File size: 6,368 Bytes
a9e46a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
from __future__ import annotations

from dataclasses import asdict, dataclass, field
from datetime import datetime, timezone
from typing import Any
import uuid


def utc_now_iso() -> str:
    return datetime.now(tz=timezone.utc).isoformat()


@dataclass
class FailureMode:
    step_name: str
    error_type: str
    error_message: str
    hint: str = ""


@dataclass
class ExperimentReport:
    run_id: str
    created_at: str
    task: str
    status: str
    input_manifest: dict[str, Any]
    pipeline_config_id: str | None
    output_artifacts: list[str]
    metrics: dict[str, Any]
    execution_log: str
    failures: list[FailureMode] = field(default_factory=list)
    notes: str = ""

    @staticmethod
    def new(
        task: str,
        input_manifest: dict[str, Any],
        pipeline_config_id: str | None = None,
    ) -> "ExperimentReport":
        return ExperimentReport(
            run_id=f"exp-{uuid.uuid4().hex[:12]}",
            created_at=utc_now_iso(),
            task=task,
            status="running",
            input_manifest=input_manifest,
            pipeline_config_id=pipeline_config_id,
            output_artifacts=[],
            metrics={},
            execution_log="",
        )

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)


@dataclass
class Insight:
    insight_id: str
    created_at: str
    title: str
    hypothesis: str
    recommendation: str
    confidence: float
    evidence_run_ids: list[str]
    tags: list[str] = field(default_factory=list)

    @staticmethod
    def build(
        title: str,
        hypothesis: str,
        recommendation: str,
        confidence: float,
        evidence_run_ids: list[str],
        tags: list[str] | None = None,
    ) -> "Insight":
        return Insight(
            insight_id=f"ins-{uuid.uuid4().hex[:12]}",
            created_at=utc_now_iso(),
            title=title,
            hypothesis=hypothesis,
            recommendation=recommendation,
            confidence=max(0.0, min(1.0, confidence)),
            evidence_run_ids=evidence_run_ids,
            tags=tags or [],
        )

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)


@dataclass
class PipelineConfiguration:
    config_id: str
    created_at: str
    strategy_name: str
    task_scope: str
    tools: list[str]
    parameters: dict[str, Any]
    rationale: str
    source_insight_ids: list[str] = field(default_factory=list)

    @staticmethod
    def build(
        strategy_name: str,
        task_scope: str,
        tools: list[str],
        parameters: dict[str, Any],
        rationale: str,
        source_insight_ids: list[str] | None = None,
    ) -> "PipelineConfiguration":
        return PipelineConfiguration(
            config_id=f"cfg-{uuid.uuid4().hex[:12]}",
            created_at=utc_now_iso(),
            strategy_name=strategy_name,
            task_scope=task_scope,
            tools=tools,
            parameters=parameters,
            rationale=rationale,
            source_insight_ids=source_insight_ids or [],
        )

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)


@dataclass
class Hypothesis:
    hypothesis_id: str
    created_at: str
    domain: str
    user_query: str
    title: str
    hypothesis: str
    expected_improvement: str
    theoretical_basis: str
    tags: list[str] = field(default_factory=list)
    source_examples: list[str] = field(default_factory=list)
    data_sources: list[str] = field(default_factory=list)
    data_operations: list[dict[str, Any]] = field(default_factory=list)
    historical_reflection: list[str] = field(default_factory=list)
    error_avoidance: list[str] = field(default_factory=list)
    reasoning_chain: list[str] = field(default_factory=list)

    @staticmethod
    def build(
        domain: str,
        user_query: str,
        title: str,
        hypothesis: str,
        expected_improvement: str,
        theoretical_basis: str,
        tags: list[str] | None = None,
        source_examples: list[str] | None = None,
        data_sources: list[str] | None = None,
        data_operations: list[dict[str, Any]] | None = None,
        historical_reflection: list[str] | None = None,
        error_avoidance: list[str] | None = None,
        reasoning_chain: list[str] | None = None,
    ) -> "Hypothesis":
        return Hypothesis(
            hypothesis_id=f"hyp-{uuid.uuid4().hex[:12]}",
            created_at=utc_now_iso(),
            domain=domain,
            user_query=user_query,
            title=title,
            hypothesis=hypothesis,
            expected_improvement=expected_improvement,
            theoretical_basis=theoretical_basis,
            tags=tags or [],
            source_examples=source_examples or [],
            data_sources=data_sources or [],
            data_operations=data_operations or [],
            historical_reflection=historical_reflection or [],
            error_avoidance=error_avoidance or [],
            reasoning_chain=reasoning_chain or [],
        )

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)


@dataclass
class ValidationReport:
    validation_id: str
    created_at: str
    hypothesis_id: str
    domain: str
    level: str
    status: str
    score: float
    confidence: float
    key_metrics: dict[str, Any]
    failure_reason: str
    evidence: str

    @staticmethod
    def build(
        hypothesis_id: str,
        domain: str,
        level: str,
        status: str,
        score: float,
        confidence: float,
        key_metrics: dict[str, Any] | None = None,
        failure_reason: str = "",
        evidence: str = "",
    ) -> "ValidationReport":
        normalized_status = status if status in {"success", "failed", "inconclusive"} else "inconclusive"
        return ValidationReport(
            validation_id=f"val-{uuid.uuid4().hex[:12]}",
            created_at=utc_now_iso(),
            hypothesis_id=hypothesis_id,
            domain=domain,
            level=level,
            status=normalized_status,
            score=max(0.0, min(1.0, float(score))),
            confidence=max(0.0, min(1.0, float(confidence))),
            key_metrics=key_metrics or {},
            failure_reason=failure_reason,
            evidence=evidence,
        )

    def to_dict(self) -> dict[str, Any]:
        return asdict(self)