File size: 4,092 Bytes
02c0b36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.

"""Doc Quality Env Environment Client."""

from typing import Dict

from openenv.core import EnvClient
from openenv.core.client_types import StepResult
from openenv.core.env_server.types import State

from .models import DocQualityAction, DocQualityObservation


class DocQualityEnv(
    EnvClient[DocQualityAction, DocQualityObservation, State]
):
    """
    Client for the Doc Quality Env Environment.

    This client maintains a persistent WebSocket connection to the environment server,
    enabling efficient multi-step interactions with lower latency.
    Each client instance has its own dedicated environment session on the server.

    Example:
        >>> # Connect to a running server
        >>> with DocQualityEnv(base_url="http://localhost:8000") as client:
        ...     result = client.reset()
        ...     print(result.observation.task_name)
        ...
        ...     action = DocQualityAction(
        ...         action_type="identify_issue",
        ...         content="Missing error handling",
        ...         issue_category="completeness"
        ...     )
        ...     result = client.step(action)
        ...     print(result.observation.feedback)

    Example with Docker:
        >>> # Automatically start container and connect
        >>> client = DocQualityEnv.from_docker_image("doc_quality_env-env:latest")
        >>> try:
        ...     result = client.reset()
        ...     action = DocQualityAction(
        ...         action_type="identify_issue",
        ...         content="Test issue",
        ...         issue_category="clarity"
        ...     )
        ...     result = client.step(action)
        ... finally:
        ...     client.close()
    """

    def _step_payload(self, action: DocQualityAction) -> Dict:
        """
        Convert DocQualityAction to JSON payload for step message.

        Args:
            action: DocQualityAction instance

        Returns:
            Dictionary representation suitable for JSON encoding
        """
        return {
            "action_type": action.action_type,
            "content": action.content,
            "issue_category": action.issue_category,
        }

    def _parse_result(self, payload: Dict) -> StepResult[DocQualityObservation]:
        """
        Parse server response into StepResult[DocQualityObservation].

        Args:
            payload: JSON response data from server

        Returns:
            StepResult with DocQualityObservation
        """
        obs_data = payload.get("observation", {})
        observation = DocQualityObservation(
            task_name=obs_data.get("task_name", ""),
            task_difficulty=obs_data.get("task_difficulty", "easy"),
            current_doc=obs_data.get("current_doc", ""),
            doc_section=obs_data.get("doc_section", ""),
            issues_identified=obs_data.get("issues_identified", []),
            known_issues=obs_data.get("known_issues", []),
            quality_score=obs_data.get("quality_score", 0.0),
            step_count=obs_data.get("step_count", 0),
            max_steps=obs_data.get("max_steps", 10),
            feedback=obs_data.get("feedback", ""),
            done=payload.get("done", False),
            reward=payload.get("reward"),
            metadata=obs_data.get("metadata", {}),
        )

        return StepResult(
            observation=observation,
            reward=payload.get("reward"),
            done=payload.get("done", False),
        )

    def _parse_state(self, payload: Dict) -> State:
        """
        Parse server response into State object.

        Args:
            payload: JSON response from state request

        Returns:
            State object with episode_id and step_count
        """
        return State(
            episode_id=payload.get("episode_id"),
            step_count=payload.get("step_count", 0),
        )