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.
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
"""Feature flag configuration for the compatibility adapter.
|
|
|
|
The adapter is disabled by default and must be explicitly enabled for
|
|
replay, shadow, canary, or production modes.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from enum import Enum
|
|
|
|
|
|
class AdapterMode(str, Enum):
|
|
"""Operating mode for the compatibility adapter.
|
|
|
|
- disabled: adapter does not run (default)
|
|
- replay_only: adapter runs during offline replay evaluation
|
|
- shadow_only: adapter runs in shadow mode (no downstream effect)
|
|
- canary: adapter outputs routed to a percentage of non-trading consumers
|
|
- production: adapter outputs used for all consumers
|
|
"""
|
|
|
|
DISABLED = "disabled"
|
|
REPLAY_ONLY = "replay_only"
|
|
SHADOW_ONLY = "shadow_only"
|
|
CANARY = "canary"
|
|
PRODUCTION = "production"
|
|
|
|
|
|
def is_adapter_enabled(mode: AdapterMode) -> bool:
|
|
"""Return True if the adapter should produce output in the given mode.
|
|
|
|
Only replay, shadow, canary, and production modes enable output.
|
|
The disabled mode prevents any adapter execution.
|
|
"""
|
|
return mode != AdapterMode.DISABLED
|
|
|
|
|
|
# Default mode — adapter is OFF until explicitly activated
|
|
DEFAULT_ADAPTER_MODE: AdapterMode = AdapterMode.DISABLED
|