brain-of-reese/app/rag/summarizer.py

"""Document summarizer (phase 30, task 03) + image descriptions
(phase 122, task 03).

Builds the ``SUMMARY_MODE`` prompt for one document, calls the aipi
``lite`` model through the one-shot ``LLMClient.chat`` (phase 30,
task 01), and returns the validated summary text with a
**code-deterministic** pointer line back to the source::

    Source: <source>/<path>

The pointer is appended by this module, never model-generated — the
model is told what to summarize, not to cite.

Quality contracts enforced here:

* **Capped input** — the document content is cut at
  ``BOR_SUMMARY_MAX_CHARS`` (default 12 000) before the single model
  call; overflow is cut exactly at the cap and the shared
  ``TRUNCATION_MARKER`` (``[…truncated…]``) is appended, so the model
  never sees more than the cap and the cut is visible.
* **No silent summaries** — a reply that is empty after trimming raises
  :class:`LLMError` (the client already rejects empty content; the
  summarizer re-asserts defensively and never hands the importer a
  pointer-only row).

Image descriptions (phase 122, LOCKED A3): :func:`describe_image` is
this module's second one-shot generation path — a SINGLE CHAT-model
(vision) call describing one image's bytes as a base64 data URL. The
description becomes the image document's ``content`` AND ``summary``
(it is the ONLY embedded text of the doc — the embedding model never
sees pixels, and the ``lite`` summary model is deliberately NOT used:
it is not assumed vision-capable). Fail-soft by contract: any client
error, empty reply, or non-2xx yields ``None`` — the importer skips
the doc, counts ``images_failed``, and the sync continues.

The ``SUMMARY_MODE`` / ``IMAGE_DESCRIPTION_MODE`` markers follow the
``DEFLECT_MODE`` convention: the deterministic E2E mock LLM keys on
them (``tests/e2e/mock_llm.py`` — the image branch is wired by task
06's story suite).
"""
from __future__ import annotations

import base64
import logging
from typing import Any, Protocol

from app.config import Settings, get_settings
from app.rag.llm import LLMError
from app.rag.retriever import TRUNCATION_MARKER

logger = logging.getLogger("app.summarizer")

#: System-prompt marker for summary generation — the E2E mock LLM keys on
#: it (same convention as ``DEFLECT_MODE``, PLAN §6).
SUMMARY_MODE = "SUMMARY_MODE"

#: Locked instruction for the ``lite`` model (phase 30): the summary is a
#: natural-language retrieval target, so it must be plain, concrete, and
#: strictly grounded in the document.
SUMMARY_INSTRUCTION = (
    "Write a 3-6 sentence plain-text summary of this document in natural "
    "language. Cover what it configures/defines and its most important "
    "values. Do not use markdown. Do not invent anything that is not in "
    "the document."
)

#: Full system prompt: marker first (the mock's key), then the instruction.
SYSTEM_PROMPT = f"{SUMMARY_MODE}: {SUMMARY_INSTRUCTION}"

#: Image-description marker (phase 122, task 03) — the deterministic
#: E2E mock LLM keys on it (same convention as ``SUMMARY_MODE`` /
#: ``DEFLECT_MODE``, PLAN §6; the story suite wires the mock's branch
#: in task 06). It heads the text part of the multimodal describe
#: message, so it rides the user message, not a system prompt.
IMAGE_DESCRIPTION_MODE = "IMAGE_DESCRIPTION_MODE"

#: Locked instruction for the CHAT (vision) model (phase 122, LOCKED
#: A3): the description is the ONLY retrievable text of the image
#: document (the embedding model never sees pixels), so it must be a
#: faithful, retrieval-oriented account that carries the image's full
#: meaning — what is depicted, any visible text/labels/titles,
#: diagram/table structure, salient details.
DESCRIBE_INSTRUCTION = (
    "Describe this image faithfully, in plain text, for a search index. "
    "State what is depicted, transcribe any visible text, labels, or "
    "titles, describe the structure of any diagram, table, or layout, and "
    "call out the most salient details. Write 2-4 sentences of substance. "
    "Do not use markdown. Do not invent anything that is not visible in "
    "the image. Your description is the ONLY text that will ever be "
    "retrieved for this image — it must carry the image's full meaning."
)

#: The full describe prompt: marker first (the mock's key), then the
#: instruction — the single text part of the multimodal user message.
DESCRIBE_PROMPT = f"{IMAGE_DESCRIPTION_MODE}: {DESCRIBE_INSTRUCTION}"

#: Extension → MIME type for the image family (phase 122). Dotted,
#: lowercase keys — the ``image_extension_set`` shape. Task 03 uses it
#: for the describe call's data-URL mime; task 04's serve route reuses
#: it for the image bytes' ``Content-Type`` (one map, one truth). A
#: ``BOR_IMAGE_EXTENSIONS`` token outside this map (a custom format)
#: takes the :data:`IMAGE_FALLBACK_MIME` data-URL mime in the describe
#: call — the vision endpoint may reject it, and the fail-soft skip
#: (``images_failed``) is the honest outcome.
IMAGE_MIMES: dict[str, str] = {
    ".png": "image/png",
    ".jpg": "image/jpeg",
    ".jpeg": "image/jpeg",
    ".webp": "image/webp",
    ".gif": "image/gif",
    ".bmp": "image/bmp",
}

#: The data-URL mime for an image extension :data:`IMAGE_MIMES` does not
#: name (phase 122) — the best-effort generic, never a guess at a
#: specific type.
IMAGE_FALLBACK_MIME = "application/octet-stream"


def image_data_url(data: bytes, mime: str) -> str:
    """One image's bytes as a data URL for a multimodal message (phase
    122; factored for phase 123, task 01).

    ``data:<mime>;base64,<ascii>`` — the OpenAI-compatible ``image_url``
    payload's ``url``. ONE helper, both call sites: :func:`describe_image`
    (document-image descriptions) and the chat question-image path
    (``app.api.chat``'s multimodal user message, phase 123).
    """
    return f"data:{mime};base64,{base64.b64encode(data).decode('ascii')}"


class SummaryLLM(Protocol):
    """The one-shot chat surface the summarizer needs.

    :class:`app.rag.llm.LLMClient` satisfies it; unit tests pass a
    duck-typed fake (``chat`` + ``settings``) instead — same pattern as
    the importer's ``Embedder`` protocol.

    ``content`` may be a string (text calls — ``generate_summary``) or
    a list of OpenAI-compatible parts (phase 122 multimodal image
    descriptions — ``{type: "text", …}`` + ``{type: "image_url", …}``);
    the client passes message dicts through untouched.
    """

    settings: Settings

    async def chat(
        self, messages: list[dict[str, Any]], model: str | None = None
    ) -> str: ...


def _capped_content(content: str, max_chars: int | None) -> str:
    """Document content for the user message, capped at *max_chars*.

    The default cap is ``BOR_SUMMARY_MAX_CHARS``. Overflow is cut exactly
    at the cap and the shared ``TRUNCATION_MARKER`` is appended on its
    own line; content that fits (length ≤ cap) passes through unchanged.
    """
    limit = max_chars if max_chars is not None else get_settings().summary_max_chars
    if len(content) <= limit:
        return content
    return content[:limit] + "\n" + TRUNCATION_MARKER


def build_summary_prompt(
    source: str, path: str, content: str, max_chars: int | None = None
) -> tuple[str, str]:
    """The ``(system, user)`` message pair for one summary call.

    * ``system`` — :data:`SYSTEM_PROMPT`: the ``SUMMARY_MODE`` marker +
      the locked instruction.
    * ``user`` — the document content, capped (see :func:`_capped_content`).

    *source* and *path* are part of the signature so the call site reads
    like the document it summarizes (and for :func:`generate_summary`'s
    pointer) — the pointer is built in code and deliberately **not** part
    of the prompt, so the model cannot echo or mangle it.
    """
    return SYSTEM_PROMPT, _capped_content(content, max_chars)


async def generate_summary(
    llm: SummaryLLM, *, source: str, path: str, content: str
) -> str:
    """One-shot ``lite`` summary of *content*, ending in the pointer line.

    Returns the model's text (trimmed) plus the deterministic
    ``Source: <source>/<path>`` line — the pointer is appended by code,
    never model-generated. Raises :class:`LLMError` when the model
    returns nothing usable after trimming, and propagates any
    :class:`LLMError` the client raises (the importer's fail-soft path
    turns that into a logged, counted ``summary_errors`` entry).
    """
    system, user = build_summary_prompt(source, path, content)
    raw = await llm.chat(
        [{"role": "system", "content": system}, {"role": "user", "content": user}],
        model=llm.settings.llm_summary_model,
    )
    summary = raw.strip()
    if not summary:
        raise LLMError(
            f"summary model returned empty content for {source}/{path} — "
            "refusing to store a silent summary"
        )
    return f"{summary}\nSource: {source}/{path}"


async def describe_image(
    llm: SummaryLLM,
    *,
    data: bytes,
    mime: str,
    settings: Settings | None = None,
) -> str | None:
    """One-shot CHAT-model (vision) description of one image (phase 122,
    LOCKED A3) — the text that becomes the image document's ``content``
    AND ``summary`` (the ONLY embedded text of the doc; the embedding
    model never sees pixels).

    ONE chat-model call against ``settings.llm_chat_model`` (the vision
    model — the ``lite`` summary model is NOT assumed vision-capable)
    with the multimodal user message the OpenAI-compatible API expects:
    ``[{type: "text", text: DESCRIBE_PROMPT}, {type: "image_url",
    image_url: {url: <data URL from *data* + *mime*>}}]`` — no system
    prompt, no tools, no app-level retries beyond the client's own
    (SDK-level + the house one-shot empty-content policy) — a
    description failure must not stall a sync.

    Returns the stripped reply cut exactly at
    ``(settings or llm.settings).summary_max_chars`` (the phase-30 cap —
    the description IS the summary, so it keeps the same uniform
    ceiling). Returns ``None`` on any client error, empty reply, or
    non-2xx (the client raises :class:`LLMError` for all three classes)
    — the caller (the importer's ``_describe_or_skip`` seam) fails soft:
    the doc is skipped, counted in ``images_failed``, and the sync
    continues (LOCKED A3).
    """
    data_url = image_data_url(data, mime)
    messages: list[dict[str, Any]] = [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": DESCRIBE_PROMPT},
                {"type": "image_url", "image_url": {"url": data_url}},
            ],
        }
    ]
    model = llm.settings.llm_chat_model
    try:
        raw = await llm.chat(messages, model=model)
    except LLMError as e:
        logger.warning("image description failed (model=%s): %s", model, e)
        return None
    text = raw.strip()
    if not text:
        # The client already rejects empty content; this is the
        # defensive re-assert (the duck-typed fakes may return it).
        return None
    limit = (settings or llm.settings).summary_max_chars
    return text[:limit]