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.
2026-07-13 02:14:59 +00:00
parent 84634a365e
commit a72f336ad1
227 changed files with 50403 additions and 0 deletions
@@ -0,0 +1,70 @@
+"""Migration helpers for deprecated provider records.
+
+Scans agent configuration records for deprecated provider values (e.g. "vllm")
+and produces structured deprecation warnings to guide operators toward the
+canonical protocol names.
+
+Requirements: 2.2, 3.8
+"""
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from services.shared.inference.factory import PROTOCOL_ALIASES
+
+
+@dataclass(frozen=True)
+class ProviderDeprecationWarning:
+    """Structured deprecation warning for an agent record using a deprecated provider.
+
+    Attributes:
+        agent_id: The ID of the agent with the deprecated provider.
+        current_value: The current deprecated provider string (e.g. "vllm").
+        recommended_value: The canonical protocol to migrate to.
+        message: Human-readable migration guidance.
+    """
+
+    agent_id: str
+    current_value: str
+    recommended_value: str
+    message: str
+
+
+def check_deprecated_providers(
+    agent_records: list[dict],
+) -> list[ProviderDeprecationWarning]:
+    """Scan agent records for deprecated provider values.
+
+    Checks the ``model_provider`` field of each agent record against
+    PROTOCOL_ALIASES. Records using deprecated aliases get a warning
+    with migration guidance.
+
+    Args:
+        agent_records: List of dicts, each having at least ``agent_id``
+            (or ``id``) and ``model_provider`` fields.
+
+    Returns:
+        List of ProviderDeprecationWarning for records using deprecated providers.
+    """
+    warnings_list: list[ProviderDeprecationWarning] = []
+
+    for record in agent_records:
+        agent_id = str(record.get("agent_id") or record.get("id", "unknown"))
+        provider = (record.get("model_provider") or "").strip().lower()
+
+        if provider in PROTOCOL_ALIASES:
+            recommended = PROTOCOL_ALIASES[provider]
+            warnings_list.append(
+                ProviderDeprecationWarning(
+                    agent_id=agent_id,
+                    current_value=provider,
+                    recommended_value=recommended,
+                    message=(
+                        f"Agent {agent_id} uses deprecated provider '{provider}'. "
+                        f"Migrate to protocol '{recommended}'. "
+                        f"The '{provider}' alias will be removed in a future version."
+                    ),
+                )
+            )
+
+    return warnings_list