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/sentiment/__init__.py

@@ -0,0 +1,38 @@
+"""Company-specific financial sentiment analysis.
+
+This package provides FinBERT-based sentiment classification
+on company-linked evidence groups, producing per-company probability
+distributions with full evidence provenance.
+"""
+
+from services.intelligence_pipeline_v3.sentiment.aggregation import (
+    aggregate_evidence_sentiments,
+)
+from services.intelligence_pipeline_v3.sentiment.calibrator import SentimentCalibrator
+from services.intelligence_pipeline_v3.sentiment.evidence_groups import build_evidence_groups
+from services.intelligence_pipeline_v3.sentiment.finbert_adapter import FinBERTAdapter
+from services.intelligence_pipeline_v3.sentiment.mixed_sentiment import compute_mixed_sentiment
+from services.intelligence_pipeline_v3.sentiment.models import (
+    CompanySentimentResult,
+    EvidenceGroup,
+    SentimentBatchResult,
+    TextSentiment,
+)
+from services.intelligence_pipeline_v3.sentiment.sentiment_scorer import (
+    SentimentModel,
+    SentimentScorer,
+)
+
+__all__ = [
+    "SentimentCalibrator",
+    "SentimentModel",
+    "SentimentScorer",
+    "CompanySentimentResult",
+    "EvidenceGroup",
+    "FinBERTAdapter",
+    "SentimentBatchResult",
+    "TextSentiment",
+    "aggregate_evidence_sentiments",
+    "build_evidence_groups",
+    "compute_mixed_sentiment",
+]