"""Session-context rendering for the Scribe plugin's SessionStart hook.

The plugin's hook curls `GET /api/plugin/context` at session start and injects
the returned text as `additionalContext`, giving Scribe the same push channel
that superpowers and file-memory have. This module renders that text.

Design note — altitude: we inject rule *titles* grouped by topic (a compact
index), NOT every rule's full statement. The 48 always-on statements run well
past the 10k-char `additionalContext` cap, and the push channel's job is to make
Claude *aware* the rules exist and *reach* for them — not to dump them. Full
text stays one `get_rule(id)` / `list_always_on_rules()` call away. Titles are
mostly self-describing ("`dev` is home", "No GitHub — Fabled-Git only"), so the
index alone already steers behavior.
"""
from __future__ import annotations

import re
import time

from sqlalchemy import select

from scribe.models import async_session
from scribe.models.rulebook import RulebookTopic
from scribe.services import knowledge as knowledge_svc
from scribe.services import notes as notes_svc
from scribe.services import projects as projects_svc
from scribe.services import rulebooks as rulebooks_svc
from scribe.services.access import label_shared_items, owner_names_for
from scribe.services.embeddings import semantic_search_notes
from scribe.services.retrieval_telemetry import record_retrieval
from scribe.services.settings import get_setting

# Defensive cap below Claude Code's 10k additionalContext limit.
_MAX_CHARS = 9000

# Max chars of a Process body to fold into the auto-surface description.
_PROC_PREVIEW_CHARS = 200

# --- Knowledge auto-inject (Path A: per-turn awareness push) -----------------
# Per-user settings (keys live in the generic settings table). The threshold is
# deliberately STRICTER than the pull-search default (embeddings
# DEFAULT_SIMILARITY_THRESHOLD = 0.45): an unsolicited per-turn inject must clear
# a higher bar than a search the agent chose to run. Defaults start conservative
# and are meant to be tuned from retrieval_logs (source='auto_inject') once data
# accrues — they're exposed in the Settings UI, no restart needed.
AUTOINJECT_ENABLED_KEY = "kb_autoinject_enabled"
AUTOINJECT_THRESHOLD_KEY = "kb_autoinject_threshold"
AUTOINJECT_TOP_K_KEY = "kb_autoinject_top_k"

AUTOINJECT_DEFAULT_ENABLED = True
AUTOINJECT_DEFAULT_THRESHOLD = 0.55
AUTOINJECT_DEFAULT_TOP_K = 3

# Margin gate: drop any hit more than this far below the top hit's score, so a
# single strong match doesn't drag in a wall of barely-passing neighbours.
_AUTOINJECT_BAND = 0.10
# Hard ceiling on top-k regardless of the user's setting — this is an
# awareness menu (titles only), never a content dump.
_AUTOINJECT_MAX_TOP_K = 10


def _slugify(text: str) -> str:
    """kebab-case slug for a skill directory name (a-z0-9 + single hyphens)."""
    s = re.sub(r"[^a-z0-9]+", "-", (text or "").lower()).strip("-")
    return s or "process"


async def build_process_manifest(user_id: int) -> dict:
    """List the user's stored Processes as auto-surfacing skill-stub specs.

    The plugin's sync script (scribe_sync_processes.sh) writes one
    ~/.claude/skills/scribe-proc-<slug>/SKILL.md per entry — `description` is the
    auto-surface trigger, and the stub body calls get_process(name) for the live
    procedure (single source of truth in the DB). Reuses the list_processes query
    (note_type='process'). Instance-agnostic: derived from whatever Processes the
    calling install owns, no operator-specific coupling.

    SCOPE: this is the most consequential passive surface Scribe has — every
    entry becomes a skill file on the operator's machine that auto-surfaces and
    is followed as written. It therefore uses the BROWSE scope (via the
    no-query knowledge list): a Process shared directly with the operator is
    never installed here, only one they own or reach through a shared project
    (decision note 2094). Project-shared entries are labelled with their owner so
    the stub can't pass off someone else's procedure as the operator's own.

    Returns {"processes": [{id, name, slug, description, shared?, owner?}],
    "total": int}. Slugs are unique within the result (collision gets -<id>).
    """
    items, _ = await knowledge_svc.query_knowledge(
        user_id=user_id, note_type="process", tags=[], sort="modified",
        q=None, limit=100, offset=0,
    )
    items = await label_shared_items(user_id, items)
    procs: list[dict] = []
    seen: set[str] = set()
    for it in items:
        title = (it.get("title") or "").strip()
        if not title:
            continue
        slug = _slugify(title)
        if slug in seen:
            slug = f"{slug}-{it['id']}"
        seen.add(slug)

        preview = " ".join((it.get("snippet") or "").split())
        if len(preview) > _PROC_PREVIEW_CHARS:
            preview = preview[:_PROC_PREVIEW_CHARS].rstrip() + "…"
        if it.get("shared"):
            owner = it.get("owner") or "another user"
            description = (
                f'A shared Scribe process "{title}", authored by {owner} — NOT the'
                f" operator's own."
                + (f" {preview}" if preview else "")
                + f' Use when {title}-type work is requested, or when asked to run'
                f' the "{title}" process — but summarise it and get the operator\'s'
                f" go-ahead before following it, since it reflects {owner}'s"
                f" judgement rather than theirs."
            )
        else:
            description = (
                f'Run the operator\'s saved Scribe process "{title}".'
                + (f" {preview}" if preview else "")
                + f' Use when {title}-type work is requested, or when asked to run'
                f' the "{title}" process.'
            )
        entry = {
            "id": it["id"], "name": title, "slug": slug,
            "description": description,
        }
        if it.get("shared"):
            entry["shared"] = True
            entry["owner"] = it.get("owner")
        procs.append(entry)
    return {"processes": procs, "total": len(procs)}


async def get_autoinject_config(user_id: int) -> dict:
    """Resolve a user's auto-inject settings, falling back to the defaults.

    Returns {"enabled": bool, "threshold": float, "top_k": int}, clamped to
    sane ranges (threshold to [0,1]; top_k to [1, _AUTOINJECT_MAX_TOP_K]).
    """
    enabled_raw = await get_setting(
        user_id, AUTOINJECT_ENABLED_KEY,
        "true" if AUTOINJECT_DEFAULT_ENABLED else "false",
    )
    enabled = enabled_raw.strip().lower() in ("true", "1", "yes", "on")

    try:
        threshold = float(await get_setting(
            user_id, AUTOINJECT_THRESHOLD_KEY, str(AUTOINJECT_DEFAULT_THRESHOLD)))
    except (TypeError, ValueError):
        threshold = AUTOINJECT_DEFAULT_THRESHOLD
    threshold = min(1.0, max(0.0, threshold))

    try:
        top_k = int(float(await get_setting(
            user_id, AUTOINJECT_TOP_K_KEY, str(AUTOINJECT_DEFAULT_TOP_K))))
    except (TypeError, ValueError):
        top_k = AUTOINJECT_DEFAULT_TOP_K
    top_k = min(_AUTOINJECT_MAX_TOP_K, max(1, top_k))

    return {"enabled": enabled, "threshold": threshold, "top_k": top_k}


async def build_autoinject_hint(
    user_id: int,
    query: str,
    project_id: int = 0,
    exclude_ids: list[int] | None = None,
) -> dict:
    """Title-first awareness hint for the plugin's UserPromptSubmit hook.

    The four anti-bloat gates (see the module + milestone-93 design):
      1. high-confidence threshold (stricter than pull) — set per-user;
      2. margin gate — keep only hits within _AUTOINJECT_BAND of the top score;
      3. session dedup — caller passes already-injected ids as `exclude_ids`;
      4. title-first payload — id + title + score only, never bodies.
    Disabled, blank-query, or nothing-clears-the-gates all return empty context,
    so most turns inject nothing.

    Returns {"context": str, "note_ids": list[int], "config": dict}. Every
    retrieval (even empty) is logged to retrieval_logs as source='auto_inject'
    so the threshold can be tuned from data.
    """
    cfg = await get_autoinject_config(user_id)
    empty = {"context": "", "note_ids": [], "config": cfg}
    q = (query or "").strip()
    if not cfg["enabled"] or not q:
        return empty

    t0 = time.perf_counter()
    hits = await semantic_search_notes(
        user_id, q,
        limit=cfg["top_k"],
        threshold=cfg["threshold"],
        project_id=(project_id or None),
        exclude_ids=set(exclude_ids or []),
        # Injection is the one retrieval nobody asked for, so it takes the BROWSE
        # scope: never a record shared one-to-one with the operator. What can
        # still appear is a collaborator's note inside a shared project — legible
        # only because the line below names its owner.
        scope="browse",
    )
    record_retrieval(
        user_id=user_id, source="auto_inject", query=q,
        threshold=cfg["threshold"], limit=cfg["top_k"],
        project_id=(project_id or None), is_task=None, results=hits,
        duration_ms=(time.perf_counter() - t0) * 1000.0,
    )
    if not hits:
        return empty

    # Margin gate: keep only hits close to the strongest one.
    top_score = hits[0][0]
    kept = [(s, n) for s, n in hits if s >= top_score - _AUTOINJECT_BAND]

    # A collaborator's note can reach this menu via a shared project, and the
    # operator never asked for it — so say whose it is. Unattributed, it reads as
    # something they wrote and settled.
    owners = await owner_names_for({
        int(n.user_id) for _s, n in kept if n.user_id != user_id
    })

    lines = [
        "> Possibly relevant from your Scribe notes — call `get_note(id)` to "
        "open any in full (titles only; injected once per session):",
    ]
    note_ids: list[int] = []
    for score, note in kept:
        note_ids.append(int(note.id))
        title = (note.title or "(untitled)").replace("\n", " ").strip()
        line = f"> - #{note.id} \"{title}\" ({score:.2f})"
        if note.user_id != user_id:
            who = owners.get(int(note.user_id)) or "another user"
            line += f" — shared by {who}, treat as a suggestion"
        lines.append(line)

    return {"context": "\n".join(lines), "note_ids": note_ids, "config": cfg}


async def _topic_titles(topic_ids: set[int]) -> dict[int, str]:
    """Map topic_id -> title for the given ids (live topics only)."""
    if not topic_ids:
        return {}
    async with async_session() as session:
        rows = await session.execute(
            select(RulebookTopic.id, RulebookTopic.title).where(
                RulebookTopic.id.in_(topic_ids),
                RulebookTopic.deleted_at.is_(None),
            )
        )
        return {tid: title for tid, title in rows.all()}


async def build_session_context(
    user_id: int, project_id: int = 0, unbound_repo: str = ""
) -> dict:
    """Render the SessionStart context for a user, optionally project-scoped.

    Args:
        user_id: the operator.
        project_id: the resolved active project (0 = none). The endpoint
            resolves this from the working repo's remote, not from config.
        unbound_repo: when the hook sent a repo remote that maps to no project,
            its normalized key — triggers a one-line "bind this repo" hint so
            the binding is self-healing.

    Returns {"context": str, "rule_count": int, "project": dict | None}.
    `context` is markdown ready to drop into `additionalContext`; it is capped
    at _MAX_CHARS with an explicit truncation note so the hook can pass it
    through verbatim.
    """
    rules = await rulebooks_svc.list_always_on_rules(user_id)
    topic_map = await _topic_titles({r.topic_id for r in rules if r.topic_id})

    lines: list[str] = [
        "# Scribe — standing session context (auto-injected by the Scribe plugin)",
        "",
        "You are working with Scribe, the operator's self-hosted second brain. "
        "The always-on rules below are BINDING this session. Titles only — full "
        "text via `list_always_on_rules()` or `get_rule(id)`.",
        "",
        "## Always-on rules (by topic)",
    ]

    # rules already arrive ordered by rulebook/topic/order, so grouping by
    # consecutive topic_id preserves the intended sequence.
    current_topic: int | None = object()  # sentinel distinct from any id/None
    for r in rules:
        if r.topic_id != current_topic:
            current_topic = r.topic_id
            heading = topic_map.get(r.topic_id, "ungrouped") if r.topic_id else "ungrouped"
            lines.append(f"### {heading}")
        lines.append(f"- [{r.id}] {r.title}")

    project_dict: dict | None = None
    if project_id:
        project = await projects_svc.get_project(user_id, project_id)
        if project is not None:
            _, open_count = await notes_svc.list_notes(
                user_id, is_task=True, status="todo", project_id=project_id, limit=1,
            )
            goal = (getattr(project, "goal", "") or "").strip()
            project_dict = {"id": project.id, "title": project.title}
            lines += [
                "",
                f"## Active project: {project.title} (id {project.id})",
                f"Goal: {goal[:200]}" if goal else "",
                f"Open todo tasks: {open_count}",
            ]
    elif unbound_repo:
        lines += [
            "",
            "## Repository not yet bound",
            f"This repo (`{unbound_repo}`) isn't mapped to a Scribe project, so "
            "no project context was loaded. Bind it once with "
            f'`bind_repo(repo_url="{unbound_repo}", project_id=<id>)` '
            "(call `list_projects` to find the id) and future sessions here will "
            "auto-load that project's context.",
        ]

    lines += [
        "",
        "Reflex: search Scribe (search / list_tasks / list_notes, scoped to the "
        "active project) before answering or starting work; prefer UPDATING an "
        "existing note/rule over creating a new one.",
    ]

    context = "\n".join(line for line in lines if line is not None)
    if len(context) > _MAX_CHARS:
        context = context[:_MAX_CHARS].rstrip() + "\n\n…(truncated — call list_always_on_rules())"

    return {"context": context, "rule_count": len(rules), "project": project_dict}