"""thinking x Vertex AI.

Drive the real `claude` CLI against a running LiteLLM proxy that routes
Claude requests to Anthropic's models on Google Cloud Vertex AI, enable
extended thinking via `--effort high`, and assert that the
upstream returned a `thinking` content block.

The (feature, provider) for this cell is inferred from the file path by
`tests/e2e/claude_code/conftest.py`:

    tests/e2e/claude_code/thinking/test_vertex_ai.py
                       ^^^^^^^^      ^^^^^^^^^
                       feature_id    provider
"""

from __future__ import annotations

from typing import Any, Mapping, Sequence

import pytest

from claude_code._env import require_proxy
from claude_code.cli_driver import (
    ClaudeCLIError,
    failure_diagnostic,
    run_claude_models_parallel,
)


VERTEX_AI_MODELS = [
    "claude-haiku-4-5-vertex",
    "claude-sonnet-4-5-vertex",
    "claude-opus-4-7-vertex",
]

THINKING_ARGS = ["--effort", "max"]
THINKING_PROMPT = (
    "I have a 3-gallon jug and a 5-gallon jug. How can I measure "
    "exactly 4 gallons of water? Think through the steps carefully."
)


def _has_thinking_block(events: Sequence[Mapping[str, Any]]) -> bool:
    for event in events:
        if event.get("type") != "assistant":
            continue
        message = event.get("message") or {}
        content = message.get("content")
        if not isinstance(content, list):
            continue
        for block in content:
            if isinstance(block, dict) and block.get("type") == "thinking":
                return True
    return False


@pytest.mark.covers("llm.messages.vertex.thinking.nonstream.works")
def test_thinking_vertex_ai(compat_result):
    """Drive the `claude` CLI against the LiteLLM proxy with thinking
    enabled and assert a `thinking` content block was emitted."""
    base_url, api_key = require_proxy(compat_result)

    outcomes = run_claude_models_parallel(
        models=VERTEX_AI_MODELS,
        prompt=THINKING_PROMPT,
        base_url=base_url,
        api_key=api_key,
        extra_args=THINKING_ARGS,
    )

    failures = []
    for model in VERTEX_AI_MODELS:
        outcome = outcomes[model]
        if isinstance(outcome, ClaudeCLIError):
            error = f"[{model}] {outcome}"
            compat_result.add({"status": "fail", "error": error})
            failures.append(error)
            continue

        if outcome.exit_code != 0:
            error = f"[{model}] claude CLI failed: {failure_diagnostic(outcome)}"
            compat_result.add({"status": "fail", "error": error})
            failures.append(error)
            continue

        if not _has_thinking_block(outcome.events):
            error = (
                f"[{model}] no `thinking` content block observed in stream-json events"
            )
            compat_result.add({"status": "fail", "error": error})
            failures.append(error)
            continue

        compat_result.add({"status": "pass"})

    if failures:
        pytest.fail("; ".join(failures), pytrace=False)