"""First-class Pydantic provenance stamp.

Provenance is authoritative framework data — **independent** of MAF's ``Annotation`` type,
which silently drops on the Python streaming path (#4316, research 02 Dim 2). A
``ProvenanceStamp`` is a Pydantic model that must carry at least one ``Citation`` (a
``min_length=1`` constraint), the model + role that produced the proposal, the validator's
decision, and the token usage. ``to_annotations()`` maps to MAF ``Annotation`` dicts for
DISPLAY only — never the source of truth.

The locator type (``TextSpan``) is owned by ``retrieval.py`` (Step 5) and imported here, so
a citation's span is the same exact object the retriever produced.
"""

from __future__ import annotations

from typing import Literal

from agent_framework import Annotation, TextSpanRegion
from pydantic import BaseModel, Field

from portfolio_optimiser.retrieval import TextSpan


class Citation(BaseModel):
    """One exact-span citation into a source document (locator owned by retrieval.py)."""

    file: str
    locator: TextSpan
    snippet: str


class ExternalCall(BaseModel):
    """One external service call a run actually made (Trekk B4).

    **What this is evidence of, and what it is not.** It records that ``tool`` was invoked and which
    configured ``server`` it belongs to. It is NOT evidence that the service's answer reached the
    proposal, and it is not a verified rendering of what the service returned — the framework hands
    the answer to the agent, and what the agent does with it is the agent's. Reading this as "the
    figure came from the price register" would claim more than the record supports.

    ``server`` is ``""`` when the tool name cannot be attributed to exactly one configured server.
    MEASURED against a real MCP stdio subprocess: MAF passes the BARE tool name to function
    middleware, with no server prefix, so two servers exposing one tool name are indistinguishable
    at this seam. Unattributed is the honest answer there; naming the first match would put a
    service in the record that may never have been contacted.
    """

    server: str
    tool: str


class ProvenanceStamp(BaseModel):
    """Authoritative provenance for one proposal — at least one citation is mandatory."""

    citations: list[Citation] = Field(min_length=1)
    model: str
    role: str
    validator_decision: Literal["validated", "rejected"]
    token_usage: int
    #: External service calls the run made (B4). EMPTY is a positive statement — "nothing outside
    #: this process was contacted" — not an absent field, which is why it is always serialized.
    external_calls: list[ExternalCall] = Field(default_factory=list)

    def to_annotations(self) -> list[Annotation]:
        """Map to MAF ``Annotation`` dicts for display only (NOT the source of truth)."""
        return [
            Annotation(
                type="citation",
                snippet=c.snippet,
                annotated_regions=[
                    TextSpanRegion(
                        type="text_span",
                        start_index=c.locator.start_index,
                        end_index=c.locator.end_index,
                    )
                ],
                additional_properties={"file": c.file},
            )
            for c in self.citations
        ]