"""Ollama client for digest synthesis.

Talks to the existing Phase 3 Ollama host over plain HTTP (`/api/generate` with
`"format": "json"`, Ollama's structured-output mode) — no SDK, matching this
project's preference for not pulling a dependency to make one POST.

DIGEST JSON SCHEMA
------------------
Every call returns exactly one document of this shape. The same schema is
restated in each prompt file under synth/prompts/ so the model sees it verbatim;
keep the two in sync when changing either.

    {
      "generated_at": "2026-07-28T12:00:00Z",
      "detail_level": "compact" | "full",
      "section": "personal" | "political" | "household" | "network",
      "windows": [
        {
          "id": "string, unique within this section",
          "title": "string",
          "kind": "text" | "list" | "globe",
          "content": "markdown-ish string for kind=text, or an array of strings for kind=list",
          "sources": [
            {
              "title": "headline or page title",
              "outlet": "who published it",
              "owner": "who owns that outlet, as the context gives it",
              "bias": "that outlet's politics, as the context gives it",
              "url": "https://...",
              "quote": "verbatim excerpt"
            }
          ],
          "globe_markers": [
            {
              "lat": 0.0,
              "lon": 0.0,
              "label": "string",
              "icon": "star|hammer-sickle|default",
              "color": "#hex",
              "glow": true,
              "summary": "what is happening at this location",
              "sources": [ ... same shape as above ... ]
            }
          ]
        }
      ],
      "narration": "a short plain-text script suitable for TTS narration of this section, 2-4 sentences"
    }

`globe_markers` is only present (and non-empty) on `kind: "globe"` windows, which
in practice only the political section produces.

`sources` is optional everywhere and may appear on any window and on any marker.
The renderer folds it into a collapsed "Sources (n)" block — on screen the claim
is what you read and the citations are one tap underneath, so a section can be
fully sourced without turning the canvas into a bibliography. A marker's
`summary` is its briefing, rendered under the globe rather than as a tooltip,
because the globe rotates and a marker's own face is not always toward you.

WHICH SECTIONS RUN
------------------
`SECTIONS` is every section this component knows how to generate; which of them a
given run actually generates is decided by the household, not here — see
../preferences.py and generate_all()'s `sections` argument. A section nobody has
ticked in the identity admin panel costs no call at all.

DETAIL LEVELS
-------------
Each enabled section is generated twice per run, once at `compact` and once at
`full`, rather than generating `full` once and truncating it client-side:
truncation gives you the first N windows of a document written to be expansive,
so a "compact" window can still hold a 400-word blob that overflows the HA
Lovelace iframe card, whereas a second pass yields prose actually written to be
terse. The cost is one extra call per enabled section against a local, self-hosted
Ollama on a batch timer — no per-token bill and no latency anyone is waiting on —
so correctness of the compact rendering wins. Both passes reuse one ingestion pass
and one assembled context, which is what docs/project-plan.md means by "without
needing two independent generation passes".
"""

import json
import logging
import os
from datetime import datetime, timezone
from pathlib import Path

import requests

LOG = logging.getLogger(__name__)

# Every section this component can generate, in the order they are laid out on the
# canvas. `network` was carved out of the household section rather than added next to
# it: the household prompt was already carrying the firewall's IDS summary as "one
# small household item", and a household that wants to know about its calendar without
# a nightly intrusion-detection readout (or the reverse) had no way to say so while the
# two shared one document.
SECTIONS = ("personal", "political", "household", "network")
DETAIL_LEVELS = ("compact", "full")

PROMPT_DIR = Path(__file__).parent / "prompts"

DETAIL_INSTRUCTIONS = {
    "compact": "detail_level: compact — keep to 1-2 windows, terse",
    "full": "detail_level: full — feel free to compose 3-6 windows with more depth",
}


def _now_iso():
    return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")


def _fallback_document(section, detail_level, text, title="Digest (plain text fallback)"):
    """A schema-valid document wrapping whatever the model actually said.

    The render layer already degrades gracefully on malformed input, but emitting
    a valid document here means the failure shows up as one readable window
    instead of a <pre> dump of a stack trace.
    """
    return {
        "generated_at": _now_iso(),
        "detail_level": detail_level,
        "section": section,
        "windows": [
            {
                "id": f"{section}-fallback",
                "title": title,
                "kind": "text",
                "content": text or "No digest content was produced for this section.",
            }
        ],
        "narration": "",
        "degraded": True,
    }


def _coerce_sources(raw):
    """Normalises a window's or a marker's `sources` list, dropping anything that
    isn't at least identifiable. Kept permissive on purpose: a citation with a
    title and no URL is still a citation, and dropping it would make the digest
    look better-sourced than it is by hiding the weak entries. What it is NOT
    permissive about is shape — a string, or a dict of nothing, is not a source.
    """
    sources = []
    for entry in raw or []:
        if not isinstance(entry, dict):
            continue
        source = {
            key: str(entry.get(key)).strip()
            for key in ("title", "outlet", "owner", "bias", "url", "quote")
            if entry.get(key)
        }
        if source:
            sources.append(source)
    return sources


def _coerce_document(raw, section, detail_level):
    if not isinstance(raw, dict):
        raise ValueError("model output was not a JSON object")

    windows = []
    for index, window in enumerate(raw.get("windows") or []):
        if not isinstance(window, dict):
            continue
        kind = window.get("kind") if window.get("kind") in ("text", "list", "globe") else "text"
        coerced = {
            "id": str(window.get("id") or f"{section}-{index}"),
            "title": str(window.get("title") or ""),
            "kind": kind,
            "content": window.get("content", ""),
        }
        sources = _coerce_sources(window.get("sources"))
        if sources:
            coerced["sources"] = sources
        if kind == "globe":
            markers = []
            for marker in window.get("globe_markers") or []:
                if not isinstance(marker, dict):
                    continue
                try:
                    coerced_marker = {
                        "lat": float(marker.get("lat", 0.0)),
                        "lon": float(marker.get("lon", 0.0)),
                        "label": str(marker.get("label") or ""),
                        "icon": str(marker.get("icon") or "default"),
                        "color": str(marker.get("color") or "#8ab4ff"),
                        "glow": bool(marker.get("glow", False)),
                    }
                except (TypeError, ValueError):
                    continue
                # The marker's own briefing: what is happening there, and the
                # citations behind it, rendered under the globe by render.js. Both
                # optional — a marker with neither is still a marker.
                if marker.get("summary"):
                    coerced_marker["summary"] = str(marker["summary"])
                marker_sources = _coerce_sources(marker.get("sources"))
                if marker_sources:
                    coerced_marker["sources"] = marker_sources
                markers.append(coerced_marker)
            coerced["globe_markers"] = markers
        windows.append(coerced)

    if not windows:
        raise ValueError("model output contained no usable windows")

    return {
        "generated_at": raw.get("generated_at") or _now_iso(),
        "detail_level": detail_level,
        "section": section,
        "windows": windows,
        "narration": str(raw.get("narration") or ""),
    }


def load_prompt(section):
    return (PROMPT_DIR / f"{section}.md").read_text(encoding="utf-8")


def _merge_instruction(context):
    """Added centrally here rather than in each of the three prompt files: whether the
    previous run went unviewed is run-orchestration state (see ../viewed_tracker.py and
    run.py's should_merge()), identical in wording for every section, and unrelated to
    each section's own analytical framing — duplicating it three times in prose that's
    supposed to stay in sync would be the actual maintenance burden, not this.
    """
    if not context.get("previous_unviewed_digest"):
        return ""
    return (
        "\n## Unviewed previous digest\n\n"
        "`previous_unviewed_digest` in the context below is this section's own "
        "content from the last run — and nobody has looked at it yet: no thin client "
        "has shown a digest since it was generated (see its `generated_at`). Combine "
        "it with this run's new material into ONE digest, not two: carry forward "
        "whatever in it is still current, drop whatever this run's material has "
        "superseded, corrected, or made irrelevant, and never state the same point "
        "twice. Do not mention that a merge happened, and do not treat the previous "
        "narration as something to read verbatim — write one narration for the "
        "combined result.\n"
    )


def build_prompt(section, detail_level, context):
    return (
        f"{load_prompt(section)}\n"
        f"{_merge_instruction(context)}\n"
        "## Run context\n\n"
        "```json\n"
        f"{json.dumps(context, indent=2, ensure_ascii=False, default=str)}\n"
        "```\n\n"
        f"{DETAIL_INSTRUCTIONS[detail_level]}\n"
        f"current time (UTC): {_now_iso()}\n"
    )


def generate_section(section, detail_level, context):
    host = os.environ.get("OLLAMA_HOST", "http://llm-host:11434").rstrip("/")
    model = os.environ.get("OLLAMA_MODEL", "qwen2.5:14b-instruct")
    timeout = float(os.environ.get("OLLAMA_TIMEOUT", "600"))

    payload = {
        "model": model,
        "prompt": build_prompt(section, detail_level, context),
        "stream": False,
        "format": "json",
        "options": {"temperature": float(os.environ.get("OLLAMA_TEMPERATURE", "0.4"))},
    }

    try:
        response = requests.post(f"{host}/api/generate", json=payload, timeout=timeout)
        response.raise_for_status()
        text = response.json().get("response", "")
    except Exception:
        LOG.warning(
            "synth: Ollama call failed for %s/%s, emitting a degraded document",
            section,
            detail_level,
            exc_info=True,
        )
        return _fallback_document(
            section,
            detail_level,
            f"The {section} digest could not be generated: the LLM host at {host} did not respond.",
            title=f"{section.title()} — unavailable",
        )

    try:
        return _coerce_document(json.loads(text), section, detail_level)
    except Exception:
        LOG.warning(
            "synth: %s/%s output did not match the digest schema, falling back to plain text",
            section,
            detail_level,
            exc_info=True,
        )
        return _fallback_document(section, detail_level, text.strip())


def generate_all(section_contexts, sections=None):
    """`sections` is the subset the household actually asked for (../preferences.py);
    None means all of them. Ordering always follows SECTIONS rather than the caller's
    list, so the canvas doesn't reshuffle itself when somebody edits a checkbox.
    """
    wanted = SECTIONS if sections is None else [s for s in SECTIONS if s in sections]
    documents = {level: [] for level in DETAIL_LEVELS}
    for detail_level in DETAIL_LEVELS:
        for section in wanted:
            LOG.info("synth: generating %s/%s", section, detail_level)
            documents[detail_level].append(
                generate_section(section, detail_level, section_contexts.get(section, {}))
            )
    return documents