"""Integration: the agent DB accessors against real Postgres (phase 37;
the harness-aligned ``ls``/``read``/``grep`` surface, phase 70).

``list_catalog`` must order rows by ``(source, path)`` — the same order
as ``GET /api/docs`` — ``list_source_names`` must resolve the
registered source names (the scoped ``ls`` join), and ``find_document``
must resolve a hit to the full document row (content included, for the
never-truncated read) and return ``None`` for unknown pairs. Phase 70:
the ``ls``/``read``/``grep`` tools are pinned here too — the locked
parameter shape in ``AGENT_TOOLS``, and scripted ``ToolCallPiece``s
executed through ``run_agent`` against the real DB: ``ls`` scoped to a
registered source name (unknown name → refusal), ``read`` on the
canonical combined ``source/path`` form (first-slash split; a bare
source name and an unknown identity get the no-document refusal), and
``grep`` (``all_documents`` for a whole-KB search, ``find_document`` for
a scoped one).

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 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.models import Document, GitSource
from app.rag import agent
from app.rag.agent import AGENT_TOOLS, AgentHolder, run_agent
from app.rag.llm import LLMClient, RetryPiece, StreamPiece, ToolCallPiece

if TYPE_CHECKING:
    from app.rag.scaffolding import ScaffoldingFilter


def _doc(db: Session, source: str, path: str, title: str, content: str) -> Document:
    doc = Document(
        id=uuid.uuid4(),
        source=source,
        path=path,
        full_path=f"/tmp/{source}/{path}",
        title=title,
        content=content,
        content_hash="0" * 64,
    )
    db.add(doc)
    return doc


@pytest.fixture()
def kb(db) -> Iterator[None]:
    """Fresh documents table (chunks first — the FK) for these accessors."""
    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, so the row is inserted and deleted around
    the tests (``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()


def test_list_catalog_orders_by_source_then_path(kb, db) -> None:
    _doc(db, "Zeta", "b/second.md", "Zeta B", "ZB")
    _doc(db, "Zeta", "a/first.md", "Zeta A", "ZA")
    _doc(db, "Alpha", "c/third.md", "Alpha C", "AC")
    db.commit()

    assert agent.list_catalog(db) == [
        ("Alpha", "c/third.md", "Alpha C"),
        ("Zeta", "a/first.md", "Zeta A"),
        ("Zeta", "b/second.md", "Zeta B"),
    ]


def test_list_catalog_is_empty_without_rows(kb, db) -> None:
    assert agent.list_catalog(db) == []


def test_list_source_names_resolves_registry_rows(db) -> None:
    """The real registry: git names resolve through the import pipeline's
    ``repo_name`` (trailing ``.git`` stripped); a second row resolving to
    the same name (the phase-69 sibling case) is listed once."""
    a = GitSource(url="https://github.com/reese/Homelab.git", kind="git")
    b = GitSource(url="https://github.com/reese/Homelab", kind="git")  # sibling
    c = GitSource(url="https://e.com/deployments", kind="git")
    db.add_all([a, b, c])
    db.commit()
    try:
        assert agent.list_source_names(db).count("Homelab") == 1  # deduped
        assert "deployments" in agent.list_source_names(db)
    finally:
        db.execute(delete(GitSource).where(GitSource.id.in_([a.id, b.id, c.id])))
        db.commit()


def test_find_document_hit_returns_full_row(kb, db) -> None:
    created = _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
    db.commit()

    found = agent.find_document(db, "Alpha", "deep/nested/doc.md")
    assert found is not None
    assert found.id == created.id
    assert found.source == "Alpha"
    assert found.path == "deep/nested/doc.md"
    assert found.title == "The Doc"
    assert found.content == "FULL-TEXT"  # the read tool feeds this, untruncated


def test_find_document_none_for_unknown_pairs(kb, db) -> None:
    _doc(db, "Alpha", "x.md", "X", "X-CONTENT")
    db.commit()

    assert agent.find_document(db, "Alpha", "nope.md") is None  # wrong path
    assert agent.find_document(db, "Beta", "x.md") is None  # wrong source
    assert agent.find_document(db, "nope", "nope.md") is None  # nothing at all


# ---------- AGENT_TOOLS surface (phase 70: ls / read / grep) ----------


def test_agent_tools_offers_the_harness_aligned_surface() -> None:
    by_name = {t["function"]["name"]: t for t in AGENT_TOOLS}
    assert list(by_name) == [  # the harness order, phase 70
        "ls",
        "read",
        "grep",
    ]
    ls = by_name["ls"]["function"]["parameters"]
    assert ls["type"] == "object"
    assert ls["required"] == []  # path is optional
    assert set(ls["properties"]) == {"path"}
    read = by_name["read"]["function"]["parameters"]
    assert read["type"] == "object"
    assert read["required"] == ["path"]
    assert set(read["properties"]) == {"path"}
    grep = by_name["grep"]["function"]["parameters"]
    assert grep["type"] == "object"
    assert grep["required"] == ["pattern"]
    assert set(grep["properties"]) == {"pattern", "path"}
    assert all(p["type"] == "string" for p in grep["properties"].values())


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,  # phase 71 pass-through
    ) -> 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(llm, db, holder))
    return holder, llm


async def _consume(
    llm: ScriptedToolLLM, db: Session, holder: AgentHolder
) -> list[StreamPiece | ToolCallPiece | RetryPiece]:
    out: list[StreamPiece | ToolCallPiece | RetryPiece] = []
    async for piece in run_agent(
        cast("LLMClient", llm),
        db,
        system_prompt="SYSTEM_PROMPT",
        user_message="QUESTION",
        seed_docs=[],
        settings=_settings(),
        holder=holder,
    ):
        out.append(piece)
    return out


# ---------- ls (scoped through the real registry) ----------


def test_ls_scoped_to_registered_source_through_run_agent(kb, src, db) -> None:
    _doc(db, "Homelab", "a.md", "A", "A-CONTENT")
    _doc(db, "Other", "b.md", "B", "B-CONTENT")
    db.commit()

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

    # Offered: the first request carries AGENT_TOOLS (the 3-tool list).
    assert llm.requests[0][1] == AGENT_TOOLS
    # Executed against the real DB: the listing filtered to the source.
    assert llm.requests[1][0][3]["content"] == (
        "1 documents:\nsource: Homelab | path: a.md | title: A"
    )
    assert holder.tool_calls == 1
    assert holder.read_docs == []


def test_ls_scoped_unknown_source_refused_through_run_agent(kb, src, db) -> None:
    _doc(db, "Homelab", "a.md", "A", "A-CONTENT")
    db.commit()

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

    assert (
        llm.requests[1][0][3]["content"] == "No source named 'Ghost' — check the ls output."
    )
    assert holder.tool_calls == 0 and holder.read_docs == []


# ---------- read (the canonical combined source/path form) ----------


def test_read_combined_path_through_run_agent(kb, db) -> None:
    """The combined ``source/path`` identity resolves at the FIRST slash
    against the REAL table (a path with further slashes included): the
    read executes, the holder records the row, the result header carries
    the true source/path."""
    created = _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
    db.commit()

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

    assert llm.requests[1][0][3]["content"] == (
        "Document Alpha/deep/nested/doc.md:\nFULL-TEXT"
    )
    assert holder.tool_calls == 1
    assert holder.read_docs == [created]


def test_read_bare_source_name_refused_through_run_agent(kb, db) -> None:
    """A bare source name (no '/') can never be a document — the
    no-document refusal echoing the argument as passed; the old
    split-teaching refusal is gone (phase 70)."""
    _doc(db, "Alpha", "deep/nested/doc.md", "The Doc", "FULL-TEXT")
    db.commit()

    holder, llm = _run_call(db, "read", {"path": "Alpha"})

    assert (
        llm.requests[1][0][3]["content"] == "No document at 'Alpha' — check the ls output."
    )
    assert holder.tool_calls == 0 and holder.read_docs == []


def test_read_unknown_combined_path_refused_through_run_agent(kb, db) -> None:
    """A combined identity that matches nothing gets the no-document
    refusal (the argument echoed as passed — the model sees its own
    form)."""
    _doc(db, "Alpha", "x.md", "X", "X-CONTENT")
    db.commit()

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

    assert (
        llm.requests[1][0][3]["content"]
        == "No document at 'Alpha/nope/deep.md' — check the ls output."
    )
    assert holder.tool_calls == 0 and holder.read_docs == []


# ---------- grep (the phase-68 A5 contract under the new name) ----------


def test_all_documents_orders_by_source_then_path(kb, db) -> None:
    _doc(db, "Zeta", "b/second.md", "Zeta B", "ZB")
    _doc(db, "Zeta", "a/first.md", "Zeta A", "ZA")
    _doc(db, "Alpha", "c/third.md", "Alpha C", "AC")
    db.commit()

    docs = agent.all_documents(db)
    assert [(d.source, d.path) for d in docs] == [
        ("Alpha", "c/third.md"),
        ("Zeta", "a/first.md"),
        ("Zeta", "b/second.md"),
    ]
    assert [d.content for d in docs] == ["AC", "ZA", "ZB"]  # full rows


def test_grep_whole_kb_through_run_agent(kb, db) -> None:
    _doc(db, "Beta", "b/two.md", "Two", "no hit\nNEEDLE in two\nlast")
    _doc(db, "Alpha", "a/one.md", "One", "first\nneedle in one\nthird")
    db.commit()

    holder, llm = _run_call(db, "grep", {"pattern": "needle"})

    # Offered: the first request carries AGENT_TOOLS (the 3-tool list).
    assert llm.requests[0][1] == AGENT_TOOLS
    # Executed against the real DB: catalog order, grep-style lines.
    assert llm.requests[1][0][3]["content"] == (
        "Alpha/a/one.md:2: needle in one\n"
        "Beta/b/two.md:2: NEEDLE in two"
    )
    assert holder.tool_calls == 1
    assert holder.read_docs == []  # locked A5: grep adds no context


def test_grep_scoped_through_run_agent(kb, db) -> None:
    _doc(db, "Alpha", "a/one.md", "One", "first\nNeedle here\nthird")
    _doc(db, "Beta", "b/two.md", "Two", "NEEDLE too")
    db.commit()

    holder, llm = _run_call(db, "grep", {"pattern": "needle", "path": "Alpha/a/one.md"})

    # Only the named document is searched — the other one's hit is absent.
    assert llm.requests[1][0][3]["content"] == "Alpha/a/one.md:2: Needle here"
    assert holder.tool_calls == 1
    assert holder.read_docs == []


def test_grep_scoped_missing_doc_refused_through_run_agent(kb, db) -> None:
    _doc(db, "Alpha", "a/one.md", "One", "nothing")
    db.commit()

    holder, llm = _run_call(db, "grep", {"pattern": "needle", "path": "Alpha/ghost.md"})

    assert (
        llm.requests[1][0][3]["content"]
        == "No document at 'Alpha/ghost.md' — check the ls output."
    )
    assert holder.tool_calls == 0 and holder.read_docs == []


def test_grep_no_matches_through_run_agent(kb, db) -> None:
    _doc(db, "Alpha", "a/one.md", "One", "nothing matching")
    db.commit()

    holder, llm = _run_call(db, "grep", {"pattern": "zebra"})

    assert llm.requests[1][0][3]["content"] == (
        "No matches for 'zebra' in the knowledge base."
    )
    assert holder.tool_calls == 1  # an executed grep with zero hits
    assert holder.read_docs == []