"""LabAgent — in-flow feedback over simulated sandbox telemetry (REQ-2-007).

Scenario-driven: consumes a LabTelemetryScenario from the corpus, renders
the event timeline into the conversation, streams concrete feedback.
No session chat — each request is one scenario read.
"""

from collections.abc import AsyncIterator

from ..config import Settings
from ..corpus.learner_context import LearnerContext, get_learner_context
from ..corpus.telemetry import LabTelemetryScenario, summarize_scenario
from ..llm.base import LLMProvider
from ..prompts.lab import SYSTEM_PROMPT, render_context
from .base import BaseAgent


class LabAgent(BaseAgent):
    name = "lab"

    def __init__(self, provider: LLMProvider, settings: Settings) -> None:
        super().__init__(provider, settings)

    def system_prompt(self, learner_context: LearnerContext | None = None) -> str:
        ctx = learner_context or get_learner_context()
        return SYSTEM_PROMPT.format_map(render_context(ctx))

    async def stream_feedback(
        self,
        scenario: LabTelemetryScenario,
        learner_context: LearnerContext | None = None,
    ) -> AsyncIterator[str]:
        timeline = summarize_scenario(scenario)
        async for token in self.stream_reply(
            history=None, user_input=timeline, learner_context=learner_context
        ):
            yield token