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.

services/intelligence_pipeline_v3/benchmark/__init__.py

@@ -0,0 +1,46 @@
+"""Benchmark configuration and comparison framework for Intelligence Pipeline v3.
+
+Defines extraction configurations for controlled comparison between the current
+production pipeline and corrected variants. Supports attribution of improvement
+sources (temperature fix, schema constraints, architecture changes).
+
+Validates: Requirements 16.2, 16.3, 16.5
+"""
+
+from services.intelligence_pipeline_v3.benchmark.comparison import (
+    ComparisonReport,
+    ConfigDelta,
+    FieldDelta,
+    ResourceDelta,
+    compare_configurations,
+)
+from services.intelligence_pipeline_v3.benchmark.configurations import (
+    BASELINE_CURRENT,
+    BASELINE_STRICT_SCHEMA,
+    BASELINE_TEMP_ZERO,
+    BenchmarkConfig,
+    StructuredOutputMode,
+    list_configurations,
+)
+from services.intelligence_pipeline_v3.benchmark.runner import (
+    BenchmarkDocumentResult,
+    BenchmarkRun,
+    BenchmarkRunner,
+)
+
+__all__ = [
+    "BASELINE_CURRENT",
+    "BASELINE_STRICT_SCHEMA",
+    "BASELINE_TEMP_ZERO",
+    "BenchmarkConfig",
+    "BenchmarkDocumentResult",
+    "BenchmarkRun",
+    "BenchmarkRunner",
+    "ComparisonReport",
+    "ConfigDelta",
+    "FieldDelta",
+    "ResourceDelta",
+    "StructuredOutputMode",
+    "compare_configurations",
+    "list_configurations",
+]