"""Integration: the phase-106 D5 date surfaces against REAL Postgres
rows (task 06).

The two tool surfaces the model reads carry the document's creation
date: the ``read`` result's SECOND line (``date: YYYY-MM-DD`` — the
FIRST line stays the byte-identical ``Document {source}/{path}:``
header the E2E mock's ``_READ_RESULT_PREFIX`` contract keys on) and
the ``ls`` FILE line's APPENDED `` | date: YYYY-MM-DD`` field (the
mock's ``_CATALOG_LINE_RE`` ``title: .+$`` tail absorbs it). The rows
carry DISTINCT fixed ``created_at`` values, so the pins prove the date
is the ROW's date (per row), not a constant.

Requires:  podman compose up -d db
"""
from __future__ import annotations

import asyncio
import uuid
from collections.abc import AsyncIterator, Iterator
from copy import deepcopy
from datetime import UTC, datetime
from typing import TYPE_CHECKING, Any, cast

import pytest
from sqlalchemy import delete, text
from sqlalchemy.orm import Session

from app.config import Settings
from app.db import SessionLocal
from app.models import Document, GitSource
from app.rag.agent import AgentHolder, run_agent
from app.rag.llm import LLMClient, RetryPiece, StreamPiece, ToolCallPiece, ToolResultPiece

if TYPE_CHECKING:
    from app.rag.scaffolding import ScaffoldingFilter

#: DISTINCT fixed creation dates — the per-row date pins (task 06):
#: each document renders ITS OWN row's UTC date part.
D1 = datetime(2019, 6, 15, 3, 4, 6, tzinfo=UTC)  # "2019-06-15"
D2 = datetime(2020, 1, 2, 5, 0, 0, tzinfo=UTC)  # "2020-01-02"
D3 = datetime(2024, 6, 15, 23, 59, 59, tzinfo=UTC)  # "2024-06-15" (late UTC instant)

D1_STR, D2_STR, D3_STR = "2019-06-15", "2020-01-02", "2024-06-15"


def _doc(
    db: Session,
    source: str,
    path: str,
    title: str,
    content: str,
    created_at: datetime,
) -> Document:
    doc = Document(
        id=uuid.uuid4(),
        source=source,
        path=path,
        full_path=f"/tmp/{source}/{path}",
        title=title,
        content=content,
        content_hash="0" * 64,
        created_at=created_at,  # D1: explicit — the pins prove per-row dates
    )
    db.add(doc)
    return doc


@pytest.fixture()
def kb(db) -> Iterator[None]:
    """Fresh documents table (chunks first — the FK)."""
    db.execute(text("TRUNCATE chunks, documents"))
    db.commit()
    yield
    db.execute(text("TRUNCATE chunks, documents"))
    db.commit()


@pytest.fixture()
def src(db) -> Iterator[GitSource]:
    """One registered git source — the scoped ``ls`` source-name check
    reads the real registry (``repo_name`` resolves the URL to
    ``Homelab``)."""
    row = GitSource(url="https://github.com/reese/Homelab.git", kind="git")
    db.add(row)
    db.commit()
    yield row
    db.execute(delete(GitSource).where(GitSource.id == row.id))
    db.commit()


class ScriptedToolLLM:
    """One scripted tool-call stream, then one canned answer stream.
    Records every ``chat_stream`` request's messages and tools."""

    def __init__(self, call: ToolCallPiece) -> None:
        self.call = call
        self.requests: list[
            tuple[list[dict[str, Any]], list[dict[str, Any]] | None]
        ] = []

    async def chat_stream(
        self,
        messages: list[dict[str, str]],
        tools: list[dict[str, Any]] | None = None,
        scaffolding: ScaffoldingFilter | None = None,
    ) -> AsyncIterator[StreamPiece | ToolCallPiece]:
        self.requests.append((deepcopy(messages), deepcopy(tools)))
        if len(self.requests) == 1:
            yield self.call
        else:
            yield StreamPiece("content", "ans")


def _settings(**kwargs: Any) -> Settings:
    kwargs.setdefault("_env_file", None)
    return Settings(**kwargs)  # pyright: ignore[reportCallIssue]


def _run_call(
    db: Session, name: str, arguments: dict[str, Any]
) -> tuple[AgentHolder, ScriptedToolLLM]:
    """Drive one scripted tool call through ``run_agent``."""
    holder = AgentHolder()
    llm = ScriptedToolLLM(ToolCallPiece(id="call_1", name=name, arguments=arguments))
    asyncio.run(_consume(cast("LLMClient", llm), db, holder))
    return holder, llm


async def _consume(
    llm: LLMClient, db: Session, holder: AgentHolder
) -> list[StreamPiece | ToolCallPiece | RetryPiece | ToolResultPiece]:
    """SEC-14-04: uses a short-lived session per tool call."""
    out: list[StreamPiece | ToolCallPiece | RetryPiece | ToolResultPiece] = []
    async for piece in run_agent(
        llm,
        lambda: SessionLocal(),  # SEC-14-04: session factory (short-lived sessions)
        system_prompt="SYSTEM_PROMPT",
        user_message="QUESTION",
        seed_docs=[],
        settings=_settings(),
        holder=holder,
    ):
        out.append(piece)
    return out


# --------------------------------------------------------------------
# read — the date is the stored row's date, on the SECOND line
# --------------------------------------------------------------------


def test_read_result_second_line_is_stored_date(kb, db) -> None:
    """A real row (distinct ``created_at``): the ``read`` result's
    SECOND line is the stored date (the UTC date part), the FIRST line
    stays the byte-identical header, and the content follows whole."""
    created = _doc(
        db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT", D2
    )
    db.commit()

    holder, llm = _run_call(db, "read", {"path": "Alpha/deep/nested/doc.md"})

    content = llm.requests[1][0][3]["content"]
    lines = content.splitlines()
    assert lines[0] == "Document Alpha/deep/nested/doc.md:"  # byte-identical header
    assert lines[1] == f"date: {D2_STR}"  # the STORED date (row's UTC date part)
    assert lines[2:] == ["FULL-TEXT"]
    # SEC-14-04: short-lived session loads fresh copies
    assert [d.id for d in holder.read_docs] == [created.id]
    assert holder.tool_calls == 1


def test_read_result_date_is_the_row_date_not_a_constant(kb, db) -> None:
    """Two rows with DISTINCT dates: each ``read`` renders its OWN
    row's date (a late-UTC instant renders its date part, no time)."""
    a = _doc(db, "Alpha", "a.md", "A", "A-TEXT", D1)
    b = _doc(db, "Alpha", "b.md", "B", "B-TEXT", D3)
    db.commit()

    holder_a, llm_a = _run_call(db, "read", {"path": "Alpha/a.md"})
    assert llm_a.requests[1][0][3]["content"] == (
        f"Document Alpha/a.md:\ndate: {D1_STR}\nA-TEXT"
    )
    holder_b, llm_b = _run_call(db, "read", {"path": "Alpha/b.md"})
    assert llm_b.requests[1][0][3]["content"] == (
        f"Document Alpha/b.md:\ndate: {D3_STR}\nB-TEXT"
    )
    # SEC-14-04: short-lived sessions
    assert [d.id for d in holder_a.read_docs] == [a.id]
    assert [d.id for d in holder_b.read_docs] == [b.id]


# --------------------------------------------------------------------
# ls — every FILE line carries its date in the appended field
# --------------------------------------------------------------------


def test_ls_drill_file_lines_carry_their_dates(kb, src, db) -> None:
    """A source drill against real rows: EVERY file line ends with the
    appended `` | date: YYYY-MM-DD`` field — each row's OWN stored date
    — while the header and subfolder lines stay date-free."""
    _doc(db, "Homelab", "backups/cron.md", "Cron", "CRON", D1)
    _doc(db, "Homelab", "backups/restic.md", "Restic", "RESTIC", D2)
    _doc(db, "Homelab", "networking/lan.md", "LAN", "LAN", D3)
    _doc(db, "Homelab", "readme.md", "Readme", "README", D1)
    db.commit()

    holder, llm = _run_call(db, "ls", {"path": "Homelab"})

    content = llm.requests[1][0][3]["content"]
    lines = content.splitlines()
    # The root level: one direct file (readme.md — D1) + the two
    # subfolder lines (date-free) + the date-free header.
    assert lines[0] == "Homelab — 1 documents, 2 folders:"
    assert lines[2] == "  backups/ — 2 documents"  # subfolder: no date
    assert lines[3] == "  networking/ — 1 documents"  # subfolder: no date
    assert lines[5] == (
        f"source: Homelab | path: readme.md | title: Readme | date: {D1_STR}"
    )
    assert holder.tool_calls == 1

    # Drill into backups: BOTH files list, each with its OWN date.
    holder2, llm2 = _run_call(db, "ls", {"path": "Homelab/backups"})
    lines2 = llm2.requests[1][0][3]["content"].splitlines()
    assert lines2[0] == "Homelab/backups — 2 documents, 0 folders:"
    assert lines2[2] == (
        f"source: Homelab | path: backups/cron.md | title: Cron | date: {D1_STR}"
    )
    assert lines2[3] == (
        f"source: Homelab | path: backups/restic.md | title: Restic | date: {D2_STR}"
    )
    assert holder2.tool_calls == 1


def test_ls_top_level_source_lines_carry_no_date(kb, db) -> None:
    """The top level (source lines) is UNCHANGED in shape — sources are
    not documents, so no date rides them (only FILE lines do). The
    registry is FRESH (truncated + the one source re-registered), so
    the top level is exactly the one source block."""
    db.execute(text("TRUNCATE git_sources"))
    db.commit()
    db.add(GitSource(url="https://github.com/reese/Homelab.git", kind="git"))
    db.commit()
    try:
        _doc(db, "Homelab", "a.md", "A", "A-TEXT", D1)
        db.commit()

        holder, llm = _run_call(db, "ls", {})

        content = llm.requests[1][0][3]["content"]
        assert content == "1 sources:\n\nHomelab — 1 documents"
        assert "date" not in content
        assert holder.tool_calls == 1
    finally:
        db.execute(text("TRUNCATE git_sources"))
        db.commit()