf-agent run --goal "draft a one-line opening" --max-iterations 5
-pf-agent service serve         # local HTTP API on 127.0.0.1:8765
-```
+your configured default model. Without setup, it runs against the offline
+fake provider so you can tour the CLI with no keys.
 
 Set provider API keys in your environment (or `.env`, see
 `.env.example`): `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, and friends.
-Any command accepts `--provider fake` for a no-key offline tour.
+Every command accepts `--provider fake` for a no-key offline tour.
+
+## Project Boundary
+
+ProseForge Agent does **not** reimplement the writing engine. The engine at
+`$PROSEFORGE_ROOT` remains the source of truth for project slots, pipeline
+actions, guards, reports, and exports. This package owns orchestration:
+model calls, provider routing, schedules, evidence packs, agent memory,
+workflow state, conversational agent loops, and background event handling.
+
+## Release Status
+
+`v0.2.0` was published on July 3, 2026 through PyPI Trusted Publishing.
+Release links: [PyPI](https://pypi.org/project/proseforge-agent/),
+[GitHub Release](https://github.com/remacheybn408-boop/ProseForge-Agent/releases/tag/v0.2.0),
+[GHCR image](https://github.com/remacheybn408-boop/ProseForge-Agent/pkgs/container/proseforge-agent),
+and [`CHANGELOG.md`](CHANGELOG.md).
 
-## Feature overview
+## Technical Overview
 
 The full stack: core orchestration, agent runtime, chat, native install,
 hardening, autonomous runtime, agent tooling, guided setup, novel
@@ -198,11 +224,11 @@ with deterministic replay.
 
 ### MCP integration
 
-MCP client foundation (`stdio` and HTTP/SSE transports with
-`StaticMCPTransport` for tests), server registry, security boundary, tool
-approval gate, tool schema validation, and credentials boundary. Real
-process/network transports are pluggable at call time; test suites use
-the deterministic in-process transport.
+MCP client foundation, server registry, security boundary, tool approval
+gate, tool schema validation, and credentials boundary. The `stdio`
+transport is real (subprocess JSON-RPC:
+`pf-agent mcp inspect/tools/call`); HTTP/SSE transports are pluggable at
+call time, and tests use deterministic in-process transports.
 
 ### Provider & tool resilience
 
@@ -295,7 +321,9 @@ requests re-checked by downstream policy, plus research-ready
 `PyPIPublisher` — real `python -m build` + `twine upload` for TestPyPI /
 PyPI, gated by the Task 47 `PackageChecker` and duplicate-version refusal,
 with injectable runner + `dry_run` for offline tests; tokens never appear
-in the plan, report, or logs.
+in the plan, report, or logs. The public `v0.2.0` release path uses PyPI
+Trusted Publishing / OIDC, so no long-lived PyPI token is stored in the
+repository.
 
 `BinaryBuilder` — real PyInstaller invocation derived from the Task 48
 `BinaryManifest`, followed by the `pf-agent --version` smoke command as
@@ -412,7 +440,7 @@ configs/                    agent and provider example configs
 docs/                       operator, developer, implementation, and
                             task-card plans (docs/superpowers/plans/)
 samples/                    sample extensions
-tests/                      pytest suite (1301 tests) + contract / golden
+tests/                      pytest suite (1338 tests) + contract / golden
                             tiers + fixtures
 .github/workflows/ci.yml    cross-platform CI (Windows, macOS, Linux)
 ```
@@ -542,38 +570,35 @@ GLM, Mimo, MiniMax, Doubao**.
 Keep secrets in environment variables or local ignored config files. Do
 not commit API keys into provider YAML.
 
-## What is production-ready and what is contract-only
-
-The project intentionally splits "contract + fake" from "real wiring" so
-tests stay deterministic and offline. A few tracks are contract-complete
-with fake/dry-run implementations that the operator wires to real
-transports at call time:
-
-- **Production ready today** — LLM providers (real HTTP via `urllib`,
-  10 profiles), memory (SQLite), workspace + config, planning / daily /
-  chapter / workflow, tool registry + permission policy, attachment
-  ingestion, embeddings + retrieval + RAG, skills, hosted cron
-  verification, telemetry & trajectory export, the real
-  publish/binary/installer chain (tag-triggered release workflow:
-  PyPI + GHCR + GitHub Release), **MCP `stdio`** (real JSON-RPC
-  subprocess transport: `pf-agent mcp inspect/tools/call`), the
-  **local execution environment** (real subprocess execution behind
-  `pf-agent environments exec`, permission + approval gated), the
-  **Telegram gateway** (real Bot API long-polling:
-  `pf-agent gateway telegram start`), and the **local HTTP service**
-  (`pf-agent service serve` on port 8765, bearer-token auth for
-  non-loopback binds — this is what the Docker image runs).
-- **Contract-complete with pluggable transport** — MCP over HTTP/SSE
-  (placeholder; stdio is real), remote execution environments
-  (Docker/Modal/Daytona/SSH/Singularity emit deterministic dry-run
-  plans that a real backend can execute), and the remaining gateway
-  platform adapters (Slack/Discord/Signal/Email ship contract shape +
-  fake transport; wire real HTTP at call time like the Telegram
-  adapter does).
-
-The 1301-test suite covers both tracks via injectable runners and fake
-transports, so `python -m pytest -q` is fully offline and requires no
-credentials.
+## Readiness table
+
+Every command surface reports one of three readiness states, and any
+report that isn't `ready` is stamped with a visible badge in its title
+(`[contract]` or `[planned]`) so you know at a glance when you're
+looking at a real transport vs a scaffold. Pass `--strict` to refuse
+any non-ready command (exits 3).
+
+| Surface | Command | Readiness | Notes |
+| --- | --- | --- | --- |
+| LLM providers (10 vendors) | `pf-agent chat --provider <name>` | ✅ ready | real HTTPS via `urllib`, keys from env |
+| Memory / workspace / config | `pf-agent memory ...` / `pf-agent config ...` | ✅ ready | SQLite, portable YAML |
+| Planning / daily / chapter / workflow | `pf-agent plan ...` / `pf-agent chapter ...` | ✅ ready | real |
+| Retrieval + RAG | `pf-agent retrieval ...` | ✅ ready | real |
+| Local HTTP service (port 8765) | `pf-agent service serve` | ✅ ready | bearer auth on non-loopback |
+| MCP over stdio | `pf-agent mcp inspect/tools/call` | ✅ ready | real subprocess JSON-RPC |
+| Local execution env | `pf-agent environments exec` | ✅ ready | real subprocess, permission-gated |
+| Telegram gateway | `pf-agent gateway telegram start` | ✅ ready | real Bot API long-polling |
+| Release chain | tag `v*` push | ✅ ready | PyPI Trusted Publishing + GHCR + GH Release |
+| MCP over HTTP / SSE | `pf-agent mcp add --transport http ...` | ⚠️ contract | placeholder; opt-in via env |
+| Docker / SSH / Singularity / Modal / Daytona backends | `pf-agent environments check <backend>` | ⚠️ contract | dry-run plans only; real runner injectable |
+| Slack / Discord / Signal / Email gateways | `pf-agent gateway <platform> check` | ⚠️ contract | fake transport; wire like Telegram |
+| Skills hub search / install / update | `pf-agent skills search` etc. | ⚠️ contract | fake hub client + dry-run plans |
+| Anything the CLI routes through `_planned_report` | (many groups) | 🟡 planned | scaffold only, no real code path |
+
+The tests-passing count in this README's Status section refers to the
+whole offline suite (fakes + real integration paths together); the four
+"ready" rows above are exercised by the small real-integration subset
+(`pytest -m integration`).
 
 ## ProseForge Engine Boundary
 

proseforge_agent-0.2.0/src/proseforge_agent.egg-info/PKG-INFO → proseforge_agent-0.3.0/README.md

@@ -1,111 +1,118 @@
-Metadata-Version: 2.4
-Name: proseforge-agent
-Version: 0.2.0
-Summary: Agentic orchestration layer for long-form novel production on top of the ProseForge engine.
-Author: ProseForge Agent
-License: Apache-2.0
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: tomli>=2.0; python_version < "3.11"
-Provides-Extra: dev
-Requires-Dist: pytest>=7.0; extra == "dev"
-Dynamic: license-file
-
 > 🌐 [English](README.md) · [简体中文](README.zh-CN.md)
 
-# ProseForge Agent
+<p align="center">
+  <img src="assets/banner.png" alt="ProseForge Agent novel-writing command center" width="100%">
+</p>
 
-An agentic orchestration layer for long-form novel production. It wraps the
-canonical **ProseForge engine** (`$PROSEFORGE_ROOT`) with planning, retrieval,
-drafting, review, revision, deep memory, multi-provider model routing, daily
-workbooks, reports, extensions, an agent runtime, chat, an autonomous
-goal-directed loop, MCP integration, execution environments, skills, hosted
-cron, observability, middleware, and a real publish/binary/installer chain.
+<h1 align="center">ProseForge Agent</h1>
 
-ProseForge Agent does **not** reimplement the writing engine. The engine at
-`$PROSEFORGE_ROOT` remains the source of truth for project slots, pipeline
-actions, guards, reports, and exports. This package owns orchestration:
-model calls, provider routing, schedules, evidence packs, agent memory,
-workflow state, conversational agent loop, and background event processing.
+<p align="center">
+  <strong>An AI command layer for long-form novel production.</strong>
+</p>
+
+<p align="center">
+  <a href="README.zh-CN.md">简体中文</a> ·
+  <a href="https://pypi.org/project/proseforge-agent/">PyPI</a> ·
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/releases/tag/v0.2.0">Release v0.2.0</a> ·
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/pkgs/container/proseforge-agent">GHCR</a>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/proseforge-agent/"><img src="https://img.shields.io/pypi/v/proseforge-agent?style=for-the-badge&label=PyPI" alt="PyPI version"></a>
+  <a href="https://pypi.org/project/proseforge-agent/"><img src="https://img.shields.io/pypi/pyversions/proseforge-agent?style=for-the-badge" alt="Python versions"></a>
+  <a href="https://github.com/remacheybn408-boop/ProseForge-Agent/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/remacheybn408-boop/ProseForge-Agent/ci.yml?branch=main&style=for-the-badge&label=CI" alt="CI status"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache--2.0-green?style=for-the-badge" alt="Apache-2.0 license"></a>
+</p>
+
+ProseForge Agent turns a novel project into a managed creative workflow:
+plan the book, retrieve canon, draft scenes, review prose, rewrite chapters,
+track memory, and run the whole process through your preferred model
+provider. It sits above the canonical **ProseForge engine**
+(`$PROSEFORGE_ROOT`) and handles orchestration rather than replacing the
+writing engine.
 
-## Status
+Use it as a CLI, a full-screen terminal UI, a local HTTP service, a Docker
+image, or a background agent with gateway integrations.
 
-**v0.2.0 — first public release.** 1301 tests passing on Python
-3.10/3.11/3.12 across Windows, macOS, and Linux. See `CHANGELOG.md` for
-release notes, and "What is production-ready and what is contract-only"
-below for exactly which surfaces are live.
+<table>
+<tr><td><b>Plan the whole book</b></td><td>Turn a project goal into phase plans, daily workbooks, chapter tasks, and scene-level workflow.</td></tr>
+<tr><td><b>Draft with memory</b></td><td>Retrieve canon, timeline, character notes, prior scenes, and evidence packs before the model writes.</td></tr>
+<tr><td><b>Review and revise</b></td><td>Run a chapter lifecycle from draft to review, rewrite, and accept, with quality gates and rollback-friendly artifacts.</td></tr>
+<tr><td><b>Use the model you want</b></td><td>Profiles for OpenAI, Anthropic, Gemini, xAI/Grok, DeepSeek, Qwen, GLM, Mimo, MiniMax, Doubao, plus an offline fake provider.</td></tr>
+<tr><td><b>Run it like a real tool</b></td><td>Interactive REPL, full-screen TUI, local API, Docker image, Telegram gateway, MCP stdio, local execution, cron, and telemetry.</td></tr>
+<tr><td><b>Published now</b></td><td><code>v0.2.0</code> is live on PyPI, GHCR, and GitHub Releases. Release gate: <code>1358 tests passing</code> — 35 integration (real subprocess / HTTP / SQLite), the rest offline fakes.</td></tr>
+</table>
 
-## Installation
+---
 
-From PyPI (recommended):
+## Quick Install
+
+### Python package
 
 ```bash
 pip install proseforge-agent
 pf-agent --help
 ```
 
-One-line installer (Linux / macOS / WSL2 — installs `uv` or uses `pipx`
-and puts `pf-agent` on your PATH):
+### Linux, macOS, WSL2
 
 ```bash
 curl -fsSL https://raw.githubusercontent.com/remacheybn408-boop/ProseForge-Agent/main/scripts/install.sh | sh
 ```
 
-Windows PowerShell:
+### Windows PowerShell
 
 ```powershell
 iex (irm https://raw.githubusercontent.com/remacheybn408-boop/ProseForge-Agent/main/scripts/install.ps1)
 ```
 
-Docker (runs the HTTP service on port 8765; a bearer token is required
-for the non-loopback bind):
+### Docker
 
 ```bash
 docker pull ghcr.io/remacheybn408-boop/proseforge-agent:latest
 PF_AGENT_SERVICE_TOKEN=<your-token> docker compose up
 ```
 
-From source:
-
-```bash
-git clone https://github.com/remacheybn408-boop/ProseForge-Agent.git
-cd ProseForge-Agent
-pip install -e ".[dev]"
-```
+Install from source, or pass `--git main` to `install.sh`, only when you
+want unreleased changes from `main`.
 
-> PyPI and GHCR artifacts are published by the tag-triggered release
-> workflow; if a brand-new version has not been tagged yet, install from
-> source or pass `--git main` to `install.sh`.
-
-## Quickstart
+## Getting Started
 
 ```bash
 pf-agent setup                 # guided wizard: providers, keys, workspace
-pf-agent                       # bare command opens the interactive chat REPL
+pf-agent                       # interactive chat REPL
+pf-agent tui                   # full-screen terminal UI
+pf-agent chat --message "draft an opening" --provider fake
+pf-agent run --goal "draft a one-line opening" --max-iterations 5
+pf-agent service serve         # local HTTP API on 127.0.0.1:8765
 ```
 
 The bare `pf-agent` command works like other coding agents' CLIs: the
 first run bootstraps a workspace, and after `pf-agent setup` it talks to
-your configured default model (the REPL banner shows which provider and
-model are active). Without setup it runs against the offline fake
-provider so you can tour the CLI with no keys.
-
-More entry points:
-
-```bash
-pf-agent doctor                # verify the installation and wiring
-pf-agent chat --message "draft an opening"        # one-shot chat turn
-pf-agent run --goal "draft a one-line opening" --max-iterations 5
-pf-agent service serve         # local HTTP API on 127.0.0.1:8765
-```
+your configured default model. Without setup, it runs against the offline
+fake provider so you can tour the CLI with no keys.
 
 Set provider API keys in your environment (or `.env`, see
 `.env.example`): `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, and friends.
-Any command accepts `--provider fake` for a no-key offline tour.
+Every command accepts `--provider fake` for a no-key offline tour.
+
+## Project Boundary
+
+ProseForge Agent does **not** reimplement the writing engine. The engine at
+`$PROSEFORGE_ROOT` remains the source of truth for project slots, pipeline
+actions, guards, reports, and exports. This package owns orchestration:
+model calls, provider routing, schedules, evidence packs, agent memory,
+workflow state, conversational agent loops, and background event handling.
+
+## Release Status
+
+`v0.2.0` was published on July 3, 2026 through PyPI Trusted Publishing.
+Release links: [PyPI](https://pypi.org/project/proseforge-agent/),
+[GitHub Release](https://github.com/remacheybn408-boop/ProseForge-Agent/releases/tag/v0.2.0),
+[GHCR image](https://github.com/remacheybn408-boop/ProseForge-Agent/pkgs/container/proseforge-agent),
+and [`CHANGELOG.md`](CHANGELOG.md).
 
-## Feature overview
+## Technical Overview
 
 The full stack: core orchestration, agent runtime, chat, native install,
 hardening, autonomous runtime, agent tooling, guided setup, novel
@@ -198,11 +205,11 @@ with deterministic replay.
 
 ### MCP integration
 
-MCP client foundation (`stdio` and HTTP/SSE transports with
-`StaticMCPTransport` for tests), server registry, security boundary, tool
-approval gate, tool schema validation, and credentials boundary. Real
-process/network transports are pluggable at call time; test suites use
-the deterministic in-process transport.
+MCP client foundation, server registry, security boundary, tool approval
+gate, tool schema validation, and credentials boundary. The `stdio`
+transport is real (subprocess JSON-RPC:
+`pf-agent mcp inspect/tools/call`); HTTP/SSE transports are pluggable at
+call time, and tests use deterministic in-process transports.
 
 ### Provider & tool resilience
 
@@ -295,7 +302,9 @@ requests re-checked by downstream policy, plus research-ready
 `PyPIPublisher` — real `python -m build` + `twine upload` for TestPyPI /
 PyPI, gated by the Task 47 `PackageChecker` and duplicate-version refusal,
 with injectable runner + `dry_run` for offline tests; tokens never appear
-in the plan, report, or logs.
+in the plan, report, or logs. The public `v0.2.0` release path uses PyPI
+Trusted Publishing / OIDC, so no long-lived PyPI token is stored in the
+repository.
 
 `BinaryBuilder` — real PyInstaller invocation derived from the Task 48
 `BinaryManifest`, followed by the `pf-agent --version` smoke command as
@@ -412,7 +421,7 @@ configs/                    agent and provider example configs
 docs/                       operator, developer, implementation, and
                             task-card plans (docs/superpowers/plans/)
 samples/                    sample extensions
-tests/                      pytest suite (1301 tests) + contract / golden
+tests/                      pytest suite (1338 tests) + contract / golden
                             tiers + fixtures
 .github/workflows/ci.yml    cross-platform CI (Windows, macOS, Linux)
 ```
@@ -542,38 +551,35 @@ GLM, Mimo, MiniMax, Doubao**.
 Keep secrets in environment variables or local ignored config files. Do
 not commit API keys into provider YAML.
 
-## What is production-ready and what is contract-only
-
-The project intentionally splits "contract + fake" from "real wiring" so
-tests stay deterministic and offline. A few tracks are contract-complete
-with fake/dry-run implementations that the operator wires to real
-transports at call time:
-
-- **Production ready today** — LLM providers (real HTTP via `urllib`,
-  10 profiles), memory (SQLite), workspace + config, planning / daily /
-  chapter / workflow, tool registry + permission policy, attachment
-  ingestion, embeddings + retrieval + RAG, skills, hosted cron
-  verification, telemetry & trajectory export, the real
-  publish/binary/installer chain (tag-triggered release workflow:
-  PyPI + GHCR + GitHub Release), **MCP `stdio`** (real JSON-RPC
-  subprocess transport: `pf-agent mcp inspect/tools/call`), the
-  **local execution environment** (real subprocess execution behind
-  `pf-agent environments exec`, permission + approval gated), the
-  **Telegram gateway** (real Bot API long-polling:
-  `pf-agent gateway telegram start`), and the **local HTTP service**
-  (`pf-agent service serve` on port 8765, bearer-token auth for
-  non-loopback binds — this is what the Docker image runs).
-- **Contract-complete with pluggable transport** — MCP over HTTP/SSE
-  (placeholder; stdio is real), remote execution environments
-  (Docker/Modal/Daytona/SSH/Singularity emit deterministic dry-run
-  plans that a real backend can execute), and the remaining gateway
-  platform adapters (Slack/Discord/Signal/Email ship contract shape +
-  fake transport; wire real HTTP at call time like the Telegram
-  adapter does).
-
-The 1301-test suite covers both tracks via injectable runners and fake
-transports, so `python -m pytest -q` is fully offline and requires no
-credentials.
+## Readiness table
+
+Every command surface reports one of three readiness states, and any
+report that isn't `ready` is stamped with a visible badge in its title
+(`[contract]` or `[planned]`) so you know at a glance when you're
+looking at a real transport vs a scaffold. Pass `--strict` to refuse
+any non-ready command (exits 3).
+
+| Surface | Command | Readiness | Notes |
+| --- | --- | --- | --- |
+| LLM providers (10 vendors) | `pf-agent chat --provider <name>` | ✅ ready | real HTTPS via `urllib`, keys from env |
+| Memory / workspace / config | `pf-agent memory ...` / `pf-agent config ...` | ✅ ready | SQLite, portable YAML |
+| Planning / daily / chapter / workflow | `pf-agent plan ...` / `pf-agent chapter ...` | ✅ ready | real |
+| Retrieval + RAG | `pf-agent retrieval ...` | ✅ ready | real |
+| Local HTTP service (port 8765) | `pf-agent service serve` | ✅ ready | bearer auth on non-loopback |
+| MCP over stdio | `pf-agent mcp inspect/tools/call` | ✅ ready | real subprocess JSON-RPC |
+| Local execution env | `pf-agent environments exec` | ✅ ready | real subprocess, permission-gated |
+| Telegram gateway | `pf-agent gateway telegram start` | ✅ ready | real Bot API long-polling |
+| Release chain | tag `v*` push | ✅ ready | PyPI Trusted Publishing + GHCR + GH Release |
+| MCP over HTTP / SSE | `pf-agent mcp add --transport http ...` | ⚠️ contract | placeholder; opt-in via env |
+| Docker / SSH / Singularity / Modal / Daytona backends | `pf-agent environments check <backend>` | ⚠️ contract | dry-run plans only; real runner injectable |
+| Slack / Discord / Signal / Email gateways | `pf-agent gateway <platform> check` | ⚠️ contract | fake transport; wire like Telegram |
+| Skills hub search / install / update | `pf-agent skills search` etc. | ⚠️ contract | fake hub client + dry-run plans |
+| Anything the CLI routes through `_planned_report` | (many groups) | 🟡 planned | scaffold only, no real code path |
+
+The tests-passing count in this README's Status section refers to the
+whole offline suite (fakes + real integration paths together); the four
+"ready" rows above are exercised by the small real-integration subset
+(`pytest -m integration`).
 
 ## ProseForge Engine Boundary
 

{proseforge_agent-0.2.0 → proseforge_agent-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "proseforge-agent"
-version = "0.2.0"
+version = "0.3.0"
 description = "Agentic orchestration layer for long-form novel production on top of the ProseForge engine."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -14,6 +14,7 @@ dependencies = ["pyyaml>=6.0", "tomli>=2.0; python_version < '3.11'"]
 
 [project.optional-dependencies]
 dev = ["pytest>=7.0"]
+ci = ["pytest>=7.0", "pytest-rerunfailures>=13.0", "pytest-repeat>=0.9"]
 
 [project.scripts]
 pf-agent = "proseforge_agent.cli:main"
@@ -27,3 +28,6 @@ where = ["src"]
 [tool.pytest.ini_options]
 pythonpath = ["src"]
 testpaths = ["tests"]
+markers = [
+    "integration: touches a real subprocess, real HTTP over urllib, or a real sqlite file (opt-in via `pytest -m integration`)",
+]

{proseforge_agent-0.2.0 → proseforge_agent-0.3.0}/src/proseforge_agent/__init__.py

@@ -5,6 +5,6 @@ or require API keys. Subsystem behavior lives behind dedicated submodules
 that are imported explicitly by their callers.
 """
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 
 __all__ = ["__version__"]