release: bump version to 0.43.0

This commit is contained in:
linkong
2026-04-28 16:10:17 +08:00
parent 1cd2dab0ee
commit ac69d5d354
69 changed files with 6954 additions and 1141 deletions

View File

@@ -1,20 +1,34 @@
"""DataSourceConfig API for user-defined data sources"""
from typing import Optional
from typing import Any, Optional
from datetime import datetime
import base64
import json
import re
from fastapi import APIRouter, Depends, HTTPException, status
from sqlalchemy import select, func
from sqlalchemy.ext.asyncio import AsyncSession
from pydantic import BaseModel, Field
import httpx
from app.core.target_schema_registry import get_target_schema, list_target_schemas
from app.db.session import get_db
from app.models.user import User
from app.models.datasource_config import DataSourceConfig
from app.models.datasource_mapping import DataSourceMappingTemplate
from app.core.security import get_current_user
from app.core.cache import cache
from app.core.time import to_iso8601_utc
from app.schemas.ai import SituationalAnalysisRequest
from app.services.ai_client import AIProviderClient, get_ai_provider_client
from app.services.datasource_mapping import (
MappingError,
build_heuristic_mapping,
execute_mapping,
persist_mapped_records,
redact_for_llm,
stable_payload_hash,
)
router = APIRouter()
@@ -59,6 +73,44 @@ class DataSourceConfigResponse(BaseModel):
from_attributes = True
class CustomSampleRequest(BaseModel):
datasource_config_id: Optional[int] = None
config: Optional[DataSourceConfigCreate] = None
limit_bytes: int = Field(default=200000, ge=1000, le=1000000)
class MappingProposeRequest(BaseModel):
sample_payload: Any
target_schema: str
use_ai: bool = True
class MappingPreviewRequest(BaseModel):
sample_payload: Any
target_schema: str
mapping_json: dict
limit: int = Field(default=20, ge=1, le=100)
class MappingTemplateCreate(BaseModel):
datasource_config_id: int
target_schema: str
mapping_json: dict
sample_payload: Any | None = None
sample_payload_hash: Optional[str] = None
validation_status: str = Field(default="draft", pattern="^(draft|valid|invalid)$")
is_active: bool = False
class MappingTemplateUpdate(BaseModel):
target_schema: Optional[str] = None
mapping_json: Optional[dict] = None
sample_payload: Any | None = None
sample_payload_hash: Optional[str] = None
validation_status: Optional[str] = Field(default=None, pattern="^(draft|valid|invalid)$")
is_active: Optional[bool] = None
async def test_endpoint(
endpoint: str,
auth_type: str,
@@ -96,6 +148,134 @@ async def test_endpoint(
}
def _build_request_headers(auth_type: str, auth_config: dict, headers: dict) -> dict[str, str]:
request_headers = {str(key): str(value) for key, value in (headers or {}).items()}
auth_type = str(auth_type or "none").lower()
auth_config = auth_config or {}
if auth_type == "bearer" and auth_config.get("token"):
request_headers["Authorization"] = f"Bearer {auth_config['token']}"
elif auth_type == "api_key" and auth_config.get("api_key"):
location = str(auth_config.get("in") or auth_config.get("location") or "header").lower()
if location != "query":
key_name = auth_config.get("key_name", "X-API-Key")
request_headers[str(key_name)] = str(auth_config["api_key"])
elif auth_type == "basic":
username = auth_config.get("username", "")
password = auth_config.get("password", "")
credentials = f"{username}:{password}"
encoded = base64.b64encode(credentials.encode()).decode()
request_headers["Authorization"] = f"Basic {encoded}"
return request_headers
def _build_query_params(auth_type: str, auth_config: dict, config: dict) -> dict[str, Any]:
params = {}
candidate = (config or {}).get("params") or (config or {}).get("query_params")
if isinstance(candidate, dict):
params.update(candidate)
auth_type = str(auth_type or "none").lower()
auth_config = auth_config or {}
if auth_type == "api_key" and auth_config.get("api_key"):
location = str(auth_config.get("in") or auth_config.get("location") or "header").lower()
if location == "query":
key_name = auth_config.get("key_name") or auth_config.get("param_name") or "api_key"
params[str(key_name)] = auth_config["api_key"]
return params
async def fetch_custom_sample_from_config(config: DataSourceConfig, limit_bytes: int) -> Any:
request_config = config.config or {}
method = str(request_config.get("method") or request_config.get("request_method") or "GET").upper()
if method not in {"GET", "POST"}:
raise HTTPException(status_code=400, detail="Only GET and POST sample requests are supported.")
headers = _build_request_headers(config.auth_type, config.auth_config or {}, config.headers or {})
params = _build_query_params(config.auth_type, config.auth_config or {}, request_config)
timeout = float(request_config.get("timeout", 30))
json_body = request_config.get("json_body")
if json_body is None and str(request_config.get("body_type") or "").lower() in {"json", ""}:
candidate = request_config.get("body")
if isinstance(candidate, (dict, list)):
json_body = candidate
async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
response = await client.request(
method,
config.endpoint,
headers=headers,
params=params or None,
json=json_body,
)
response.raise_for_status()
content = response.content[:limit_bytes]
if "application/json" in response.headers.get("content-type", ""):
return json.loads(content.decode(response.encoding or "utf-8"))
return {"text": content.decode(response.encoding or "utf-8", errors="replace")}
def _parse_mapping_from_ai_text(content: str) -> dict[str, Any] | None:
if not content:
return None
candidates = [content]
fenced = re.findall(r"```(?:json)?\s*(\{.*?\})\s*```", content, flags=re.DOTALL)
candidates = fenced + candidates
for candidate in candidates:
try:
parsed = json.loads(candidate)
except json.JSONDecodeError:
continue
if isinstance(parsed, dict) and isinstance(parsed.get("fields"), dict):
return parsed
return None
async def _get_config_for_sample(
payload: CustomSampleRequest,
db: AsyncSession,
) -> DataSourceConfig:
if payload.datasource_config_id is not None:
result = await db.execute(
select(DataSourceConfig).where(DataSourceConfig.id == payload.datasource_config_id)
)
config = result.scalar_one_or_none()
if not config:
raise HTTPException(status_code=404, detail="Configuration not found")
return config
if payload.config is None:
raise HTTPException(status_code=400, detail="datasource_config_id or config is required")
config_data = payload.config
return DataSourceConfig(
name=config_data.name,
description=config_data.description,
source_type=config_data.source_type,
endpoint=config_data.endpoint,
auth_type=config_data.auth_type,
auth_config=config_data.auth_config,
headers=config_data.headers,
config=config_data.config,
)
def serialize_mapping_template(template: DataSourceMappingTemplate) -> dict[str, Any]:
return {
"id": template.id,
"datasource_config_id": template.datasource_config_id,
"target_schema": template.target_schema,
"mapping_json": template.mapping_json,
"sample_payload_hash": template.sample_payload_hash,
"validation_status": template.validation_status,
"version": template.version,
"is_active": template.is_active,
"created_at": to_iso8601_utc(template.created_at),
"updated_at": to_iso8601_utc(template.updated_at),
}
@router.get("/configs")
async def list_configs(
active_only: bool = False,
@@ -345,3 +525,311 @@ async def list_all_datasources(
)
return {"total": len(result), "data": result}
@router.post("/custom/sample")
async def fetch_custom_sample(
payload: CustomSampleRequest,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
"""Fetch a sample payload for a saved or draft custom data source."""
config = await _get_config_for_sample(payload, db)
try:
sample = await fetch_custom_sample_from_config(config, payload.limit_bytes)
except httpx.HTTPStatusError as exc:
raise HTTPException(
status_code=exc.response.status_code,
detail=f"Sample request failed: HTTP {exc.response.status_code}",
) from exc
except httpx.HTTPError as exc:
raise HTTPException(status_code=502, detail=f"Sample request failed: {exc}") from exc
return {
"success": True,
"sample_payload": sample,
"sample_payload_hash": stable_payload_hash(sample),
"redacted_preview": redact_for_llm(sample),
}
@router.get("/target-schemas")
async def get_datasource_target_schemas(
current_user: User = Depends(get_current_user),
):
"""List target schemas available for custom datasource mapping."""
return {"data": list_target_schemas()}
@router.post("/mappings/propose")
async def propose_datasource_mapping(
payload: MappingProposeRequest,
current_user: User = Depends(get_current_user),
ai_client: AIProviderClient = Depends(get_ai_provider_client),
):
"""Generate a mapping draft for a sample payload and target schema."""
schema = get_target_schema(payload.target_schema)
redacted_sample = redact_for_llm(payload.sample_payload)
fallback_mapping = build_heuristic_mapping(redacted_sample, payload.target_schema)
ai_error: str | None = None
mapping = fallback_mapping
generated_by = "heuristic"
if payload.use_ai:
try:
response = await ai_client.analyze(
SituationalAnalysisRequest(
title=f"Generate datasource mapping for {schema.key}",
objective=(
"Return only JSON for a deterministic mapping DSL. "
"The JSON must contain source.items_path and fields. "
"Do not include prose or code."
),
context={
"target_schema": schema.to_dict(),
"sample_payload": redacted_sample,
"mapping_dsl_example": fallback_mapping,
},
observations=[
"Use JSONPath-like paths beginning with $.",
"Never generate executable code.",
"Use field types from the target schema.",
],
constraints=[
"Return a single JSON object.",
"Do not include credentials or secrets.",
"Mark uncertain optional fields with default null.",
],
)
)
parsed = _parse_mapping_from_ai_text(response.content)
if parsed:
mapping = parsed
generated_by = "ai_provider"
else:
ai_error = "AI provider did not return a valid mapping JSON object."
except HTTPException as exc:
ai_error = str(exc.detail)
mapping.setdefault("meta", {})
if isinstance(mapping["meta"], dict):
mapping["meta"].update(
{
"generated_by": generated_by,
"requires_review": True,
"ai_error": ai_error,
}
)
return {
"target_schema": schema.to_dict(),
"mapping_json": mapping,
"sample_payload_hash": stable_payload_hash(payload.sample_payload),
"redacted_sample_payload": redacted_sample,
}
@router.post("/mappings/preview")
async def preview_datasource_mapping(
payload: MappingPreviewRequest,
current_user: User = Depends(get_current_user),
):
"""Preview deterministic mapping output for a sample payload."""
try:
preview = execute_mapping(
payload.sample_payload,
payload.mapping_json,
payload.target_schema,
limit=payload.limit,
)
except (MappingError, ValueError) as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
return {
"success": preview["failed_count"] == 0,
"preview": preview,
"sample_payload_hash": stable_payload_hash(payload.sample_payload),
}
@router.get("/mappings")
async def list_datasource_mappings(
datasource_config_id: Optional[int] = None,
active_only: bool = False,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
"""List saved mapping templates."""
query = select(DataSourceMappingTemplate).order_by(
DataSourceMappingTemplate.datasource_config_id,
DataSourceMappingTemplate.version.desc(),
)
if datasource_config_id is not None:
query = query.where(DataSourceMappingTemplate.datasource_config_id == datasource_config_id)
if active_only:
query = query.where(DataSourceMappingTemplate.is_active.is_(True))
result = await db.execute(query)
mappings = result.scalars().all()
return {"total": len(mappings), "data": [serialize_mapping_template(item) for item in mappings]}
@router.post("/mappings")
async def create_datasource_mapping(
payload: MappingTemplateCreate,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
"""Save a mapping template for a datasource config."""
get_target_schema(payload.target_schema)
datasource = await db.get(DataSourceConfig, payload.datasource_config_id)
if not datasource:
raise HTTPException(status_code=404, detail="Configuration not found")
if payload.sample_payload is not None:
try:
execute_mapping(payload.sample_payload, payload.mapping_json, payload.target_schema, limit=100)
except (MappingError, ValueError) as exc:
raise HTTPException(status_code=400, detail=f"Mapping validation failed: {exc}") from exc
result = await db.execute(
select(func.max(DataSourceMappingTemplate.version)).where(
DataSourceMappingTemplate.datasource_config_id == payload.datasource_config_id,
DataSourceMappingTemplate.target_schema == payload.target_schema,
)
)
next_version = int(result.scalar() or 0) + 1
if payload.is_active:
await db.execute(
DataSourceMappingTemplate.__table__.update()
.where(DataSourceMappingTemplate.datasource_config_id == payload.datasource_config_id)
.values(is_active=False)
)
template = DataSourceMappingTemplate(
datasource_config_id=payload.datasource_config_id,
target_schema=payload.target_schema,
mapping_json=payload.mapping_json,
sample_payload_hash=payload.sample_payload_hash
or (stable_payload_hash(payload.sample_payload) if payload.sample_payload is not None else None),
validation_status=payload.validation_status,
version=next_version,
is_active=payload.is_active,
)
db.add(template)
await db.commit()
await db.refresh(template)
return {"message": "Mapping template saved successfully", "data": serialize_mapping_template(template)}
@router.put("/mappings/{mapping_id}")
async def update_datasource_mapping(
mapping_id: int,
payload: MappingTemplateUpdate,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
"""Update a mapping template in place."""
template = await db.get(DataSourceMappingTemplate, mapping_id)
if not template:
raise HTTPException(status_code=404, detail="Mapping template not found")
target_schema = payload.target_schema or template.target_schema
mapping_json = payload.mapping_json or template.mapping_json
get_target_schema(target_schema)
if payload.sample_payload is not None:
try:
execute_mapping(payload.sample_payload, mapping_json, target_schema, limit=100)
except (MappingError, ValueError) as exc:
raise HTTPException(status_code=400, detail=f"Mapping validation failed: {exc}") from exc
if payload.is_active is True:
await db.execute(
DataSourceMappingTemplate.__table__.update()
.where(DataSourceMappingTemplate.datasource_config_id == template.datasource_config_id)
.where(DataSourceMappingTemplate.id != template.id)
.values(is_active=False)
)
template.target_schema = target_schema
template.mapping_json = mapping_json
if payload.sample_payload_hash is not None:
template.sample_payload_hash = payload.sample_payload_hash
elif payload.sample_payload is not None:
template.sample_payload_hash = stable_payload_hash(payload.sample_payload)
if payload.validation_status is not None:
template.validation_status = payload.validation_status
if payload.is_active is not None:
template.is_active = payload.is_active
await db.commit()
await db.refresh(template)
return {"message": "Mapping template updated successfully", "data": serialize_mapping_template(template)}
@router.post("/{config_id}/run-mapped")
async def run_mapped_datasource(
config_id: int,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
"""Run a saved custom datasource through its active deterministic mapping."""
datasource = await db.get(DataSourceConfig, config_id)
if not datasource:
raise HTTPException(status_code=404, detail="Configuration not found")
result = await db.execute(
select(DataSourceMappingTemplate)
.where(DataSourceMappingTemplate.datasource_config_id == config_id)
.where(DataSourceMappingTemplate.is_active.is_(True))
.order_by(DataSourceMappingTemplate.version.desc())
.limit(1)
)
mapping = result.scalar_one_or_none()
if not mapping:
raise HTTPException(status_code=404, detail="No active mapping template found")
try:
sample = await fetch_custom_sample_from_config(datasource, 5_000_000)
mapped = execute_mapping(sample, mapping.mapping_json, mapping.target_schema)
except httpx.HTTPStatusError as exc:
raise HTTPException(
status_code=exc.response.status_code,
detail=f"Datasource request failed: HTTP {exc.response.status_code}",
) from exc
except httpx.HTTPError as exc:
raise HTTPException(status_code=502, detail=f"Datasource request failed: {exc}") from exc
except (MappingError, ValueError) as exc:
raise HTTPException(status_code=400, detail=f"Mapping failed: {exc}") from exc
if mapped["failed_count"] > 0:
return {
"status": "failed",
"datasource_config_id": config_id,
"mapping_id": mapping.id,
"mapping_version": mapping.version,
"target_schema": mapping.target_schema,
"mapped_count": mapped["mapped_count"],
"failed_count": mapped["failed_count"],
"errors": mapped["errors"][:20],
}
written_count = await persist_mapped_records(
db,
datasource_name=datasource.name,
datasource_config_id=datasource.id,
target_schema=mapping.target_schema,
records=mapped["records"],
mapping_version=mapping.version,
)
return {
"status": "success",
"datasource_config_id": config_id,
"mapping_id": mapping.id,
"mapping_version": mapping.version,
"target_schema": mapping.target_schema,
"fetched_count": mapped["total_items"],
"mapped_count": mapped["mapped_count"],
"written_count": written_count,
}

View File

@@ -9,6 +9,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
from app.core.time import to_iso8601_utc
from app.core.security import get_current_user
from app.core.data_sources import get_data_sources_config
from app.core.datasource_defaults import DEFAULT_DATASOURCES
from app.db.session import get_db
from app.models.collected_data import CollectedData
from app.models.data_snapshot import DataSnapshot
@@ -35,6 +36,17 @@ def format_frequency_label(minutes: int) -> str:
return f"{minutes}m"
def datasource_metadata(source: str) -> dict:
info = DEFAULT_DATASOURCES.get(source, {})
return {
"display_name": info.get("display_name") or info.get("name") or source,
"is_free": bool(info.get("is_free", True)),
"requires_credentials": bool(info.get("requires_credentials", False)),
"credential_provider": info.get("credential_provider"),
"credential_status": info.get("credential_status", "none"),
}
def is_due_for_collection(datasource: DataSource, now: datetime) -> bool:
if datasource.last_run_at is None:
return True
@@ -72,31 +84,6 @@ async def _load_latest_running_tasks(
return {task.datasource_id: task for task in result.scalars().all()}
async def _load_latest_completed_tasks(
db: AsyncSession,
datasource_ids: list[int],
) -> dict[int, CollectionTask]:
if not datasource_ids:
return {}
ranked_tasks = (
select(
CollectionTask.id.label("task_id"),
_task_rank_column(CollectionTask.completed_at),
)
.where(CollectionTask.datasource_id.in_(datasource_ids))
.where(CollectionTask.completed_at.isnot(None))
.where(CollectionTask.status.in_(("success", "failed", "cancelled")))
.subquery()
)
result = await db.execute(
select(CollectionTask)
.join(ranked_tasks, CollectionTask.id == ranked_tasks.c.task_id)
.where(ranked_tasks.c.row_num == 1)
)
return {task.datasource_id: task for task in result.scalars().all()}
async def _load_latest_task_ids(
db: AsyncSession,
datasource_ids: list[int],
@@ -123,21 +110,6 @@ async def _load_latest_task_ids(
return {datasource_id: task_id for datasource_id, task_id in result.all()}
async def _load_datasource_data_counts(
db: AsyncSession,
sources: list[str],
) -> dict[str, int]:
if not sources:
return {}
result = await db.execute(
select(CollectedData.source, func.count(CollectedData.id))
.where(CollectedData.source.in_(sources))
.group_by(CollectedData.source)
)
return {source: count for source, count in result.all()}
async def _load_datasource_endpoint_overrides(
db: AsyncSession,
sources: list[str],
@@ -161,7 +133,7 @@ async def _load_datasource_endpoint_overrides(
async def _load_datasource_list_context(
db: AsyncSession,
datasources: list[DataSource],
) -> tuple[dict[int, CollectionTask], dict[int, CollectionTask], dict[str, int], dict[str, str]]:
) -> tuple[dict[int, CollectionTask], dict[str, str]]:
datasource_ids = [datasource.id for datasource in datasources]
sources = [datasource.source for datasource in datasources]
@@ -185,10 +157,8 @@ async def _load_datasource_list_context(
if stale_datasource_ids:
running_tasks = await _load_latest_running_tasks(db, datasource_ids)
completed_tasks = await _load_latest_completed_tasks(db, datasource_ids)
data_counts = await _load_datasource_data_counts(db, sources)
endpoint_overrides = await _load_datasource_endpoint_overrides(db, sources)
return running_tasks, completed_tasks, data_counts, endpoint_overrides
return running_tasks, endpoint_overrides
async def get_datasource_record(db: AsyncSession, source_id: str) -> Optional[DataSource]:
@@ -401,27 +371,19 @@ async def list_datasources(
collector_list = []
config = get_data_sources_config()
running_tasks, completed_tasks, data_counts, endpoint_overrides = await _load_datasource_list_context(
db,
datasources,
)
running_tasks, endpoint_overrides = await _load_datasource_list_context(db, datasources)
for datasource in datasources:
running_task = running_tasks.get(datasource.id)
last_task = completed_tasks.get(datasource.id)
endpoint = endpoint_overrides.get(datasource.source) or config.get_yaml_url(
datasource.source,
)
data_count = data_counts.get(datasource.source, 0)
last_run_at = datasource.last_run_at or (last_task.completed_at if last_task else None)
last_run = to_iso8601_utc(last_run_at)
last_status = datasource.last_status or (last_task.status if last_task else None)
endpoint = endpoint_overrides.get(datasource.source) or config.get_yaml_url(datasource.source)
last_run_at = datasource.last_run_at
last_status = datasource.last_status
collector_list.append(
{
"id": datasource.id,
"source": datasource.source,
"name": datasource.name,
**datasource_metadata(datasource.source),
"module": datasource.module,
"priority": datasource.priority,
"frequency": format_frequency_label(datasource.frequency_minutes),
@@ -429,11 +391,9 @@ async def list_datasources(
"is_active": datasource.is_active,
"collector_class": datasource.collector_class,
"endpoint": endpoint,
"last_run": last_run,
"last_run": to_iso8601_utc(last_run_at),
"last_run_at": to_iso8601_utc(last_run_at),
"last_status": last_status,
"last_records_processed": last_task.records_processed if last_task else None,
"data_count": data_count,
"is_running": running_task is not None,
"task_id": running_task.id if running_task else None,
"progress": running_task.progress if running_task else None,
@@ -576,6 +536,7 @@ async def get_datasource(
return {
"id": datasource.id,
"name": datasource.name,
**datasource_metadata(datasource.source),
"module": datasource.module,
"priority": datasource.priority,
"frequency": format_frequency_label(datasource.frequency_minutes),

View File

@@ -9,10 +9,19 @@ from sqlalchemy.ext.asyncio import AsyncSession
from app.core.security import get_current_user
from app.core.time import to_iso8601_utc
from app.core.config import settings as app_settings
from app.core.data_sources import get_data_sources_config
from app.core.datasource_defaults import DEFAULT_DATASOURCES
from app.db.session import get_db
from app.models.datasource import DataSource
from app.models.datasource_config import DataSourceConfig
from app.models.system_setting import SystemSetting
from app.models.user import User
from app.services.llm_provider_catalog import (
get_fallback_llm_provider_preset,
list_fallback_llm_provider_presets,
refresh_llm_provider_preset,
)
from app.services.scheduler import sync_datasource_job
from app.services.tv_streams import DEFAULT_TV_SETTINGS, get_tv_settings_payload, normalize_tv_settings
@@ -39,6 +48,21 @@ DEFAULT_SETTINGS = {
"password_policy": "medium",
},
"tv": DEFAULT_TV_SETTINGS,
"external_integrations": {
"ai_provider": {
"service_url": "",
"service_token": "",
"provider": "minimax",
"provider_api": "anthropic-messages",
"base_url": "https://api.minimaxi.com/anthropic",
"model": "MiniMax-M2.7",
"api_key": "",
"max_tokens": 1200,
"anthropic_version": "2023-06-01",
"timeout_seconds": 60,
"retry_attempts": 2,
}
},
}
@@ -96,6 +120,34 @@ class TVSettingsUpdate(BaseModel):
sources: list[TVStreamSourceUpdate] = Field(default_factory=list)
class AIProviderIntegrationUpdate(BaseModel):
service_url: str = ""
service_token: Optional[str] = None
provider: str = Field(default="minimax", max_length=80)
provider_api: str = Field(default="anthropic-messages", max_length=80)
base_url: str = Field(default="", max_length=500)
model: str = Field(default="", max_length=200)
api_key: Optional[str] = None
max_tokens: int = Field(default=1200, ge=1, le=200000)
anthropic_version: str = Field(default="2023-06-01", max_length=40)
timeout_seconds: int = Field(default=60, ge=5, le=600)
retry_attempts: int = Field(default=2, ge=1, le=10)
clear_service_token: bool = False
clear_api_key: bool = False
class BarentsWatchIntegrationUpdate(BaseModel):
endpoint: str = ""
client_id: str = ""
client_secret: Optional[str] = None
clear_client_secret: bool = False
class ExternalIntegrationsUpdate(BaseModel):
ai_provider: AIProviderIntegrationUpdate
barentswatch: BarentsWatchIntegrationUpdate
def merge_with_defaults(category: str, payload: Optional[dict]) -> dict:
merged = deepcopy(DEFAULT_SETTINGS[category])
if payload:
@@ -146,6 +198,158 @@ async def save_setting_payload(db: AsyncSession, category: str, payload: dict) -
return merge_with_defaults(category, record.payload)
def _mask_secret(value: Optional[str]) -> dict:
if not value:
return {"configured": False, "preview": ""}
text = str(value)
if "-" in text:
prefix = text.split("-", 1)[0] + "-"
preview = prefix + ("*" * max(len(text) - len(prefix), 1))
else:
prefix_len = min(4, len(text))
preview = text[:prefix_len] + ("*" * max(len(text) - prefix_len, 1))
return {"configured": True, "preview": preview}
async def get_runtime_ai_provider_config(db: AsyncSession) -> dict:
runtime_record = await get_setting_record(db, "external_integrations")
payload = merge_with_defaults(
"external_integrations",
runtime_record.payload if runtime_record else None,
)
ai_payload = payload.get("ai_provider") or {}
has_runtime_llm_config = bool(
runtime_record
and isinstance(runtime_record.payload, dict)
and isinstance(runtime_record.payload.get("ai_provider"), dict)
)
return {
"service_url": ai_payload.get("service_url") or app_settings.AI_PROVIDER_SERVICE_URL,
"service_token": ai_payload.get("service_token") or app_settings.AI_PROVIDER_SERVICE_TOKEN,
"timeout_seconds": int(
ai_payload.get("timeout_seconds") or app_settings.AI_PROVIDER_TIMEOUT_SECONDS
),
"retry_attempts": int(
ai_payload.get("retry_attempts") or app_settings.AI_PROVIDER_RETRY_ATTEMPTS
),
"llm_config": {
"provider": ai_payload.get("provider") or "minimax",
"provider_api": ai_payload.get("provider_api") or "anthropic-messages",
"base_url": ai_payload.get("base_url") or "https://api.minimaxi.com/anthropic",
"model": ai_payload.get("model") or "MiniMax-M2.7",
"api_key": ai_payload.get("api_key") or "",
"max_tokens": int(ai_payload.get("max_tokens") or 1200),
"anthropic_version": ai_payload.get("anthropic_version") or "2023-06-01",
} if has_runtime_llm_config else {},
}
async def get_barentswatch_config_record(db: AsyncSession) -> Optional[DataSourceConfig]:
result = await db.execute(
select(DataSourceConfig)
.where(DataSourceConfig.name == "barentswatch_vessels")
.where(DataSourceConfig.is_active.is_(True))
)
return result.scalar_one_or_none()
async def serialize_external_integrations(db: AsyncSession) -> dict:
ai_config = await get_runtime_ai_provider_config(db)
runtime_setting = await get_setting_record(db, "external_integrations")
display_llm_config = ai_config["llm_config"] or DEFAULT_SETTINGS["external_integrations"]["ai_provider"]
barentswatch_record = await get_barentswatch_config_record(db)
yaml_config = get_data_sources_config()
barentswatch_auth = barentswatch_record.auth_config if barentswatch_record else {}
barentswatch_auth = barentswatch_auth or {}
return {
"ai_provider": {
"service_url": ai_config["service_url"],
"service_token": _mask_secret(ai_config["service_token"]),
"provider": display_llm_config.get("provider") or "minimax",
"provider_api": display_llm_config.get("provider_api") or "anthropic-messages",
"base_url": display_llm_config.get("base_url") or "https://api.minimaxi.com/anthropic",
"model": display_llm_config.get("model") or "MiniMax-M2.7",
"api_key": _mask_secret(display_llm_config.get("api_key")),
"max_tokens": int(display_llm_config.get("max_tokens") or 1200),
"anthropic_version": display_llm_config.get("anthropic_version") or "2023-06-01",
"timeout_seconds": ai_config["timeout_seconds"],
"retry_attempts": ai_config["retry_attempts"],
"source": "runtime" if runtime_setting else "env",
},
"barentswatch": {
"endpoint": (
barentswatch_record.endpoint
if barentswatch_record and barentswatch_record.endpoint
else yaml_config.get_yaml_url("barentswatch_vessels")
),
"client_id": barentswatch_auth.get("client_id") or "",
"client_secret": _mask_secret(barentswatch_auth.get("client_secret")),
"source": "datasource_config" if barentswatch_record else "default",
},
}
async def save_external_integrations_payload(
db: AsyncSession,
update: ExternalIntegrationsUpdate,
) -> dict:
current_payload = await get_setting_payload(db, "external_integrations")
current_ai = current_payload.get("ai_provider") or {}
ai_payload = {
"service_url": update.ai_provider.service_url.strip()
or app_settings.AI_PROVIDER_SERVICE_URL,
"service_token": current_ai.get("service_token") or "",
"provider": update.ai_provider.provider.strip() or "minimax",
"provider_api": update.ai_provider.provider_api.strip() or "anthropic-messages",
"base_url": update.ai_provider.base_url.strip(),
"model": update.ai_provider.model.strip(),
"api_key": current_ai.get("api_key") or "",
"max_tokens": update.ai_provider.max_tokens,
"anthropic_version": update.ai_provider.anthropic_version.strip() or "2023-06-01",
"timeout_seconds": update.ai_provider.timeout_seconds,
"retry_attempts": update.ai_provider.retry_attempts,
}
if update.ai_provider.clear_service_token:
ai_payload["service_token"] = ""
elif update.ai_provider.service_token not in (None, ""):
ai_payload["service_token"] = update.ai_provider.service_token
if update.ai_provider.clear_api_key:
ai_payload["api_key"] = ""
elif update.ai_provider.api_key not in (None, ""):
ai_payload["api_key"] = update.ai_provider.api_key
await save_setting_payload(db, "external_integrations", {"ai_provider": ai_payload})
default_endpoint = get_data_sources_config().get_yaml_url("barentswatch_vessels")
barentswatch_record = await get_barentswatch_config_record(db)
if barentswatch_record is None:
barentswatch_record = DataSourceConfig(
name="barentswatch_vessels",
description="BarentsWatch Live AIS credentials",
source_type="api",
endpoint=update.barentswatch.endpoint.strip() or default_endpoint,
auth_type="oauth_client_credentials",
auth_config={},
headers={},
config={},
is_active=True,
)
db.add(barentswatch_record)
current_auth = dict(barentswatch_record.auth_config or {})
if update.barentswatch.clear_client_secret:
current_auth.pop("client_secret", None)
elif update.barentswatch.client_secret not in (None, ""):
current_auth["client_secret"] = update.barentswatch.client_secret
current_auth["client_id"] = update.barentswatch.client_id.strip()
barentswatch_record.endpoint = update.barentswatch.endpoint.strip() or default_endpoint
barentswatch_record.auth_type = "oauth_client_credentials"
barentswatch_record.auth_config = current_auth
await db.commit()
return await serialize_external_integrations(db)
def format_frequency_label(minutes: int) -> str:
if minutes % 1440 == 0:
return f"{minutes // 1440}d"
@@ -155,9 +359,11 @@ def format_frequency_label(minutes: int) -> str:
def serialize_collector(datasource: DataSource) -> dict:
defaults = DEFAULT_DATASOURCES.get(datasource.source, {})
return {
"id": datasource.id,
"name": datasource.name,
"display_name": defaults.get("display_name") or datasource.name,
"source": datasource.source,
"module": datasource.module,
"priority": datasource.priority,
@@ -167,6 +373,10 @@ def serialize_collector(datasource: DataSource) -> dict:
"last_run_at": to_iso8601_utc(datasource.last_run_at),
"last_status": datasource.last_status,
"next_run_at": to_iso8601_utc(datasource.next_run_at),
"is_free": bool(defaults.get("is_free", True)),
"requires_credentials": bool(defaults.get("requires_credentials", False)),
"credential_provider": defaults.get("credential_provider"),
"credential_status": defaults.get("credential_status", "none"),
}
@@ -243,6 +453,46 @@ async def update_tv_settings(
return {"status": "updated", "tv": normalize_tv_settings(saved)}
@router.get("/integrations")
async def get_external_integrations(
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
return {"integrations": await serialize_external_integrations(db)}
@router.get("/integrations/ai-provider/presets")
async def get_ai_provider_presets(
current_user: User = Depends(get_current_user),
):
return {"data": list_fallback_llm_provider_presets()}
@router.post("/integrations/ai-provider/presets/{provider}/refresh")
async def refresh_ai_provider_preset(
provider: str,
current_user: User = Depends(get_current_user),
):
try:
return {"data": await refresh_llm_provider_preset(provider)}
except ValueError as exc:
raise HTTPException(status_code=404, detail=str(exc)) from exc
except Exception as exc:
fallback = get_fallback_llm_provider_preset(provider)
fallback["refresh_error"] = str(exc)
return {"data": fallback}
@router.put("/integrations")
async def update_external_integrations(
payload: ExternalIntegrationsUpdate,
current_user: User = Depends(get_current_user),
db: AsyncSession = Depends(get_db),
):
saved = await save_external_integrations_payload(db, payload)
return {"status": "updated", "integrations": saved}
@router.get("/collectors")
async def get_collector_settings(
current_user: User = Depends(get_current_user),
@@ -289,6 +539,7 @@ async def get_all_settings(
"notifications": setting_payloads["notifications"],
"security": setting_payloads["security"],
"tv": await get_tv_settings_payload(db),
"integrations": await serialize_external_integrations(db),
"collectors": [serialize_collector(datasource) for datasource in datasources],
"generated_at": to_iso8601_utc(datetime.now(UTC)),
}

View File

@@ -4,7 +4,7 @@ Unified API for all visualization data sources.
Returns GeoJSON format compatible with Three.js, CesiumJS, and Unreal Cesium.
"""
from datetime import UTC, datetime
from datetime import UTC, datetime, timedelta
import math
import httpx
from fastapi import APIRouter, HTTPException, Depends, Query, Response
@@ -20,6 +20,7 @@ from app.db.session import get_db
from app.models.bgp_anomaly import BGPAnomaly
from app.models.bgp_incident import BGPIncident
from app.models.collected_data import CollectedData
from app.models.vessel import VesselPosition, VesselStatic
from app.services.bgp_collectors import build_bgp_collector_coverage
from app.services.cable_graph import build_graph_from_data, CableGraph, haversine_distance
from app.services.collectors.bgp_common import RIPE_RIS_COLLECTOR_COORDS
@@ -511,7 +512,7 @@ def _normalize_capacity_band(capacity_value: Optional[float], capacity_unit: str
if unit in {"pflop/s", "pflops", "pflop"}:
normalized_tflops = capacity_value * 1000
elif unit in {"gflop/s", "gflops", "gflop"}:
normalized_tflops = capacity_value / 1000
normalized_tflops = capacity_value
else:
normalized_tflops = capacity_value
@@ -609,6 +610,108 @@ def convert_compute_centers_to_geojson(records: List[CollectedData]) -> Dict[str
return {"type": "FeatureCollection", "features": features}
VESSEL_TYPE_FILTERS = {
"cargo": lambda props: str(props.get("vessel_type_name", "")).lower() == "cargo"
or 70 <= int(props.get("vessel_type") or -1) <= 79,
"tanker": lambda props: str(props.get("vessel_type_name", "")).lower() == "tanker"
or 80 <= int(props.get("vessel_type") or -1) <= 89,
"passenger": lambda props: str(props.get("vessel_type_name", "")).lower() == "passenger"
or 60 <= int(props.get("vessel_type") or -1) <= 69,
"fishing": lambda props: str(props.get("vessel_type_name", "")).lower() == "fishing"
or int(props.get("vessel_type") or -1) == 30,
"military": lambda props: str(props.get("vessel_type_name", "")).lower() == "military"
or int(props.get("vessel_type") or -1) == 35,
"other": lambda props: str(props.get("vessel_type_name", "")).lower()
not in {"cargo", "tanker", "passenger", "fishing", "military"},
}
def convert_vessels_to_geojson(rows: List[Any]) -> Dict[str, Any]:
features = []
for position, static in rows:
if position.lat is None or position.lon is None:
continue
props = {
"mmsi": position.mmsi,
"name": getattr(static, "name", None) or f"MMSI {position.mmsi}",
"callsign": getattr(static, "callsign", None),
"imo": getattr(static, "imo", None),
"vessel_type": getattr(static, "vessel_type", None),
"vessel_type_name": getattr(static, "vessel_type_name", None) or "Other",
"flag": getattr(static, "flag", None),
"length": getattr(static, "length", None),
"width": getattr(static, "width", None),
"draught": getattr(static, "draught", None),
"sog": position.sog,
"cog": position.cog,
"heading": position.heading,
"nav_status": position.nav_status,
"received_at": to_iso8601_utc(position.received_at),
"data_type": "vessel",
}
features.append(
{
"type": "Feature",
"id": position.mmsi,
"geometry": {
"type": "Point",
"coordinates": [position.lon, position.lat],
},
"properties": props,
}
)
return {"type": "FeatureCollection", "features": features}
def _parse_bbox(value: Optional[str]) -> tuple[float, float, float, float] | None:
if not value:
return None
parts = [part.strip() for part in value.split(",")]
if len(parts) != 4:
raise HTTPException(status_code=400, detail="bbox must be lon_min,lat_min,lon_max,lat_max")
try:
lon_min, lat_min, lon_max, lat_max = [float(part) for part in parts]
except ValueError as exc:
raise HTTPException(status_code=400, detail="bbox values must be numbers") from exc
if lat_min > lat_max:
lat_min, lat_max = lat_max, lat_min
if lon_min > lon_max:
lon_min, lon_max = lon_max, lon_min
return lon_min, lat_min, lon_max, lat_max
def _matches_vessel_type(props: dict[str, Any], requested_types: set[str]) -> bool:
if not requested_types:
return True
for requested_type in requested_types:
predicate = VESSEL_TYPE_FILTERS.get(requested_type)
if predicate and predicate(props):
return True
return False
def _build_vessel_stats(features: List[dict[str, Any]]) -> dict[str, Any]:
by_type: dict[str, int] = {}
underway = 0
anchored_or_moored = 0
for feature in features:
props = feature.get("properties", {})
vessel_type = str(props.get("vessel_type_name") or "Other")
by_type[vessel_type] = by_type.get(vessel_type, 0) + 1
nav_status = props.get("nav_status")
if nav_status in (1, 5):
anchored_or_moored += 1
else:
underway += 1
return {
"total": len(features),
"by_type": by_type,
"underway": underway,
"anchored_or_moored": anchored_or_moored,
}
def convert_bgp_anomalies_to_geojson(
records: List[BGPAnomaly],
geography_hints: Optional[Dict[str, Dict[str, Any]]] = None,
@@ -1298,6 +1401,137 @@ async def get_compute_centers_geojson(
}
@router.get("/geo/vessels")
async def get_vessels_geojson(
bbox: Optional[str] = Query(
None,
description="Viewport bbox as lon_min,lat_min,lon_max,lat_max",
),
type: Optional[str] = Query(
None,
description="Comma-separated vessel types: cargo,tanker,passenger,fishing,military,other",
),
limit: int = Query(5000, ge=1, le=50000),
db: AsyncSession = Depends(get_db),
):
"""Return latest vessel positions as GeoJSON points."""
latest_times = (
select(
VesselPosition.mmsi.label("mmsi"),
func.max(VesselPosition.received_at).label("received_at"),
)
.group_by(VesselPosition.mmsi)
.subquery()
)
stmt = (
select(VesselPosition, VesselStatic)
.join(
latest_times,
(VesselPosition.mmsi == latest_times.c.mmsi)
& (VesselPosition.received_at == latest_times.c.received_at),
)
.outerjoin(VesselStatic, VesselStatic.mmsi == VesselPosition.mmsi)
.order_by(VesselPosition.received_at.desc())
.limit(limit)
)
parsed_bbox = _parse_bbox(bbox)
if parsed_bbox is not None:
lon_min, lat_min, lon_max, lat_max = parsed_bbox
stmt = stmt.where(
VesselPosition.lon >= lon_min,
VesselPosition.lon <= lon_max,
VesselPosition.lat >= lat_min,
VesselPosition.lat <= lat_max,
)
result = await db.execute(stmt)
rows = list(result.all())
geojson = convert_vessels_to_geojson(rows)
requested_types = {
item.strip().lower()
for item in (type or "").split(",")
if item.strip()
}
if requested_types:
geojson["features"] = [
feature
for feature in geojson.get("features", [])
if _matches_vessel_type(feature.get("properties", {}), requested_types)
]
features = geojson.get("features", [])
return {
**geojson,
"count": len(features),
"stats": _build_vessel_stats(features),
}
@router.get("/vessels/{mmsi}")
async def get_vessel_detail(mmsi: int, db: AsyncSession = Depends(get_db)):
latest_position_stmt = (
select(VesselPosition)
.where(VesselPosition.mmsi == mmsi)
.order_by(VesselPosition.received_at.desc())
.limit(1)
)
static = await db.get(VesselStatic, mmsi)
result = await db.execute(latest_position_stmt)
position = result.scalar_one_or_none()
if position is None:
raise HTTPException(status_code=404, detail="Vessel not found")
geojson = convert_vessels_to_geojson([(position, static)])
return {
**(geojson["features"][0]["properties"]),
"latitude": position.lat,
"longitude": position.lon,
}
@router.get("/vessels/{mmsi}/track")
async def get_vessel_track(
mmsi: int,
hours: int = Query(6, ge=1, le=24),
db: AsyncSession = Depends(get_db),
):
cutoff = datetime.now(UTC) - timedelta(hours=hours)
result = await db.execute(
select(VesselPosition)
.where(VesselPosition.mmsi == mmsi)
.where(VesselPosition.received_at >= cutoff)
.order_by(VesselPosition.received_at.asc())
)
positions = list(result.scalars().all())
if not positions:
return {
"type": "FeatureCollection",
"features": [],
"count": 0,
}
return {
"type": "FeatureCollection",
"features": [
{
"type": "Feature",
"geometry": {
"type": "LineString",
"coordinates": [[position.lon, position.lat] for position in positions],
},
"properties": {
"mmsi": mmsi,
"hours": hours,
"point_count": len(positions),
"start_at": to_iso8601_utc(positions[0].received_at),
"end_at": to_iso8601_utc(positions[-1].received_at),
},
}
],
"count": 1,
}
@router.get("/geo/bgp-anomalies")
async def get_bgp_anomalies_geojson(
severity: Optional[str] = Query(None),
@@ -1394,6 +1628,10 @@ async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db)):
db,
source_filter=("ris_live_bgp", "bgpstream_bgp"),
)
vessel_count_result = await db.execute(
select(func.count(func.distinct(VesselPosition.mmsi))),
)
vessel_count = int(vessel_count_result.scalar() or 0)
return {
"generated_at": to_iso8601_utc(datetime.now(UTC)),
@@ -1402,6 +1640,7 @@ async def get_visualization_geo_summary(db: AsyncSession = Depends(get_db)):
"landing_point_count": len(landing_points.get("features", [])),
"satellite_count": len(satellites.get("features", [])),
"compute_center_count": len(compute_features),
"vessel_count": vessel_count,
"supercomputer_count": sum(
1 for feature in compute_features
if feature.get("properties", {}).get("site_type") == "supercomputer"

View File

@@ -31,6 +31,7 @@ COLLECTOR_URL_KEYS = {
"opengeofeed_prefix_geo": "opengeofeed.public_csv_url",
"nro_delegated_prefix_geo": "nro.delegated_stats_url",
"news_live_streams": "news_live_streams.channels_url",
"barentswatch_vessels": "barentswatch_vessels.url",
}

View File

@@ -94,3 +94,7 @@ news_live_streams:
streams_url: "https://iptv-org.github.io/api/streams.json"
# IPTV-org 台标 JSON
logos_url: "https://iptv-org.github.io/api/logos.json"
barentswatch_vessels:
# BarentsWatch Live AIS latest combined endpoint. Requires an AIS bearer token.
url: "https://live.ais.barentswatch.no/v1/latest/combined"

View File

@@ -4,163 +4,246 @@ DEFAULT_DATASOURCES = {
"top500": {
"id": 1,
"name": "TOP500 Supercomputers",
"display_name": "TOP500 超算榜单",
"module": "L1",
"priority": "P0",
"frequency_minutes": 240,
"is_free": True,
"requires_credentials": False,
},
"epoch_ai_gpu": {
"id": 2,
"name": "Epoch AI GPU Clusters",
"display_name": "Epoch AI GPU 集群",
"module": "L1",
"priority": "P0",
"frequency_minutes": 360,
"is_free": True,
"requires_credentials": False,
},
"huggingface_models": {
"id": 3,
"name": "HuggingFace Models",
"display_name": "Hugging Face 模型",
"module": "L2",
"priority": "P1",
"frequency_minutes": 720,
"is_free": True,
"requires_credentials": False,
},
"huggingface_datasets": {
"id": 4,
"name": "HuggingFace Datasets",
"display_name": "Hugging Face 数据集",
"module": "L2",
"priority": "P1",
"frequency_minutes": 720,
"is_free": True,
"requires_credentials": False,
},
"huggingface_spaces": {
"id": 5,
"name": "HuggingFace Spaces",
"display_name": "Hugging Face Spaces",
"module": "L2",
"priority": "P2",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"peeringdb_ixp": {
"id": 6,
"name": "PeeringDB IXP",
"display_name": "PeeringDB 交换中心",
"module": "L2",
"priority": "P1",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"peeringdb_network": {
"id": 7,
"name": "PeeringDB Networks",
"display_name": "PeeringDB 网络",
"module": "L2",
"priority": "P2",
"frequency_minutes": 2880,
"is_free": True,
"requires_credentials": False,
},
"peeringdb_facility": {
"id": 8,
"name": "PeeringDB Facilities",
"display_name": "PeeringDB 设施",
"module": "L2",
"priority": "P2",
"frequency_minutes": 2880,
"is_free": True,
"requires_credentials": False,
},
"telegeography_cables": {
"id": 9,
"name": "Submarine Cables",
"display_name": "海底光缆",
"module": "L2",
"priority": "P1",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"telegeography_landing": {
"id": 10,
"name": "Cable Landing Points",
"display_name": "光缆登陆点",
"module": "L2",
"priority": "P2",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"telegeography_systems": {
"id": 11,
"name": "Cable Systems",
"display_name": "光缆系统",
"module": "L2",
"priority": "P2",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"arcgis_cables": {
"id": 15,
"name": "ArcGIS Submarine Cables",
"display_name": "ArcGIS 海底光缆",
"module": "L2",
"priority": "P1",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"arcgis_landing_points": {
"id": 16,
"name": "ArcGIS Landing Points",
"display_name": "ArcGIS 登陆点",
"module": "L2",
"priority": "P1",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"arcgis_cable_landing_relation": {
"id": 17,
"name": "ArcGIS Cable-Landing Relations",
"display_name": "ArcGIS 光缆登陆关系",
"module": "L2",
"priority": "P1",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"fao_landing_points": {
"id": 18,
"name": "FAO Landing Points",
"display_name": "FAO 登陆点",
"module": "L2",
"priority": "P1",
"frequency_minutes": 10080,
"is_free": True,
"requires_credentials": False,
},
"spacetrack_tle": {
"id": 19,
"name": "Space-Track TLE",
"display_name": "Space-Track 轨道根数",
"module": "L3",
"priority": "P2",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": True,
"credential_provider": "spacetrack",
"credential_status": "planned",
},
"celestrak_tle": {
"id": 20,
"name": "CelesTrak TLE",
"display_name": "CelesTrak 轨道根数",
"module": "L3",
"priority": "P2",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"ris_live_bgp": {
"id": 21,
"name": "RIPE RIS Live BGP",
"display_name": "RIPE RIS 实时 BGP",
"module": "L3",
"priority": "P1",
"frequency_minutes": 15,
"is_free": True,
"requires_credentials": False,
},
"bgpstream_bgp": {
"id": 22,
"name": "CAIDA BGPStream Backfill",
"display_name": "CAIDA BGPStream 回填",
"module": "L3",
"priority": "P1",
"frequency_minutes": 360,
"is_free": True,
"requires_credentials": False,
},
"iptoasn_prefix_geo": {
"id": 23,
"name": "IPtoASN Prefix Geography",
"display_name": "IPtoASN 前缀地理",
"module": "L3",
"priority": "P1",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"opengeofeed_prefix_geo": {
"id": 24,
"name": "OpenGeoFeed Prefix Geography",
"display_name": "OpenGeoFeed 前缀地理",
"module": "L3",
"priority": "P1",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"nro_delegated_prefix_geo": {
"id": 25,
"name": "NRO Delegated Prefix Geography",
"display_name": "NRO 分配前缀地理",
"module": "L3",
"priority": "P1",
"frequency_minutes": 1440,
"is_free": True,
"requires_credentials": False,
},
"news_live_streams": {
"id": 26,
"name": "News Live Streams",
"display_name": "新闻直播源",
"module": "L4",
"priority": "P2",
"frequency_minutes": 720,
"is_free": True,
"requires_credentials": False,
},
"barentswatch_vessels": {
"id": 27,
"name": "BarentsWatch AIS Vessels",
"display_name": "BarentsWatch AIS 船舶",
"module": "L4",
"priority": "P1",
"frequency_minutes": 1,
"is_free": True,
"requires_credentials": True,
"credential_provider": "barentswatch",
"credential_status": "supported",
},
}

View File

@@ -0,0 +1,151 @@
"""Registry of target schemas supported by mapped custom data sources."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime
from typing import Any
from pydantic import BaseModel, Field, ValidationError, field_validator
class VesselAISRecord(BaseModel):
mmsi: int = Field(ge=100000000, le=999999999)
lat: float = Field(ge=-90, le=90)
lon: float = Field(ge=-180, le=180)
sog: float | None = None
cog: float | None = Field(default=None, ge=0, le=360)
heading: int | None = Field(default=None, ge=0, le=511)
name: str | None = None
vessel_type: str | int | None = None
received_at: datetime | None = None
class GeoPointRecord(BaseModel):
lat: float = Field(ge=-90, le=90)
lon: float = Field(ge=-180, le=180)
name: str | None = None
type: str | None = None
source_id: str | None = None
observed_at: datetime | None = None
metadata: dict[str, Any] = Field(default_factory=dict)
class GenericRecord(BaseModel):
data: dict[str, Any] = Field(default_factory=dict)
source_id: str | None = None
observed_at: datetime | None = None
@field_validator("data")
@classmethod
def require_payload(cls, value: dict[str, Any]) -> dict[str, Any]:
if not value:
raise ValueError("generic_records requires a non-empty data object")
return value
@dataclass(frozen=True)
class TargetField:
name: str
type: str
required: bool = False
description: str = ""
example: Any = None
def to_dict(self) -> dict[str, Any]:
return {
"name": self.name,
"type": self.type,
"required": self.required,
"description": self.description,
"example": self.example,
}
@dataclass(frozen=True)
class TargetSchema:
key: str
label: str
description: str
fields: tuple[TargetField, ...]
model: type[BaseModel]
destination: str
def to_dict(self) -> dict[str, Any]:
return {
"key": self.key,
"label": self.label,
"description": self.description,
"destination": self.destination,
"fields": [field.to_dict() for field in self.fields],
}
def validate_record(self, record: dict[str, Any]) -> tuple[dict[str, Any] | None, list[str]]:
try:
return self.model.model_validate(record).model_dump(mode="json"), []
except ValidationError as exc:
return None, [
".".join(str(part) for part in error["loc"]) + f": {error['msg']}"
for error in exc.errors()
]
TARGET_SCHEMAS: dict[str, TargetSchema] = {
"vessel_ais": TargetSchema(
key="vessel_ais",
label="船舶 AIS",
description="船只位置、航速、航向、MMSI 等 AIS 数据。",
destination="vessel_position",
model=VesselAISRecord,
fields=(
TargetField("mmsi", "integer", True, "MMSI 九位船舶标识", 257123000),
TargetField("lat", "float", True, "纬度", 59.91),
TargetField("lon", "float", True, "经度", 10.75),
TargetField("sog", "float", False, "对地航速,单位节", 12.4),
TargetField("cog", "float", False, "对地航向0-360 度", 184.5),
TargetField("heading", "integer", False, "船首向0-511", 186),
TargetField("name", "string", False, "船名", "OSLO EXPRESS"),
TargetField("vessel_type", "string", False, "船型", "cargo"),
TargetField("received_at", "datetime", False, "数据接收时间", "2026-04-28T00:00:00Z"),
),
),
"geo_points": TargetSchema(
key="geo_points",
label="通用地理点",
description="带经纬度的通用实体或事件点位。",
destination="generic_geo_points",
model=GeoPointRecord,
fields=(
TargetField("lat", "float", True, "纬度", 1.3),
TargetField("lon", "float", True, "经度", 103.8),
TargetField("name", "string", False, "点位名称", "Singapore"),
TargetField("type", "string", False, "点位类型", "datacenter"),
TargetField("source_id", "string", False, "来源侧 ID", "sg-1"),
TargetField("observed_at", "datetime", False, "观测时间", "2026-04-28T00:00:00Z"),
TargetField("metadata", "object", False, "扩展字段", {"provider": "example"}),
),
),
"generic_records": TargetSchema(
key="generic_records",
label="通用结构化记录",
description="未知结构数据沉淀,不直接进入 Earth 图层。",
destination="collected_data",
model=GenericRecord,
fields=(
TargetField("data", "object", True, "结构化记录主体", {"raw": "value"}),
TargetField("source_id", "string", False, "来源侧 ID", "record-1"),
TargetField("observed_at", "datetime", False, "观测时间", "2026-04-28T00:00:00Z"),
),
),
}
def list_target_schemas() -> list[dict[str, Any]]:
return [schema.to_dict() for schema in TARGET_SCHEMAS.values()]
def get_target_schema(key: str) -> TargetSchema:
try:
return TARGET_SCHEMAS[key]
except KeyError as exc:
raise ValueError(f"Unsupported target schema: {key}") from exc

View File

@@ -110,6 +110,8 @@ async def init_db():
import app.models.playground_session # noqa: F401
import app.models.playground_message # noqa: F401
import app.models.system_log # noqa: F401
import app.models.vessel # noqa: F401
import app.models.datasource_mapping # noqa: F401
logger.warning_event(
"Database pool settings active",

View File

@@ -12,6 +12,8 @@ from app.models.system_setting import SystemSetting
from app.models.playground_session import PlaygroundSession
from app.models.playground_message import PlaygroundMessage
from app.models.system_log import SystemLog, AuditLog
from app.models.vessel import VesselPosition, VesselStatic
from app.models.datasource_mapping import DataSourceMappingTemplate
__all__ = [
"User",
@@ -29,4 +31,7 @@ __all__ = [
"BGPObservation",
"SystemLog",
"AuditLog",
"VesselPosition",
"VesselStatic",
"DataSourceMappingTemplate",
]

View File

@@ -0,0 +1,32 @@
"""Mapping templates for user-defined data source payloads."""
from sqlalchemy import Boolean, Column, DateTime, ForeignKey, Integer, JSON, String
from sqlalchemy.sql import func
from app.db.session import Base
class DataSourceMappingTemplate(Base):
__tablename__ = "datasource_mapping_templates"
id = Column(Integer, primary_key=True, autoincrement=True)
datasource_config_id = Column(
Integer,
ForeignKey("datasource_configs.id"),
nullable=False,
index=True,
)
target_schema = Column(String(80), nullable=False, index=True)
mapping_json = Column(JSON, nullable=False, default={})
sample_payload_hash = Column(String(64), nullable=True)
validation_status = Column(String(30), nullable=False, default="draft")
version = Column(Integer, nullable=False, default=1)
is_active = Column(Boolean, nullable=False, default=False, index=True)
created_at = Column(DateTime(timezone=True), server_default=func.now())
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
def __repr__(self):
return (
f"<DataSourceMappingTemplate {self.id}: "
f"{self.datasource_config_id}/{self.target_schema}/v{self.version}>"
)

View File

@@ -0,0 +1,75 @@
"""Vessel AIS models for live maritime tracking."""
from sqlalchemy import BigInteger, Column, DateTime, Float, Index, Integer, SmallInteger, String
from sqlalchemy.sql import func
from app.core.time import to_iso8601_utc
from app.db.session import Base
class VesselStatic(Base):
"""Slow-changing vessel identity and dimensions."""
__tablename__ = "vessel_static"
mmsi = Column(BigInteger, primary_key=True)
name = Column(String(128), nullable=True)
callsign = Column(String(16), nullable=True)
vessel_type = Column(SmallInteger, nullable=True, index=True)
vessel_type_name = Column(String(64), nullable=True, index=True)
flag = Column(String(4), nullable=True, index=True)
length = Column(Float, nullable=True)
width = Column(Float, nullable=True)
draught = Column(Float, nullable=True)
imo = Column(BigInteger, nullable=True)
updated_at = Column(DateTime(timezone=True), nullable=False, server_default=func.now())
def to_dict(self) -> dict:
return {
"mmsi": self.mmsi,
"name": self.name,
"callsign": self.callsign,
"vessel_type": self.vessel_type,
"vessel_type_name": self.vessel_type_name,
"flag": self.flag,
"length": self.length,
"width": self.width,
"draught": self.draught,
"imo": self.imo,
"updated_at": to_iso8601_utc(self.updated_at),
}
class VesselPosition(Base):
"""Append-only AIS positions retained for short history windows."""
__tablename__ = "vessel_position"
id = Column(Integer, primary_key=True, autoincrement=True)
mmsi = Column(BigInteger, nullable=False, index=True)
lat = Column(Float, nullable=False)
lon = Column(Float, nullable=False)
sog = Column(Float, nullable=True)
cog = Column(Float, nullable=True)
heading = Column(SmallInteger, nullable=True)
nav_status = Column(SmallInteger, nullable=True, index=True)
received_at = Column(DateTime(timezone=True), nullable=False, server_default=func.now(), index=True)
__table_args__ = (
Index("idx_vessel_pos_mmsi_time", "mmsi", "received_at"),
Index("idx_vessel_pos_time", "received_at"),
Index("idx_vessel_pos_lat_lon", "lat", "lon"),
)
def to_dict(self) -> dict:
return {
"id": self.id,
"mmsi": self.mmsi,
"lat": self.lat,
"lon": self.lon,
"sog": self.sog,
"cog": self.cog,
"heading": self.heading,
"nav_status": self.nav_status,
"received_at": to_iso8601_utc(self.received_at),
}

View File

@@ -3,9 +3,11 @@ from __future__ import annotations
import asyncio
import httpx
from fastapi import HTTPException, status
from fastapi import Depends, HTTPException, status
from sqlalchemy.ext.asyncio import AsyncSession
from app.core.config import settings
from app.db.session import get_db
from app.schemas.ai import (
AIProviderStatusResponse,
SituationalAnalysisRequest,
@@ -14,11 +16,27 @@ from app.schemas.ai import (
class AIProviderClient:
def __init__(self) -> None:
self.service_url = settings.AI_PROVIDER_SERVICE_URL.rstrip("/")
self.service_token = settings.AI_PROVIDER_SERVICE_TOKEN
self.timeout = settings.AI_PROVIDER_TIMEOUT_SECONDS
self.retry_attempts = max(settings.AI_PROVIDER_RETRY_ATTEMPTS, 1)
def __init__(
self,
*,
service_url: str | None = None,
service_token: str | None = None,
timeout: int | None = None,
retry_attempts: int | None = None,
llm_config: dict | None = None,
) -> None:
self.service_url = (
service_url if service_url is not None else settings.AI_PROVIDER_SERVICE_URL
).rstrip("/")
self.service_token = (
service_token if service_token is not None else settings.AI_PROVIDER_SERVICE_TOKEN
)
self.timeout = timeout if timeout is not None else settings.AI_PROVIDER_TIMEOUT_SECONDS
self.retry_attempts = max(
retry_attempts if retry_attempts is not None else settings.AI_PROVIDER_RETRY_ATTEMPTS,
1,
)
self.llm_config = llm_config or {}
def _headers(self, request_id: str | None = None) -> dict[str, str]:
headers = {"Content-Type": "application/json"}
@@ -26,6 +44,19 @@ class AIProviderClient:
headers["X-Provider-Token"] = self.service_token
if request_id:
headers["X-Request-ID"] = request_id
llm_header_map = {
"provider": "X-AI-Provider",
"provider_api": "X-AI-Provider-API",
"base_url": "X-AI-Base-URL",
"api_key": "X-AI-API-Key",
"model": "X-AI-Model",
"max_tokens": "X-AI-Max-Tokens",
"anthropic_version": "X-AI-Anthropic-Version",
}
for key, header_name in llm_header_map.items():
value = self.llm_config.get(key)
if value not in (None, ""):
headers[header_name] = str(value)
return headers
async def get_status(self, request_id: str | None = None) -> AIProviderStatusResponse:
@@ -105,5 +136,14 @@ class AIProviderClient:
)
def get_ai_provider_client() -> AIProviderClient:
return AIProviderClient()
async def get_ai_provider_client(db: AsyncSession = Depends(get_db)) -> AIProviderClient:
from app.api.v1.settings import get_runtime_ai_provider_config
runtime_config = await get_runtime_ai_provider_config(db)
return AIProviderClient(
service_url=runtime_config["service_url"],
service_token=runtime_config["service_token"],
timeout=runtime_config["timeout_seconds"],
retry_attempts=runtime_config["retry_attempts"],
llm_config=runtime_config.get("llm_config") or {},
)

View File

@@ -36,6 +36,7 @@ from app.services.collectors.iptoasn import IPtoASNPrefixGeoCollector
from app.services.collectors.opengeofeed import OpenGeoFeedPrefixGeoCollector
from app.services.collectors.nro_delegated import NRODelegatedPrefixGeoCollector
from app.services.collectors.news_live_streams import NewsLiveStreamsCollector
from app.services.collectors.vessel_ais import VesselAISCollector
collector_registry.register(TOP500Collector())
collector_registry.register(EpochAIGPUCollector())
@@ -63,3 +64,4 @@ collector_registry.register(IPtoASNPrefixGeoCollector())
collector_registry.register(OpenGeoFeedPrefixGeoCollector())
collector_registry.register(NRODelegatedPrefixGeoCollector())
collector_registry.register(NewsLiveStreamsCollector())
collector_registry.register(VesselAISCollector())

View File

@@ -0,0 +1,326 @@
"""BarentsWatch AIS collector for vessel tracking."""
from datetime import UTC, datetime, timedelta
import os
from typing import Any
import httpx
from sqlalchemy import delete, select
from sqlalchemy.ext.asyncio import AsyncSession
from app.models.vessel import VesselPosition, VesselStatic
from app.services.collectors.base import BaseCollector
BARENTSWATCH_LATEST_URL = "https://live.ais.barentswatch.no/v1/latest/combined"
BARENTSWATCH_TOKEN_URL = "https://id.barentswatch.no/connect/token"
VESSEL_TYPE_NAMES = {
30: "Fishing",
35: "Military",
60: "Passenger",
70: "Cargo",
80: "Tanker",
}
class VesselAISCollector(BaseCollector):
"""Collect latest AIS positions and append them to vessel tables."""
name = "barentswatch_vessels"
priority = "P1"
module = "L4"
frequency_hours = 1
data_type = "vessel_ais"
@property
def base_url(self) -> str:
return self._resolved_url or BARENTSWATCH_LATEST_URL
async def _load_datasource_config(self) -> dict[str, Any]:
if not self._db_session:
return {}
try:
from sqlalchemy import select
from app.models.datasource_config import DataSourceConfig
result = await self._db_session.execute(
select(DataSourceConfig)
.where(DataSourceConfig.name == self.name)
.where(DataSourceConfig.is_active.is_(True))
)
datasource_config = result.scalar_one_or_none()
except Exception:
return {}
if not datasource_config:
return {}
return {
"auth_config": datasource_config.auth_config or {},
"config": datasource_config.config or {},
}
async def _get_access_token(self, client: httpx.AsyncClient) -> str | None:
datasource_config = await self._load_datasource_config()
auth_config = datasource_config.get("auth_config") or {}
config = datasource_config.get("config") or {}
client_id = (
auth_config.get("client_id")
or config.get("client_id")
or os.getenv("BARENTSWATCH_CLIENT_ID")
or os.getenv("BARRENTSWATCH_CLIENT_ID")
)
client_secret = (
auth_config.get("client_secret")
or config.get("client_secret")
or os.getenv("BARENTSWATCH_CLIENT_SECRET")
or os.getenv("BARRENTSWATCH_CLIENT_SECRET")
)
if not client_id or not client_secret:
return None
response = await client.post(
BARENTSWATCH_TOKEN_URL,
data={
"client_id": client_id,
"client_secret": client_secret,
"scope": "ais",
"grant_type": "client_credentials",
},
headers={"Content-Type": "application/x-www-form-urlencoded"},
)
response.raise_for_status()
payload = response.json()
token = payload.get("access_token")
return str(token) if token else None
async def fetch(self) -> list[dict[str, Any]]:
async with httpx.AsyncClient(timeout=60.0) as client:
headers: dict[str, str] = {}
token = await self._get_access_token(client)
if token:
headers["Authorization"] = f"Bearer {token}"
response = await client.get(self.base_url, headers=headers)
if response.status_code == 401 and not token:
return self._get_sample_data()
response.raise_for_status()
payload = response.json()
if isinstance(payload, list):
return [item for item in payload if isinstance(item, dict)]
if isinstance(payload, dict):
for key in ("features", "data", "items", "vessels"):
value = payload.get(key)
if isinstance(value, list):
if key == "features":
return [
{
**(item.get("properties") or {}),
"geometry": item.get("geometry"),
}
for item in value
if isinstance(item, dict)
]
return [item for item in value if isinstance(item, dict)]
return self._get_sample_data()
def transform(self, raw_data: list[dict[str, Any]]) -> list[dict[str, Any]]:
transformed = []
for item in raw_data:
record = self._normalize_record(item)
if record:
transformed.append(record)
return transformed
async def _save_data(
self,
db: AsyncSession,
data: list[dict[str, Any]],
task_id: int | None = None,
snapshot_id: int | None = None,
) -> int:
now = datetime.now(UTC)
records_added = 0
for index, item in enumerate(data):
static = await db.get(VesselStatic, item["mmsi"])
if static is None:
static = VesselStatic(mmsi=item["mmsi"])
db.add(static)
for field in (
"name",
"callsign",
"vessel_type",
"vessel_type_name",
"flag",
"length",
"width",
"draught",
"imo",
):
value = item.get(field)
if value not in (None, ""):
setattr(static, field, value)
static.updated_at = now
db.add(
VesselPosition(
mmsi=item["mmsi"],
lat=item["lat"],
lon=item["lon"],
sog=item.get("sog"),
cog=item.get("cog"),
heading=item.get("heading"),
nav_status=item.get("nav_status"),
received_at=item.get("received_at") or now,
)
)
records_added += 1
if (index + 1) % 1000 == 0:
await self.update_progress(index + 1, commit=True)
await db.execute(
delete(VesselPosition).where(VesselPosition.received_at < now - timedelta(hours=24))
)
await db.commit()
await self.update_progress(records_added, force=True)
return records_added
def _normalize_record(self, item: dict[str, Any]) -> dict[str, Any] | None:
mmsi = _as_int(_pick(item, "mmsi", "MMSI", "Mmsi"))
lat = _as_float(_pick(item, "lat", "latitude", "Latitude"))
lon = _as_float(_pick(item, "lon", "lng", "longitude", "Longitude"))
geometry = item.get("geometry")
coordinates = geometry.get("coordinates") if isinstance(geometry, dict) else None
if (lat is None or lon is None) and isinstance(coordinates, list) and len(coordinates) >= 2:
lon = _as_float(coordinates[0])
lat = _as_float(coordinates[1])
if mmsi is None or lat is None or lon is None:
return None
if not (-90 <= lat <= 90 and -180 <= lon <= 180):
return None
vessel_type = _as_int(_pick(item, "vessel_type", "shipType", "ship_type", "ShipType"))
vessel_type_name = (
_pick(item, "vessel_type_name", "shipTypeName", "ship_type_name", "VesselTypeName")
or _vessel_type_name(vessel_type)
)
received_at = _parse_datetime(_pick(item, "received_at", "timestamp", "time", "msgtime"))
return {
"mmsi": mmsi,
"name": _pick(item, "name", "shipName", "ship_name", "Name"),
"callsign": _pick(item, "callsign", "callSign", "CallSign"),
"vessel_type": vessel_type,
"vessel_type_name": vessel_type_name,
"flag": _pick(item, "flag", "country", "Flag"),
"length": _as_float(_pick(item, "length", "shipLength", "Length")),
"width": _as_float(_pick(item, "width", "shipWidth", "Width")),
"draught": _as_float(_pick(item, "draught", "draft", "Draught")),
"imo": _as_int(_pick(item, "imo", "IMO", "imoNumber")),
"lat": lat,
"lon": lon,
"sog": _as_float(_pick(item, "sog", "speedOverGround", "SOG")),
"cog": _as_float(_pick(item, "cog", "courseOverGround", "COG")),
"heading": _as_int(_pick(item, "heading", "trueHeading", "Heading")),
"nav_status": _as_int(_pick(item, "nav_status", "navStatus", "NavigationalStatus")),
"received_at": received_at,
}
def _get_sample_data(self) -> list[dict[str, Any]]:
return [
{
"mmsi": 257123000,
"name": "OSLO TRADER",
"lat": 59.91,
"lon": 10.73,
"sog": 12.4,
"cog": 214,
"heading": 215,
"nav_status": 0,
"vessel_type": 70,
"vessel_type_name": "Cargo",
"flag": "NO",
"length": 185,
},
{
"mmsi": 257456000,
"name": "NORDIC FJORD",
"lat": 60.39,
"lon": 5.32,
"sog": 0.2,
"cog": 82,
"heading": 80,
"nav_status": 1,
"vessel_type": 60,
"vessel_type_name": "Passenger",
"flag": "NO",
"length": 126,
},
]
def _pick(item: dict[str, Any], *keys: str) -> Any:
for key in keys:
if key in item and item[key] not in (None, ""):
return item[key]
return None
def _as_float(value: Any) -> float | None:
try:
if value in (None, ""):
return None
return float(value)
except (TypeError, ValueError):
return None
def _as_int(value: Any) -> int | None:
try:
if value in (None, ""):
return None
return int(float(value))
except (TypeError, ValueError):
return None
def _parse_datetime(value: Any) -> datetime | None:
if isinstance(value, datetime):
return value if value.tzinfo else value.replace(tzinfo=UTC)
if not value:
return None
if isinstance(value, (int, float)):
timestamp = float(value)
if timestamp > 10_000_000_000:
timestamp /= 1000
return datetime.fromtimestamp(timestamp, UTC)
if isinstance(value, str):
try:
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
return parsed if parsed.tzinfo else parsed.replace(tzinfo=UTC)
except ValueError:
return None
return None
def _vessel_type_name(vessel_type: int | None) -> str:
if vessel_type is None:
return "Other"
if 70 <= vessel_type <= 79:
return "Cargo"
if 80 <= vessel_type <= 89:
return "Tanker"
if 60 <= vessel_type <= 69:
return "Passenger"
if vessel_type == 30:
return "Fishing"
if vessel_type == 35:
return "Military"
return VESSEL_TYPE_NAMES.get(vessel_type, "Other")

View File

@@ -0,0 +1,358 @@
"""Deterministic mapping support for custom data sources."""
from __future__ import annotations
import hashlib
import json
import re
from datetime import UTC, datetime
from typing import Any
from sqlalchemy.ext.asyncio import AsyncSession
from app.core.target_schema_registry import TargetSchema, get_target_schema
SECRET_KEY_PATTERN = re.compile(
r"(token|secret|password|passwd|authorization|api[_-]?key|client[_-]?secret)",
re.IGNORECASE,
)
class MappingError(ValueError):
"""Raised when a mapping definition cannot be executed."""
def stable_payload_hash(payload: Any) -> str:
encoded = json.dumps(payload, ensure_ascii=False, sort_keys=True, default=str).encode()
return hashlib.sha256(encoded).hexdigest()
def redact_for_llm(value: Any) -> Any:
if isinstance(value, dict):
redacted = {}
for key, item in value.items():
if SECRET_KEY_PATTERN.search(str(key)):
redacted[key] = "[REDACTED]"
else:
redacted[key] = redact_for_llm(item)
return redacted
if isinstance(value, list):
return [redact_for_llm(item) for item in value[:20]]
return value
def extract_path(payload: Any, path: str | None) -> Any:
if not path or path == "$":
return payload
normalized = path.strip()
if normalized.startswith("$."):
normalized = normalized[2:]
elif normalized.startswith("$"):
normalized = normalized[1:]
normalized = normalized.strip(".")
if not normalized:
return payload
current = payload
for raw_segment in normalized.split("."):
segment = raw_segment.strip()
if not segment:
continue
list_all = segment.endswith("[*]")
if list_all:
segment = segment[:-3]
index = None
match = re.fullmatch(r"(.+)\[(\d+)\]", segment)
if match:
segment = match.group(1)
index = int(match.group(2))
if segment:
if isinstance(current, dict):
current = current.get(segment)
else:
return None
if list_all:
return current if isinstance(current, list) else []
if index is not None:
if not isinstance(current, list) or index >= len(current):
return None
current = current[index]
return current
def _convert_value(value: Any, target_type: str | None) -> Any:
if value is None or target_type in (None, "", "any"):
return value
if target_type == "string":
return str(value)
if target_type == "integer":
return int(value)
if target_type == "float":
return float(value)
if target_type == "boolean":
if isinstance(value, bool):
return value
if isinstance(value, str):
return value.strip().lower() in {"1", "true", "yes", "y", "on"}
return bool(value)
if target_type == "datetime":
if isinstance(value, datetime):
return value
if isinstance(value, (int, float)):
return datetime.fromtimestamp(value)
if isinstance(value, str):
return datetime.fromisoformat(value.replace("Z", "+00:00"))
return value
if target_type == "object":
if isinstance(value, dict):
return value
raise ValueError("expected object")
if target_type == "array":
if isinstance(value, list):
return value
raise ValueError("expected array")
return value
def _apply_enum(value: Any, enum_map: Any) -> Any:
if not isinstance(enum_map, dict):
return value
key = str(value)
return enum_map.get(key, enum_map.get(value, value))
def _map_one(item: Any, field_mapping: dict[str, Any]) -> tuple[dict[str, Any], list[str]]:
output: dict[str, Any] = {}
errors: list[str] = []
for field_name, rule in field_mapping.items():
if isinstance(rule, str):
rule = {"path": rule}
if not isinstance(rule, dict):
errors.append(f"{field_name}: mapping rule must be an object or path string")
continue
value = extract_path(item, rule.get("path"))
if value is None and "default" in rule:
value = rule.get("default")
value = _apply_enum(value, rule.get("enum"))
try:
value = _convert_value(value, rule.get("type"))
except (TypeError, ValueError) as exc:
errors.append(f"{field_name}: failed to convert value {value!r}: {exc}")
continue
if value is not None or rule.get("include_null", False):
output[field_name] = value
return output, errors
def execute_mapping(
payload: Any,
mapping_json: dict[str, Any],
target_schema: str | TargetSchema,
*,
limit: int | None = None,
) -> dict[str, Any]:
schema = get_target_schema(target_schema) if isinstance(target_schema, str) else target_schema
source = mapping_json.get("source") or {}
fields = mapping_json.get("fields")
if not isinstance(fields, dict) or not fields:
raise MappingError("mapping_json.fields must be a non-empty object")
items_path = source.get("items_path") or mapping_json.get("items_path") or "$"
items = extract_path(payload, items_path)
if isinstance(items, dict):
items = [items]
elif not isinstance(items, list):
items = []
if limit is not None:
items = items[:limit]
mapped_records: list[dict[str, Any]] = []
errors: list[dict[str, Any]] = []
for index, item in enumerate(items):
mapped, mapping_errors = _map_one(item, fields)
validated, validation_errors = schema.validate_record(mapped)
all_errors = mapping_errors + validation_errors
if all_errors:
errors.append({"index": index, "errors": all_errors, "record": mapped})
continue
if validated is not None:
mapped_records.append(validated)
return {
"target_schema": schema.key,
"total_items": len(items),
"mapped_count": len(mapped_records),
"failed_count": len(errors),
"records": mapped_records,
"errors": errors,
}
def build_heuristic_mapping(sample_payload: Any, target_schema_key: str) -> dict[str, Any]:
schema = get_target_schema(target_schema_key)
items_path = "$"
sample_item = sample_payload
if isinstance(sample_payload, dict):
for key in ("data", "items", "results", "features", "vessels"):
candidate = sample_payload.get(key)
if isinstance(candidate, list) and candidate:
items_path = f"$.{key}[*]"
sample_item = candidate[0]
break
elif isinstance(sample_payload, list) and sample_payload:
items_path = "$"
sample_item = sample_payload[0]
available = _flatten_keys(sample_item if isinstance(sample_item, dict) else {})
fields: dict[str, Any] = {}
for field in schema.fields:
candidate = _best_field_match(field.name, available)
if candidate:
fields[field.name] = {"path": f"$.{candidate}", "type": field.type}
elif field.name == "data" and target_schema_key == "generic_records":
fields[field.name] = {"path": "$", "type": "object"}
elif not field.required:
fields[field.name] = {"path": f"$.{field.name}", "type": field.type, "default": None}
return {
"source": {"items_path": items_path},
"fields": fields,
"meta": {
"generated_by": "heuristic",
"requires_review": True,
},
}
def _flatten_keys(payload: dict[str, Any], prefix: str = "") -> list[str]:
keys: list[str] = []
for key, value in payload.items():
dotted = f"{prefix}.{key}" if prefix else str(key)
keys.append(dotted)
if isinstance(value, dict):
keys.extend(_flatten_keys(value, dotted))
return keys
def _best_field_match(field_name: str, candidates: list[str]) -> str | None:
aliases = {
"lat": ("lat", "latitude", "y"),
"lon": ("lon", "lng", "longitude", "x"),
"mmsi": ("mmsi",),
"sog": ("sog", "speed", "speedOverGround"),
"cog": ("cog", "course", "courseOverGround"),
"received_at": ("received_at", "timestamp", "time", "updated_at"),
"observed_at": ("observed_at", "timestamp", "time", "updated_at"),
"source_id": ("id", "source_id", "uuid"),
}.get(field_name, (field_name,))
lowered = {candidate.lower(): candidate for candidate in candidates}
for alias in aliases:
if alias.lower() in lowered:
return lowered[alias.lower()]
for candidate in candidates:
tail = candidate.split(".")[-1].lower()
if tail in {alias.lower() for alias in aliases}:
return candidate
return None
def _parse_datetime(value: Any) -> datetime | None:
if value is None:
return None
if isinstance(value, datetime):
return value
if isinstance(value, str):
return datetime.fromisoformat(value.replace("Z", "+00:00"))
return None
async def persist_mapped_records(
db: AsyncSession,
*,
datasource_name: str,
datasource_config_id: int,
target_schema: str,
records: list[dict[str, Any]],
mapping_version: int,
) -> int:
"""Persist validated mapped records to the destination for a target schema."""
if target_schema == "vessel_ais":
from app.models.vessel import VesselPosition
for record in records:
db.add(
VesselPosition(
mmsi=record["mmsi"],
lat=record["lat"],
lon=record["lon"],
sog=record.get("sog"),
cog=record.get("cog"),
heading=record.get("heading"),
received_at=_parse_datetime(record.get("received_at")) or datetime.now(UTC),
)
)
await db.commit()
return len(records)
from app.models.collected_data import CollectedData
collected_at = datetime.now(UTC)
for index, record in enumerate(records):
if target_schema == "geo_points":
source_id = record.get("source_id") or f"{datasource_config_id}:{index}"
name = record.get("name")
metadata = {
"latitude": record.get("lat"),
"longitude": record.get("lon"),
"type": record.get("type"),
"mapping_version": mapping_version,
"target_schema": target_schema,
**(record.get("metadata") or {}),
}
reference_date = _parse_datetime(record.get("observed_at"))
else:
source_id = record.get("source_id") or f"{datasource_config_id}:{index}"
name = None
metadata = {
"data": record.get("data") or {},
"mapping_version": mapping_version,
"target_schema": target_schema,
}
reference_date = _parse_datetime(record.get("observed_at"))
db.add(
CollectedData(
source=datasource_name,
source_id=str(source_id),
entity_key=f"{datasource_name}:{source_id}",
data_type=target_schema,
name=name,
title=name,
extra_data=metadata,
collected_at=collected_at,
reference_date=reference_date,
is_valid=1,
is_current=True,
change_type="created",
change_summary={},
)
)
await db.commit()
return len(records)

View File

@@ -0,0 +1,150 @@
"""LLM provider presets used by Settings and the runtime AI provider bridge."""
from __future__ import annotations
from typing import Any
import httpx
MODELS_DEV_URL = "https://models.dev/api.json"
FALLBACK_LLM_PROVIDER_PRESETS: dict[str, dict[str, Any]] = {
"minimax": {
"provider": "minimax",
"label": "MiniMax",
"provider_api": "anthropic-messages",
"base_url": "https://api.minimaxi.com/anthropic",
"model": "MiniMax-M2.7",
"models": ["MiniMax-M2.7", "MiniMax-M2.7-highspeed", "MiniMax-M2.5", "MiniMax-M2"],
"api_key_env": "MINIMAX_API_KEY",
"source": "fallback",
},
"openai": {
"provider": "openai",
"label": "OpenAI",
"provider_api": "openai-completions",
"base_url": "https://api.openai.com/v1",
"model": "gpt-5.1",
"models": ["gpt-5.1", "gpt-5.1-codex", "gpt-4.1", "gpt-4o"],
"api_key_env": "OPENAI_API_KEY",
"source": "fallback",
},
"anthropic": {
"provider": "anthropic",
"label": "Anthropic",
"provider_api": "anthropic-messages",
"base_url": "https://api.anthropic.com/v1",
"model": "claude-sonnet-4-6",
"models": ["claude-sonnet-4-6", "claude-opus-4-5", "claude-3-5-haiku-20241022"],
"api_key_env": "ANTHROPIC_API_KEY",
"source": "fallback",
},
"deepseek": {
"provider": "deepseek",
"label": "DeepSeek",
"provider_api": "openai-completions",
"base_url": "https://api.deepseek.com/v1",
"model": "deepseek-chat",
"models": ["deepseek-chat", "deepseek-reasoner"],
"api_key_env": "DEEPSEEK_API_KEY",
"source": "fallback",
},
"alibaba": {
"provider": "alibaba",
"label": "Alibaba Qwen / DashScope",
"provider_api": "openai-completions",
"base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"model": "qwen3-max",
"models": ["qwen3-max", "qwen3.5-plus", "qwen-max", "qwen-plus"],
"api_key_env": "DASHSCOPE_API_KEY",
"source": "fallback",
},
"moonshotai": {
"provider": "moonshotai",
"label": "Moonshot AI / Kimi",
"provider_api": "openai-completions",
"base_url": "https://api.moonshot.ai/v1",
"model": "kimi-k2.5",
"models": ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"],
"api_key_env": "MOONSHOT_API_KEY",
"source": "fallback",
},
"openrouter": {
"provider": "openrouter",
"label": "OpenRouter",
"provider_api": "openai-completions",
"base_url": "https://openrouter.ai/api/v1",
"model": "openai/gpt-5.1",
"models": ["openai/gpt-5.1", "anthropic/claude-sonnet-4.5", "qwen/qwen3-max"],
"api_key_env": "OPENROUTER_API_KEY",
"source": "fallback",
},
"ollama": {
"provider": "ollama",
"label": "Ollama Local",
"provider_api": "ollama-generate",
"base_url": "http://127.0.0.1:11434",
"model": "qwen2.5:7b",
"models": ["qwen2.5:7b", "llama3.1:8b", "mistral:7b"],
"api_key_env": "",
"source": "fallback",
},
}
MODELS_DEV_PROVIDER_KEYS = {
"minimax": "minimax",
"openai": "openai",
"anthropic": "anthropic",
"deepseek": "deepseek",
"alibaba": "alibaba",
"moonshotai": "moonshotai",
"openrouter": "openrouter",
}
def list_fallback_llm_provider_presets() -> list[dict[str, Any]]:
return [dict(value) for value in FALLBACK_LLM_PROVIDER_PRESETS.values()]
def get_fallback_llm_provider_preset(provider: str) -> dict[str, Any]:
key = provider.strip().lower()
if key not in FALLBACK_LLM_PROVIDER_PRESETS:
raise ValueError(f"Unsupported LLM provider preset: {provider}")
return dict(FALLBACK_LLM_PROVIDER_PRESETS[key])
async def refresh_llm_provider_preset(provider: str) -> dict[str, Any]:
fallback = get_fallback_llm_provider_preset(provider)
models_dev_key = MODELS_DEV_PROVIDER_KEYS.get(fallback["provider"])
if not models_dev_key:
return fallback
async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as client:
response = await client.get(
MODELS_DEV_URL,
headers={"User-Agent": "Planet/1.0"},
)
response.raise_for_status()
catalog = response.json()
upstream = catalog.get(models_dev_key)
if not isinstance(upstream, dict):
return fallback
upstream_models = upstream.get("models") if isinstance(upstream.get("models"), dict) else {}
model_ids = list(upstream_models.keys())[:80]
base_url = upstream.get("api") or fallback["base_url"]
if fallback["provider"] == "deepseek" and base_url == "https://api.deepseek.com":
base_url = "https://api.deepseek.com/v1"
refreshed = {
**fallback,
"label": upstream.get("name") or fallback["label"],
"base_url": base_url,
"model": model_ids[0] if model_ids else fallback["model"],
"models": model_ids or fallback["models"],
"api_key_env": (upstream.get("env") or [fallback["api_key_env"]])[0],
"source": MODELS_DEV_URL,
}
return refreshed