feat: Intelligence Pipeline v3 — full implementation
Multi-stage evidence-grounded inference architecture replacing the monolithic 9B model extraction pipeline. CPU-first specialist services handle routine extraction while the 9B vLLM model is preserved for semantic adjudication of ambiguous cases. Key components: - Capability-aware inference gateway (OpenAI-compatible + Ollama) - Endpoint registry with DB migrations and REST API - Sentence-aware document segmenter (property tests) - Deterministic financial parsing with offset integrity - Symbol resolution with ambiguity detection - Specialist service (GLiNER2, dynamic batching, K8s deployment) - Company-specific sentiment (FinBERT, calibration) - Retrieval-based novelty and duplicate detection - Confidence calibration pipeline - Deterministic routing engine (property tests) - 9B adjudication layer with VRAM gating - Stock-specific impact model (features, labels, baseline, trained) - Pipeline orchestrator (state machine, queues, leases, feature flags) - Bounded parallelism (async workers, semaphore, load shedding) - Observability (tracing, metrics, alerts) - Compatibility adapter (v3→v2 golden mapping tests) - Shadow/canary promotion framework - Active learning and fine-tuning pipeline Test results: 1,161 tests pass, ruff lint clean. All 282 spec tasks completed.
This commit is contained in:
@@ -0,0 +1,129 @@
|
||||
"""Security helpers for the inference registry API.
|
||||
|
||||
Ensures auth_secret_ref values are NEVER exposed in API responses.
|
||||
Replaces the actual secret reference with a status string.
|
||||
|
||||
Requirements: 3.6
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from services.inference_registry.schemas import (
|
||||
BindingResponse,
|
||||
DeploymentResponse,
|
||||
EndpointListResponse,
|
||||
EndpointResponse,
|
||||
)
|
||||
|
||||
|
||||
def redact_endpoint(endpoint_dict: dict[str, Any]) -> EndpointResponse:
|
||||
"""Convert a raw endpoint dict to an EndpointResponse with secrets redacted.
|
||||
|
||||
The auth_secret_ref value is replaced with a status string:
|
||||
- "configured" if a secret reference exists
|
||||
- "not_configured" if no secret reference is set
|
||||
|
||||
The actual secret ref value is NEVER included in the response.
|
||||
"""
|
||||
auth_secret_ref = endpoint_dict.get("auth_secret_ref")
|
||||
auth_secret_status = "configured" if auth_secret_ref else "not_configured"
|
||||
|
||||
return EndpointResponse(
|
||||
id=endpoint_dict["id"],
|
||||
name=endpoint_dict["name"],
|
||||
protocol=endpoint_dict["protocol"],
|
||||
base_url=endpoint_dict["base_url"],
|
||||
auth_secret_status=auth_secret_status,
|
||||
auth_scheme=endpoint_dict.get("auth_scheme", "bearer"),
|
||||
default_headers=endpoint_dict.get("default_headers") or {},
|
||||
health_path=endpoint_dict.get("health_path"),
|
||||
enabled=endpoint_dict.get("enabled", True),
|
||||
revision=endpoint_dict.get("revision", 1),
|
||||
created_at=endpoint_dict.get("created_at"),
|
||||
updated_at=endpoint_dict.get("updated_at"),
|
||||
)
|
||||
|
||||
|
||||
def redact_endpoint_for_list(endpoint_dict: dict[str, Any]) -> EndpointListResponse:
|
||||
"""Convert a raw endpoint dict to a list response with secrets redacted."""
|
||||
auth_secret_ref = endpoint_dict.get("auth_secret_ref")
|
||||
auth_secret_status = "configured" if auth_secret_ref else "not_configured"
|
||||
|
||||
return EndpointListResponse(
|
||||
id=endpoint_dict["id"],
|
||||
name=endpoint_dict["name"],
|
||||
protocol=endpoint_dict["protocol"],
|
||||
base_url=endpoint_dict["base_url"],
|
||||
auth_secret_status=auth_secret_status,
|
||||
enabled=endpoint_dict.get("enabled", True),
|
||||
revision=endpoint_dict.get("revision", 1),
|
||||
created_at=endpoint_dict.get("created_at"),
|
||||
updated_at=endpoint_dict.get("updated_at"),
|
||||
)
|
||||
|
||||
|
||||
def redact_deployment(deployment_dict: dict[str, Any]) -> DeploymentResponse:
|
||||
"""Convert a raw deployment dict to a DeploymentResponse."""
|
||||
return DeploymentResponse(
|
||||
id=deployment_dict["id"],
|
||||
endpoint_id=deployment_dict["endpoint_id"],
|
||||
served_model_name=deployment_dict["served_model_name"],
|
||||
display_name=deployment_dict["display_name"],
|
||||
capabilities=deployment_dict.get("capabilities") or {},
|
||||
context_window=deployment_dict.get("context_window"),
|
||||
max_output_tokens=deployment_dict.get("max_output_tokens"),
|
||||
quantization=deployment_dict.get("quantization"),
|
||||
runtime_metadata=deployment_dict.get("runtime_metadata") or {},
|
||||
enabled=deployment_dict.get("enabled", True),
|
||||
revision=deployment_dict.get("revision", 1),
|
||||
)
|
||||
|
||||
|
||||
def redact_binding(binding_dict: dict[str, Any]) -> BindingResponse:
|
||||
"""Convert a raw binding dict to a BindingResponse."""
|
||||
return BindingResponse(
|
||||
id=binding_dict["id"],
|
||||
agent_id=binding_dict["agent_id"],
|
||||
stage=binding_dict["stage"],
|
||||
model_deployment_id=binding_dict.get("model_deployment_id"),
|
||||
route_order=binding_dict.get("route_order", 0),
|
||||
routing_config=binding_dict.get("routing_config") or {},
|
||||
is_active=binding_dict.get("is_active", True),
|
||||
revision=binding_dict.get("revision", 1),
|
||||
)
|
||||
|
||||
|
||||
def is_external_endpoint(base_url: str) -> bool:
|
||||
"""Determine if an endpoint URL points to an external (non-cluster) service.
|
||||
|
||||
External endpoints require egress confirmation before enablement.
|
||||
Local/cluster endpoints match:
|
||||
- localhost / 127.0.0.1
|
||||
- *.svc.cluster.local (Kubernetes internal)
|
||||
- 10.x.x.x / 192.168.x.x (private network)
|
||||
"""
|
||||
from urllib.parse import urlparse
|
||||
|
||||
parsed = urlparse(base_url)
|
||||
hostname = parsed.hostname or ""
|
||||
|
||||
# Cluster-local patterns
|
||||
if hostname in ("localhost", "127.0.0.1", "::1"):
|
||||
return False
|
||||
if hostname.endswith(".svc.cluster.local"):
|
||||
return False
|
||||
if hostname.startswith("10.") or hostname.startswith("192.168."):
|
||||
return False
|
||||
# Additional private ranges
|
||||
if hostname.startswith("172."):
|
||||
parts = hostname.split(".")
|
||||
if len(parts) >= 2:
|
||||
try:
|
||||
second = int(parts[1])
|
||||
if 16 <= second <= 31:
|
||||
return False
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
return True
|
||||
Reference in New Issue
Block a user