jason/mempalace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: resolve ruff lint and format errors across codebase

Browse Source 
Fix E402 import ordering, F841 unused variable, F541 unnecessary
f-strings, F401 unused import, and auto-format 6 files.
This commit is contained in:
bensig
2026-04-04 18:37:17 -07:00
parent 0f8fa8c7d5
commit 6d8c462219
7 changed files with 333 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/convomem_bench.py
+4 -5
View File
@@ -25,20 +25,19 @@ import os
import sys import sys
import json import json
import shutil import shutil
import ssl
import tempfile import tempfile
import argparse import argparse
import urllib.request import urllib.request
import ssl
# Bypass SSL for restricted environments
ssl._create_default_https_context = ssl._create_unverified_context
from pathlib import Path from pathlib import Path
from collections import defaultdict from collections import defaultdict
from datetime import datetime from datetime import datetime
import chromadb import chromadb
# Bypass SSL for restricted environments
ssl._create_default_https_context = ssl._create_unverified_context
sys.path.insert(0, str(Path(__file__).parent.parent)) sys.path.insert(0, str(Path(__file__).parent.parent))
HF_BASE = "https://huggingface.co/datasets/Salesforce/ConvoMem/resolve/main/core_benchmark/evidence_questions" HF_BASE = "https://huggingface.co/datasets/Salesforce/ConvoMem/resolve/main/core_benchmark/evidence_questions"
mempalace/cli.py
+7 -3
View File
@@ -334,15 +334,19 @@ def main():
) )
p_split.add_argument("dir", help="Directory containing transcript files") p_split.add_argument("dir", help="Directory containing transcript files")
p_split.add_argument( p_split.add_argument(
"--output-dir", default=None, "--output-dir",
default=None,
help="Write split files here (default: same directory as source files)", help="Write split files here (default: same directory as source files)",
) )
p_split.add_argument( p_split.add_argument(
"--dry-run", action="store_true", "--dry-run",
action="store_true",
help="Show what would be split without writing files", help="Show what would be split without writing files",
) )
p_split.add_argument( p_split.add_argument(
"--min-sessions", type=int, default=2, "--min-sessions",
type=int,
default=2,
help="Only split files containing at least N sessions (default: 2)", help="Only split files containing at least N sessions (default: 2)",
) )
mempalace/knowledge_graph.py
+103 -69
View File
@@ -101,16 +101,23 @@ class KnowledgeGraph:
conn = self._conn() conn = self._conn()
conn.execute( conn.execute(
"INSERT OR REPLACE INTO entities (id, name, type, properties) VALUES (?, ?, ?, ?)", "INSERT OR REPLACE INTO entities (id, name, type, properties) VALUES (?, ?, ?, ?)",
(eid, name, entity_type, props) (eid, name, entity_type, props),
) )
conn.commit() conn.commit()
conn.close() conn.close()
return eid return eid
def add_triple(self, subject: str, predicate: str, obj: str, def add_triple(
valid_from: str = None, valid_to: str = None, self,
confidence: float = 1.0, source_closet: str = None, subject: str,
source_file: str = None): predicate: str,
obj: str,
valid_from: str = None,
valid_to: str = None,
confidence: float = 1.0,
source_closet: str = None,
source_file: str = None,
):
""" """
Add a relationship triple: subject → predicate → object. Add a relationship triple: subject → predicate → object.
@@ -125,19 +132,13 @@ class KnowledgeGraph:
# Auto-create entities if they don't exist # Auto-create entities if they don't exist
conn = self._conn() conn = self._conn()
conn.execute( conn.execute("INSERT OR IGNORE INTO entities (id, name) VALUES (?, ?)", (sub_id, subject))
"INSERT OR IGNORE INTO entities (id, name) VALUES (?, ?)", conn.execute("INSERT OR IGNORE INTO entities (id, name) VALUES (?, ?)", (obj_id, obj))
(sub_id, subject)
)
conn.execute(
"INSERT OR IGNORE INTO entities (id, name) VALUES (?, ?)",
(obj_id, obj)
)
# Check for existing identical triple # Check for existing identical triple
existing = conn.execute( existing = conn.execute(
"SELECT id FROM triples WHERE subject=? AND predicate=? AND object=? AND valid_to IS NULL", "SELECT id FROM triples WHERE subject=? AND predicate=? AND object=? AND valid_to IS NULL",
(sub_id, pred, obj_id) (sub_id, pred, obj_id),
).fetchone() ).fetchone()
if existing: if existing:
@@ -149,7 +150,17 @@ class KnowledgeGraph:
conn.execute( conn.execute(
"""INSERT INTO triples (id, subject, predicate, object, valid_from, valid_to, confidence, source_closet, source_file) """INSERT INTO triples (id, subject, predicate, object, valid_from, valid_to, confidence, source_closet, source_file)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""", VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
(triple_id, sub_id, pred, obj_id, valid_from, valid_to, confidence, source_closet, source_file) (
triple_id,
sub_id,
pred,
obj_id,
valid_from,
valid_to,
confidence,
source_closet,
source_file,
),
) )
conn.commit() conn.commit()
conn.close() conn.close()
@@ -165,7 +176,7 @@ class KnowledgeGraph:
conn = self._conn() conn = self._conn()
conn.execute( conn.execute(
"UPDATE triples SET valid_to=? WHERE subject=? AND predicate=? AND object=? AND valid_to IS NULL", "UPDATE triples SET valid_to=? WHERE subject=? AND predicate=? AND object=? AND valid_to IS NULL",
(ended, sub_id, pred, obj_id) (ended, sub_id, pred, obj_id),
) )
conn.commit() conn.commit()
conn.close() conn.close()
@@ -191,17 +202,19 @@ class KnowledgeGraph:
query += " AND (t.valid_from IS NULL OR t.valid_from <= ?) AND (t.valid_to IS NULL OR t.valid_to >= ?)" query += " AND (t.valid_from IS NULL OR t.valid_from <= ?) AND (t.valid_to IS NULL OR t.valid_to >= ?)"
params.extend([as_of, as_of]) params.extend([as_of, as_of])
for row in conn.execute(query, params).fetchall(): for row in conn.execute(query, params).fetchall():
results.append({ results.append(
"direction": "outgoing", {
"subject": name, "direction": "outgoing",
"predicate": row[2], "subject": name,
"object": row[10], # obj_name "predicate": row[2],
"valid_from": row[4], "object": row[10], # obj_name
"valid_to": row[5], "valid_from": row[4],
"confidence": row[6], "valid_to": row[5],
"source_closet": row[7], "confidence": row[6],
"current": row[5] is None, "source_closet": row[7],
}) "current": row[5] is None,
}
)
if direction in ("incoming", "both"): if direction in ("incoming", "both"):
query = "SELECT t.*, e.name as sub_name FROM triples t JOIN entities e ON t.subject = e.id WHERE t.object = ?" query = "SELECT t.*, e.name as sub_name FROM triples t JOIN entities e ON t.subject = e.id WHERE t.object = ?"
@@ -210,17 +223,19 @@ class KnowledgeGraph:
query += " AND (t.valid_from IS NULL OR t.valid_from <= ?) AND (t.valid_to IS NULL OR t.valid_to >= ?)" query += " AND (t.valid_from IS NULL OR t.valid_from <= ?) AND (t.valid_to IS NULL OR t.valid_to >= ?)"
params.extend([as_of, as_of]) params.extend([as_of, as_of])
for row in conn.execute(query, params).fetchall(): for row in conn.execute(query, params).fetchall():
results.append({ results.append(
"direction": "incoming", {
"subject": row[10], # sub_name "direction": "incoming",
"predicate": row[2], "subject": row[10], # sub_name
"object": name, "predicate": row[2],
"valid_from": row[4], "object": name,
"valid_to": row[5], "valid_from": row[4],
"confidence": row[6], "valid_to": row[5],
"source_closet": row[7], "confidence": row[6],
"current": row[5] is None, "source_closet": row[7],
}) "current": row[5] is None,
}
)
conn.close() conn.close()
return results return results
@@ -243,14 +258,16 @@ class KnowledgeGraph:
results = [] results = []
for row in conn.execute(query, params).fetchall(): for row in conn.execute(query, params).fetchall():
results.append({ results.append(
"subject": row[10], {
"predicate": pred, "subject": row[10],
"object": row[11], "predicate": pred,
"valid_from": row[4], "object": row[11],
"valid_to": row[5], "valid_from": row[4],
"current": row[5] is None, "valid_to": row[5],
}) "current": row[5] is None,
}
)
conn.close() conn.close()
return results return results
@@ -259,14 +276,17 @@ class KnowledgeGraph:
conn = self._conn() conn = self._conn()
if entity_name: if entity_name:
eid = self._entity_id(entity_name) eid = self._entity_id(entity_name)
rows = conn.execute(""" rows = conn.execute(
"""
SELECT t.*, s.name as sub_name, o.name as obj_name SELECT t.*, s.name as sub_name, o.name as obj_name
FROM triples t FROM triples t
JOIN entities s ON t.subject = s.id JOIN entities s ON t.subject = s.id
JOIN entities o ON t.object = o.id JOIN entities o ON t.object = o.id
WHERE (t.subject = ? OR t.object = ?) WHERE (t.subject = ? OR t.object = ?)
ORDER BY t.valid_from ASC NULLS LAST ORDER BY t.valid_from ASC NULLS LAST
""", (eid, eid)).fetchall() """,
(eid, eid),
).fetchall()
else: else:
rows = conn.execute(""" rows = conn.execute("""
SELECT t.*, s.name as sub_name, o.name as obj_name SELECT t.*, s.name as sub_name, o.name as obj_name
@@ -278,14 +298,17 @@ class KnowledgeGraph:
""").fetchall() """).fetchall()
conn.close() conn.close()
return [{ return [
"subject": r[10], {
"predicate": r[2], "subject": r[10],
"object": r[11], "predicate": r[2],
"valid_from": r[4], "object": r[11],
"valid_to": r[5], "valid_from": r[4],
"current": r[5] is None, "valid_to": r[5],
} for r in rows] "current": r[5] is None,
}
for r in rows
]
# ── Stats ───────────────────────────────────────────────────────────── # ── Stats ─────────────────────────────────────────────────────────────
@@ -295,9 +318,12 @@ class KnowledgeGraph:
triples = conn.execute("SELECT COUNT(*) FROM triples").fetchone()[0] triples = conn.execute("SELECT COUNT(*) FROM triples").fetchone()[0]
current = conn.execute("SELECT COUNT(*) FROM triples WHERE valid_to IS NULL").fetchone()[0] current = conn.execute("SELECT COUNT(*) FROM triples WHERE valid_to IS NULL").fetchone()[0]
expired = triples - current expired = triples - current
predicates = [r[0] for r in conn.execute( predicates = [
"SELECT DISTINCT predicate FROM triples ORDER BY predicate" r[0]
).fetchall()] for r in conn.execute(
"SELECT DISTINCT predicate FROM triples ORDER BY predicate"
).fetchall()
]
conn.close() conn.close()
return { return {
"entities": entities, "entities": entities,
@@ -317,16 +343,21 @@ class KnowledgeGraph:
for key, facts in entity_facts.items(): for key, facts in entity_facts.items():
name = facts.get("full_name", key.capitalize()) name = facts.get("full_name", key.capitalize())
etype = facts.get("type", "person") etype = facts.get("type", "person")
self.add_entity(name, etype, { self.add_entity(
"gender": facts.get("gender", ""), name,
"birthday": facts.get("birthday", ""), etype,
}) {
"gender": facts.get("gender", ""),
"birthday": facts.get("birthday", ""),
},
)
# Relationships # Relationships
parent = facts.get("parent") parent = facts.get("parent")
if parent: if parent:
self.add_triple(name, "child_of", parent.capitalize(), self.add_triple(
valid_from=facts.get("birthday")) name, "child_of", parent.capitalize(), valid_from=facts.get("birthday")
)
partner = facts.get("partner") partner = facts.get("partner")
if partner: if partner:
@@ -334,8 +365,12 @@ class KnowledgeGraph:
relationship = facts.get("relationship", "") relationship = facts.get("relationship", "")
if relationship == "daughter": if relationship == "daughter":
self.add_triple(name, "is_child_of", facts.get("parent", "").capitalize() or name, self.add_triple(
valid_from=facts.get("birthday")) name,
"is_child_of",
facts.get("parent", "").capitalize() or name,
valid_from=facts.get("birthday"),
)
elif relationship == "husband": elif relationship == "husband":
self.add_triple(name, "is_partner_of", facts.get("partner", name).capitalize()) self.add_triple(name, "is_partner_of", facts.get("partner", name).capitalize())
elif relationship == "brother": elif relationship == "brother":
@@ -346,5 +381,4 @@ class KnowledgeGraph:
# Interests # Interests
for interest in facts.get("interests", []): for interest in facts.get("interests", []):
self.add_triple(name, "loves", interest.capitalize(), self.add_triple(name, "loves", interest.capitalize(), valid_from="2025-01-01")
valid_from="2025-01-01")
mempalace/mcp_server.py
+94 -40
View File
@@ -26,12 +26,12 @@ from datetime import datetime
from .config import MempalaceConfig from .config import MempalaceConfig
from .searcher import search_memories from .searcher import search_memories
from .palace_graph import traverse, find_tunnels, graph_stats from .palace_graph import traverse, find_tunnels, graph_stats
import chromadb
from .knowledge_graph import KnowledgeGraph from .knowledge_graph import KnowledgeGraph
_kg = KnowledgeGraph() _kg = KnowledgeGraph()
import chromadb
logging.basicConfig(level=logging.INFO, format="%(message)s", stream=sys.stderr) logging.basicConfig(level=logging.INFO, format="%(message)s", stream=sys.stderr)
logger = logging.getLogger("mempalace_mcp") logger = logging.getLogger("mempalace_mcp")
@@ -312,19 +312,24 @@ def tool_kg_query(entity: str, as_of: str = None, direction: str = "both"):
return {"entity": entity, "as_of": as_of, "facts": results, "count": len(results)} return {"entity": entity, "as_of": as_of, "facts": results, "count": len(results)}
def tool_kg_add(subject: str, predicate: str, object: str, def tool_kg_add(
valid_from: str = None, source_closet: str = None): subject: str, predicate: str, object: str, valid_from: str = None, source_closet: str = None
):
"""Add a relationship to the knowledge graph.""" """Add a relationship to the knowledge graph."""
triple_id = _kg.add_triple(subject, predicate, object, triple_id = _kg.add_triple(
valid_from=valid_from, source_closet=source_closet) subject, predicate, object, valid_from=valid_from, source_closet=source_closet
return {"success": True, "triple_id": triple_id, )
"fact": f"{subject} → {predicate} → {object}"} return {"success": True, "triple_id": triple_id, "fact": f"{subject} → {predicate} → {object}"}
def tool_kg_invalidate(subject: str, predicate: str, object: str, ended: str = None): def tool_kg_invalidate(subject: str, predicate: str, object: str, ended: str = None):
"""Mark a fact as no longer true (set end date).""" """Mark a fact as no longer true (set end date)."""
_kg.invalidate(subject, predicate, object, ended=ended) _kg.invalidate(subject, predicate, object, ended=ended)
return {"success": True, "fact": f"{subject} → {predicate} → {object}", "ended": ended or "today"} return {
"success": True,
"fact": f"{subject} → {predicate} → {object}",
"ended": ended or "today",
}
def tool_kg_timeline(entity: str = None): def tool_kg_timeline(entity: str = None):
@@ -362,16 +367,18 @@ def tool_diary_write(agent_name: str, entry: str, topic: str = "general"):
col.add( col.add(
ids=[entry_id], ids=[entry_id],
documents=[entry], documents=[entry],
metadatas=[{ metadatas=[
"wing": wing, {
"room": room, "wing": wing,
"hall": "hall_diary", "room": room,
"topic": topic, "hall": "hall_diary",
"type": "diary_entry", "topic": topic,
"agent": agent_name, "type": "diary_entry",
"filed_at": now.isoformat(), "agent": agent_name,
"date": now.strftime("%Y-%m-%d"), "filed_at": now.isoformat(),
}], "date": now.strftime("%Y-%m-%d"),
}
],
) )
logger.info(f"Diary entry: {entry_id} → {wing}/diary/{topic}") logger.info(f"Diary entry: {entry_id} → {wing}/diary/{topic}")
return { return {
@@ -407,12 +414,14 @@ def tool_diary_read(agent_name: str, last_n: int = 10):
# Combine and sort by timestamp # Combine and sort by timestamp
entries = [] entries = []
for doc, meta in zip(results["documents"], results["metadatas"]): for doc, meta in zip(results["documents"], results["metadatas"]):
entries.append({ entries.append(
"date": meta.get("date", ""), {
"timestamp": meta.get("filed_at", ""), "date": meta.get("date", ""),
"topic": meta.get("topic", ""), "timestamp": meta.get("filed_at", ""),
"content": doc, "topic": meta.get("topic", ""),
}) "content": doc,
}
)
entries.sort(key=lambda x: x["timestamp"], reverse=True) entries.sort(key=lambda x: x["timestamp"], reverse=True)
entries = entries[:last_n] entries = entries[:last_n]
@@ -465,9 +474,18 @@ TOOLS = {
"input_schema": { "input_schema": {
"type": "object", "type": "object",
"properties": { "properties": {
"entity": {"type": "string", "description": "Entity to query (e.g. 'Max', 'MyProject', 'Alice')"}, "entity": {
"as_of": {"type": "string", "description": "Date filter — only facts valid at this date (YYYY-MM-DD, optional)"}, "type": "string",
"direction": {"type": "string", "description": "outgoing (entity→?), incoming (?→entity), or both (default: both)"}, "description": "Entity to query (e.g. 'Max', 'MyProject', 'Alice')",
},
"as_of": {
"type": "string",
"description": "Date filter — only facts valid at this date (YYYY-MM-DD, optional)",
},
"direction": {
"type": "string",
"description": "outgoing (entity→?), incoming (?→entity), or both (default: both)",
},
}, },
"required": ["entity"], "required": ["entity"],
}, },
@@ -479,10 +497,19 @@ TOOLS = {
"type": "object", "type": "object",
"properties": { "properties": {
"subject": {"type": "string", "description": "The entity doing/being something"}, "subject": {"type": "string", "description": "The entity doing/being something"},
"predicate": {"type": "string", "description": "The relationship type (e.g. 'loves', 'works_on', 'daughter_of')"}, "predicate": {
"type": "string",
"description": "The relationship type (e.g. 'loves', 'works_on', 'daughter_of')",
},
"object": {"type": "string", "description": "The entity being connected to"}, "object": {"type": "string", "description": "The entity being connected to"},
"valid_from": {"type": "string", "description": "When this became true (YYYY-MM-DD, optional)"}, "valid_from": {
"source_closet": {"type": "string", "description": "Closet ID where this fact appears (optional)"}, "type": "string",
"description": "When this became true (YYYY-MM-DD, optional)",
},
"source_closet": {
"type": "string",
"description": "Closet ID where this fact appears (optional)",
},
}, },
"required": ["subject", "predicate", "object"], "required": ["subject", "predicate", "object"],
}, },
@@ -496,7 +523,10 @@ TOOLS = {
"subject": {"type": "string", "description": "Entity"}, "subject": {"type": "string", "description": "Entity"},
"predicate": {"type": "string", "description": "Relationship"}, "predicate": {"type": "string", "description": "Relationship"},
"object": {"type": "string", "description": "Connected entity"}, "object": {"type": "string", "description": "Connected entity"},
"ended": {"type": "string", "description": "When it stopped being true (YYYY-MM-DD, default: today)"}, "ended": {
"type": "string",
"description": "When it stopped being true (YYYY-MM-DD, default: today)",
},
}, },
"required": ["subject", "predicate", "object"], "required": ["subject", "predicate", "object"],
}, },
@@ -507,7 +537,10 @@ TOOLS = {
"input_schema": { "input_schema": {
"type": "object", "type": "object",
"properties": { "properties": {
"entity": {"type": "string", "description": "Entity to get timeline for (optional — omit for full timeline)"}, "entity": {
"type": "string",
"description": "Entity to get timeline for (optional — omit for full timeline)",
},
}, },
}, },
"handler": tool_kg_timeline, "handler": tool_kg_timeline,
@@ -522,8 +555,14 @@ TOOLS = {
"input_schema": { "input_schema": {
"type": "object", "type": "object",
"properties": { "properties": {
"start_room": {"type": "string", "description": "Room to start from (e.g. 'chromadb-setup', 'riley-school')"}, "start_room": {
"max_hops": {"type": "integer", "description": "How many connections to follow (default: 2)"}, "type": "string",
"description": "Room to start from (e.g. 'chromadb-setup', 'riley-school')",
},
"max_hops": {
"type": "integer",
"description": "How many connections to follow (default: 2)",
},
}, },
"required": ["start_room"], "required": ["start_room"],
}, },
@@ -611,9 +650,18 @@ TOOLS = {
"input_schema": { "input_schema": {
"type": "object", "type": "object",
"properties": { "properties": {
"agent_name": {"type": "string", "description": "Your name — each agent gets their own diary wing"}, "agent_name": {
"entry": {"type": "string", "description": "Your diary entry in AAAK format — compressed, entity-coded, emotion-marked"}, "type": "string",
"topic": {"type": "string", "description": "Topic tag (optional, default: general)"}, "description": "Your name — each agent gets their own diary wing",
},
"entry": {
"type": "string",
"description": "Your diary entry in AAAK format — compressed, entity-coded, emotion-marked",
},
"topic": {
"type": "string",
"description": "Topic tag (optional, default: general)",
},
}, },
"required": ["agent_name", "entry"], "required": ["agent_name", "entry"],
}, },
@@ -624,8 +672,14 @@ TOOLS = {
"input_schema": { "input_schema": {
"type": "object", "type": "object",
"properties": { "properties": {
"agent_name": {"type": "string", "description": "Your name — each agent gets their own diary wing"}, "agent_name": {
"last_n": {"type": "integer", "description": "Number of recent entries to read (default: 10)"}, "type": "string",
"description": "Your name — each agent gets their own diary wing",
},
"last_n": {
"type": "integer",
"description": "Number of recent entries to read (default: 10)",
},
}, },
"required": ["agent_name"], "required": ["agent_name"],
}, },
mempalace/onboarding.py
+30 -21
View File
@@ -263,7 +263,9 @@ def _warn_ambiguous(people: list) -> list:
# ───────────────────────────────────────────────────────────────────────────── # ─────────────────────────────────────────────────────────────────────────────
def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: str, config_dir: Path = None): def _generate_aaak_bootstrap(
people: list, projects: list, wings: list, mode: str, config_dir: Path = None
):
""" """
Generate AAAK entity registry + critical facts bootstrap from onboarding data. Generate AAAK entity registry + critical facts bootstrap from onboarding data.
These files teach the AI about the user's world from session one. These files teach the AI about the user's world from session one.
@@ -292,7 +294,6 @@ def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: st
name = p["name"] name = p["name"]
code = entity_codes[name] code = entity_codes[name]
rel = p.get("relationship", "") rel = p.get("relationship", "")
ctx = p.get("context", "")
registry_lines.append(f" {code}={name} ({rel})" if rel else f" {code}={name}") registry_lines.append(f" {code}={name} ({rel})" if rel else f" {code}={name}")
if projects: if projects:
@@ -301,13 +302,15 @@ def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: st
code = proj[:4].upper() code = proj[:4].upper()
registry_lines.append(f" {code}={proj}") registry_lines.append(f" {code}={proj}")
registry_lines.extend([ registry_lines.extend(
"", [
"## AAAK Quick Reference", "",
" Symbols: ♡=love ★=importance ⚠=warning →=relationship |=separator", "## AAAK Quick Reference",
" Structure: KEY:value | GROUP(details) | entity.attribute", " Symbols: ♡=love ★=importance ⚠=warning →=relationship |=separator",
" Read naturally — expand codes, treat *markers* as emotional context.", " Structure: KEY:value | GROUP(details) | entity.attribute",
]) " Read naturally — expand codes, treat *markers* as emotional context.",
]
)
(mempalace_dir / "aaak_entities.md").write_text("\n".join(registry_lines)) (mempalace_dir / "aaak_entities.md").write_text("\n".join(registry_lines))
@@ -325,7 +328,9 @@ def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: st
for p in personal_people: for p in personal_people:
code = entity_codes[p["name"]] code = entity_codes[p["name"]]
rel = p.get("relationship", "") rel = p.get("relationship", "")
facts_lines.append(f"- **{p['name']}** ({code}) — {rel}" if rel else f"- **{p['name']}** ({code})") facts_lines.append(
f"- **{p['name']}** ({code}) — {rel}" if rel else f"- **{p['name']}** ({code})"
)
facts_lines.append("") facts_lines.append("")
if work_people: if work_people:
@@ -333,7 +338,9 @@ def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: st
for p in work_people: for p in work_people:
code = entity_codes[p["name"]] code = entity_codes[p["name"]]
rel = p.get("relationship", "") rel = p.get("relationship", "")
facts_lines.append(f"- **{p['name']}** ({code}) — {rel}" if rel else f"- **{p['name']}** ({code})") facts_lines.append(
f"- **{p['name']}** ({code}) — {rel}" if rel else f"- **{p['name']}** ({code})"
)
facts_lines.append("") facts_lines.append("")
if projects: if projects:
@@ -342,13 +349,15 @@ def _generate_aaak_bootstrap(people: list, projects: list, wings: list, mode: st
facts_lines.append(f"- **{proj}**") facts_lines.append(f"- **{proj}**")
facts_lines.append("") facts_lines.append("")
facts_lines.extend([ facts_lines.extend(
"## Palace", [
f"Wings: {', '.join(wings)}", "## Palace",
f"Mode: {mode}", f"Wings: {', '.join(wings)}",
"", f"Mode: {mode}",
"*This file will be enriched by palace_facts.py after mining.*", "",
]) "*This file will be enriched by palace_facts.py after mining.*",
]
)
(mempalace_dir / "critical_facts.md").write_text("\n".join(facts_lines)) (mempalace_dir / "critical_facts.md").write_text("\n".join(facts_lines))
@@ -433,9 +442,9 @@ def run_onboarding(
print(f" {registry.summary()}") print(f" {registry.summary()}")
print(f"\n Wings: {', '.join(wings)}") print(f"\n Wings: {', '.join(wings)}")
print(f"\n Registry saved to: {registry._path}") print(f"\n Registry saved to: {registry._path}")
print(f"\n AAAK entity registry: ~/.mempalace/aaak_entities.md") print("\n AAAK entity registry: ~/.mempalace/aaak_entities.md")
print(f" Critical facts bootstrap: ~/.mempalace/critical_facts.md") print(" Critical facts bootstrap: ~/.mempalace/critical_facts.md")
print(f"\n Your AI will know your world from the first session.") print("\n Your AI will know your world from the first session.")
print() print()
return registry return registry
mempalace/palace_graph.py
+42 -31
View File
@@ -71,15 +71,17 @@ def build_graph(col=None, config=None):
wings = sorted(data["wings"]) wings = sorted(data["wings"])
if len(wings) >= 2: if len(wings) >= 2:
for i, wa in enumerate(wings): for i, wa in enumerate(wings):
for wb in wings[i + 1:]: for wb in wings[i + 1 :]:
for hall in data["halls"]: for hall in data["halls"]:
edges.append({ edges.append(
"room": room, {
"wing_a": wa, "room": room,
"wing_b": wb, "wing_a": wa,
"hall": hall, "wing_b": wb,
"count": data["count"], "hall": hall,
}) "count": data["count"],
}
)
# Convert sets to lists for JSON serialization # Convert sets to lists for JSON serialization
nodes = {} nodes = {}
@@ -104,17 +106,22 @@ def traverse(start_room: str, col=None, config=None, max_hops: int = 2):
nodes, edges = build_graph(col, config) nodes, edges = build_graph(col, config)
if start_room not in nodes: if start_room not in nodes:
return {"error": f"Room '{start_room}' not found", "suggestions": _fuzzy_match(start_room, nodes)} return {
"error": f"Room '{start_room}' not found",
"suggestions": _fuzzy_match(start_room, nodes),
}
start = nodes[start_room] start = nodes[start_room]
visited = {start_room} visited = {start_room}
results = [{ results = [
"room": start_room, {
"wings": start["wings"], "room": start_room,
"halls": start["halls"], "wings": start["wings"],
"count": start["count"], "halls": start["halls"],
"hop": 0, "count": start["count"],
}] "hop": 0,
}
]
# BFS traversal # BFS traversal
frontier = [(start_room, 0)] frontier = [(start_room, 0)]
@@ -133,14 +140,16 @@ def traverse(start_room: str, col=None, config=None, max_hops: int = 2):
shared_wings = current_wings & set(data["wings"]) shared_wings = current_wings & set(data["wings"])
if shared_wings: if shared_wings:
visited.add(room) visited.add(room)
results.append({ results.append(
"room": room, {
"wings": data["wings"], "room": room,
"halls": data["halls"], "wings": data["wings"],
"count": data["count"], "halls": data["halls"],
"hop": depth + 1, "count": data["count"],
"connected_via": sorted(shared_wings), "hop": depth + 1,
}) "connected_via": sorted(shared_wings),
}
)
if depth + 1 < max_hops: if depth + 1 < max_hops:
frontier.append((room, depth + 1)) frontier.append((room, depth + 1))
@@ -167,13 +176,15 @@ def find_tunnels(wing_a: str = None, wing_b: str = None, col=None, config=None):
if wing_b and wing_b not in wings: if wing_b and wing_b not in wings:
continue continue
tunnels.append({ tunnels.append(
"room": room, {
"wings": wings, "room": room,
"halls": data["halls"], "wings": wings,
"count": data["count"], "halls": data["halls"],
"recent": data["dates"][-1] if data["dates"] else "", "count": data["count"],
}) "recent": data["dates"][-1] if data["dates"] else "",
}
)
tunnels.sort(key=lambda x: -x["count"]) tunnels.sort(key=lambda x: -x["count"])
return tunnels[:50] return tunnels[:50]
mempalace/split_mega_files.py
+53 -31
View File
@@ -26,16 +26,16 @@ import argparse
import json import json
import os import os
import re import re
import sys
from pathlib import Path from pathlib import Path
HOME = Path.home() HOME = Path.home()
LUMI_DIR = Path(os.environ.get("MEMPALACE_SOURCE_DIR", str(HOME / "Desktop/transcripts"))) LUMI_DIR = Path(os.environ.get("MEMPALACE_SOURCE_DIR", str(HOME / "Desktop/transcripts")))
# People we know about (for name detection in content) # People we know about (for name detection in content)
# Loaded from ~/.mempalace/known_names.json if it exists, otherwise generic fallback. # Loaded from ~/.mempalace/known_names.json if it exists, otherwise generic fallback.
_KNOWN_NAMES_PATH = HOME / ".mempalace" / "known_names.json" _KNOWN_NAMES_PATH = HOME / ".mempalace" / "known_names.json"
def _load_known_people() -> list: def _load_known_people() -> list:
"""Load known names from config file, falling back to a generic list.""" """Load known names from config file, falling back to a generic list."""
if _KNOWN_NAMES_PATH.exists(): if _KNOWN_NAMES_PATH.exists():
@@ -49,6 +49,7 @@ def _load_known_people() -> list:
# Generic fallback — override by creating ~/.mempalace/known_names.json # Generic fallback — override by creating ~/.mempalace/known_names.json
return ["Alice", "Ben", "Riley", "Max", "Sam", "Devon", "Jordan"] return ["Alice", "Ben", "Riley", "Max", "Sam", "Devon", "Jordan"]
KNOWN_PEOPLE = _load_known_people() KNOWN_PEOPLE = _load_known_people()
@@ -69,7 +70,7 @@ def is_true_session_start(lines, idx):
True session start: 'Claude Code v' header NOT followed by 'Ctrl+E'/'previous messages' True session start: 'Claude Code v' header NOT followed by 'Ctrl+E'/'previous messages'
within the next 6 lines (those are context restores, not new sessions). within the next 6 lines (those are context restores, not new sessions).
""" """
nearby = "".join(lines[idx:idx + 6]) nearby = "".join(lines[idx : idx + 6])
return "Ctrl+E" not in nearby and "previous messages" not in nearby return "Ctrl+E" not in nearby and "previous messages" not in nearby
@@ -87,13 +88,20 @@ def extract_timestamp(lines):
Find the first timestamp line: ⏺ H:MM AM/PM Weekday, Month DD, YYYY Find the first timestamp line: ⏺ H:MM AM/PM Weekday, Month DD, YYYY
Returns (datetime_str, iso_str) or (None, None). Returns (datetime_str, iso_str) or (None, None).
""" """
ts_pattern = re.compile( ts_pattern = re.compile(r"⏺\s+(\d{1,2}:\d{2}\s+[AP]M)\s+\w+,\s+(\w+)\s+(\d{1,2}),\s+(\d{4})")
r"⏺\s+(\d{1,2}:\d{2}\s+[AP]M)\s+\w+,\s+(\w+)\s+(\d{1,2}),\s+(\d{4})"
)
months = { months = {
"January": "01", "February": "02", "March": "03", "April": "04", "January": "01",
"May": "05", "June": "06", "July": "07", "August": "08", "February": "02",
"September": "09", "October": "10", "November": "11", "December": "12", "March": "03",
"April": "04",
"May": "05",
"June": "06",
"July": "07",
"August": "08",
"September": "09",
"October": "10",
"November": "11",
"December": "12",
} }
for line in lines[:50]: for line in lines[:50]:
m = ts_pattern.search(line) m = ts_pattern.search(line)
@@ -177,16 +185,16 @@ def split_file(filepath, output_dir, dry_run=False):
continue # Skip tiny fragments continue # Skip tiny fragments
ts_human, ts_iso = extract_timestamp(chunk) ts_human, ts_iso = extract_timestamp(chunk)
people = extract_people(chunk) people = extract_people(chunk)
subject = extract_subject(chunk) subject = extract_subject(chunk)
# Build filename: SOURCESTEM__DATE_TIME_People_subject.txt # Build filename: SOURCESTEM__DATE_TIME_People_subject.txt
# Source stem prefix prevents collisions when multiple mega-files # Source stem prefix prevents collisions when multiple mega-files
# produce sessions with the same timestamp/people/subject. # produce sessions with the same timestamp/people/subject.
ts_part = ts_human or f"part{i+1:02d}" ts_part = ts_human or f"part{i + 1:02d}"
people_part = "-".join(people[:3]) if people else "unknown" people_part = "-".join(people[:3]) if people else "unknown"
src_stem = re.sub(r"[^\w-]", "_", path.stem)[:40] src_stem = re.sub(r"[^\w-]", "_", path.stem)[:40]
name = f"{src_stem}__{ts_part}_{people_part}_{subject}.txt" name = f"{src_stem}__{ts_part}_{people_part}_{subject}.txt"
# Sanitize # Sanitize
name = re.sub(r"[^\w\.\-]", "_", name) name = re.sub(r"[^\w\.\-]", "_", name)
name = re.sub(r"_+", "_", name) name = re.sub(r"_+", "_", name)
@@ -194,7 +202,7 @@ def split_file(filepath, output_dir, dry_run=False):
out_path = out_dir / name out_path = out_dir / name
if dry_run: if dry_run:
print(f" [{i+1}/{len(boundaries)-1}] {name} ({len(chunk)} lines)") print(f" [{i + 1}/{len(boundaries) - 1}] {name} ({len(chunk)} lines)")
else: else:
out_path.write_text("".join(chunk)) out_path.write_text("".join(chunk))
print(f" ✓ {name} ({len(chunk)} lines)") print(f" ✓ {name} ({len(chunk)} lines)")
@@ -208,19 +216,33 @@ def main():
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description="Split concatenated transcript mega-files into per-session files" description="Split concatenated transcript mega-files into per-session files"
) )
parser.add_argument("--source", type=str, default=None, parser.add_argument(
help="Source directory (default: MEMPALACE_SOURCE_DIR or ~/Desktop/transcripts)") "--source",
parser.add_argument("--output-dir", type=str, default=None, type=str,
help="Output directory (default: same as source)") default=None,
parser.add_argument("--min-sessions", type=int, default=2, help="Source directory (default: MEMPALACE_SOURCE_DIR or ~/Desktop/transcripts)",
help="Only split files with at least N sessions (default: 2)") )
parser.add_argument("--dry-run", action="store_true", parser.add_argument(
help="Show what would happen without writing files") "--output-dir", type=str, default=None, help="Output directory (default: same as source)"
parser.add_argument("--file", type=str, default=None, )
help="Split a single specific file instead of scanning dir") parser.add_argument(
"--min-sessions",
type=int,
default=2,
help="Only split files with at least N sessions (default: 2)",
)
parser.add_argument(
"--dry-run", action="store_true", help="Show what would happen without writing files"
)
parser.add_argument(
"--file",
type=str,
default=None,
help="Split a single specific file instead of scanning dir",
)
args = parser.parse_args() args = parser.parse_args()
src_dir = Path(args.source) if args.source else LUMI_DIR src_dir = Path(args.source) if args.source else LUMI_DIR
output_dir = args.output_dir or None # None = same dir as file output_dir = args.output_dir or None # None = same dir as file
if args.file: if args.file:
@@ -239,13 +261,13 @@ def main():
print(f"No mega-files found in {src_dir} (min {args.min_sessions} sessions).") print(f"No mega-files found in {src_dir} (min {args.min_sessions} sessions).")
return return
print(f"\n{'='*60}") print(f"\n{'=' * 60}")
print(f" Mega-file splitter — {'DRY RUN' if args.dry_run else 'SPLITTING'}") print(f" Mega-file splitter — {'DRY RUN' if args.dry_run else 'SPLITTING'}")
print(f"{'='*60}") print(f"{'=' * 60}")
print(f" Source: {src_dir}") print(f" Source: {src_dir}")
print(f" Output: {output_dir or 'same dir as source'}") print(f" Output: {output_dir or 'same dir as source'}")
print(f" Mega-files: {len(mega_files)}") print(f" Mega-files: {len(mega_files)}")
print(f"{'─'*60}\n") print(f"{'─' * 60}\n")
total_written = 0 total_written = 0
for f, n_sessions in mega_files: for f, n_sessions in mega_files:
@@ -260,7 +282,7 @@ def main():
else: else:
print() print()
print(f"{'─'*60}") print(f"{'─' * 60}")
if args.dry_run: if args.dry_run:
print(f" DRY RUN — would create {total_written} files from {len(mega_files)} mega-files") print(f" DRY RUN — would create {total_written} files from {len(mega_files)} mega-files")
else: else: