Anto01
3ca19724a5
Addresses the triage-quality problems the user observed:
- Candidates getting wrong project/product attribution
- Stale facts promoted as if still true
- "Hard to decide" items reaching human queue without real value
Solution: let sonnet handle the easy 80%, escalate borderline cases
to opus, auto-discard (or flag) what two models can't resolve.
Plus enrich the context the triage model sees so it can catch
misattribution, contradictions, and temporal drift earlier.
THE 3-TIER FLOW (scripts/auto_triage.py):
Tier 1: sonnet (fast, cheap)
- confidence >= 0.8 + clear verdict → PROMOTE or REJECT (done)
- otherwise → escalate to tier 2
Tier 2: opus (smarter, sees tier-1 verdict + reasoning)
- second opinion with explicit "sonnet said X, resolve the uncertainty"
- confidence >= 0.8 → PROMOTE or REJECT with note="[opus]"
- still uncertain → tier 3
Tier 3: configurable (default discard)
- ATOCORE_TRIAGE_TIER3=discard (default): auto-reject with
"two models couldn't decide" reason
- ATOCORE_TRIAGE_TIER3=human: leave in queue for /admin/triage
Configuration via env vars:
ATOCORE_TRIAGE_MODEL_TIER1 (default sonnet)
ATOCORE_TRIAGE_MODEL_TIER2 (default opus)
ATOCORE_TRIAGE_TIER3 (default discard)
ATOCORE_TRIAGE_ESCALATION_THRESHOLD (default 0.75)
ATOCORE_TRIAGE_TIER2_TIMEOUT_S (default 120 — opus is slower)
ENRICHED CONTEXT shown to the triage model (both tiers):
- List of registered project ids so misattribution is detectable
- Trusted project state entries (ground truth, higher trust than memories)
- Top 30 active memories for the claimed project (was 20)
- Tier 2 additionally sees tier 1's verdict + reason
PROJECT MISATTRIBUTION DETECTION:
- Triage prompt asks the model to output "suggested_project" when it
detects the claimed project is wrong but the content clearly belongs
to a registered one
- Main loop auto-applies the fix via PUT /memory/{id} (which canonicalizes
through the registry)
- Misattribution is the #1 pollution source — this catches it upstream
TEMPORAL AGGRESSIVENESS:
- Prompt upgraded: "be aggressive with valid_until for anything that
reads like 'current state' or 'this week'. When in doubt, 2-4 week
expiry rather than null."
- Stale facts decay automatically via Phase 3's expiry filter
CONFIDENCE GRADING (new in prompt):
- 0.9+: crystal clear durable fact or clear noise
- 0.75-0.9: confident but not cryptographic-certain
- 0.6-0.75: borderline — WILL escalate
- <0.6: genuinely ambiguous — human or discard
Tests: 356 → 366 (10 new, all in test_triage_escalation.py):
- High-confidence tier-1 promote/reject → no tier-2 call
- Low-confidence tier-1 → tier-2 escalates → decides
- needs_human always escalates regardless of confidence
- tier-2 uncertain → discard by default
- tier-2 uncertain → human when configured
- dry-run skips all API calls
- suggested_project flag surfaces + gets printed
- parse_verdict captures suggested_project
Runtime behavior unchanged for the clear cases (sonnet still handles
them). The 20-30% of candidates that currently land as needs_human
will now route through opus, and only the genuinely stuck get a human
(or discard) action.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
AtoCore
Personal context engine that enriches LLM interactions with durable memory, structured context, and project knowledge.
Quick Start
pip install -e .
uvicorn src.atocore.main:app --port 8100
Usage
# Ingest markdown files
curl -X POST http://localhost:8100/ingest \
-H "Content-Type: application/json" \
-d '{"path": "/path/to/notes"}'
# Build enriched context for a prompt
curl -X POST http://localhost:8100/context/build \
-H "Content-Type: application/json" \
-d '{"prompt": "What is the project status?", "project": "myproject"}'
# CLI ingestion
python scripts/ingest_folder.py --path /path/to/notes
# Live operator client
python scripts/atocore_client.py health
python scripts/atocore_client.py audit-query "gigabit" 5
API Endpoints
| Method | Path | Description |
|---|---|---|
| POST | /ingest | Ingest markdown file or folder |
| POST | /query | Retrieve relevant chunks |
| POST | /context/build | Build full context pack |
| GET | /health | Health check |
| GET | /debug/context | Inspect last context pack |
Architecture
FastAPI (port 8100)
|- Ingestion: markdown -> parse -> chunk -> embed -> store
|- Retrieval: query -> embed -> vector search -> rank
|- Context Builder: retrieve -> boost -> budget -> format
|- SQLite (documents, chunks, memories, projects, interactions)
'- ChromaDB (vector embeddings)
Configuration
Set via environment variables (prefix ATOCORE_):
| Variable | Default | Description |
|---|---|---|
| ATOCORE_DEBUG | false | Enable debug logging |
| ATOCORE_PORT | 8100 | Server port |
| ATOCORE_CHUNK_MAX_SIZE | 800 | Max chunk size (chars) |
| ATOCORE_CONTEXT_BUDGET | 3000 | Context pack budget (chars) |
| ATOCORE_EMBEDDING_MODEL | paraphrase-multilingual-MiniLM-L12-v2 | Embedding model |
Testing
pip install -e ".[dev]"
pytest
Operations
scripts/atocore_client.pyprovides a live API client for project refresh, project-state inspection, and retrieval-quality audits.docs/operations.mdcaptures the current operational priority order: retrieval quality, Wave 2 trusted-operational ingestion, AtoDrive scoping, and restore validation.
Architecture Notes
Implementation-facing architecture notes live under docs/architecture/.
Current additions:
docs/architecture/engineering-knowledge-hybrid-architecture.md— 5-layer hybrid modeldocs/architecture/engineering-ontology-v1.md— V1 object and relationship inventorydocs/architecture/engineering-query-catalog.md— 20 v1-required queriesdocs/architecture/memory-vs-entities.md— canonical home splitdocs/architecture/promotion-rules.md— Layer 0 to Layer 2 pipelinedocs/architecture/conflict-model.md— contradictory facts detection and resolution