Compare commits

..

5 Commits

Author SHA1 Message Date
25eee03f6b docs: add archive_snapshot to FEATURES.yaml (#1268)
Some checks failed
CI / test (pull_request) Failing after 9s
CI / validate (pull_request) Failing after 15s
Review Approval Gate / verify-review (pull_request) Failing after 3s
2026-04-12 09:44:44 +00:00
5e033c9014 test: add snapshot test suite (#1268)
test_snapshot_create, test_snapshot_list, test_snapshot_restore, test_snapshot_diff
2026-04-12 09:43:25 +00:00
c2dd1f974f feat: add snapshot CLI commands (#1268)
mnemosyne snapshot create|list|restore|diff
2026-04-12 09:42:14 +00:00
46159b05b8 feat: export snapshot functions from mnemosyne package (#1268) 2026-04-12 09:41:32 +00:00
bbdf4fbbff feat: add archive snapshot module (#1268)
Point-in-time backup and restore for Mnemosyne.
snapshot_create, snapshot_list, snapshot_restore, snapshot_diff.
2026-04-12 09:40:54 +00:00
22 changed files with 628 additions and 1053 deletions

View File

@@ -177,7 +177,7 @@ The rule is:
- rescue good work from legacy Matrix
- rebuild inside `the-nexus`
- keep telemetry and durable truth flowing through the Hermes harness
- Hermes is the sole harness — no external gateway dependencies
- keep OpenClaw as a sidecar, not the authority
## Verified historical browser-world snapshot

9
app.js
View File

@@ -1,4 +1,4 @@
import ResonanceVisualizer from './nexus/components/resonance-visualizer.js';\nimport * as THREE from 'three';
import * as THREE from 'three';
import { EffectComposer } from 'three/addons/postprocessing/EffectComposer.js';
import { RenderPass } from 'three/addons/postprocessing/RenderPass.js';
import { UnrealBloomPass } from 'three/addons/postprocessing/UnrealBloomPass.js';
@@ -597,7 +597,7 @@ class PSELayer {
let pseLayer;
let resonanceViz, metaLayer, neuroBridge, cbr, symbolicPlanner, knowledgeGraph, blackboard, symbolicEngine, calibrator;
let metaLayer, neuroBridge, cbr, symbolicPlanner, knowledgeGraph, blackboard, symbolicEngine, calibrator;
let agentFSMs = {};
function setupGOFAI() {
@@ -666,7 +666,7 @@ async function init() {
scene = new THREE.Scene();
scene.fog = new THREE.FogExp2(0x050510, 0.012);
setupGOFAI();\n resonanceViz = new ResonanceVisualizer(scene);
setupGOFAI();
camera = new THREE.PerspectiveCamera(65, window.innerWidth / window.innerHeight, 0.1, 1000);
camera.position.copy(playerPos);
@@ -3650,6 +3650,3 @@ init().then(() => {
connectMemPalace();
mineMemPalaceContent();
});
// Memory optimization loop
setInterval(() => { console.log('Running optimization...'); }, 60000);

View File

@@ -26,7 +26,7 @@
| Term | Meaning |
|------|---------|
| **The Robing** | ~~DEPRECATED~~ — Hermes handles all layers directly. No external gateway. |
| **The Robing** | OpenClaw (gateway) + Hermes (body) running together on one machine. |
| **Robed** | Gateway + Hermes running = fully operational wizard. |
| **Unrobed** | No gateway + Hermes = capable but invisible. |
| **Lobster** | Gateway + no Hermes = reachable but empty. **The FAILURE state.** |
@@ -117,14 +117,14 @@
**Why it works:** Naturally models the wizard hierarchy. Queries like "who can do X?" and "what blocks task Y?" resolve instantly.
**Every agent must:** Register themselves in the knowledge graph when they come online.
### TECHNIQUE 4: Hermes-Native Communication (No Gateway Layer)
### TECHNIQUE 4: The Robing Pattern (Gateway + Body Cohabitation)
**Where:** Every wizard deployment
**How:** Hermes handles both reasoning and external communication directly. No intermediary gateway. Two states: Online (Hermes running) or Dead (nothing running).
**Why it works:** Single process. No split-brain failure modes. No Lobster state possible.
**Every agent must:** Know their own state and report it via Hermes heartbeat.
**How:** OpenClaw gateway handles external communication. Hermes body handles reasoning. Both on same machine via localhost. Four states: Robed, Unrobed, Lobster, Dead.
**Why it works:** Separation of concerns. Gateway can restart without losing agent state.
**Every agent must:** Know their own state. A Lobster is a failure. Report it.
### TECHNIQUE 5: Cron-Driven Autonomous Work Dispatch
**Where:** hermes-work.sh, task-monitor.sh, progress-report.sh
**Where:** openclaw-work.sh, task-monitor.sh, progress-report.sh
**How:** Every 20 min: scan queue > pick P0 > mark IN_PROGRESS > create trigger file. Every 10 min: check completion. Every 30 min: progress report to father-messages/.
**Why it works:** No human needed for steady-state. Self-healing. Self-reporting.
**Every agent must:** Have a work queue. Have a cron schedule. Report progress.

View File

@@ -1,4 +1,4 @@
const giteaApiUrl = 'https://forge.alexanderwhitestone.com/api/v1';
const GiteaApiUrl = 'https://forge.alexanderwhitestone.com/api/v1';
const token = process.env.GITEA_TOKEN; // Should be stored securely in environment variables
const repos = ['hermes-agent', 'the-nexus', 'timmy-home', 'timmy-config'];
@@ -13,6 +13,31 @@ const branchProtectionSettings = {
// Special handling for the-nexus (CI disabled)
};
async function applyBranchProtection(repo) {
try {
const response = await fetch(`${giteaApiUrl}/repos/Timmy_Foundation/${repo}/branches/main/protection`, {
method: 'POST',
headers: {
'Authorization': `token ${token}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
...branchProtectionSettings,
// Special handling for the-nexus (CI disabled)
requiredStatusChecks: repo === 'the-nexus' ? false : true
})
});
if (!response.ok) {
throw new Error(`Failed to apply branch protection to ${repo}: ${await response.text()}`);
}
console.log(`✅ Branch protection applied to ${repo}`);
} catch (error) {
console.error(`❌ Error applying branch protection to ${repo}: ${error.message}`);
}
}
async function applyBranchProtection(repo) {
try {
const response = await fetch(`${giteaApiUrl}/repos/Timmy_Foundation/${repo}/branches/main/protection`, {

View File

@@ -1,18 +1,99 @@
// ═══════════════════════════════════════════
// PROJECT MNEMOSYNE — MEMORY OPTIMIZER (GOFAI)
// ═══════════════════════════════════════════
//
// Heuristic-based memory pruning and organization.
// Operates without LLMs to maintain a lean, high-signal spatial index.
//
// Heuristics:
// 1. Strength Decay: Memories lose strength over time if not accessed.
// 2. Redundancy: Simple string similarity to identify duplicates.
// 3. Isolation: Memories with no connections are lower priority.
// 4. Aging: Old memories in 'working' are moved to 'archive'.
// ═══════════════════════════════════════════
class MemoryOptimizer {
constructor(options = {}) {
this.threshold = options.threshold || 0.3;
this.decayRate = options.decayRate || 0.01;
this.lastRun = Date.now();
const MemoryOptimizer = (() => {
const DECAY_RATE = 0.01; // Strength lost per optimization cycle
const PRUNE_THRESHOLD = 0.1; // Remove if strength < this
const SIMILARITY_THRESHOLD = 0.85; // Jaccard similarity for redundancy
/**
* Run a full optimization pass on the spatial memory index.
* @param {object} spatialMemory - The SpatialMemory component instance.
* @returns {object} Summary of actions taken.
*/
function optimize(spatialMemory) {
const memories = spatialMemory.getAllMemories();
const results = { pruned: 0, moved: 0, updated: 0 };
// 1. Strength Decay & Aging
memories.forEach(mem => {
let strength = mem.strength || 0.7;
strength -= DECAY_RATE;
if (strength < PRUNE_THRESHOLD) {
spatialMemory.removeMemory(mem.id);
results.pruned++;
return;
}
// Move old working memories to archive
if (mem.category === 'working') {
const timestamp = mem.timestamp || new Date().toISOString();
const age = Date.now() - new Date(timestamp).getTime();
if (age > 1000 * 60 * 60 * 24) { // 24 hours
spatialMemory.removeMemory(mem.id);
spatialMemory.placeMemory({ ...mem, category: 'archive', strength });
results.moved++;
return;
}
}
spatialMemory.updateMemory(mem.id, { strength });
results.updated++;
});
// 2. Redundancy Check (Jaccard Similarity)
const activeMemories = spatialMemory.getAllMemories();
for (let i = 0; i < activeMemories.length; i++) {
const m1 = activeMemories[i];
// Skip if already pruned in this loop
if (!spatialMemory.getAllMemories().find(m => m.id === m1.id)) continue;
for (let j = i + 1; j < activeMemories.length; j++) {
const m2 = activeMemories[j];
if (m1.category !== m2.category) continue;
const sim = _calculateSimilarity(m1.content, m2.content);
if (sim > SIMILARITY_THRESHOLD) {
// Keep the stronger one, prune the weaker
const toPrune = m1.strength >= m2.strength ? m2.id : m1.id;
spatialMemory.removeMemory(toPrune);
results.pruned++;
// If we pruned m1, we must stop checking it against others
if (toPrune === m1.id) break;
}
}
}
optimize(memories) {
const now = Date.now();
const elapsed = (now - this.lastRun) / 1000;
this.lastRun = now;
return memories.map(m => {
const decay = (m.importance || 1) * this.decayRate * elapsed;
return { ...m, strength: Math.max(0, (m.strength || 1) - decay) };
}).filter(m => m.strength > this.threshold || m.locked);
}
}
export default MemoryOptimizer;
console.info('[Mnemosyne] Optimization complete:', results);
return results;
}
/**
* Calculate Jaccard similarity between two strings.
* @private
*/
function _calculateSimilarity(s1, s2) {
if (!s1 || !s2) return 0;
const set1 = new Set(s1.toLowerCase().split(/\s+/));
const set2 = new Set(s2.toLowerCase().split(/\s+/));
const intersection = new Set([...set1].filter(x => set2.has(x)));
const union = new Set([...set1, ...set2]);
return intersection.size / union.size;
}
return { optimize };
})();
export { MemoryOptimizer };

View File

@@ -1,16 +0,0 @@
import * as THREE from 'three';
class ResonanceVisualizer {
constructor(scene) {
this.scene = scene;
this.links = [];
}
addLink(p1, p2, strength) {
const geometry = new THREE.BufferGeometry().setFromPoints([p1, p2]);
const material = new THREE.LineBasicMaterial({ color: 0x00ff00, transparent: true, opacity: strength });
const line = new THREE.Line(geometry, material);
this.scene.add(line);
this.links.push(line);
}
}
export default ResonanceVisualizer;

View File

@@ -20,6 +20,12 @@ from nexus.mnemosyne.embeddings import (
TfidfEmbeddingBackend,
get_embedding_backend,
)
from nexus.mnemosyne.snapshot import (
snapshot_create,
snapshot_list,
snapshot_restore,
snapshot_diff,
)
__all__ = [
"MnemosyneArchive",
@@ -31,4 +37,8 @@ __all__ = [
"OllamaEmbeddingBackend",
"TfidfEmbeddingBackend",
"get_embedding_backend",
"snapshot_create",
"snapshot_list",
"snapshot_restore",
"snapshot_diff",
]

View File

@@ -1105,241 +1105,6 @@ class MnemosyneArchive:
steps.append({"id": entry_id, "title": "[unknown]", "topics": []})
return steps
# ─── Snapshot / Backup ────────────────────────────────────
def _snapshot_dir(self) -> Path:
"""Return (and create) the snapshots directory next to the archive."""
d = self.path.parent / "snapshots"
d.mkdir(parents=True, exist_ok=True)
return d
@staticmethod
def _snapshot_filename(timestamp: str, label: str) -> str:
"""Build a deterministic snapshot filename."""
safe_label = "".join(c if c.isalnum() or c in "-_" else "_" for c in label) if label else "snapshot"
return f"{timestamp}_{safe_label}.json"
def snapshot_create(self, label: str = "") -> dict:
"""Serialize the current archive state to a timestamped snapshot file.
Args:
label: Human-readable label for the snapshot (optional).
Returns:
Dict with keys: snapshot_id, label, created_at, entry_count, path
"""
now = datetime.now(timezone.utc)
timestamp = now.strftime("%Y%m%d_%H%M%S")
filename = self._snapshot_filename(timestamp, label)
snapshot_id = filename[:-5] # strip .json
snap_path = self._snapshot_dir() / filename
payload = {
"snapshot_id": snapshot_id,
"label": label,
"created_at": now.isoformat(),
"entry_count": len(self._entries),
"archive_path": str(self.path),
"entries": [e.to_dict() for e in self._entries.values()],
}
with open(snap_path, "w") as f:
json.dump(payload, f, indent=2)
return {
"snapshot_id": snapshot_id,
"label": label,
"created_at": payload["created_at"],
"entry_count": payload["entry_count"],
"path": str(snap_path),
}
def snapshot_list(self) -> list[dict]:
"""List available snapshots, newest first.
Returns:
List of dicts with keys: snapshot_id, label, created_at, entry_count, path
"""
snap_dir = self._snapshot_dir()
snapshots = []
for snap_path in sorted(snap_dir.glob("*.json"), reverse=True):
try:
with open(snap_path) as f:
data = json.load(f)
snapshots.append({
"snapshot_id": data.get("snapshot_id", snap_path.stem),
"label": data.get("label", ""),
"created_at": data.get("created_at", ""),
"entry_count": data.get("entry_count", len(data.get("entries", []))),
"path": str(snap_path),
})
except (json.JSONDecodeError, OSError):
continue
return snapshots
def snapshot_restore(self, snapshot_id: str) -> dict:
"""Restore the archive from a snapshot, replacing all current entries.
Args:
snapshot_id: The snapshot_id returned by snapshot_create / snapshot_list.
Returns:
Dict with keys: snapshot_id, restored_count, previous_count
Raises:
FileNotFoundError: If no snapshot with that ID exists.
"""
snap_dir = self._snapshot_dir()
snap_path = snap_dir / f"{snapshot_id}.json"
if not snap_path.exists():
raise FileNotFoundError(f"Snapshot not found: {snapshot_id}")
with open(snap_path) as f:
data = json.load(f)
previous_count = len(self._entries)
self._entries = {}
for entry_data in data.get("entries", []):
entry = ArchiveEntry.from_dict(entry_data)
self._entries[entry.id] = entry
self._save()
return {
"snapshot_id": snapshot_id,
"restored_count": len(self._entries),
"previous_count": previous_count,
}
def snapshot_diff(self, snapshot_id: str) -> dict:
"""Compare a snapshot against the current archive state.
Args:
snapshot_id: The snapshot_id to compare against current state.
Returns:
Dict with keys:
- snapshot_id: str
- added: list of {id, title} — in current, not in snapshot
- removed: list of {id, title} — in snapshot, not in current
- modified: list of {id, title, snapshot_hash, current_hash}
- unchanged: int — count of identical entries
Raises:
FileNotFoundError: If no snapshot with that ID exists.
"""
snap_dir = self._snapshot_dir()
snap_path = snap_dir / f"{snapshot_id}.json"
if not snap_path.exists():
raise FileNotFoundError(f"Snapshot not found: {snapshot_id}")
with open(snap_path) as f:
data = json.load(f)
snap_entries: dict[str, dict] = {}
for entry_data in data.get("entries", []):
snap_entries[entry_data["id"]] = entry_data
current_ids = set(self._entries.keys())
snap_ids = set(snap_entries.keys())
added = []
for eid in current_ids - snap_ids:
e = self._entries[eid]
added.append({"id": e.id, "title": e.title})
removed = []
for eid in snap_ids - current_ids:
snap_e = snap_entries[eid]
removed.append({"id": snap_e["id"], "title": snap_e.get("title", "")})
modified = []
unchanged = 0
for eid in current_ids & snap_ids:
current_hash = self._entries[eid].content_hash
snap_hash = snap_entries[eid].get("content_hash")
if current_hash != snap_hash:
modified.append({
"id": eid,
"title": self._entries[eid].title,
"snapshot_hash": snap_hash,
"current_hash": current_hash,
})
else:
unchanged += 1
return {
"snapshot_id": snapshot_id,
"added": sorted(added, key=lambda x: x["title"]),
"removed": sorted(removed, key=lambda x: x["title"]),
"modified": sorted(modified, key=lambda x: x["title"]),
"unchanged": unchanged,
}
def resonance(
self,
threshold: float = 0.3,
limit: int = 20,
topic: Optional[str] = None,
) -> list[dict]:
"""Discover latent connections — pairs with high similarity but no existing link.
The holographic linker connects entries above its threshold at ingest
time. ``resonance()`` finds entry pairs that are *semantically close*
but have *not* been linked — the hidden potential edges in the graph.
These "almost-connected" pairs reveal thematic overlap that was missed
because entries were ingested at different times or sit just below the
linker threshold.
Args:
threshold: Minimum similarity score to surface a pair (default 0.3).
Pairs already linked are excluded regardless of score.
limit: Maximum number of pairs to return (default 20).
topic: If set, restrict candidates to entries that carry this topic
(case-insensitive). Both entries in a pair must match.
Returns:
List of dicts, sorted by ``score`` descending::
{
"entry_a": {"id": str, "title": str, "topics": list[str]},
"entry_b": {"id": str, "title": str, "topics": list[str]},
"score": float, # similarity in [0, 1]
}
"""
entries = list(self._entries.values())
if topic:
topic_lower = topic.lower()
entries = [e for e in entries if topic_lower in [t.lower() for t in e.topics]]
results: list[dict] = []
for i, entry_a in enumerate(entries):
for entry_b in entries[i + 1:]:
# Skip pairs that are already linked
if entry_b.id in entry_a.links or entry_a.id in entry_b.links:
continue
score = self.linker.compute_similarity(entry_a, entry_b)
if score < threshold:
continue
results.append({
"entry_a": {
"id": entry_a.id,
"title": entry_a.title,
"topics": entry_a.topics,
},
"entry_b": {
"id": entry_b.id,
"title": entry_b.title,
"topics": entry_b.topics,
},
"score": round(score, 4),
})
results.sort(key=lambda x: x["score"], reverse=True)
return results[:limit]
def rebuild_links(self, threshold: Optional[float] = None) -> int:
"""Recompute all links from scratch.

View File

@@ -7,8 +7,7 @@ Provides: mnemosyne ingest, mnemosyne search, mnemosyne link, mnemosyne stats,
mnemosyne timeline, mnemosyne neighbors, mnemosyne path,
mnemosyne touch, mnemosyne decay, mnemosyne vitality,
mnemosyne fading, mnemosyne vibrant,
mnemosyne snapshot create|list|restore|diff,
mnemosyne resonance
mnemosyne snapshot create|list|restore|diff
"""
from __future__ import annotations
@@ -19,7 +18,8 @@ import sys
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.entry import ArchiveEntry
from nexus.mnemosyne.ingest import ingest_event, ingest_directory
from nexus.mnemosyne.ingest import ingest_event
from nexus.mnemosyne.snapshot import snapshot_create, snapshot_list, snapshot_restore, snapshot_diff
def cmd_stats(args):
@@ -65,13 +65,6 @@ def cmd_ingest(args):
print(f"Ingested: [{entry.id[:8]}] {entry.title} ({len(entry.links)} links)")
def cmd_ingest_dir(args):
archive = MnemosyneArchive()
ext = [e.strip() for e in args.ext.split(",")] if args.ext else None
added = ingest_directory(archive, args.path, extensions=ext)
print(f"Ingested {added} new entries from {args.path}")
def cmd_link(args):
archive = MnemosyneArchive()
entry = archive.get(args.entry_id)
@@ -312,86 +305,6 @@ def cmd_fading(args):
print()
def cmd_snapshot(args):
archive = MnemosyneArchive()
if args.snapshot_cmd == "create":
result = archive.snapshot_create(label=args.label or "")
print(f"Snapshot created: {result['snapshot_id']}")
print(f" Label: {result['label'] or '(none)'}")
print(f" Entries: {result['entry_count']}")
print(f" Path: {result['path']}")
elif args.snapshot_cmd == "list":
snapshots = archive.snapshot_list()
if not snapshots:
print("No snapshots found.")
return
for s in snapshots:
print(f"[{s['snapshot_id']}]")
print(f" Label: {s['label'] or '(none)'}")
print(f" Created: {s['created_at']}")
print(f" Entries: {s['entry_count']}")
print()
elif args.snapshot_cmd == "restore":
try:
result = archive.snapshot_restore(args.snapshot_id)
except FileNotFoundError as e:
print(str(e))
sys.exit(1)
print(f"Restored from snapshot: {result['snapshot_id']}")
print(f" Entries restored: {result['restored_count']}")
print(f" Previous count: {result['previous_count']}")
elif args.snapshot_cmd == "diff":
try:
diff = archive.snapshot_diff(args.snapshot_id)
except FileNotFoundError as e:
print(str(e))
sys.exit(1)
print(f"Diff vs snapshot: {diff['snapshot_id']}")
print(f" Added ({len(diff['added'])}): ", end="")
if diff["added"]:
print()
for e in diff["added"]:
print(f" + [{e['id'][:8]}] {e['title']}")
else:
print("none")
print(f" Removed ({len(diff['removed'])}): ", end="")
if diff["removed"]:
print()
for e in diff["removed"]:
print(f" - [{e['id'][:8]}] {e['title']}")
else:
print("none")
print(f" Modified({len(diff['modified'])}): ", end="")
if diff["modified"]:
print()
for e in diff["modified"]:
print(f" ~ [{e['id'][:8]}] {e['title']}")
else:
print("none")
print(f" Unchanged: {diff['unchanged']}")
else:
print(f"Unknown snapshot subcommand: {args.snapshot_cmd}")
sys.exit(1)
def cmd_resonance(args):
archive = MnemosyneArchive()
topic = args.topic if args.topic else None
pairs = archive.resonance(threshold=args.threshold, limit=args.limit, topic=topic)
if not pairs:
print("No resonant pairs found.")
return
for p in pairs:
a = p["entry_a"]
b = p["entry_b"]
print(f"Score: {p['score']:.4f}")
print(f" [{a['id'][:8]}] {a['title']}")
print(f" Topics: {', '.join(a['topics']) if a['topics'] else '(none)'}")
print(f" [{b['id'][:8]}] {b['title']}")
print(f" Topics: {', '.join(b['topics']) if b['topics'] else '(none)'}")
print()
def cmd_vibrant(args):
archive = MnemosyneArchive()
results = archive.vibrant(limit=args.limit)
@@ -404,6 +317,58 @@ def cmd_vibrant(args):
print()
def cmd_snapshot_create(args):
archive = MnemosyneArchive()
result = snapshot_create(archive, label=args.label)
print(f"Snapshot created: {result['snapshot_id']}")
print(f" Entries: {result['entry_count']}")
print(f" Label: {result['label'] or '(none)'}")
print(f" Path: {result['path']}")
def cmd_snapshot_list(args):
archive = MnemosyneArchive()
snaps = snapshot_list(archive)
if not snaps:
print("No snapshots found.")
return
for s in snaps:
label = f" ({s['label']})" if s['label'] else ""
print(f" {s['snapshot_id']} {s['created_at'][:19]} {s['entry_count']} entries{label}")
def cmd_snapshot_restore(args):
archive = MnemosyneArchive()
try:
result = snapshot_restore(archive, args.snapshot_id)
except FileNotFoundError as e:
print(str(e))
sys.exit(1)
print(f"Restored snapshot {result['snapshot_id']}")
print(f" Entries restored: {result['restored_entries']}")
print(f" Previous count: {result['previous_count']}")
def cmd_snapshot_diff(args):
archive = MnemosyneArchive()
try:
result = snapshot_diff(archive, args.snapshot_id)
except FileNotFoundError as e:
print(str(e))
sys.exit(1)
print(f"Diff: snapshot {result['snapshot_id']} vs current")
print(f" Snapshot: {result['snapshot_entries']} entries")
print(f" Current: {result['current_entries']} entries")
print(f" Added: {result['added']}")
print(f" Removed: {result['removed']}")
print(f" Changed: {result['changed']}")
if result['changed_details']:
print()
for c in result['changed_details']:
print(f" [{c['id'][:8]}] {c['title']}")
def main():
parser = argparse.ArgumentParser(prog="mnemosyne", description="The Living Holographic Archive")
sub = parser.add_subparsers(dest="command")
@@ -420,10 +385,6 @@ def main():
i.add_argument("--content", required=True)
i.add_argument("--topics", default="", help="Comma-separated topics")
id_ = sub.add_parser("ingest-dir", help="Ingest a directory of files")
id_.add_argument("path", help="Directory to ingest")
id_.add_argument("--ext", default="", help="Comma-separated extensions (default: md,txt,json)")
l = sub.add_parser("link", help="Show linked entries")
l.add_argument("entry_id", help="Entry ID (or prefix)")
l.add_argument("-d", "--depth", type=int, default=1)
@@ -494,34 +455,30 @@ def main():
vb = sub.add_parser("vibrant", help="Show most alive entries (highest vitality)")
vb.add_argument("-n", "--limit", type=int, default=10, help="Max entries to show")
rs = sub.add_parser("resonance", help="Discover latent connections between entries")
rs.add_argument("-t", "--threshold", type=float, default=0.3, help="Minimum similarity score (default: 0.3)")
rs.add_argument("-n", "--limit", type=int, default=20, help="Max pairs to show (default: 20)")
rs.add_argument("--topic", default="", help="Restrict to entries with this topic")
sn = sub.add_parser("snapshot", help="Point-in-time backup and restore")
sn_sub = sn.add_subparsers(dest="snapshot_cmd")
sn_create = sn_sub.add_parser("create", help="Create a new snapshot")
sn_create.add_argument("--label", default="", help="Human-readable label for the snapshot")
sn_sub.add_parser("list", help="List available snapshots")
sn_restore = sn_sub.add_parser("restore", help="Restore archive from a snapshot")
sn_restore.add_argument("snapshot_id", help="Snapshot ID to restore")
sn_diff = sn_sub.add_parser("diff", help="Show what changed since a snapshot")
sn_diff.add_argument("snapshot_id", help="Snapshot ID to compare against")
args = parser.parse_args()
if not args.command:
parser.print_help()
sys.exit(1)
if args.command == "snapshot" and not args.snapshot_cmd:
sn.print_help()
sys.exit(1)
# Snapshot subcommands
sp = sub.add_parser("snapshot", help="Archive snapshot operations")
sp_sub = sp.add_subparsers(dest="snapshot_command")
sp_create = sp_sub.add_parser("create", help="Create a point-in-time snapshot")
sp_create.add_argument("-l", "--label", default="", help="Human-readable label")
sp_sub.add_parser("list", help="List available snapshots")
sp_restore = sp_sub.add_parser("restore", help="Restore from a snapshot")
sp_restore.add_argument("snapshot_id", help="Snapshot ID (or prefix)")
sp_diff = sp_sub.add_parser("diff", help="Diff snapshot vs current archive")
sp_diff.add_argument("snapshot_id", help="Snapshot ID (or prefix)")
dispatch = {
"stats": cmd_stats,
"search": cmd_search,
"ingest": cmd_ingest,
"ingest-dir": cmd_ingest_dir,
"link": cmd_link,
"topics": cmd_topics,
"remove": cmd_remove,
@@ -542,11 +499,26 @@ def main():
"vitality": cmd_vitality,
"fading": cmd_fading,
"vibrant": cmd_vibrant,
"resonance": cmd_resonance,
"snapshot": cmd_snapshot,
"snapshot": lambda args: _dispatch_snapshot(args),
}
dispatch[args.command](args)
def _dispatch_snapshot(args):
"""Route snapshot subcommands to handlers."""
cmd = getattr(args, "snapshot_command", None)
if cmd == "create":
cmd_snapshot_create(args)
elif cmd == "list":
cmd_snapshot_list(args)
elif cmd == "restore":
cmd_snapshot_restore(args)
elif cmd == "diff":
cmd_snapshot_diff(args)
else:
print("Usage: mnemosyne snapshot {create|list|restore|diff}")
sys.exit(1)
if __name__ == "__main__":
main()

View File

@@ -1,135 +1,15 @@
"""Ingestion pipeline — feeds data into the archive.
Supports ingesting from MemPalace, raw events, manual entries, and files.
Supports ingesting from MemPalace, raw events, and manual entries.
"""
from __future__ import annotations
import re
from pathlib import Path
from typing import Optional, Union
from typing import Optional
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.entry import ArchiveEntry
_DEFAULT_EXTENSIONS = [".md", ".txt", ".json"]
_MAX_CHUNK_CHARS = 4000 # ~1000 tokens; split large files into chunks
def _extract_title(content: str, path: Path) -> str:
"""Return first # heading, or the file stem if none found."""
for line in content.splitlines():
stripped = line.strip()
if stripped.startswith("# "):
return stripped[2:].strip()
return path.stem
def _make_source_ref(path: Path, mtime: float) -> str:
"""Stable identifier for a specific version of a file."""
return f"file:{path}:{int(mtime)}"
def _chunk_content(content: str) -> list[str]:
"""Split content into chunks at ## headings, falling back to fixed windows."""
if len(content) <= _MAX_CHUNK_CHARS:
return [content]
# Prefer splitting on ## section headings
parts = re.split(r"\n(?=## )", content)
if len(parts) > 1:
chunks: list[str] = []
current = ""
for part in parts:
if current and len(current) + len(part) > _MAX_CHUNK_CHARS:
chunks.append(current)
current = part
else:
current = (current + "\n" + part) if current else part
if current:
chunks.append(current)
return chunks
# Fixed-window fallback
return [content[i : i + _MAX_CHUNK_CHARS] for i in range(0, len(content), _MAX_CHUNK_CHARS)]
def ingest_file(
archive: MnemosyneArchive,
path: Union[str, Path],
) -> list[ArchiveEntry]:
"""Ingest a single file into the archive.
- Title is taken from the first ``# heading`` or the filename stem.
- Deduplication is via ``source_ref`` (absolute path + mtime); an
unchanged file is skipped and its existing entries are returned.
- Files over ``_MAX_CHUNK_CHARS`` are split on ``## `` headings (or
fixed character windows as a fallback).
Returns a list of ArchiveEntry objects (one per chunk).
"""
path = Path(path).resolve()
mtime = path.stat().st_mtime
base_ref = _make_source_ref(path, mtime)
# Return existing entries if this file version was already ingested
existing = [e for e in archive._entries.values() if e.source_ref and e.source_ref.startswith(base_ref)]
if existing:
return existing
content = path.read_text(encoding="utf-8", errors="replace")
title = _extract_title(content, path)
chunks = _chunk_content(content)
entries: list[ArchiveEntry] = []
for i, chunk in enumerate(chunks):
chunk_ref = base_ref if len(chunks) == 1 else f"{base_ref}:chunk{i}"
chunk_title = title if len(chunks) == 1 else f"{title} (part {i + 1})"
entry = ArchiveEntry(
title=chunk_title,
content=chunk,
source="file",
source_ref=chunk_ref,
metadata={
"file_path": str(path),
"chunk": i,
"total_chunks": len(chunks),
},
)
archive.add(entry)
entries.append(entry)
return entries
def ingest_directory(
archive: MnemosyneArchive,
dir_path: Union[str, Path],
extensions: Optional[list[str]] = None,
) -> int:
"""Walk a directory tree and ingest all matching files.
``extensions`` defaults to ``[".md", ".txt", ".json"]``.
Values may be given with or without a leading dot.
Returns the count of new archive entries created.
"""
dir_path = Path(dir_path).resolve()
if extensions is None:
exts = _DEFAULT_EXTENSIONS
else:
exts = [e if e.startswith(".") else f".{e}" for e in extensions]
added = 0
for file_path in sorted(dir_path.rglob("*")):
if not file_path.is_file():
continue
if file_path.suffix.lower() not in exts:
continue
before = archive.count
ingest_file(archive, file_path)
added += archive.count - before
return added
def ingest_from_mempalace(
archive: MnemosyneArchive,

View File

@@ -1,14 +0,0 @@
class Reasoner:
def __init__(self, rules):
self.rules = rules
def evaluate(self, entries):
return [r['action'] for r in self.rules if self._check(r['condition'], entries)]
def _check(self, cond, entries):
if cond.startswith('count'):
# e.g. count(type=anomaly)>3
p = cond.replace('count(', '').split(')')
key, val = p[0].split('=')
count = sum(1 for e in entries if e.get(key) == val)
return eval(f"{count}{p[1]}")
return False

View File

@@ -1,22 +0,0 @@
"""Resonance Linker — Finds second-degree connections in the holographic graph."""
class ResonanceLinker:
def __init__(self, archive):
self.archive = archive
def find_resonance(self, entry_id, depth=2):
"""Find entries that are connected via shared neighbors."""
if entry_id not in self.archive._entries: return []
entry = self.archive._entries[entry_id]
neighbors = set(entry.links)
resonance = {}
for neighbor_id in neighbors:
if neighbor_id in self.archive._entries:
for second_neighbor in self.archive._entries[neighbor_id].links:
if second_neighbor != entry_id and second_neighbor not in neighbors:
resonance[second_neighbor] = resonance.get(second_neighbor, 0) + 1
return sorted(resonance.items(), key=lambda x: x[1], reverse=True)

View File

@@ -1,6 +0,0 @@
[
{
"condition": "count(type=anomaly)>3",
"action": "alert"
}
]

View File

@@ -1,2 +1,206 @@
"""Archive snapshot — point-in-time backup and restore.
Lets users create timestamped snapshots of the archive, list them,
restore from any snapshot, and diff a snapshot against the current state.
Snapshots are stored as JSON files in a ``snapshots/`` subdirectory next
to the archive file.
"""
from __future__ import annotations
import json
# Snapshot logic
import uuid
from datetime import datetime, timezone
from pathlib import Path
from typing import Optional
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.entry import ArchiveEntry
def _snapshots_dir(archive: MnemosyneArchive) -> Path:
"""Return the snapshots directory, creating it if needed."""
d = archive.path.parent / "snapshots"
d.mkdir(parents=True, exist_ok=True)
return d
def snapshot_create(
archive: MnemosyneArchive,
label: Optional[str] = None,
) -> dict:
"""Create a point-in-time snapshot of the archive.
Args:
archive: The archive to snapshot.
label: Optional human-readable label for the snapshot.
Returns:
Dict with keys: snapshot_id, label, created_at, entry_count, path
"""
snapshot_id = str(uuid.uuid4())[:8]
now = datetime.now(timezone.utc).isoformat()
data = {
"snapshot_id": snapshot_id,
"label": label or "",
"created_at": now,
"entry_count": archive.count,
"entries": [e.to_dict() for e in archive._entries.values()],
}
path = _snapshots_dir(archive) / f"{snapshot_id}.json"
with open(path, "w") as f:
json.dump(data, f, indent=2)
return {
"snapshot_id": snapshot_id,
"label": label or "",
"created_at": now,
"entry_count": archive.count,
"path": str(path),
}
def snapshot_list(archive: MnemosyneArchive) -> list[dict]:
"""List all available snapshots, newest first.
Returns:
List of dicts with keys: snapshot_id, label, created_at, entry_count
"""
snapshots = []
d = _snapshots_dir(archive)
for f in sorted(d.glob("*.json")):
try:
with open(f) as fh:
meta = json.load(fh)
snapshots.append({
"snapshot_id": meta["snapshot_id"],
"label": meta.get("label", ""),
"created_at": meta["created_at"],
"entry_count": meta["entry_count"],
})
except (json.JSONDecodeError, KeyError):
continue
# Newest first
snapshots.sort(key=lambda s: s["created_at"], reverse=True)
return snapshots
def snapshot_restore(
archive: MnemosyneArchive,
snapshot_id: str,
) -> dict:
"""Restore the archive from a snapshot.
Replaces ALL current entries with the snapshot data. The archive is
saved immediately after restore.
Args:
archive: The archive to restore into.
snapshot_id: ID of the snapshot to restore (or unique prefix).
Returns:
Dict with keys: snapshot_id, restored_entries, previous_count
Raises:
FileNotFoundError: If no matching snapshot is found.
"""
d = _snapshots_dir(archive)
# Find snapshot file by prefix match
snapshot_path = None
for f in d.glob("*.json"):
if f.stem.startswith(snapshot_id):
snapshot_path = f
break
if snapshot_path is None:
raise FileNotFoundError(f"No snapshot matching '{snapshot_id}' found")
with open(snapshot_path) as fh:
data = json.load(fh)
previous_count = archive.count
# Clear and restore
archive._entries = {}
for entry_data in data["entries"]:
entry = ArchiveEntry.from_dict(entry_data)
archive._entries[entry.id] = entry
archive._save()
return {
"snapshot_id": data["snapshot_id"],
"label": data.get("label", ""),
"restored_entries": len(data["entries"]),
"previous_count": previous_count,
}
def snapshot_diff(
archive: MnemosyneArchive,
snapshot_id: str,
) -> dict:
"""Compare a snapshot against the current archive state.
Args:
archive: The current archive.
snapshot_id: ID of the snapshot to compare (or unique prefix).
Returns:
Dict with keys: snapshot_id, snapshot_entries, current_entries,
added (in current but not snapshot), removed (in snapshot but not current),
changed (same ID but different content_hash)
Raises:
FileNotFoundError: If no matching snapshot is found.
"""
d = _snapshots_dir(archive)
snapshot_path = None
for f in d.glob("*.json"):
if f.stem.startswith(snapshot_id):
snapshot_path = f
break
if snapshot_path is None:
raise FileNotFoundError(f"No snapshot matching '{snapshot_id}' found")
with open(snapshot_path) as fh:
data = json.load(fh)
snap_entries = {e["id"]: e for e in data["entries"]}
curr_entries = {e.id: e.to_dict() for e in archive._entries.values()}
snap_ids = set(snap_entries.keys())
curr_ids = set(curr_entries.keys())
added_ids = curr_ids - snap_ids
removed_ids = snap_ids - curr_ids
common_ids = snap_ids & curr_ids
changed = []
for eid in common_ids:
snap_hash = snap_entries[eid].get("content_hash", "")
curr_hash = curr_entries[eid].get("content_hash", "")
if snap_hash != curr_hash:
changed.append({
"id": eid,
"title": curr_entries[eid].get("title", ""),
"snapshot_hash": snap_hash,
"current_hash": curr_hash,
})
return {
"snapshot_id": data["snapshot_id"],
"label": data.get("label", ""),
"snapshot_entries": len(snap_entries),
"current_entries": len(curr_entries),
"added": len(added_ids),
"removed": len(removed_ids),
"changed": len(changed),
"added_ids": sorted(added_ids),
"removed_ids": sorted(removed_ids),
"changed_details": changed,
}

View File

@@ -1 +0,0 @@
# Test discover

View File

@@ -1,241 +0,0 @@
"""Tests for file-based ingestion pipeline (ingest_file / ingest_directory)."""
from __future__ import annotations
import tempfile
from pathlib import Path
import pytest
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.ingest import (
_DEFAULT_EXTENSIONS,
_MAX_CHUNK_CHARS,
_chunk_content,
_extract_title,
_make_source_ref,
ingest_directory,
ingest_file,
)
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _make_archive(tmp_path: Path) -> MnemosyneArchive:
return MnemosyneArchive(archive_path=tmp_path / "archive.json")
# ---------------------------------------------------------------------------
# Unit: _extract_title
# ---------------------------------------------------------------------------
def test_extract_title_from_heading():
content = "# My Document\n\nSome content here."
assert _extract_title(content, Path("ignored.md")) == "My Document"
def test_extract_title_fallback_to_stem():
content = "No heading at all."
assert _extract_title(content, Path("/docs/my_notes.md")) == "my_notes"
def test_extract_title_skips_non_h1():
content = "## Not an H1\n# Actual Title\nContent."
assert _extract_title(content, Path("x.md")) == "Actual Title"
# ---------------------------------------------------------------------------
# Unit: _make_source_ref
# ---------------------------------------------------------------------------
def test_source_ref_format():
p = Path("/tmp/foo.md")
ref = _make_source_ref(p, 1234567890.9)
assert ref == "file:/tmp/foo.md:1234567890"
def test_source_ref_truncates_fractional_mtime():
p = Path("/tmp/a.txt")
assert _make_source_ref(p, 100.99) == _make_source_ref(p, 100.01)
# ---------------------------------------------------------------------------
# Unit: _chunk_content
# ---------------------------------------------------------------------------
def test_chunk_short_content_is_single():
content = "Short content."
assert _chunk_content(content) == [content]
def test_chunk_splits_on_h2():
section_a = "# Intro\n\nIntroductory text. " + "x" * 100
section_b = "## Section B\n\nBody of section B. " + "y" * 100
content = section_a + "\n" + section_b
# Force chunking by using a small fake limit would require patching;
# instead build content large enough to exceed the real limit.
big_a = "# Intro\n\n" + "a" * (_MAX_CHUNK_CHARS - 50)
big_b = "## Section B\n\n" + "b" * (_MAX_CHUNK_CHARS - 50)
combined = big_a + "\n" + big_b
chunks = _chunk_content(combined)
assert len(chunks) >= 2
assert any("Section B" in c for c in chunks)
def test_chunk_fixed_window_fallback():
# Content with no ## headings but > MAX_CHUNK_CHARS
content = "word " * (_MAX_CHUNK_CHARS // 5 + 100)
chunks = _chunk_content(content)
assert len(chunks) >= 2
for c in chunks:
assert len(c) <= _MAX_CHUNK_CHARS
# ---------------------------------------------------------------------------
# ingest_file
# ---------------------------------------------------------------------------
def test_ingest_file_returns_entry(tmp_path):
archive = _make_archive(tmp_path)
doc = tmp_path / "notes.md"
doc.write_text("# My Notes\n\nHello world.")
entries = ingest_file(archive, doc)
assert len(entries) == 1
assert entries[0].title == "My Notes"
assert entries[0].source == "file"
assert "Hello world" in entries[0].content
def test_ingest_file_uses_stem_when_no_heading(tmp_path):
archive = _make_archive(tmp_path)
doc = tmp_path / "raw_log.txt"
doc.write_text("Just some plain text without a heading.")
entries = ingest_file(archive, doc)
assert entries[0].title == "raw_log"
def test_ingest_file_dedup_unchanged(tmp_path):
archive = _make_archive(tmp_path)
doc = tmp_path / "doc.md"
doc.write_text("# Title\n\nContent.")
entries1 = ingest_file(archive, doc)
assert archive.count == 1
# Re-ingest without touching the file — mtime unchanged
entries2 = ingest_file(archive, doc)
assert archive.count == 1 # no duplicate
assert entries2[0].id == entries1[0].id
def test_ingest_file_reingest_after_change(tmp_path):
import os
archive = _make_archive(tmp_path)
doc = tmp_path / "doc.md"
doc.write_text("# Title\n\nOriginal content.")
ingest_file(archive, doc)
assert archive.count == 1
# Write new content, then force mtime forward by 100s so int(mtime) differs
doc.write_text("# Title\n\nUpdated content.")
new_mtime = doc.stat().st_mtime + 100
os.utime(doc, (new_mtime, new_mtime))
ingest_file(archive, doc)
# A new entry is created for the new version
assert archive.count == 2
def test_ingest_file_source_ref_contains_path(tmp_path):
archive = _make_archive(tmp_path)
doc = tmp_path / "thing.txt"
doc.write_text("Plain text.")
entries = ingest_file(archive, doc)
assert str(doc) in entries[0].source_ref
def test_ingest_file_large_produces_chunks(tmp_path):
archive = _make_archive(tmp_path)
doc = tmp_path / "big.md"
# Build content with clear ## sections large enough to trigger chunking
big_a = "# Doc\n\n" + "a" * (_MAX_CHUNK_CHARS - 50)
big_b = "## Part Two\n\n" + "b" * (_MAX_CHUNK_CHARS - 50)
doc.write_text(big_a + "\n" + big_b)
entries = ingest_file(archive, doc)
assert len(entries) >= 2
assert any("part" in e.title.lower() for e in entries)
# ---------------------------------------------------------------------------
# ingest_directory
# ---------------------------------------------------------------------------
def test_ingest_directory_basic(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
docs.mkdir()
(docs / "a.md").write_text("# Alpha\n\nFirst doc.")
(docs / "b.txt").write_text("Beta plain text.")
(docs / "skip.py").write_text("# This should not be ingested")
added = ingest_directory(archive, docs)
assert added == 2
assert archive.count == 2
def test_ingest_directory_custom_extensions(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
docs.mkdir()
(docs / "a.md").write_text("# Alpha")
(docs / "b.py").write_text("No heading — uses stem.")
added = ingest_directory(archive, docs, extensions=["py"])
assert added == 1
titles = [e.title for e in archive._entries.values()]
assert any("b" in t for t in titles)
def test_ingest_directory_ext_without_dot(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
docs.mkdir()
(docs / "notes.md").write_text("# Notes\n\nContent.")
added = ingest_directory(archive, docs, extensions=["md"])
assert added == 1
def test_ingest_directory_no_duplicates_on_rerun(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
docs.mkdir()
(docs / "file.md").write_text("# Stable\n\nSame content.")
ingest_directory(archive, docs)
assert archive.count == 1
added_second = ingest_directory(archive, docs)
assert added_second == 0
assert archive.count == 1
def test_ingest_directory_recurses_subdirs(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
sub = docs / "sub"
sub.mkdir(parents=True)
(docs / "top.md").write_text("# Top level")
(sub / "nested.md").write_text("# Nested")
added = ingest_directory(archive, docs)
assert added == 2
def test_ingest_directory_default_extensions(tmp_path):
archive = _make_archive(tmp_path)
docs = tmp_path / "docs"
docs.mkdir()
(docs / "a.md").write_text("markdown")
(docs / "b.txt").write_text("text")
(docs / "c.json").write_text('{"key": "value"}')
(docs / "d.yaml").write_text("key: value")
added = ingest_directory(archive, docs)
assert added == 3 # md, txt, json — not yaml

View File

@@ -1 +0,0 @@
# Test resonance

View File

@@ -1 +1,139 @@
# Test snapshot
"""Tests for Mnemosyne archive snapshot — create, list, restore, diff."""
import json
import tempfile
from pathlib import Path
import pytest
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.entry import ArchiveEntry
from nexus.mnemosyne.ingest import ingest_event
from nexus.mnemosyne.snapshot import (
snapshot_create,
snapshot_list,
snapshot_restore,
snapshot_diff,
)
@pytest.fixture
def archive(tmp_path):
"""Create a fresh archive with a few entries."""
path = tmp_path / "test_archive.json"
arch = MnemosyneArchive(archive_path=path, auto_embed=False)
ingest_event(arch, title="First", content="hello world", topics=["test"])
ingest_event(arch, title="Second", content="another entry", topics=["demo"])
ingest_event(arch, title="Third", content="more content here", topics=["test", "demo"])
return arch
class TestSnapshotCreate:
def test_create_returns_metadata(self, archive):
result = snapshot_create(archive, label="test snap")
assert "snapshot_id" in result
assert result["label"] == "test snap"
assert result["entry_count"] == 3
assert Path(result["path"]).exists()
def test_create_no_label(self, archive):
result = snapshot_create(archive)
assert result["label"] == ""
def test_snapshot_file_is_valid_json(self, archive):
result = snapshot_create(archive)
with open(result["path"]) as f:
data = json.load(f)
assert data["entry_count"] == 3
assert len(data["entries"]) == 3
assert "created_at" in data
class TestSnapshotList:
def test_empty_list(self, archive):
# Snapshots dir doesn't exist yet (no snapshots created)
# Actually, create() makes the dir, so list before any create:
snaps = snapshot_list(archive)
assert snaps == []
def test_list_returns_created_snapshots(self, archive):
snapshot_create(archive, label="first")
snapshot_create(archive, label="second")
snaps = snapshot_list(archive)
assert len(snaps) == 2
# Newest first
assert snaps[0]["label"] == "second"
assert snaps[1]["label"] == "first"
def test_list_entry_count(self, archive):
snapshot_create(archive)
snaps = snapshot_list(archive)
assert snaps[0]["entry_count"] == 3
class TestSnapshotRestore:
def test_restore_replaces_entries(self, archive):
result = snapshot_create(archive, label="before change")
sid = result["snapshot_id"]
# Add more entries
ingest_event(archive, title="Fourth", content="new entry", topics=["new"])
assert archive.count == 4
# Restore
restore_result = snapshot_restore(archive, sid)
assert restore_result["restored_entries"] == 3
assert restore_result["previous_count"] == 4
assert archive.count == 3
def test_restore_prefix_match(self, archive):
result = snapshot_create(archive)
sid = result["snapshot_id"]
# Use just first 4 chars
restore_result = snapshot_restore(archive, sid[:4])
assert restore_result["snapshot_id"] == sid
def test_restore_nonexistent_raises(self, archive):
with pytest.raises(FileNotFoundError):
snapshot_restore(archive, "nonexistent-id")
def test_restore_preserves_content(self, archive):
result = snapshot_create(archive)
original_titles = sorted(e.title for e in archive._entries.values())
ingest_event(archive, title="Extra", content="extra", topics=[])
snapshot_restore(archive, result["snapshot_id"])
restored_titles = sorted(e.title for e in archive._entries.values())
assert restored_titles == original_titles
class TestSnapshotDiff:
def test_diff_identical(self, archive):
result = snapshot_create(archive)
diff = snapshot_diff(archive, result["snapshot_id"])
assert diff["added"] == 0
assert diff["removed"] == 0
assert diff["changed"] == 0
def test_diff_added_entries(self, archive):
result = snapshot_create(archive)
ingest_event(archive, title="New Entry", content="new", topics=["new"])
diff = snapshot_diff(archive, result["snapshot_id"])
assert diff["added"] == 1
assert diff["removed"] == 0
assert diff["current_entries"] == 4
assert diff["snapshot_entries"] == 3
def test_diff_removed_entries(self, archive):
result = snapshot_create(archive)
# Remove an entry
first_id = list(archive._entries.keys())[0]
archive.remove(first_id)
diff = snapshot_diff(archive, result["snapshot_id"])
assert diff["removed"] == 1
assert first_id in diff["removed_ids"]
def test_diff_nonexistent_raises(self, archive):
with pytest.raises(FileNotFoundError):
snapshot_diff(archive, "nope")

View File

@@ -1,240 +0,0 @@
"""Tests for Mnemosyne snapshot (point-in-time backup/restore) feature."""
from __future__ import annotations
import json
import tempfile
from pathlib import Path
import pytest
from nexus.mnemosyne.archive import MnemosyneArchive
from nexus.mnemosyne.ingest import ingest_event
def _make_archive(tmp_dir: str) -> MnemosyneArchive:
path = Path(tmp_dir) / "archive.json"
return MnemosyneArchive(archive_path=path, auto_embed=False)
# ─── snapshot_create ─────────────────────────────────────────────────────────
def test_snapshot_create_returns_metadata():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="Alpha", content="First entry", topics=["a"])
ingest_event(archive, title="Beta", content="Second entry", topics=["b"])
result = archive.snapshot_create(label="before-bulk-op")
assert result["entry_count"] == 2
assert result["label"] == "before-bulk-op"
assert "snapshot_id" in result
assert "created_at" in result
assert "path" in result
assert Path(result["path"]).exists()
def test_snapshot_create_no_label():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="Gamma", content="Third entry", topics=[])
result = archive.snapshot_create()
assert result["label"] == ""
assert result["entry_count"] == 1
assert Path(result["path"]).exists()
def test_snapshot_file_contains_entries():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
e = ingest_event(archive, title="Delta", content="Fourth entry", topics=["d"])
result = archive.snapshot_create(label="check-content")
with open(result["path"]) as f:
data = json.load(f)
assert data["entry_count"] == 1
assert len(data["entries"]) == 1
assert data["entries"][0]["id"] == e.id
assert data["entries"][0]["title"] == "Delta"
def test_snapshot_create_empty_archive():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
result = archive.snapshot_create(label="empty")
assert result["entry_count"] == 0
assert Path(result["path"]).exists()
# ─── snapshot_list ───────────────────────────────────────────────────────────
def test_snapshot_list_empty():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
assert archive.snapshot_list() == []
def test_snapshot_list_returns_all():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="One", content="c1", topics=[])
archive.snapshot_create(label="first")
ingest_event(archive, title="Two", content="c2", topics=[])
archive.snapshot_create(label="second")
snapshots = archive.snapshot_list()
assert len(snapshots) == 2
labels = {s["label"] for s in snapshots}
assert "first" in labels
assert "second" in labels
def test_snapshot_list_metadata_fields():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
archive.snapshot_create(label="meta-check")
snapshots = archive.snapshot_list()
s = snapshots[0]
for key in ("snapshot_id", "label", "created_at", "entry_count", "path"):
assert key in s
def test_snapshot_list_newest_first():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
archive.snapshot_create(label="a")
archive.snapshot_create(label="b")
snapshots = archive.snapshot_list()
# Filenames sort lexicographically; newest (b) should be first
# (filenames include timestamp so alphabetical = newest-last;
# snapshot_list reverses the glob order → newest first)
assert len(snapshots) == 2
# Both should be present; ordering is newest first
ids = [s["snapshot_id"] for s in snapshots]
assert ids == sorted(ids, reverse=True)
# ─── snapshot_restore ────────────────────────────────────────────────────────
def test_snapshot_restore_replaces_entries():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="Kept", content="original content", topics=["orig"])
snap = archive.snapshot_create(label="pre-change")
# Mutate archive after snapshot
ingest_event(archive, title="New entry", content="post-snapshot", topics=["new"])
assert archive.count == 2
result = archive.snapshot_restore(snap["snapshot_id"])
assert result["restored_count"] == 1
assert result["previous_count"] == 2
assert archive.count == 1
entry = list(archive._entries.values())[0]
assert entry.title == "Kept"
def test_snapshot_restore_persists_to_disk():
with tempfile.TemporaryDirectory() as tmp:
path = Path(tmp) / "archive.json"
archive = _make_archive(tmp)
ingest_event(archive, title="Persisted", content="should survive reload", topics=[])
snap = archive.snapshot_create(label="persist-test")
ingest_event(archive, title="Transient", content="added after snapshot", topics=[])
archive.snapshot_restore(snap["snapshot_id"])
# Reload from disk
archive2 = MnemosyneArchive(archive_path=path, auto_embed=False)
assert archive2.count == 1
assert list(archive2._entries.values())[0].title == "Persisted"
def test_snapshot_restore_missing_raises():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
with pytest.raises(FileNotFoundError):
archive.snapshot_restore("nonexistent_snapshot_id")
# ─── snapshot_diff ───────────────────────────────────────────────────────────
def test_snapshot_diff_no_changes():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="Stable", content="unchanged content", topics=[])
snap = archive.snapshot_create(label="baseline")
diff = archive.snapshot_diff(snap["snapshot_id"])
assert diff["added"] == []
assert diff["removed"] == []
assert diff["modified"] == []
assert diff["unchanged"] == 1
def test_snapshot_diff_detects_added():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
ingest_event(archive, title="Original", content="existing", topics=[])
snap = archive.snapshot_create(label="before-add")
ingest_event(archive, title="Newcomer", content="added after", topics=[])
diff = archive.snapshot_diff(snap["snapshot_id"])
assert len(diff["added"]) == 1
assert diff["added"][0]["title"] == "Newcomer"
assert diff["removed"] == []
assert diff["unchanged"] == 1
def test_snapshot_diff_detects_removed():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
e1 = ingest_event(archive, title="Will Be Removed", content="doomed", topics=[])
ingest_event(archive, title="Survivor", content="stays", topics=[])
snap = archive.snapshot_create(label="pre-removal")
archive.remove(e1.id)
diff = archive.snapshot_diff(snap["snapshot_id"])
assert len(diff["removed"]) == 1
assert diff["removed"][0]["title"] == "Will Be Removed"
assert diff["added"] == []
assert diff["unchanged"] == 1
def test_snapshot_diff_detects_modified():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
e = ingest_event(archive, title="Mutable", content="original content", topics=[])
snap = archive.snapshot_create(label="pre-edit")
archive.update_entry(e.id, content="updated content", auto_link=False)
diff = archive.snapshot_diff(snap["snapshot_id"])
assert len(diff["modified"]) == 1
assert diff["modified"][0]["title"] == "Mutable"
assert diff["modified"][0]["snapshot_hash"] != diff["modified"][0]["current_hash"]
assert diff["added"] == []
assert diff["removed"] == []
def test_snapshot_diff_missing_raises():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
with pytest.raises(FileNotFoundError):
archive.snapshot_diff("no_such_snapshot")
def test_snapshot_diff_includes_snapshot_id():
with tempfile.TemporaryDirectory() as tmp:
archive = _make_archive(tmp)
snap = archive.snapshot_create(label="id-check")
diff = archive.snapshot_diff(snap["snapshot_id"])
assert diff["snapshot_id"] == snap["snapshot_id"]

View File

@@ -1,5 +1,27 @@
#!/bin/bash
echo "Running GOFAI guardrails..."
# Syntax checks
find . -name "*.js" -exec node --check {} +
echo "Guardrails passed."
# [Mnemosyne] Agent Guardrails — The Nexus
# Validates code integrity and scans for secrets before deployment.
echo "--- [Mnemosyne] Running Guardrails ---"
# 1. Syntax Checks
echo "[1/3] Validating syntax..."
for f in ; do
node --check "$f" || { echo "Syntax error in $f"; exit 1; }
done
echo "Syntax OK."
# 2. JSON/YAML Validation
echo "[2/3] Validating configs..."
for f in ; do
node -e "JSON.parse(require('fs').readFileSync('$f'))" || { echo "Invalid JSON: $f"; exit 1; }
done
echo "Configs OK."
# 3. Secret Scan
echo "[3/3] Scanning for secrets..."
grep -rE "AI_|TOKEN|KEY|SECRET" . --exclude-dir=node_modules --exclude=guardrails.sh | grep -v "process.env" && {
echo "WARNING: Potential secrets found!"
} || echo "No secrets detected."
echo "--- Guardrails Passed ---"

View File

@@ -1,4 +1,26 @@
/**
* [Mnemosyne] Smoke Test — The Nexus
* Verifies core components are loadable and basic state is consistent.
*/
import MemoryOptimizer from '../nexus/components/memory-optimizer.js';
const optimizer = new MemoryOptimizer();
console.log('Smoke test passed');
import { SpatialMemory } from '../nexus/components/spatial-memory.js';
import { MemoryOptimizer } from '../nexus/components/memory-optimizer.js';
console.log('--- [Mnemosyne] Running Smoke Test ---');
// 1. Verify Components
if (!SpatialMemory || !MemoryOptimizer) {
console.error('Failed to load core components');
process.exit(1);
}
console.log('Components loaded.');
// 2. Verify Regions
const regions = Object.keys(SpatialMemory.REGIONS || {});
if (regions.length < 5) {
console.error('SpatialMemory regions incomplete:', regions);
process.exit(1);
}
console.log('Regions verified:', regions.join(', '));
console.log('--- Smoke Test Passed ---');

View File

@@ -11,7 +11,7 @@ const ASSETS_TO_CACHE = [
self.addEventListener('install', (event) => {
event.waitUntil(
caches.open(CACHE_NAME).then(cache => {
caches.open(CachedName).then(cache => {
return cache.addAll(ASSETS_TO_CACHE);
})
);