metaspn-entities 0.1.4__tar.gz → 0.1.6__tar.gz

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metaspn-entities
-Version: 0.1.4
+Version: 0.1.6
 Summary: Canonical entity resolution, aliasing, and merges for MetaSPN systems
 Author: MetaSPN Contributors
 License-Expression: MIT
@@ -99,3 +99,26 @@ Adapter behavior:
 - Extracts deterministic identifier candidates from normalized payloads.
 - Resolves a primary identifier, then adds remaining identifiers as aliases.
 - Returns only events produced during the adapter call.
+
+## M1 Context API
+
+Profiler/router workers can read consolidated context using:
+
+- `resolver.entity_context(entity_id, recent_limit=10)`
+- `resolver.confidence_summary(entity_id)`
+
+Both APIs resolve canonical redirects first, so merged IDs return coherent context.
+
+## M2 Recommendation Context API
+
+Recommendation and drafter workers can consume:
+
+- `resolver.recommendation_context(entity_id)`
+
+The recommendation context includes:
+- identity confidence
+- activity recency (days)
+- interaction history summary (evidence count + source distribution)
+- preferred channel hint
+- relationship stage hint (`cold` / `warm` / `engaged`)
+- merge-safe continuity fields keyed to canonical entity IDs

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/README.md

@@ -74,3 +74,26 @@ Adapter behavior:
 - Extracts deterministic identifier candidates from normalized payloads.
 - Resolves a primary identifier, then adds remaining identifiers as aliases.
 - Returns only events produced during the adapter call.
+
+## M1 Context API
+
+Profiler/router workers can read consolidated context using:
+
+- `resolver.entity_context(entity_id, recent_limit=10)`
+- `resolver.confidence_summary(entity_id)`
+
+Both APIs resolve canonical redirects first, so merged IDs return coherent context.
+
+## M2 Recommendation Context API
+
+Recommendation and drafter workers can consume:
+
+- `resolver.recommendation_context(entity_id)`
+
+The recommendation context includes:
+- identity confidence
+- activity recency (days)
+- interaction history summary (evidence count + source distribution)
+- preferred channel hint
+- relationship stage hint (`cold` / `warm` / `engaged`)
+- merge-safe continuity fields keyed to canonical entity IDs

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/metaspn_entities/__init__.py

@@ -1,4 +1,5 @@
 from .adapter import SignalResolutionResult, resolve_normalized_social_signal
+from .context import RecommendationContext, EntityContext, build_confidence_summary, build_recommendation_context
 from .events import EmittedEvent
 from .models import EntityResolution
 from .resolver import EntityResolver
@@ -7,6 +8,10 @@ from .sqlite_backend import SQLiteEntityStore
 __all__ = [
     "resolve_normalized_social_signal",
     "SignalResolutionResult",
+    "EntityContext",
+    "RecommendationContext",
+    "build_confidence_summary",
+    "build_recommendation_context",
     "EntityResolver",
     "EntityResolution",
     "EmittedEvent",

metaspn_entities-0.1.6/metaspn_entities/context.py

@@ -0,0 +1,191 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from typing import Any, Dict, List
+
+
+@dataclass(frozen=True)
+class EntityContext:
+    entity_id: str
+    aliases: List[Dict[str, Any]]
+    identifiers: List[Dict[str, Any]]
+    recent_evidence: List[Dict[str, Any]]
+    confidence_summary: Dict[str, Any]
+
+
+@dataclass(frozen=True)
+class RecommendationContext:
+    entity_id: str
+    identity_confidence: float
+    activity_recency_days: float
+    interaction_history_summary: Dict[str, Any]
+    preferred_channel_hint: str
+    relationship_stage_hint: str
+    continuity: Dict[str, Any]
+
+
+def build_confidence_summary(
+    aliases: List[Dict[str, Any]],
+    identifiers: List[Dict[str, Any]],
+    evidence: List[Dict[str, Any]],
+) -> Dict[str, Any]:
+    identifier_confidences = sorted(float(item["confidence"]) for item in identifiers)
+    alias_confidences = sorted(float(item["confidence"]) for item in aliases)
+    source_set = sorted(
+        {
+            str(item.get("provenance"))
+            for item in evidence
+            if item.get("provenance") not in (None, "")
+        }
+    )
+
+    identifier_avg = _avg(identifier_confidences)
+    alias_avg = _avg(alias_confidences)
+    source_diversity = min(1.0, len(source_set) / 3.0)
+
+    overall = min(1.0, (0.65 * identifier_avg) + (0.25 * alias_avg) + (0.10 * source_diversity))
+    by_identifier_type = _rollup_by_identifier_type(identifiers)
+
+    return {
+        "overall_confidence": round(overall, 6),
+        "identifier_confidence_avg": round(identifier_avg, 6),
+        "alias_confidence_avg": round(alias_avg, 6),
+        "unique_source_count": len(source_set),
+        "evidence_count": len(evidence),
+        "by_identifier_type": by_identifier_type,
+    }
+
+
+def _avg(values: List[float]) -> float:
+    if not values:
+        return 0.0
+    return sum(values) / len(values)
+
+
+def _rollup_by_identifier_type(identifiers: List[Dict[str, Any]]) -> Dict[str, Dict[str, float]]:
+    grouped: Dict[str, List[float]] = {}
+    for item in identifiers:
+        key = str(item["identifier_type"])
+        grouped.setdefault(key, []).append(float(item["confidence"]))
+
+    rollup: Dict[str, Dict[str, float]] = {}
+    for key in sorted(grouped):
+        values = sorted(grouped[key])
+        rollup[key] = {
+            "count": float(len(values)),
+            "avg_confidence": round(_avg(values), 6),
+            "max_confidence": round(max(values), 6),
+        }
+    return rollup
+
+
+def build_recommendation_context(
+    entity_id: str,
+    aliases: List[Dict[str, Any]],
+    identifiers: List[Dict[str, Any]],
+    *,
+    now: datetime | None = None,
+) -> RecommendationContext:
+    current_now = now or datetime.now(timezone.utc)
+    evidence_count = len(identifiers)
+    recent_seen = _latest_seen(identifiers)
+    activity_recency_days = _recency_days(recent_seen, current_now)
+
+    summary = build_confidence_summary(aliases, identifiers, identifiers)
+    preferred_channel = _preferred_channel_hint(identifiers)
+    relationship_stage = _relationship_stage_hint(
+        evidence_count=evidence_count,
+        recency_days=activity_recency_days,
+        confidence=summary["overall_confidence"],
+    )
+
+    provenance_counts: Dict[str, int] = {}
+    for item in identifiers:
+        provenance = str(item.get("provenance") or "unknown")
+        provenance_counts[provenance] = provenance_counts.get(provenance, 0) + 1
+
+    interaction_history_summary = {
+        "evidence_count": evidence_count,
+        "distinct_sources": len(provenance_counts),
+        "sources": {k: provenance_counts[k] for k in sorted(provenance_counts)},
+    }
+
+    continuity = {
+        "canonical_entity_id": entity_id,
+        "alias_count": len(aliases),
+        "identifier_count": len(identifiers),
+    }
+
+    return RecommendationContext(
+        entity_id=entity_id,
+        identity_confidence=float(summary["overall_confidence"]),
+        activity_recency_days=activity_recency_days,
+        interaction_history_summary=interaction_history_summary,
+        preferred_channel_hint=preferred_channel,
+        relationship_stage_hint=relationship_stage,
+        continuity=continuity,
+    )
+
+
+def _latest_seen(identifiers: List[Dict[str, Any]]) -> datetime | None:
+    timestamps = [
+        _parse_iso(str(item.get("last_seen_at")))
+        for item in identifiers
+        if item.get("last_seen_at")
+    ]
+    clean = [ts for ts in timestamps if ts is not None]
+    if not clean:
+        return None
+    return max(clean)
+
+
+def _parse_iso(raw: str) -> datetime | None:
+    text = raw.strip()
+    if not text:
+        return None
+    if text.endswith("Z"):
+        text = text[:-1] + "+00:00"
+    try:
+        dt = datetime.fromisoformat(text)
+    except ValueError:
+        return None
+    if dt.tzinfo is None:
+        dt = dt.replace(tzinfo=timezone.utc)
+    return dt.astimezone(timezone.utc)
+
+
+def _recency_days(last_seen: datetime | None, now: datetime) -> float:
+    if last_seen is None:
+        return float("inf")
+    delta = now - last_seen
+    seconds = max(0.0, delta.total_seconds())
+    return round(seconds / 86400.0, 6)
+
+
+def _preferred_channel_hint(identifiers: List[Dict[str, Any]]) -> str:
+    weights = {
+        "email": 5,
+        "linkedin_handle": 4,
+        "twitter_handle": 3,
+        "github_handle": 3,
+        "canonical_url": 2,
+        "domain": 1,
+        "name": 0,
+    }
+    scores: Dict[str, int] = {}
+    for item in identifiers:
+        id_type = str(item["identifier_type"])
+        score = weights.get(id_type, 1)
+        scores[id_type] = scores.get(id_type, 0) + score
+    if not scores:
+        return "unknown"
+    return sorted(scores.items(), key=lambda kv: (-kv[1], kv[0]))[0][0]
+
+
+def _relationship_stage_hint(*, evidence_count: int, recency_days: float, confidence: float) -> str:
+    if evidence_count >= 6 and recency_days <= 30 and confidence >= 0.8:
+        return "engaged"
+    if evidence_count >= 3 and recency_days <= 90 and confidence >= 0.65:
+        return "warm"
+    return "cold"

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/metaspn_entities/resolver.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
+from .context import RecommendationContext, EntityContext, build_confidence_summary, build_recommendation_context
 from .events import EmittedEvent, EventFactory
 from .models import (
     DEFAULT_MATCH_CONFIDENCE,
@@ -135,6 +136,36 @@ class EntityResolver:
     def aliases_for_entity(self, entity_id: str) -> List[Dict[str, Any]]:
         return self.store.list_aliases_for_entity(entity_id)
 
+    def confidence_summary(self, entity_id: str) -> Dict[str, Any]:
+        canonical_id = self.store.canonical_entity_id(entity_id)
+        aliases = self.store.list_aliases_for_entity(canonical_id)
+        identifiers = self.store.list_identifier_records_for_entity(canonical_id)
+        return build_confidence_summary(aliases, identifiers, identifiers)
+
+    def entity_context(self, entity_id: str, recent_limit: int = 10) -> EntityContext:
+        canonical_id = self.store.canonical_entity_id(entity_id)
+        aliases = self.store.list_aliases_for_entity(canonical_id)
+        identifiers = self.store.list_identifier_records_for_entity(canonical_id)
+        recent_evidence = sorted(
+            identifiers,
+            key=lambda row: (str(row["last_seen_at"]), str(row["identifier_type"]), str(row["normalized_value"])),
+            reverse=True,
+        )[: max(recent_limit, 0)]
+        summary = build_confidence_summary(aliases, identifiers, recent_evidence)
+        return EntityContext(
+            entity_id=canonical_id,
+            aliases=aliases,
+            identifiers=identifiers,
+            recent_evidence=recent_evidence,
+            confidence_summary=summary,
+        )
+
+    def recommendation_context(self, entity_id: str) -> RecommendationContext:
+        canonical_id = self.store.canonical_entity_id(entity_id)
+        aliases = self.store.list_aliases_for_entity(canonical_id)
+        identifiers = self.store.list_identifier_records_for_entity(canonical_id)
+        return build_recommendation_context(canonical_id, aliases, identifiers)
+
     def export_snapshot(self, output_path: str) -> None:
         self.store.export_snapshot(output_path)
 

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/metaspn_entities/sqlite_backend.py

@@ -276,3 +276,37 @@ class SQLiteEntityStore:
                     "normalized_value": row["normalized_value"],
                     "confidence": row["confidence"],
                 }
+
+    def list_identifier_records_for_entity(self, entity_id: str) -> List[Dict[str, Any]]:
+        target = self.canonical_entity_id(entity_id)
+        rows = self.conn.execute(
+            """
+            SELECT
+              a.entity_id,
+              i.identifier_type,
+              i.value,
+              i.normalized_value,
+              i.confidence,
+              i.first_seen_at,
+              i.last_seen_at,
+              i.provenance
+            FROM aliases a
+            JOIN identifiers i
+              ON a.identifier_type = i.identifier_type
+             AND a.normalized_value = i.normalized_value
+            ORDER BY i.identifier_type, i.normalized_value
+            """
+        ).fetchall()
+        return [
+            {
+                "identifier_type": row["identifier_type"],
+                "value": row["value"],
+                "normalized_value": row["normalized_value"],
+                "confidence": row["confidence"],
+                "first_seen_at": row["first_seen_at"],
+                "last_seen_at": row["last_seen_at"],
+                "provenance": row["provenance"],
+            }
+            for row in rows
+            if self.canonical_entity_id(row["entity_id"]) == target
+        ]

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/metaspn_entities.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metaspn-entities
-Version: 0.1.4
+Version: 0.1.6
 Summary: Canonical entity resolution, aliasing, and merges for MetaSPN systems
 Author: MetaSPN Contributors
 License-Expression: MIT
@@ -99,3 +99,26 @@ Adapter behavior:
 - Extracts deterministic identifier candidates from normalized payloads.
 - Resolves a primary identifier, then adds remaining identifiers as aliases.
 - Returns only events produced during the adapter call.
+
+## M1 Context API
+
+Profiler/router workers can read consolidated context using:
+
+- `resolver.entity_context(entity_id, recent_limit=10)`
+- `resolver.confidence_summary(entity_id)`
+
+Both APIs resolve canonical redirects first, so merged IDs return coherent context.
+
+## M2 Recommendation Context API
+
+Recommendation and drafter workers can consume:
+
+- `resolver.recommendation_context(entity_id)`
+
+The recommendation context includes:
+- identity confidence
+- activity recency (days)
+- interaction history summary (evidence count + source distribution)
+- preferred channel hint
+- relationship stage hint (`cold` / `warm` / `engaged`)
+- merge-safe continuity fields keyed to canonical entity IDs

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/metaspn_entities.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ README.md
 pyproject.toml
 metaspn_entities/__init__.py
 metaspn_entities/adapter.py
+metaspn_entities/context.py
 metaspn_entities/events.py
 metaspn_entities/models.py
 metaspn_entities/normalize.py
@@ -14,5 +15,7 @@ metaspn_entities.egg-info/dependency_links.txt
 metaspn_entities.egg-info/requires.txt
 metaspn_entities.egg-info/top_level.txt
 tests/test_adapter.py
+tests/test_context.py
 tests/test_event_contract.py
+tests/test_recommendation_context.py
 tests/test_resolver.py

{metaspn_entities-0.1.4 → metaspn_entities-0.1.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "metaspn-entities"
-version = "0.1.4"
+version = "0.1.6"
 description = "Canonical entity resolution, aliasing, and merges for MetaSPN systems"
 readme = "README.md"
 requires-python = ">=3.10"

metaspn_entities-0.1.6/tests/test_context.py

@@ -0,0 +1,90 @@
+import tempfile
+import unittest
+from pathlib import Path
+
+from metaspn_entities import SQLiteEntityStore
+from metaspn_entities.adapter import resolve_normalized_social_signal
+from metaspn_entities.resolver import EntityResolver
+
+
+class ContextTests(unittest.TestCase):
+    def setUp(self) -> None:
+        self.tempdir = tempfile.TemporaryDirectory()
+        self.db_path = str(Path(self.tempdir.name) / "entities.db")
+        self.store = SQLiteEntityStore(self.db_path)
+        self.resolver = EntityResolver(self.store)
+
+    def tearDown(self) -> None:
+        self.store.close()
+        self.tempdir.cleanup()
+
+    def test_cross_platform_handle_normalization_in_context(self) -> None:
+        twitter = {
+            "source": "social.ingest",
+            "payload": {
+                "platform": "twitter",
+                "author_handle": "Alice_One",
+                "profile_url": "https://example.com/u/alice",
+            },
+        }
+        linkedin = {
+            "source": "social.ingest",
+            "payload": {
+                "platform": "linkedin",
+                "handle": "alice-one",
+                "profile_url": "http://www.example.com/u/alice/",
+            },
+        }
+
+        first = resolve_normalized_social_signal(self.resolver, twitter)
+        second = resolve_normalized_social_signal(self.resolver, linkedin)
+        self.assertEqual(first.entity_id, second.entity_id)
+
+        context = self.resolver.entity_context(first.entity_id)
+        identifier_types = {item["identifier_type"] for item in context.identifiers}
+        self.assertIn("twitter_handle", identifier_types)
+        self.assertIn("linkedin_handle", identifier_types)
+        self.assertIn("canonical_url", identifier_types)
+
+    def test_merged_entity_context_continuity(self) -> None:
+        a = self.resolver.resolve("twitter_handle", "merge_ctx_a")
+        b = self.resolver.resolve("twitter_handle", "merge_ctx_b")
+        self.resolver.add_alias(a.entity_id, "email", "a@example.com", caused_by="manual")
+        self.resolver.add_alias(b.entity_id, "domain", "example.com", caused_by="manual")
+        self.resolver.merge_entities(a.entity_id, b.entity_id, reason="dedupe", caused_by="manual")
+
+        context_from = self.resolver.entity_context(a.entity_id)
+        context_to = self.resolver.entity_context(b.entity_id)
+
+        self.assertEqual(context_from.entity_id, context_to.entity_id)
+        normalized_values = {item["normalized_value"] for item in context_from.aliases}
+        self.assertIn("merge_ctx_a", normalized_values)
+        self.assertIn("merge_ctx_b", normalized_values)
+
+    def test_rerun_stability_for_context_and_confidence(self) -> None:
+        signal = {
+            "source": "social.ingest",
+            "payload": {
+                "platform": "twitter",
+                "author_handle": "stable_ctx",
+                "profile_url": "https://example.org/stable_ctx",
+            },
+        }
+
+        first = resolve_normalized_social_signal(self.resolver, signal)
+        context_1 = self.resolver.entity_context(first.entity_id)
+        summary_1 = self.resolver.confidence_summary(first.entity_id)
+
+        second = resolve_normalized_social_signal(self.resolver, signal)
+        context_2 = self.resolver.entity_context(second.entity_id)
+        summary_2 = self.resolver.confidence_summary(second.entity_id)
+
+        self.assertEqual(first.entity_id, second.entity_id)
+        self.assertEqual(context_1.entity_id, context_2.entity_id)
+        self.assertEqual(context_1.aliases, context_2.aliases)
+        self.assertEqual(context_1.identifiers, context_2.identifiers)
+        self.assertEqual(summary_1, summary_2)
+
+
+if __name__ == "__main__":
+    unittest.main()

metaspn_entities-0.1.6/tests/test_recommendation_context.py

@@ -0,0 +1,89 @@
+import tempfile
+import unittest
+from pathlib import Path
+
+from metaspn_entities.adapter import resolve_normalized_social_signal
+from metaspn_entities.resolver import EntityResolver
+from metaspn_entities.sqlite_backend import SQLiteEntityStore
+
+
+class RecommendationContextTests(unittest.TestCase):
+    def setUp(self) -> None:
+        self.tempdir = tempfile.TemporaryDirectory()
+        self.db_path = str(Path(self.tempdir.name) / "entities.db")
+        self.store = SQLiteEntityStore(self.db_path)
+        self.resolver = EntityResolver(self.store)
+
+    def tearDown(self) -> None:
+        self.store.close()
+        self.tempdir.cleanup()
+
+    def test_cross_source_consistency(self) -> None:
+        signal_a = {
+            "source": "social.ingest.twitter",
+            "payload": {
+                "platform": "twitter",
+                "author_handle": "rec_user",
+                "profile_url": "https://example.com/p/rec_user",
+            },
+        }
+        signal_b = {
+            "source": "social.ingest.linkedin",
+            "payload": {
+                "platform": "linkedin",
+                "handle": "rec-user",
+                "profile_url": "http://www.example.com/p/rec_user/",
+            },
+        }
+
+        first = resolve_normalized_social_signal(self.resolver, signal_a)
+        second = resolve_normalized_social_signal(self.resolver, signal_b)
+        self.assertEqual(first.entity_id, second.entity_id)
+
+        rec = self.resolver.recommendation_context(first.entity_id)
+        self.assertEqual(rec.entity_id, first.entity_id)
+        self.assertGreaterEqual(rec.identity_confidence, 0.0)
+        self.assertIn(rec.relationship_stage_hint, {"cold", "warm", "engaged"})
+        self.assertIn("social.ingest.linkedin", rec.interaction_history_summary["sources"])
+        self.assertIn("social.ingest.twitter", rec.interaction_history_summary["sources"])
+
+    def test_merge_safe_continuity(self) -> None:
+        a = self.resolver.resolve("twitter_handle", "merge_rec_a")
+        b = self.resolver.resolve("twitter_handle", "merge_rec_b")
+        self.resolver.add_alias(a.entity_id, "email", "a@rec.dev")
+        self.resolver.add_alias(b.entity_id, "domain", "rec.dev")
+        self.resolver.merge_entities(a.entity_id, b.entity_id, reason="dedupe")
+
+        rec_from = self.resolver.recommendation_context(a.entity_id)
+        rec_to = self.resolver.recommendation_context(b.entity_id)
+
+        self.assertEqual(rec_from.entity_id, rec_to.entity_id)
+        self.assertEqual(rec_from.continuity["canonical_entity_id"], rec_to.continuity["canonical_entity_id"])
+        self.assertGreaterEqual(rec_from.continuity["identifier_count"], 2)
+
+    def test_rerun_determinism(self) -> None:
+        signal = {
+            "source": "social.ingest",
+            "payload": {
+                "platform": "twitter",
+                "author_handle": "deterministic_rec",
+                "profile_url": "https://example.org/deterministic_rec",
+            },
+        }
+
+        first = resolve_normalized_social_signal(self.resolver, signal)
+        rec_1 = self.resolver.recommendation_context(first.entity_id)
+
+        second = resolve_normalized_social_signal(self.resolver, signal)
+        rec_2 = self.resolver.recommendation_context(second.entity_id)
+
+        self.assertEqual(first.entity_id, second.entity_id)
+        self.assertEqual(rec_1.entity_id, rec_2.entity_id)
+        self.assertEqual(rec_1.preferred_channel_hint, rec_2.preferred_channel_hint)
+        self.assertEqual(rec_1.relationship_stage_hint, rec_2.relationship_stage_hint)
+        self.assertEqual(rec_1.continuity, rec_2.continuity)
+        self.assertEqual(rec_1.interaction_history_summary, rec_2.interaction_history_summary)
+
+
+if __name__ == "__main__":
+    unittest.main()