refactor: no comments left - one-line module docstrings, contracts on public fields only; jobs/job.py; example config and README

This commit is contained in:
hh
2026-09-02 00:33:04 +02:00
parent 90d0fb0f00
commit c9c2e94954
65 changed files with 795 additions and 1891 deletions
+35 -175
View File
@@ -1,204 +1,64 @@
# Sample user config — grows alongside the implementation phases.
#
# Loader (beaver_gateway/config_loader.py) execs this file with
# ClaudeAgent, RaycastAgent, McpServer, ExposedMcp, Gateway already
# bound — so importing them is optional. We import explicitly here so
# IDEs and type-checkers see real symbols instead of free variables.
"""The smallest setup: one agent, one tool, one job, the built-in frontends.
The loader execs this file with ``ClaudeAgent``, ``RaycastAgent``,
``McpServer``, ``ExposedMcp`` and ``Gateway`` already bound; the imports
below are for type checkers. A real setup grows into a package next to
this file (see beaver-agent).
"""
import logging
import tempfile
from datetime import date
from datetime import UTC, datetime
from pathlib import Path
from beaver_gateway.agents.base import ExposedMcp
from beaver_gateway.agents.claude import ClaudeAgent
from beaver_gateway.agents.raycast import RaycastAgent, RemoteTool, UserPreferences
from beaver_gateway.app import Gateway
from beaver_gateway.frontends.turn_record import slugify
from beaver_gateway.agents.claude import ClaudeAgent, Prompts
from beaver_gateway.config import Gateway
from beaver_gateway.frontends.admin import AdminFrontend
from beaver_gateway.frontends.anthropic import AnthropicMessagesFrontend
from beaver_gateway.frontends.api import ApiFrontend
from beaver_gateway.frontends.markdown import MarkdownFrontend
from beaver_gateway.frontends.mcp_server import McpServerFrontend
from beaver_gateway.jobs.scheduler import Job, JobRun
from beaver_gateway.mcp.types import McpServer
log = logging.getLogger("example")
def chat_path(title: str, agent: str, vault: Path) -> Path: # noqa: ARG001
"""Where a new chat file lands in the vault.
Called by ``MarkdownFrontend`` for every conversation that needs a
file: a ``deep`` chat spawned by the dispatcher, a ``/v1/messages``
chat (``title`` = first user message), or with ``log_all_chats=True``
the archive of a stateless agent's turns. Return value can be
absolute or relative; relative paths are anchored under ``vault``.
Layout below: ``<vault>/<YYYY-MM>/<YYYY-MM-DD>_<topic>.md``.
"""
today = date.today()
return vault / f"{today:%Y-%m}" / f"{today:%Y-%m-%d}_{slugify(title, maxlen=40)}.md"
VAULT = Path(tempfile.mkdtemp(prefix="beaver-vault-")).resolve()
PROMPT = VAULT / "assistant.md"
PROMPT.write_text(
"You are a concise assistant. When asked the time, call `current_time`.\n"
)
def current_time() -> str:
"""Return the current local time as an ISO-8601 string.
return datetime.now(UTC).astimezone().isoformat()
Trivial demo tool for the Phase 2.1 internal MCP aggregator —
confirms a ``python_tool`` namespace is reachable on
``http://127.0.0.1:<INTERNAL_MCP_PORT>/mcp/time``.
"""
from datetime import datetime
return datetime.now().astimezone().isoformat()
async def heartbeat(run: JobRun) -> None:
master = await run.master()
log.info("heartbeat: master=%s", master.external_id if master else None)
gateway = Gateway(
agents=[
# Phase 2.2 — ClaudeCodeBackendAdapter routes this agent's
# ``/v1/messages`` calls through ``claude-code-api``. The
# ``time`` MCP gets exposed as ``mcp__time__current_time`` to
# the subscription claude session via
# ``BackendOptions.mcp_servers`` pointing at the internal
# aggregator on ``127.0.0.1:INTERNAL_MCP_PORT/mcp/time/``.
#
# Fresh empty tempdir (not a hardcoded ``/tmp``) for two
# reasons: claude-code-api derives the JSONL project-key from
# ``cwd``, but claude itself writes the JSONL using the cwd's
# realpath — on macOS ``/tmp`` and ``/var/folders/...`` are
# both ``/private/...`` symlinks, so unresolved cwds make
# ``JsonlWatcher`` time out waiting on the wrong path. The
# explicit ``.resolve()`` collapses the symlink before claude
# ever sees the dir, and ``mkdtemp`` guarantees the directory
# is empty so claude does not pick up leftover files.
ClaudeAgent(
name="stub",
model="claude-sonnet-4-6",
# ``system_prompt`` is appended to claude's built-in agent
# prompt (via ``--append-system-prompt``) — so it adds the
# agent's identity on top of claude-code's baseline tool
# knowledge, rather than replacing it. Same shape as the
# RaycastAgent's ``system_prompt → additional_system_instructions``
# mapping. For full ``BackendOptions`` knobs (timeouts,
# extra_args, history mode, etc.) import ``ClaudeCodeOptions``
# and pass ``options=ClaudeCodeOptions(...)``.
system_prompt=(
"You are a stub agent used to validate the Phase 0 skeleton.\n"
"If asked the current time, call the `current_time`"
" MCP tool instead of guessing."
),
cwd=Path(tempfile.mkdtemp(prefix="beaver-stub-cwd-")).resolve(),
name="assistant",
model="claude-sonnet-5",
cwd=VAULT,
prompts=Prompts(master=(PROMPT,), branch=(PROMPT,), deep=(PROMPT,)),
gateway_tools=("spawn", "say", "schedule"),
expose_mcps=(ExposedMcp(name="time"),),
),
# Phase 1.2 — a RaycastAgent the AnthropicMessagesFrontend will
# route via RaycastBackend. Phase 1.5 added the per-agent knobs
# (`temperature` / `additional_system_instructions` / etc.) —
# only `model`, `system_prompt`, and at least one of the others
# is mandatory.
RaycastAgent(
name="research",
model="Gemini 3.1 Flash Lite",
system_prompt=(
"You are a research assistant. "
"Reply in the user's language. Cite URLs when you use web search."
),
temperature=0.5,
available_native_tools=(RemoteTool.WEB_SEARCH, RemoteTool.READ_PAGE),
# Lambda so today's date is rebuilt on every request while
# locale/timezone stay pinned. ``True`` would give the same
# fresh-date behaviour but would also auto-pick host locale
# and timezone (``en-US`` / system tz), which isn't what we
# want here.
user_preferences=lambda: UserPreferences(
locale="en-GB",
timezone="Europe/Berlin",
current_date=date.today().isoformat(), # noqa: DTZ011 — local date is intended
),
),
],
mcps=[
# Phase 2.1 — bundle of plain Python callables exposed as one
# FastMCP namespace. The internal aggregator mounts it under
# ``/mcp/time`` on ``127.0.0.1:INTERNAL_MCP_PORT``; Phase 2.2's
# ClaudeCode adapter forwards that URL into
# ``BackendOptions.mcp_servers``. Phase 3's ``McpServerFrontend``
# reverse-proxies the same internal URL out to external clients.
McpServer.python_tool(name="time", tools=[current_time])
# Phase 3 — illustrates the ``lenient`` flag. Real-world stdio MCPs
# sometimes print "Processing..." or other chatter to stdout before
# their actual JSON-RPC frames; the default mcp client forwards
# those parse failures downstream as warnings (visible in
# Cursor/Cline). With ``lenient=True`` we silently drop non-JSON
# lines, so downstream UIs see clean JSON-RPC only. The command
# below is just a placeholder — replace with whatever stdio MCP
# you actually want gateway to ingest (e.g. an obsidian-mcp).
#
# Commented out by default: example users won't have the binary
# installed and an unreachable command makes ``docker compose up``
# surface a confusing "command not found" line at first request.
# Uncomment after pointing ``command`` at a real stdio MCP.
#
# McpServer.stdio(
# name="obsidian",
# command=["uvx", "mcp-obsidian"],
# env={"OBSIDIAN_API_KEY": "..."},
# lenient=True,
# ),
)
],
mcps=[McpServer.python_tool(name="time", tools=[current_time])],
frontends=[
# Phase 1.4 — expose the agents as `model=<name>` on an
# Anthropic-compatible Messages endpoint. Auth comes from
# `BOOTSTRAP_TOKENS` in the env (`name1:value1,name2:value2`).
#
# Every HTTP frontend is mounted under its own path on the one
# gateway port (`Gateway.port`, 8000 here): `/anthropic/v1/messages`.
# Behind a reverse proxy set `Gateway(public_url="https://domain.com")`
# so advertised endpoints use the outside origin; the proxy just
# forwards everything to the gateway, no prefix stripping.
AnthropicMessagesFrontend(),
# Phase 3 — re-exposes every declared `McpServer` outside the
# gateway with bearer auth + audit log. Each namespace lives at
# `/mcp/<name>/`; a flat bundle is published at `/mcp/all/`.
# Discovery page (HTML, auth-gated) at `/mcp/` with copy-pastable
# Cursor / Claude Desktop snippets. Auth re-uses `BOOTSTRAP_TOKENS`.
McpServerFrontend(),
# Phase 4.3 — browser admin UI. Creds come from
# `ADMIN_USER`/`ADMIN_PASS`; the session cookie is signed with
# `SESSION_SECRET`. Use it to mint tokens (Argon2-hashed in
# the DB), revoke them, and watch the audit log. Scope is
# enforced on the bearer frontends: tokens minted with scope
# `messages` only work on `/v1/messages`; `mcp` only on
# `/mcp/<name>`; `*` works everywhere. Served at `/admin/`; `/`
# redirects there.
AdminFrontend(),
# Obsidian-vault chat frontend. Each `.md` is one conversation
# (User/Assistant turn pairs). The Obsidian companion plugin
# POSTs `{filename, content?}` to `/chat` — the frontend reads
# the file, runs the agent if the last turn is `user`, and
# appends the assistant reply back. With `log_all_chats=True`
# *every* turn (from Anthropic Messages too) is mirrored into
# `{vault}/_logs/<agent>/` so the vault is the central archive.
#
# `vault_path` here points at a per-restart tempdir so the
# example boots cleanly; in real deployments mount the
# Obsidian-sync container's vault volume to a stable path and
# pass that instead.
# Mounted at `/md` (`/md/chat`, `/md/chat/stream`).
MarkdownFrontend(
# Point at the dedicated chats subdir of your real Obsidian
# vault — the gateway has no idea (and no need) about other
# notes outside it. Path resolution / vault-escape checks
# are anchored here, so absolute-path attempts (and ``..``
# tricks) can't reach notes alongside it.
#
# vault_path=Path("/Users/me/Obsidian/Personal/chats"),
#
# Per-restart tempdir kept here so the example boots even
# without a real vault on the host.
vault_path=Path(tempfile.mkdtemp(prefix="beaver-vault-")).resolve(),
default_agent="research",
log_all_chats=True,
# ``chat_path`` (optional) overrides the default
# ``{vault}/_logs/<agent>/<date>_<slug>.md`` layout. Heads up:
# any custom path forces ``warm_index`` to scan the entire
# vault on startup so the fingerprint→file map of archived
# stateless chats survives a restart no matter where you put
# files.
chat_path=chat_path,
),
ApiFrontend(master_agent="assistant", branch_agent="assistant"),
MarkdownFrontend(vault_path=VAULT / "chats", default_agent="assistant"),
],
jobs=[Job("heartbeat", heartbeat, cron="0 * * * *")],
tz="UTC",
)