"""Prompt rendering for modes — always natural language, never raw YAML or
JSON dumps.

The base texts (the assistant's system prompt, the no-sources note) are
admin-editable via `app/prompts/overrides.py::get_prompt`; the query mode reads
`query_system` directly and `render_context_turn` reads `query_no_sources`.
"""

from app.prompts.overrides import get_prompt
from app.rag.retrieval import SearchResult


def render_context_turn(results: list[SearchResult], question: str) -> str:
    """The final user turn: the retrieval for THIS question, then the question.

    Deliberately NOT part of the system prompt: keeping the excerpts here lets
    the system prompt AND the conversation history stay byte-identical across a
    conversation's turns, so the endpoint's prompt cache reuses them and only
    this turn's excerpts are fresh work (docs/architecture.md, prompt caching).
    """
    if not results:
        # Refusing to answer a greeting because retrieval found nothing makes the
        # assistant feel broken. It answers from general knowledge, just never as
        # if that were company policy (the UI labels these source-free).
        return f"{get_prompt('query_no_sources')}\n\n{question}"
    blocks = [
        f"[{index}] {result.heading_path or result.title}\n{result.content}"
        for index, result in enumerate(results, start=1)
    ]
    excerpts = "\n\n---\n\n".join(blocks)
    return f"Knowledge base excerpts:\n\n{excerpts}\n\nQuestion:\n{question}"