beaver-gateway/src/beaver_gateway/frontends/markdown/mirror.py

"""Vault files for ``deep`` conversations that were not typed into a file.

``materialize`` creates the file for a conversation spawned elsewhere;
``run`` appends replies produced by other origins and keeps the canonical
history in sync so a continuation typed in Obsidian resumes the same session.
"""

from __future__ import annotations

import asyncio
import logging
from datetime import UTC, datetime
from typing import TYPE_CHECKING, Any

import frontmatter

from beaver_gateway.frontends.markdown import renderer
from beaver_gateway.frontends.markdown.crossfront import strip_trailing_user_scaffold
from beaver_gateway.frontends.markdown.files import (
    read_or_empty,
    reattach_frontmatter,
    write_atomic,
)
from beaver_gateway.frontends.markdown.history import load_messages, rewrite_messages
from beaver_gateway.frontends.turn_record import slugify

if TYPE_CHECKING:
    from collections.abc import Callable, Sequence
    from pathlib import Path

    from beaver_gateway.events.bus import Event
    from beaver_gateway.frontends.base import GatewayRuntime
    from beaver_gateway.storage.models import Conversation, ConversationBinding

__all__ = ["FRONTEND", "ChatMirror"]

_log = logging.getLogger("beaver_gateway.frontends.markdown.mirror")

FRONTEND = "markdown"


class ChatMirror:
    def __init__(
        self,
        *,
        vault_path: Path,
        runtime: GatewayRuntime,
        logged_subdir: str,
        chat_path: Callable[[str, str, Path], Path] | None = None,
    ) -> None:
        self._vault = vault_path
        self._runtime = runtime
        self._root = vault_path / logged_subdir
        self._chat_path_fn = chat_path
        self._lock = asyncio.Lock()

    def path_for(self, title: str, agent: str) -> Path:
        if self._chat_path_fn is not None:
            path = self._chat_path_fn(title, agent, self._vault)
            if not path.is_absolute():
                path = self._vault / path
        else:
            day = datetime.now(UTC).strftime("%Y-%m-%d")
            path = self._root / agent / f"{day}_{slugify(title, maxlen=60)}.md"
        if path.suffix != ".md":
            path = path.with_suffix(".md")
        path = path.resolve()
        path.relative_to(self._vault)
        candidate, n = path, 1
        while candidate.exists():
            n += 1
            candidate = path.with_name(f"{path.stem} ({n}){path.suffix}")
        return candidate

    async def materialize(self, conv: Conversation) -> ConversationBinding:
        path = self.path_for(conv.title or conv.external_id, conv.agent_name)
        rel = path.relative_to(self._vault).as_posix()
        async with self._lock:
            await write_atomic(path, reattach_frontmatter(_frontmatter(conv), ""))
        binding = await self._runtime.conversations.bind(
            conv, frontend=FRONTEND, external_id=rel
        )
        _log.info("materialized %s as %s", conv.external_id, rel)
        return binding

    async def bound_path(self, conv: Conversation) -> Path | None:
        for b in await self._runtime.conversations.bindings(conv):
            if b.frontend == FRONTEND and b.visible:
                return self._vault / b.external_id
        return None

    async def run(self) -> None:
        async for event in self._runtime.bus.stream():
            if event.get("type") != "reply":
                continue
            try:
                await self._on_reply(event)
            except Exception:  # noqa: BLE001
                _log.exception("mirror of reply %s failed", event.get("turn_id"))

    async def _on_reply(self, event: Event) -> None:
        conv = await self._runtime.conversations.get(str(event["conversation_id"]))
        if conv is None:
            return
        await self.append(
            conv,
            prompt=str(event.get("prompt") or ""),
            text=str(event.get("text") or ""),
            history=event.get("history"),
        )

    async def append(
        self,
        conv: Conversation,
        *,
        prompt: str,
        text: str,
        history: Sequence[dict[str, Any]] | None = None,
    ) -> None:
        path = await self.bound_path(conv)
        if path is None:
            return
        prior = [
            {"role": str(h["role"]), "content": str(h["text"])}
            for h in history or ()
            if h.get("text")
        ]
        async with self._lock:
            parsed = frontmatter.loads(await read_or_empty(path))
            body = strip_trailing_user_scaffold(parsed.content)
            if prior and "### " not in body:
                for m in prior:
                    body = renderer.append_to_body(body, _render(m))
            body = renderer.append_to_body(body, renderer.render_user_text(prompt))
            body = renderer.append_to_body(body, renderer.render_assistant_text(text))
            body = renderer.append_to_body(body, renderer.USER_SCAFFOLD)
            metadata = {**parsed.metadata, **_frontmatter(conv)}
            metadata.pop("fingerprint", None)
            await write_atomic(path, reattach_frontmatter(metadata, body))
        await self._persist(conv, prior=prior, prompt=prompt, text=text)

    async def _persist(
        self, conv: Conversation, *, prior: list[dict[str, Any]], prompt: str, text: str
    ) -> None:
        if conv.id is None:
            return
        async with self._runtime.db.session() as session:
            stored = await load_messages(session, conversation_id=conv.id)
            canonical = [
                *(stored or prior),
                {"role": "user", "content": prompt},
                {"role": "assistant", "content": [{"type": "text", "text": text}]},
            ]
            await rewrite_messages(session, conversation_id=conv.id, messages=canonical)


def _frontmatter(conv: Conversation) -> dict[str, Any]:
    return {"agent": conv.agent_name, "conversation_id": conv.external_id}


def _render(message: dict[str, Any]) -> str:
    if message["role"] == "user":
        return renderer.render_user_text(message["content"])
    return renderer.render_assistant_text(message["content"])