codex-autorunner 0.1.1__tar.gz → 1.0.0__tar.gz

{codex_autorunner-0.1.1/src/codex_autorunner.egg-info → codex_autorunner-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codex-autorunner
-Version: 0.1.1
+Version: 1.0.0
 Summary: Codex autorunner CLI per DESIGN-V1
 Author: Codex
 License: MIT License
@@ -45,10 +45,12 @@ Requires-Dist: ptyprocess>=0.7
 Requires-Dist: python-multipart>=0.0.9
 Requires-Dist: python-dotenv>=1.0
 Requires-Dist: httpx>=0.27
+Requires-Dist: tenacity>=8.0
 Provides-Extra: dev
 Requires-Dist: black==25.11.0; extra == "dev"
 Requires-Dist: mypy>=1.10; extra == "dev"
 Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
 Requires-Dist: pytest-timeout>=2.0; extra == "dev"
 Requires-Dist: ruff>=0.5.0; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
@@ -63,11 +65,17 @@ Dynamic: license-file
 # codex-autorunner
 [![PyPI](https://img.shields.io/pypi/v/codex-autorunner.svg)](https://pypi.org/project/codex-autorunner/)
 
-An opinionated autorunner that uses the Codex CLI to work on large tasks via a simple loop. On each loop we feed the Codex instance the last one's final output along with core documents.
-1. TODO - Tracks long-horizon tasks
-2. PROGRESS - High level overview of what's been done already that may be relevant for future agents
-3. OPINIONS - Guidelines for how we should approach implementation
-4. SPEC - Source-of-truth requirements and scope for large features/projects
+An opinionated autorunner that uses the Codex app-server as the primary execution backend with OpenCode support to work on large tasks via a simple loop. On each loop we feed the Codex instance the last one's final output along with core documents.
+
+In the current model, the primary work surface is **tickets**:
+
+- `.codex-autorunner/tickets/TICKET-###.md`
+
+Optionally, you can maintain lightweight **workspace docs** (auto-created on write; missing is OK):
+
+- `.codex-autorunner/workspace/active_context.md`
+- `.codex-autorunner/workspace/decisions.md`
+- `.codex-autorunner/workspace/spec.md`
 
 ## Sneak Peak
 Run multiple agents on many repositories, with git worktree support
@@ -79,8 +87,7 @@ See the progress of your long running tasks with a high level overview
 Dive deep into specific agent execution with a rich but readable log
 ![Desktop logs](docs/screenshots/car-desktop-logs.png)
 
-All memory and opinions are markdown files! Edit them directly or chat with the document!
-![Desktop TODO](docs/screenshots/car-desktop-todo.png)
+Tickets and workspace docs are markdown files. Edit them directly or use the web UI’s file chat to iterate with the agent.
 
 Use codex CLI directly for multi-shot problem solving or `/review`
 ![Desktop terminal](docs/screenshots/car-desktop-terminal.png)
@@ -90,11 +97,10 @@ Mobile-first experience, code on the go with Whisper support (BYOK)
 
 ## What it does
 - Initializes a repo with Codex-friendly docs and config.
-- Runs Codex in a loop against the repo, streaming logs.
+- Runs Codex app-server in a loop against the repo, streaming logs via OpenCode runtime.
 - Tracks state, logs, and config under `.codex-autorunner/`.
-- Exposes a power-user HTTP API and web UI for docs, logs, runner control, and a Codex TUI terminal.
+- Exposes a power-user HTTP API and web UI for tickets, workspace docs, file chat, logs, runner control, and a Codex TUI terminal.
 - Optionally runs a Telegram bot for interactive, user-in-the-loop Codex sessions.
-- Generates a pasteable repo snapshot (`.codex-autorunner/SNAPSHOT.md`) for sharing with other LLM chats.
 
 CLI commands are available as `codex-autorunner` or the shorter `car`.
 
@@ -164,7 +170,7 @@ If you set a base path, prefix all checks with it.
 
 ## Quick start
 1) Install (editable): `pip install -e .`
-2) Initialize (hub + repo): `codex-autorunner init --git-init` (or `car init --git-init` if you prefer short). This creates the hub config at `.codex-autorunner/config.yml`, plus state/log files and the docs under `.codex-autorunner/`.
+2) Initialize (hub + repo): `codex-autorunner init --git-init` (or `car init --git-init` if you prefer short). This creates the hub config at `.codex-autorunner/config.yml`, plus state/log files and starter content under `.codex-autorunner/` (tickets and optional workspace docs).
 3) Run once: `codex-autorunner once` / `car once`
 4) Continuous loop: `codex-autorunner run` / `car run`
 5) If stuck: `codex-autorunner kill` then `codex-autorunner resume` (or the `car` equivalents)
@@ -229,19 +235,12 @@ If you set `server.auth_token_env`, the API requires `Authorization: Bearer <tok
 - `run` / `once` — run the loop (continuous or single iteration).
 - `resume` — clear stale lock/state and restart; `--once` for a single run.
 - `kill` — SIGTERM the running loop and mark state error.
-- `status` — show current state and outstanding TODO count.
+- `status` — show current state.
 - `sessions` — list terminal sessions (server-backed when available).
 - `stop-session` — stop a terminal session by repo (`--repo`) or id (`--session`).
 - `log` — view logs (tail or specific run).
-- `edit` — open TODO/PROGRESS/OPINIONS/SPEC in `$EDITOR`.
-- `ingest-spec` — generate TODO/PROGRESS/OPINIONS from SPEC using Codex (use `--force` to overwrite).
-- `clear-docs` — reset TODO/PROGRESS/OPINIONS to empty templates (type CLEAR to confirm).
-- `snapshot` — generate/update `.codex-autorunner/SNAPSHOT.md` (incremental by default when one exists; use `--from-scratch` to regenerate).
+- `edit` — open `active_context|decisions|spec` in `$EDITOR`.
 - `serve` — start the HTTP API (FastAPI) on host/port from config (defaults 127.0.0.1:4173).
 
-## Snapshot (repo briefing)
-- Web UI: open the Snapshot tab. If no snapshot exists, you’ll see “Generate snapshot”; otherwise you’ll see “Update snapshot (incremental)” and “Regenerate snapshot (from scratch)”, plus “Copy to clipboard”.
-- CLI: `codex-autorunner snapshot` (or `car snapshot`) writes `.codex-autorunner/SNAPSHOT.md` and `.codex-autorunner/snapshot_state.json`.
-
 ## Star history
 [![Star History Chart](https://api.star-history.com/svg?repos=Git-on-my-level/codex-autorunner&type=Date)](https://star-history.com/#Git-on-my-level/codex-autorunner&Date)

{codex_autorunner-0.1.1 → codex_autorunner-1.0.0}/README.md

@@ -1,11 +1,17 @@
 # codex-autorunner
 [![PyPI](https://img.shields.io/pypi/v/codex-autorunner.svg)](https://pypi.org/project/codex-autorunner/)
 
-An opinionated autorunner that uses the Codex CLI to work on large tasks via a simple loop. On each loop we feed the Codex instance the last one's final output along with core documents.
-1. TODO - Tracks long-horizon tasks
-2. PROGRESS - High level overview of what's been done already that may be relevant for future agents
-3. OPINIONS - Guidelines for how we should approach implementation
-4. SPEC - Source-of-truth requirements and scope for large features/projects
+An opinionated autorunner that uses the Codex app-server as the primary execution backend with OpenCode support to work on large tasks via a simple loop. On each loop we feed the Codex instance the last one's final output along with core documents.
+
+In the current model, the primary work surface is **tickets**:
+
+- `.codex-autorunner/tickets/TICKET-###.md`
+
+Optionally, you can maintain lightweight **workspace docs** (auto-created on write; missing is OK):
+
+- `.codex-autorunner/workspace/active_context.md`
+- `.codex-autorunner/workspace/decisions.md`
+- `.codex-autorunner/workspace/spec.md`
 
 ## Sneak Peak
 Run multiple agents on many repositories, with git worktree support
@@ -17,8 +23,7 @@ See the progress of your long running tasks with a high level overview
 Dive deep into specific agent execution with a rich but readable log
 ![Desktop logs](docs/screenshots/car-desktop-logs.png)
 
-All memory and opinions are markdown files! Edit them directly or chat with the document!
-![Desktop TODO](docs/screenshots/car-desktop-todo.png)
+Tickets and workspace docs are markdown files. Edit them directly or use the web UI’s file chat to iterate with the agent.
 
 Use codex CLI directly for multi-shot problem solving or `/review`
 ![Desktop terminal](docs/screenshots/car-desktop-terminal.png)
@@ -28,11 +33,10 @@ Mobile-first experience, code on the go with Whisper support (BYOK)
 
 ## What it does
 - Initializes a repo with Codex-friendly docs and config.
-- Runs Codex in a loop against the repo, streaming logs.
+- Runs Codex app-server in a loop against the repo, streaming logs via OpenCode runtime.
 - Tracks state, logs, and config under `.codex-autorunner/`.
-- Exposes a power-user HTTP API and web UI for docs, logs, runner control, and a Codex TUI terminal.
+- Exposes a power-user HTTP API and web UI for tickets, workspace docs, file chat, logs, runner control, and a Codex TUI terminal.
 - Optionally runs a Telegram bot for interactive, user-in-the-loop Codex sessions.
-- Generates a pasteable repo snapshot (`.codex-autorunner/SNAPSHOT.md`) for sharing with other LLM chats.
 
 CLI commands are available as `codex-autorunner` or the shorter `car`.
 
@@ -102,7 +106,7 @@ If you set a base path, prefix all checks with it.
 
 ## Quick start
 1) Install (editable): `pip install -e .`
-2) Initialize (hub + repo): `codex-autorunner init --git-init` (or `car init --git-init` if you prefer short). This creates the hub config at `.codex-autorunner/config.yml`, plus state/log files and the docs under `.codex-autorunner/`.
+2) Initialize (hub + repo): `codex-autorunner init --git-init` (or `car init --git-init` if you prefer short). This creates the hub config at `.codex-autorunner/config.yml`, plus state/log files and starter content under `.codex-autorunner/` (tickets and optional workspace docs).
 3) Run once: `codex-autorunner once` / `car once`
 4) Continuous loop: `codex-autorunner run` / `car run`
 5) If stuck: `codex-autorunner kill` then `codex-autorunner resume` (or the `car` equivalents)
@@ -167,19 +171,12 @@ If you set `server.auth_token_env`, the API requires `Authorization: Bearer <tok
 - `run` / `once` — run the loop (continuous or single iteration).
 - `resume` — clear stale lock/state and restart; `--once` for a single run.
 - `kill` — SIGTERM the running loop and mark state error.
-- `status` — show current state and outstanding TODO count.
+- `status` — show current state.
 - `sessions` — list terminal sessions (server-backed when available).
 - `stop-session` — stop a terminal session by repo (`--repo`) or id (`--session`).
 - `log` — view logs (tail or specific run).
-- `edit` — open TODO/PROGRESS/OPINIONS/SPEC in `$EDITOR`.
-- `ingest-spec` — generate TODO/PROGRESS/OPINIONS from SPEC using Codex (use `--force` to overwrite).
-- `clear-docs` — reset TODO/PROGRESS/OPINIONS to empty templates (type CLEAR to confirm).
-- `snapshot` — generate/update `.codex-autorunner/SNAPSHOT.md` (incremental by default when one exists; use `--from-scratch` to regenerate).
+- `edit` — open `active_context|decisions|spec` in `$EDITOR`.
 - `serve` — start the HTTP API (FastAPI) on host/port from config (defaults 127.0.0.1:4173).
 
-## Snapshot (repo briefing)
-- Web UI: open the Snapshot tab. If no snapshot exists, you’ll see “Generate snapshot”; otherwise you’ll see “Update snapshot (incremental)” and “Regenerate snapshot (from scratch)”, plus “Copy to clipboard”.
-- CLI: `codex-autorunner snapshot` (or `car snapshot`) writes `.codex-autorunner/SNAPSHOT.md` and `.codex-autorunner/snapshot_state.json`.
-
 ## Star history
 [![Star History Chart](https://api.star-history.com/svg?repos=Git-on-my-level/codex-autorunner&type=Date)](https://star-history.com/#Git-on-my-level/codex-autorunner&Date)

{codex_autorunner-0.1.1 → codex_autorunner-1.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "codex-autorunner"
-version = "0.1.1"
+version = "1.0.0"
 description = "Codex autorunner CLI per DESIGN-V1"
 readme = "README.md"
 license = {file = "LICENSE"}
@@ -16,6 +16,7 @@ dependencies = [
   "python-multipart>=0.0.9",
   "python-dotenv>=1.0",
   "httpx>=0.27",
+  "tenacity>=8.0",
 ]
 classifiers = [
   "License :: OSI Approved :: MIT License",
@@ -35,6 +36,7 @@ dev = [
   "black==25.11.0",
   "mypy>=1.10",
   "pytest>=7.0",
+  "pytest-asyncio>=0.23",
   "pytest-timeout>=2.0",
   "ruff>=0.5.0",
   "types-PyYAML",
@@ -84,6 +86,11 @@ markers = [
     "integration: marks tests as integration tests that require external dependencies (deselect with '-m \"not integration\"')",
     "timeout(seconds): per-test timeout (provided by pytest-timeout)",
 ]
+filterwarnings = [
+    # Cancelled auto-restart tasks can emit noisy unraisable warnings when the event
+    # loop shuts down; we explicitly clean these up, so silence the residual notice.
+    "ignore::pytest.PytestUnraisableExceptionWarning",
+]
 
 [tool.ruff]
 line-length = 88

codex_autorunner-1.0.0/src/codex_autorunner/__main__.py

@@ -0,0 +1,4 @@
+from .cli import app
+
+if __name__ == "__main__":
+    app()

codex_autorunner-1.0.0/src/codex_autorunner/agents/__init__.py

@@ -0,0 +1,21 @@
+"""Agent harness abstractions."""
+
+from .registry import (
+    AgentCapability,
+    AgentDescriptor,
+    get_agent_descriptor,
+    get_available_agents,
+    get_registered_agents,
+    has_capability,
+    validate_agent_id,
+)
+
+__all__ = [
+    "AgentCapability",
+    "AgentDescriptor",
+    "get_registered_agents",
+    "get_available_agents",
+    "get_agent_descriptor",
+    "validate_agent_id",
+    "has_capability",
+]

{codex_autorunner-0.1.1 → codex_autorunner-1.0.0}/src/codex_autorunner/agents/base.py

@@ -3,11 +3,11 @@ from __future__ import annotations
 from pathlib import Path
 from typing import Any, AsyncIterator, Optional, Protocol
 
-from .types import ConversationRef, ModelCatalog, TurnRef
+from .types import AgentId, ConversationRef, ModelCatalog, TurnRef
 
 
 class AgentHarness(Protocol):
-    agent_id: str
+    agent_id: AgentId
     display_name: str
 
     async def ensure_ready(self, workspace_root: Path) -> None: ...

{codex_autorunner-0.1.1 → codex_autorunner-1.0.0}/src/codex_autorunner/agents/codex/harness.py

@@ -73,7 +73,7 @@ def _coerce_reasoning_efforts(entry: dict[str, Any]) -> list[str]:
 
 
 class CodexHarness(AgentHarness):
-    agent_id: AgentId = "codex"
+    agent_id: AgentId = AgentId("codex")
     display_name = "Codex"
 
     def __init__(

{codex_autorunner-0.1.1 → codex_autorunner-1.0.0}/src/codex_autorunner/agents/opencode/__init__.py

@@ -3,12 +3,16 @@
 from .client import OpenCodeClient
 from .events import SSEEvent, parse_sse_lines
 from .harness import OpenCodeHarness
+from .run_prompt import OpenCodeRunConfig, OpenCodeRunResult, run_opencode_prompt
 from .supervisor import OpenCodeSupervisor
 
 __all__ = [
     "OpenCodeClient",
     "OpenCodeHarness",
+    "OpenCodeRunConfig",
+    "OpenCodeRunResult",
     "OpenCodeSupervisor",
     "SSEEvent",
     "parse_sse_lines",
+    "run_opencode_prompt",
 ]

codex_autorunner-1.0.0/src/codex_autorunner/agents/opencode/agent_config.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+
+import asyncio
+import logging
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger(__name__)
+
+
+async def ensure_agent_config(
+    workspace_root: Path,
+    agent_id: str,
+    model: Optional[str],
+    title: Optional[str] = None,
+    description: Optional[str] = None,
+) -> None:
+    """Ensure .opencode/agent/<agent_id>.md exists with frontmatter config.
+
+    Args:
+        workspace_root: Path to the workspace root
+        agent_id: Agent ID (e.g., "subagent")
+        model: Model ID in format "providerID/modelID" (e.g., "zai-coding-plan/glm-4.7-flashx")
+        title: Optional title for the agent
+        description: Optional description for the agent
+    """
+    if model is None:
+        logger.debug(f"Skipping agent config for {agent_id}: no model configured")
+        return
+
+    agent_dir = workspace_root / ".opencode" / "agent"
+    agent_file = agent_dir / f"{agent_id}.md"
+
+    # Check if file already exists and has the correct model
+    if agent_file.exists():
+        existing_content = agent_file.read_text(encoding="utf-8")
+        existing_model = _extract_model_from_frontmatter(existing_content)
+        if existing_model == model:
+            logger.debug(f"Agent config already exists for {agent_id}: {agent_file}")
+            return
+
+    # Create agent directory if needed
+    await asyncio.to_thread(agent_dir.mkdir, parents=True, exist_ok=True)
+
+    # Build agent markdown with frontmatter
+    content = _build_agent_md(
+        agent_id=agent_id,
+        model=model,
+        title=title or agent_id,
+        description=description or f"Subagent for {agent_id} tasks",
+    )
+
+    # Write atomically
+    await asyncio.to_thread(agent_file.write_text, content, encoding="utf-8")
+    logger.info(f"Created agent config: {agent_file} with model {model}")
+
+
+def _build_agent_md(
+    agent_id: str,
+    model: str,
+    title: str,
+    description: str,
+) -> str:
+    """Generate markdown with YAML frontmatter.
+
+    Frontmatter format per OpenCode config schema:
+    ---
+    agent: <agent_id>
+    title: "<title>"
+    description: "<description>"
+    model: <providerID>/<modelID>
+    ---
+
+    <Optional agent instructions go here>
+    """
+    return f"""---
+agent: {agent_id}
+title: "{title}"
+description: "{description}"
+model: {model}
+---
+"""
+
+
+def _extract_model_from_frontmatter(content: str) -> Optional[str]:
+    """Extract model value from YAML frontmatter.
+
+    Returns None if frontmatter or model field is not found.
+    """
+    lines = content.splitlines()
+    if not lines or not lines[0].startswith("---"):
+        return None
+
+    for _i, line in enumerate(lines[1:], start=1):
+        if line.startswith("---"):
+            break
+        if line.startswith("model:"):
+            model = line.split(":", 1)[1].strip()
+            return model if model else None
+
+    return None
+
+
+__all__ = ["ensure_agent_config"]