Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 3e71dbc70b | |||
| 23160a0957 |
@@ -1,265 +0,0 @@
|
||||
# Holographic + Vector Hybrid Memory Architecture
|
||||
|
||||
**Issue:** #663 — Research: Combining HRR Compositional Queries with Semantic Search
|
||||
**Date:** 2026-04-14
|
||||
|
||||
## Executive Summary
|
||||
|
||||
The optimal memory architecture is a **hybrid** combining three methods:
|
||||
- **HRR (Holographic Reduced Representations)** — Compositional reasoning
|
||||
- **Vector Search (Qdrant)** — Semantic similarity
|
||||
- **FTS5 (SQLite Full-Text Search)** — Exact keyword matching
|
||||
|
||||
No single method covers all use cases. Each excels at different query types.
|
||||
|
||||
## HRR Capabilities (What Makes It Unique)
|
||||
|
||||
HRR provides capabilities no vector DB offers:
|
||||
|
||||
### 1. Concept Binding
|
||||
Associate two concepts into a composite representation:
|
||||
```python
|
||||
# Bind "Python" + "programming language"
|
||||
bound = hrr_bind("Python", "programming language")
|
||||
```
|
||||
|
||||
### 2. Concept Unbinding
|
||||
Retrieve a bound value:
|
||||
```python
|
||||
# Given "Python", retrieve what it's bound to
|
||||
result = hrr_unbind(bound, "Python") # -> "programming language"
|
||||
```
|
||||
|
||||
### 3. Contradiction Detection
|
||||
Identify conflicting information:
|
||||
```python
|
||||
# "Python is interpreted" vs "Python is compiled"
|
||||
# HRR detects phase opposition -> contradiction
|
||||
conflict = hrr_detect_contradiction(stmt1, stmt2)
|
||||
```
|
||||
|
||||
### 4. Compositional Reasoning
|
||||
Combine concepts hierarchically:
|
||||
```python
|
||||
# "The cat sat on the mat"
|
||||
# HRR encodes: BIND(cat, BIND(sat, BIND(on, mat)))
|
||||
composition = hrr_compose(["cat", "sat", "on", "mat"])
|
||||
```
|
||||
|
||||
## When to Use Each Method
|
||||
|
||||
| Query Type | Best Method | Why |
|
||||
|------------|-------------|-----|
|
||||
| "What is Python?" | Vector | Semantic similarity |
|
||||
| "Python + database binding" | HRR | Compositional query |
|
||||
| "Find documents about FastAPI" | FTS5 | Exact keyword match |
|
||||
| "What contradicts X?" | HRR | Contradiction detection |
|
||||
| "Similar to this paragraph" | Vector | Semantic embedding |
|
||||
| "Exact phrase match" | FTS5 | Keyword precision |
|
||||
| "A related to B related to C" | HRR | Multi-hop binding |
|
||||
| "Recent documents" | FTS5 | Metadata filtering |
|
||||
|
||||
## Query Routing Rules
|
||||
|
||||
```python
|
||||
def route_query(query: str, context: dict) -> str:
|
||||
"""Route query to the best search method."""
|
||||
|
||||
# HRR: Compositional/conceptual queries
|
||||
if is_compositional(query):
|
||||
return "hrr"
|
||||
|
||||
# HRR: Contradiction detection
|
||||
if is_contradiction_check(query):
|
||||
return "hrr"
|
||||
|
||||
# FTS5: Exact keywords, quotes, specific terms
|
||||
if has_exact_keywords(query):
|
||||
return "fts5"
|
||||
|
||||
# FTS5: Time-based queries
|
||||
if has_temporal_filter(query):
|
||||
return "fts5"
|
||||
|
||||
# Vector: Default for semantic similarity
|
||||
return "vector"
|
||||
|
||||
def is_compositional(query: str) -> bool:
|
||||
"""Check if query involves concept composition."""
|
||||
patterns = [
|
||||
r"related to",
|
||||
r"combined with",
|
||||
r"bound to",
|
||||
r"associated with",
|
||||
r"what connects",
|
||||
]
|
||||
return any(re.search(p, query.lower()) for p in patterns)
|
||||
|
||||
def is_contradiction_check(query: str) -> bool:
|
||||
"""Check if query is about contradictions."""
|
||||
patterns = [
|
||||
r"contradicts?",
|
||||
r"conflicts? with",
|
||||
r"inconsistent",
|
||||
r"opposite of",
|
||||
]
|
||||
return any(re.search(p, query.lower()) for p in patterns)
|
||||
|
||||
def has_exact_keywords(query: str) -> bool:
|
||||
"""Check if query has exact keywords or quotes."""
|
||||
return '"' in query or "'" in query or len(query.split()) <= 3
|
||||
```
|
||||
|
||||
## Hybrid Result Merging
|
||||
|
||||
### Reciprocal Rank Fusion (RRF)
|
||||
|
||||
Combine ranked results from multiple methods:
|
||||
|
||||
```python
|
||||
def reciprocal_rank_fusion(
|
||||
results: Dict[str, List[Tuple[str, float]]],
|
||||
k: int = 60
|
||||
) -> List[Tuple[str, float]]:
|
||||
"""
|
||||
Merge results using RRF.
|
||||
|
||||
Args:
|
||||
results: {"hrr": [(id, score), ...], "vector": [...], "fts5": [...]}
|
||||
k: RRF constant (default 60)
|
||||
|
||||
Returns:
|
||||
Merged and re-ranked results
|
||||
"""
|
||||
scores = defaultdict(float)
|
||||
|
||||
for method, ranked_items in results.items():
|
||||
for rank, (item_id, _) in enumerate(ranked_items, 1):
|
||||
scores[item_id] += 1.0 / (k + rank)
|
||||
|
||||
return sorted(scores.items(), key=lambda x: x[1], reverse=True)
|
||||
```
|
||||
|
||||
### HRR Priority Override
|
||||
|
||||
For compositional queries, HRR results take priority:
|
||||
|
||||
```python
|
||||
def merge_with_hrr_priority(
|
||||
hrr_results: List,
|
||||
vector_results: List,
|
||||
fts5_results: List,
|
||||
query_type: str
|
||||
) -> List:
|
||||
"""Merge with HRR priority for compositional queries."""
|
||||
|
||||
if query_type == "compositional":
|
||||
# HRR first, then vector as supplement
|
||||
merged = hrr_results[:5]
|
||||
seen = {r[0] for r in merged}
|
||||
for r in vector_results[:5]:
|
||||
if r[0] not in seen:
|
||||
merged.append(r)
|
||||
return merged
|
||||
|
||||
# Default: RRF merge
|
||||
return reciprocal_rank_fusion({
|
||||
"hrr": hrr_results,
|
||||
"vector": vector_results,
|
||||
"fts5": fts5_results
|
||||
})
|
||||
```
|
||||
|
||||
## Integration Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────┐
|
||||
│ Query Router │
|
||||
│ (classifies query → routes to best method) │
|
||||
└───────────┬──────────────┬──────────────┬───────────┘
|
||||
│ │ │
|
||||
┌──────▼──────┐ ┌────▼────┐ ┌───────▼───────┐
|
||||
│ HRR │ │ Qdrant │ │ FTS5 │
|
||||
│ Holographic │ │ Vector │ │ SQLite Full │
|
||||
│ Compose │ │ Search │ │ Text Search │
|
||||
└──────┬──────┘ └────┬────┘ └───────┬───────┘
|
||||
│ │ │
|
||||
┌──────▼──────────────▼──────────────▼───────┐
|
||||
│ Result Merger (RRF) │
|
||||
│ - Deduplication │
|
||||
│ - Score normalization │
|
||||
│ - HRR priority for compositional queries │
|
||||
└───────────────────┬─────────────────────────┘
|
||||
│
|
||||
┌────▼────┐
|
||||
│ Results │
|
||||
└─────────┘
|
||||
```
|
||||
|
||||
### Storage Layout
|
||||
|
||||
```
|
||||
~/.hermes/memory/
|
||||
├── holographic/
|
||||
│ ├── hrr_store.pkl # HRR vectors (numpy arrays)
|
||||
│ ├── bindings.pkl # Concept bindings
|
||||
│ └── contradictions.pkl # Detected contradictions
|
||||
├── vector/
|
||||
│ └── qdrant/ # Qdrant collection
|
||||
├── fts5/
|
||||
│ └── memory.db # SQLite with FTS5
|
||||
└── index.json # Unified index
|
||||
```
|
||||
|
||||
## Preserving HRR Unique Capabilities
|
||||
|
||||
### Rules
|
||||
|
||||
1. **Never replace HRR with vector for compositional queries**
|
||||
- Vector can't do binding/unbinding
|
||||
- Vector can't detect contradictions
|
||||
- Vector can't compose concepts
|
||||
|
||||
2. **HRR is primary for relational queries**
|
||||
- "What relates X to Y?"
|
||||
- "What contradicts this?"
|
||||
- "Combine concept A with concept B"
|
||||
|
||||
3. **Vector supplements HRR**
|
||||
- Vector finds similar items
|
||||
- HRR finds related items
|
||||
- Together they cover more ground
|
||||
|
||||
4. **FTS5 handles exact matches**
|
||||
- Keyword search
|
||||
- Time-based filtering
|
||||
- Metadata queries
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Phase 1: HRR Plugin (Existing)
|
||||
- Implement holographic.py with binding/unbinding
|
||||
- Phase encoding for compositional queries
|
||||
- Contradiction detection via phase opposition
|
||||
|
||||
### Phase 2: Vector Integration
|
||||
- Add Qdrant as vector backend
|
||||
- Embed memories for semantic search
|
||||
- Maintain HRR alongside vector
|
||||
|
||||
### Phase 3: Hybrid Router
|
||||
- Query classification
|
||||
- Method selection
|
||||
- Result merging with RRF
|
||||
|
||||
### Phase 4: Testing
|
||||
- Benchmark each method
|
||||
- Test hybrid routing
|
||||
- Verify HRR preservation
|
||||
|
||||
## Success Metrics
|
||||
|
||||
- HRR compositional queries: 90%+ accuracy
|
||||
- Vector semantic search: 85%+ relevance
|
||||
- Hybrid routing: Correct method 95%+ of the time
|
||||
- Contradiction detection: 80%+ precision
|
||||
@@ -1,97 +0,0 @@
|
||||
"""
|
||||
Tests for hybrid memory query router
|
||||
|
||||
Issue: #663
|
||||
"""
|
||||
|
||||
import unittest
|
||||
from tools.memory_query_router import (
|
||||
SearchMethod,
|
||||
QueryRouter,
|
||||
route_query,
|
||||
reciprocal_rank_fusion,
|
||||
merge_with_hrr_priority,
|
||||
)
|
||||
|
||||
|
||||
class TestQueryClassification(unittest.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
self.router = QueryRouter()
|
||||
|
||||
def test_contradiction_routes_hrr(self):
|
||||
c = self.router.classify("What contradicts this statement?")
|
||||
self.assertEqual(c.method, SearchMethod.HRR)
|
||||
self.assertGreater(c.confidence, 0.9)
|
||||
|
||||
def test_compositional_routes_hrr(self):
|
||||
c = self.router.classify("How does Python relate to machine learning?")
|
||||
self.assertEqual(c.method, SearchMethod.HRR)
|
||||
|
||||
c = self.router.classify("What is associated with quantum computing?")
|
||||
self.assertEqual(c.method, SearchMethod.HRR)
|
||||
|
||||
def test_exact_keywords_routes_fts5(self):
|
||||
c = self.router.classify('Find documents containing "FastAPI tutorial"')
|
||||
self.assertEqual(c.method, SearchMethod.FTS5)
|
||||
|
||||
def test_short_query_routes_fts5(self):
|
||||
c = self.router.classify("Python syntax")
|
||||
self.assertEqual(c.method, SearchMethod.FTS5)
|
||||
|
||||
def test_temporal_routes_fts5(self):
|
||||
c = self.router.classify("Recent changes to the config")
|
||||
self.assertEqual(c.method, SearchMethod.FTS5)
|
||||
|
||||
def test_semantic_routes_vector(self):
|
||||
c = self.router.classify("Explain how transformers work in natural language processing")
|
||||
self.assertEqual(c.method, SearchMethod.VECTOR)
|
||||
|
||||
|
||||
class TestReciprocalRankFusion(unittest.TestCase):
|
||||
|
||||
def test_basic_fusion(self):
|
||||
results = {
|
||||
"hrr": [("a", 0.9), ("b", 0.8)],
|
||||
"vector": [("b", 0.85), ("c", 0.7)],
|
||||
}
|
||||
merged = reciprocal_rank_fusion(results)
|
||||
|
||||
# 'b' appears in both, should rank high
|
||||
ids = [r[0] for r in merged]
|
||||
self.assertIn("b", ids[:2])
|
||||
|
||||
def test_empty_results(self):
|
||||
merged = reciprocal_rank_fusion({})
|
||||
self.assertEqual(len(merged), 0)
|
||||
|
||||
|
||||
class TestHRRPriority(unittest.TestCase):
|
||||
|
||||
def test_compositional_hrr_first(self):
|
||||
hrr = [("a", 0.9), ("b", 0.8)]
|
||||
vector = [("c", 0.85), ("d", 0.7)]
|
||||
fts5 = [("e", 0.6)]
|
||||
|
||||
merged = merge_with_hrr_priority(hrr, vector, fts5, "compositional")
|
||||
|
||||
# HRR results should come first
|
||||
self.assertEqual(merged[0][0], "a")
|
||||
self.assertEqual(merged[1][0], "b")
|
||||
|
||||
|
||||
class TestHybridDecision(unittest.TestCase):
|
||||
|
||||
def test_low_confidence_uses_hybrid(self):
|
||||
from tools.memory_query_router import should_use_hybrid
|
||||
# Ambiguous query
|
||||
self.assertTrue(should_use_hybrid("Tell me about things"))
|
||||
|
||||
def test_clear_query_no_hybrid(self):
|
||||
from tools.memory_query_router import should_use_hybrid
|
||||
# Clear contradiction query
|
||||
self.assertFalse(should_use_hybrid("What contradicts X?"))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
44
tests/test_resource_limits.py
Normal file
44
tests/test_resource_limits.py
Normal file
@@ -0,0 +1,44 @@
|
||||
"""
|
||||
Tests for resource limits (#755).
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from tools.resource_limits import ResourceLimiter, ResourceLimits, ResourceResult, ResourceViolation
|
||||
|
||||
|
||||
class TestResourceLimiter:
|
||||
def test_successful_execution(self):
|
||||
limiter = ResourceLimiter(ResourceLimits(memory_mb=2048, timeout_seconds=10))
|
||||
result = limiter.execute("echo hello")
|
||||
assert result.success is True
|
||||
assert result.exit_code == 0
|
||||
assert "hello" in result.stdout
|
||||
assert result.violation == ResourceViolation.NONE
|
||||
|
||||
def test_timeout_violation(self):
|
||||
limiter = ResourceLimiter(ResourceLimits(timeout_seconds=1))
|
||||
result = limiter.execute("sleep 10")
|
||||
assert result.success is False
|
||||
assert result.violation == ResourceViolation.TIME
|
||||
assert result.killed is True
|
||||
|
||||
def test_failed_command(self):
|
||||
limiter = ResourceLimiter()
|
||||
result = limiter.execute("exit 1")
|
||||
assert result.success is False
|
||||
assert result.exit_code == 1
|
||||
|
||||
def test_resource_report(self):
|
||||
from tools.resource_limits import format_resource_report
|
||||
result = ResourceResult(
|
||||
success=True, stdout="", stderr="", exit_code=0,
|
||||
violation=ResourceViolation.NONE, violation_message="",
|
||||
memory_used_mb=100, cpu_time_seconds=0.5, wall_time_seconds=1.0,
|
||||
)
|
||||
report = format_resource_report(result)
|
||||
assert "Exit code: 0" in report
|
||||
assert "100MB" in report
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pytest.main([__file__])
|
||||
@@ -1,209 +0,0 @@
|
||||
"""
|
||||
Hybrid Memory Query Router
|
||||
|
||||
Routes queries to the best search method:
|
||||
- HRR: Compositional/conceptual queries
|
||||
- Vector: Semantic similarity
|
||||
- FTS5: Exact keyword matching
|
||||
|
||||
Issue: #663
|
||||
"""
|
||||
|
||||
import re
|
||||
from collections import defaultdict
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
|
||||
class SearchMethod(Enum):
|
||||
"""Available search methods."""
|
||||
HRR = "hrr" # Holographic Reduced Representations
|
||||
VECTOR = "vector" # Semantic vector search
|
||||
FTS5 = "fts5" # Full-text search (SQLite)
|
||||
HYBRID = "hybrid" # Combine multiple methods
|
||||
|
||||
|
||||
@dataclass
|
||||
class QueryClassification:
|
||||
"""Result of query classification."""
|
||||
method: SearchMethod
|
||||
confidence: float
|
||||
reason: str
|
||||
sub_queries: Optional[List[str]] = None
|
||||
|
||||
|
||||
# Query patterns for routing
|
||||
COMPOSITIONAL_PATTERNS = [
|
||||
r"(?i)\brelated\s+to\b",
|
||||
r"(?i)\bcombined\s+with\b",
|
||||
r"(?i)\bbound\s+to\b",
|
||||
r"(?i)\bassociated\s+with\b",
|
||||
r"(?i)\bwhat\s+connects?\b",
|
||||
r"(?i)\bhow\s+.*\s+relate\b",
|
||||
r"(?i)\brelationship\s+between\b",
|
||||
]
|
||||
|
||||
CONTRADICTION_PATTERNS = [
|
||||
r"(?i)\bcontradicts?\b",
|
||||
r"(?i)\bconflicts?\s+with\b",
|
||||
r"(?i)\binconsistent\b",
|
||||
r"(?i)\bopposite\s+of\b",
|
||||
r"(?i)\bopposes?\b",
|
||||
r"(?i)\bdisagrees?\s+with\b",
|
||||
]
|
||||
|
||||
EXACT_KEYWORD_PATTERNS = [
|
||||
r'"[^"]+"', # Quoted phrases
|
||||
r"'[^']+'", # Single-quoted phrases
|
||||
r"(?i)\bexact\b",
|
||||
r"(?i)\bprecisely\b",
|
||||
r"(?i)\bspecifically\b",
|
||||
]
|
||||
|
||||
TEMPORAL_PATTERNS = [
|
||||
r"(?i)\brecent\b",
|
||||
r"(?i)\btoday\b",
|
||||
r"(?i)\byesterday\b",
|
||||
r"(?i)\blast\s+(week|month|hour)\b",
|
||||
r"(?i)\bsince\b",
|
||||
r"(?i)\bbefore\b",
|
||||
r"(?i)\bafter\b",
|
||||
]
|
||||
|
||||
|
||||
class QueryRouter:
|
||||
"""Route queries to the best search method."""
|
||||
|
||||
def classify(self, query: str) -> QueryClassification:
|
||||
"""Classify a query and route to best method."""
|
||||
|
||||
# Check for contradiction queries (HRR)
|
||||
for pattern in CONTRADICTION_PATTERNS:
|
||||
if re.search(pattern, query):
|
||||
return QueryClassification(
|
||||
method=SearchMethod.HRR,
|
||||
confidence=0.95,
|
||||
reason="Contradiction detection query"
|
||||
)
|
||||
|
||||
# Check for compositional queries (HRR)
|
||||
for pattern in COMPOSITIONAL_PATTERNS:
|
||||
if re.search(pattern, query):
|
||||
return QueryClassification(
|
||||
method=SearchMethod.HRR,
|
||||
confidence=0.90,
|
||||
reason="Compositional/conceptual query"
|
||||
)
|
||||
|
||||
# Check for exact keyword queries (FTS5)
|
||||
for pattern in EXACT_KEYWORD_PATTERNS:
|
||||
if re.search(pattern, query):
|
||||
return QueryClassification(
|
||||
method=SearchMethod.FTS5,
|
||||
confidence=0.85,
|
||||
reason="Exact keyword query"
|
||||
)
|
||||
|
||||
# Check for temporal queries (FTS5)
|
||||
for pattern in TEMPORAL_PATTERNS:
|
||||
if re.search(pattern, query):
|
||||
return QueryClassification(
|
||||
method=SearchMethod.FTS5,
|
||||
confidence=0.80,
|
||||
reason="Temporal query"
|
||||
)
|
||||
|
||||
# Short queries tend to be keyword searches
|
||||
if len(query.split()) <= 3:
|
||||
return QueryClassification(
|
||||
method=SearchMethod.FTS5,
|
||||
confidence=0.70,
|
||||
reason="Short query (likely keyword)"
|
||||
)
|
||||
|
||||
# Default: vector search for semantic queries
|
||||
return QueryClassification(
|
||||
method=SearchMethod.VECTOR,
|
||||
confidence=0.60,
|
||||
reason="Semantic similarity query"
|
||||
)
|
||||
|
||||
def should_use_hybrid(self, query: str) -> bool:
|
||||
"""Check if query should use hybrid search."""
|
||||
classification = self.classify(query)
|
||||
|
||||
# Low confidence -> use hybrid
|
||||
if classification.confidence < 0.70:
|
||||
return True
|
||||
|
||||
# Mixed signals -> use hybrid
|
||||
has_compositional = any(re.search(p, query) for p in COMPOSITIONAL_PATTERNS)
|
||||
has_keywords = any(re.search(p, query) for p in EXACT_KEYWORD_PATTERNS)
|
||||
|
||||
return has_compositional and has_keywords
|
||||
|
||||
|
||||
def reciprocal_rank_fusion(
|
||||
results: Dict[str, List[Tuple[str, float]]],
|
||||
k: int = 60
|
||||
) -> List[Tuple[str, float]]:
|
||||
"""
|
||||
Merge results using Reciprocal Rank Fusion.
|
||||
|
||||
Args:
|
||||
results: Dict of method -> [(item_id, score), ...]
|
||||
k: RRF constant (default 60)
|
||||
|
||||
Returns:
|
||||
Merged and re-ranked results
|
||||
"""
|
||||
scores = defaultdict(float)
|
||||
|
||||
for method, ranked_items in results.items():
|
||||
for rank, (item_id, _) in enumerate(ranked_items, 1):
|
||||
scores[item_id] += 1.0 / (k + rank)
|
||||
|
||||
return sorted(scores.items(), key=lambda x: x[1], reverse=True)
|
||||
|
||||
|
||||
def merge_with_hrr_priority(
|
||||
hrr_results: List[Tuple[str, float]],
|
||||
vector_results: List[Tuple[str, float]],
|
||||
fts5_results: List[Tuple[str, float]],
|
||||
query_type: str = "default"
|
||||
) -> List[Tuple[str, float]]:
|
||||
"""
|
||||
Merge results with HRR priority for compositional queries.
|
||||
"""
|
||||
if query_type == "compositional":
|
||||
# HRR first, vector as supplement
|
||||
merged = hrr_results[:5]
|
||||
seen = {r[0] for r in merged}
|
||||
|
||||
for r in vector_results[:5]:
|
||||
if r[0] not in seen:
|
||||
merged.append(r)
|
||||
|
||||
return merged
|
||||
|
||||
# Default: RRF merge
|
||||
return reciprocal_rank_fusion({
|
||||
"hrr": hrr_results,
|
||||
"vector": vector_results,
|
||||
"fts5": fts5_results
|
||||
})
|
||||
|
||||
|
||||
# Module-level router
|
||||
_router = QueryRouter()
|
||||
|
||||
|
||||
def route_query(query: str) -> QueryClassification:
|
||||
"""Route a query to the best search method."""
|
||||
return _router.classify(query)
|
||||
|
||||
|
||||
def should_use_hybrid(query: str) -> bool:
|
||||
"""Check if query should use hybrid search."""
|
||||
return _router.should_use_hybrid(query)
|
||||
249
tools/resource_limits.py
Normal file
249
tools/resource_limits.py
Normal file
@@ -0,0 +1,249 @@
|
||||
"""
|
||||
Terminal Sandbox Resource Limits — CPU, memory, time.
|
||||
|
||||
Provides resource limits for agent terminal commands to prevent
|
||||
OOM kills, runaway processes, and excessive resource consumption.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import signal
|
||||
import subprocess
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Optional, Dict, Any
|
||||
from enum import Enum
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ResourceViolation(Enum):
|
||||
"""Types of resource violations."""
|
||||
MEMORY = "memory"
|
||||
CPU = "cpu"
|
||||
TIME = "time"
|
||||
NONE = "none"
|
||||
|
||||
|
||||
@dataclass
|
||||
class ResourceLimits:
|
||||
"""Resource limits for a subprocess."""
|
||||
memory_mb: int = 2048 # 2GB default
|
||||
cpu_percent: int = 80 # 80% of one core
|
||||
timeout_seconds: int = 300 # 5 minutes
|
||||
kill_timeout: int = 10 # SIGKILL after 10s if SIGTERM fails
|
||||
|
||||
|
||||
@dataclass
|
||||
class ResourceResult:
|
||||
"""Result of a resource-limited execution."""
|
||||
success: bool
|
||||
stdout: str
|
||||
stderr: str
|
||||
exit_code: int
|
||||
violation: ResourceViolation
|
||||
violation_message: str
|
||||
memory_used_mb: float
|
||||
cpu_time_seconds: float
|
||||
wall_time_seconds: float
|
||||
killed: bool = False
|
||||
|
||||
|
||||
class ResourceLimiter:
|
||||
"""Apply resource limits to subprocess execution."""
|
||||
|
||||
def __init__(self, limits: Optional[ResourceLimits] = None):
|
||||
self.limits = limits or ResourceLimits()
|
||||
|
||||
def _get_resource_rlimit(self) -> Dict[str, Any]:
|
||||
"""Get resource limits for subprocess (Unix only)."""
|
||||
import resource
|
||||
|
||||
rlimit = {}
|
||||
|
||||
# Memory limit (RSS)
|
||||
if self.limits.memory_mb > 0:
|
||||
mem_bytes = self.limits.memory_mb * 1024 * 1024
|
||||
rlimit[resource.RLIMIT_AS] = (mem_bytes, mem_bytes)
|
||||
|
||||
# CPU time limit
|
||||
if self.limits.timeout_seconds > 0:
|
||||
rlimit[resource.RLIMIT_CPU] = (self.limits.timeout_seconds, self.limits.timeout_seconds)
|
||||
|
||||
return rlimit
|
||||
|
||||
def _check_resource_usage(self, process: subprocess.Popen) -> Dict[str, float]:
|
||||
"""Check resource usage of a process (Unix only)."""
|
||||
try:
|
||||
import resource
|
||||
usage = resource.getrusage(resource.RUSAGE_CHILDREN)
|
||||
return {
|
||||
"user_time": usage.ru_utime,
|
||||
"system_time": usage.ru_stime,
|
||||
"max_rss_mb": usage.ru_maxrss / 1024, # KB to MB
|
||||
}
|
||||
except:
|
||||
return {"user_time": 0, "system_time": 0, "max_rss_mb": 0}
|
||||
|
||||
def execute(self, command: str, **kwargs) -> ResourceResult:
|
||||
"""
|
||||
Execute a command with resource limits.
|
||||
|
||||
Args:
|
||||
command: Shell command to execute
|
||||
**kwargs: Additional subprocess arguments
|
||||
|
||||
Returns:
|
||||
ResourceResult with execution details
|
||||
"""
|
||||
start_time = time.time()
|
||||
|
||||
# Try to use resource limits (Unix only)
|
||||
preexec_fn = None
|
||||
try:
|
||||
import resource
|
||||
rlimit = self._get_resource_rlimit()
|
||||
|
||||
def set_limits():
|
||||
for res, limits in rlimit.items():
|
||||
resource.setrlimit(res, limits)
|
||||
|
||||
preexec_fn = set_limits
|
||||
except ImportError:
|
||||
logger.debug("resource module not available, skipping limits")
|
||||
|
||||
try:
|
||||
# Execute with timeout
|
||||
result = subprocess.run(
|
||||
command,
|
||||
shell=True,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=self.limits.timeout_seconds,
|
||||
preexec_fn=preexec_fn,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
wall_time = time.time() - start_time
|
||||
usage = self._check_resource_usage(result)
|
||||
|
||||
# Check for violations
|
||||
violation = ResourceViolation.NONE
|
||||
violation_message = ""
|
||||
|
||||
# Check memory (if we can get it)
|
||||
if usage["max_rss_mb"] > self.limits.memory_mb:
|
||||
violation = ResourceViolation.MEMORY
|
||||
violation_message = f"Memory limit exceeded: {usage['max_rss_mb']:.0f}MB > {self.limits.memory_mb}MB"
|
||||
|
||||
return ResourceResult(
|
||||
success=result.returncode == 0,
|
||||
stdout=result.stdout,
|
||||
stderr=result.stderr,
|
||||
exit_code=result.returncode,
|
||||
violation=violation,
|
||||
violation_message=violation_message,
|
||||
memory_used_mb=usage["max_rss_mb"],
|
||||
cpu_time_seconds=usage["user_time"] + usage["system_time"],
|
||||
wall_time_seconds=wall_time,
|
||||
)
|
||||
|
||||
except subprocess.TimeoutExpired as e:
|
||||
wall_time = time.time() - start_time
|
||||
|
||||
# Try to kill gracefully
|
||||
if hasattr(e, 'process') and e.process:
|
||||
try:
|
||||
e.process.terminate()
|
||||
time.sleep(self.limits.kill_timeout)
|
||||
if e.process.poll() is None:
|
||||
e.process.kill()
|
||||
except:
|
||||
pass
|
||||
|
||||
return ResourceResult(
|
||||
success=False,
|
||||
stdout=e.stdout.decode() if e.stdout else "",
|
||||
stderr=e.stderr.decode() if e.stderr else "",
|
||||
exit_code=-1,
|
||||
violation=ResourceViolation.TIME,
|
||||
violation_message=f"Timeout after {self.limits.timeout_seconds}s",
|
||||
memory_used_mb=0,
|
||||
cpu_time_seconds=0,
|
||||
wall_time_seconds=wall_time,
|
||||
killed=True,
|
||||
)
|
||||
|
||||
except MemoryError:
|
||||
wall_time = time.time() - start_time
|
||||
return ResourceResult(
|
||||
success=False,
|
||||
stdout="",
|
||||
stderr=f"Memory limit exceeded ({self.limits.memory_mb}MB)",
|
||||
exit_code=-1,
|
||||
violation=ResourceViolation.MEMORY,
|
||||
violation_message=f"Memory limit exceeded: {self.limits.memory_mb}MB",
|
||||
memory_used_mb=self.limits.memory_mb,
|
||||
cpu_time_seconds=0,
|
||||
wall_time_seconds=wall_time,
|
||||
killed=True,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
wall_time = time.time() - start_time
|
||||
return ResourceResult(
|
||||
success=False,
|
||||
stdout="",
|
||||
stderr=str(e),
|
||||
exit_code=-1,
|
||||
violation=ResourceViolation.NONE,
|
||||
violation_message=f"Execution error: {e}",
|
||||
memory_used_mb=0,
|
||||
cpu_time_seconds=0,
|
||||
wall_time_seconds=wall_time,
|
||||
)
|
||||
|
||||
|
||||
def format_resource_report(result: ResourceResult) -> str:
|
||||
"""Format resource usage as a report string."""
|
||||
lines = [
|
||||
f"Exit code: {result.exit_code}",
|
||||
f"Wall time: {result.wall_time_seconds:.2f}s",
|
||||
f"CPU time: {result.cpu_time_seconds:.2f}s",
|
||||
f"Memory: {result.memory_used_mb:.0f}MB",
|
||||
]
|
||||
|
||||
if result.violation != ResourceViolation.NONE:
|
||||
lines.append(f"⚠️ Violation: {result.violation_message}")
|
||||
|
||||
if result.killed:
|
||||
lines.append("🔴 Process killed")
|
||||
|
||||
return " | ".join(lines)
|
||||
|
||||
|
||||
def execute_with_limits(
|
||||
command: str,
|
||||
memory_mb: int = 2048,
|
||||
cpu_percent: int = 80,
|
||||
timeout_seconds: int = 300,
|
||||
) -> ResourceResult:
|
||||
"""
|
||||
Convenience function to execute with resource limits.
|
||||
|
||||
Args:
|
||||
command: Shell command
|
||||
memory_mb: Memory limit in MB
|
||||
cpu_percent: CPU limit as percent of one core
|
||||
timeout_seconds: Timeout in seconds
|
||||
|
||||
Returns:
|
||||
ResourceResult
|
||||
"""
|
||||
limits = ResourceLimits(
|
||||
memory_mb=memory_mb,
|
||||
cpu_percent=cpu_percent,
|
||||
timeout_seconds=timeout_seconds,
|
||||
)
|
||||
limiter = ResourceLimiter(limits)
|
||||
return limiter.execute(command)
|
||||
Reference in New Issue
Block a user