src/agents/slow_path/prompt.py

"""Builds the Assembler LLM human-message content.

The system prompt (`config/prompts/assembler.md`) carries the role and rules. This
module assembles the per-call human content: the business context + the executed
`RunState` (task objectives, statuses, and structured tool outputs) + the original
question. Tool outputs are rendered compactly as data — the model turns them into
prose and markdown tables.
"""

from __future__ import annotations

from ..planner.contracts import BusinessContext, ToolOutput
from ..planner.prompt import render_business_context
from .schemas import RunAssessment, RunState, TaskResult

_MAX_ROWS = 20


def render_run_state(run_state: RunState) -> str:
    lines = [f"Plan: {run_state.plan_id}"]
    if run_state.open_questions:
        lines.append("Open questions carried from the plan:")
        lines.extend(f"  - {q}" for q in run_state.open_questions)
    lines.append("")
    lines.append("Task results (in execution order):")
    for task_id, result in run_state.results.items():
        lines.append(_render_task(task_id, result))
    return "\n".join(lines)


def _render_task(task_id: str, result: TaskResult) -> str:
    lines = [f"- [{result.status}] {task_id}: {result.objective}"]
    if result.error:
        lines.append(f"    note: {result.error}")
    for output in result.outputs:
        lines.append(f"    {_render_output(output)}")
    return "\n".join(lines)


def _render_output(output: ToolOutput) -> str:
    if output.kind == "error":
        return f"({output.tool}) error: {output.error}"
    if output.kind == "table" and output.columns is not None:
        header = ", ".join(output.columns)
        rows = output.rows or []
        preview = "; ".join(
            " | ".join(str(cell) for cell in row) for row in rows[:_MAX_ROWS]
        )
        more = "" if len(rows) <= _MAX_ROWS else f" … (+{len(rows) - _MAX_ROWS} more rows)"
        return f"({output.tool}) table [{header}]: {preview}{more}"
    if output.kind == "chart" and isinstance(output.value, dict):
        # W2 (SPINE_V2_PLAN §4.3): one-line summary only — the raw spec's x/y
        # arrays would flood the prompt. The chart itself reaches the user via
        # GET /api/v1/charts; the narrative only refers to it.
        chart_type = output.value.get("chart_type", "chart")
        title = output.value.get("title") or ""
        plotly = output.value.get("plotly")
        traces = plotly.get("data") if isinstance(plotly, dict) else None
        n_traces = len(traces) if isinstance(traces, list) else 0
        return (
            f"({output.tool}) chart: {chart_type} \"{title}\" ({n_traces} series) — "
            "shown to the user alongside this answer; refer to it, do not restate "
            "its data points"
        )
    meta = f" meta={output.meta}" if output.meta else ""
    return f"({output.tool}) {output.kind}: {output.value}{meta}"


def render_assessment(assessment: RunAssessment) -> str | None:
    """The S1a checkpoint's flags as a short block (SPINE_V2_PLAN §3) — only tasks
    that carry specific notes; a clean run renders nothing (no behavior change)."""
    flagged = [t for t in assessment.tasks if t.notes]
    if not flagged:
        return None
    lines = [f"Overall execution: {assessment.overall}."]
    for t in flagged:
        lines.extend(f"- [{t.verdict}] {t.task_id}: {note}" for note in t.notes)
    lines.append(
        "Name these limitations specifically in the answer — say what was affected "
        "and how it scopes the findings. Do not present partial results as complete, "
        "and never fall back to a generic \"couldn't compute\"."
    )
    return "\n".join(lines)


def build_assembler_prompt(
    run_state: RunState,
    context: BusinessContext,
    question: str | None = None,
    reply_language: str | None = None,
    assessment: RunAssessment | None = None,
) -> str:
    sections = [
        f"# Business context\n\n{render_business_context(context)}",
        f"# Analysis results\n\n{render_run_state(run_state)}",
    ]
    if assessment is not None:
        block = render_assessment(assessment)
        if block:
            sections.append(f"# Execution assessment\n\n{block}")
    if question:
        sections.append(f"# Original question\n\n{question}")
    if reply_language:
        # Imperative + resolved language name (a bare "[Reply language]: X" label is too
        # weak for the structured-output call — the English data render drowns it out).
        # The full rule (incl. explicit-request exception) lives in assembler.md.
        sections.append(
            f"# Reply language (MANDATORY)\n\n"
            f"Write `chat_answer` AND every narrative field entirely in **{reply_language}**. "
            f"The results above use English column names and labels — do NOT let that switch "
            f"your reply to English. (If the user explicitly asked for a different language, "
            f"follow that instead.)"
        )
    return "\n\n".join(sections)