Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 517e2c571e |
@@ -1,42 +0,0 @@
|
||||
# Holographic + Vector Hybrid Memory Architecture
|
||||
|
||||
Research issue #879. Combining HRR (holographic) and vector (Qdrant) memory.
|
||||
|
||||
## Architecture
|
||||
|
||||
Three memory backends, each with unique strengths:
|
||||
|
||||
| Backend | Strength | Weakness | Use Case |
|
||||
|---------|----------|----------|----------|
|
||||
| FTS5 | Exact keyword match | No semantic understanding | Precise recall |
|
||||
| Vector (Qdrant) | Semantic similarity | No compositional queries | Topic search |
|
||||
| HRR (Holographic) | Compositional queries | Limited scale | Complex reasoning |
|
||||
|
||||
## Why Hybrid
|
||||
|
||||
- FTS5 alone: misses ~30-40% of semantically relevant content
|
||||
- Vector alone: can't do compositional queries ("what did I discuss about X after doing Y?")
|
||||
- HRR alone: unique capability but no semantic fallback
|
||||
- Hybrid: best of all three, RRF fusion for ranking
|
||||
|
||||
## Implementation: Reciprocal Rank Fusion
|
||||
|
||||
Results from each backend are merged using RRF:
|
||||
- score = sum(weight / (k + rank)) for each backend
|
||||
- k=60 (standard RRF constant)
|
||||
- Weights: FTS5=0.6, Vector=0.4 (configurable)
|
||||
|
||||
## Status
|
||||
|
||||
- FTS5: EXISTS (hermes_state.py)
|
||||
- Vector (Qdrant): implemented (tools/hybrid_search.py)
|
||||
- HRR: EXISTS (plugins/memory/holographic.py)
|
||||
- RRF fusion: implemented (tools/hybrid_search.py)
|
||||
- Ingestion pipeline: partial
|
||||
|
||||
## Next Steps
|
||||
|
||||
1. Wire HRR into hybrid_search.py
|
||||
2. Session-level vector ingestion
|
||||
3. Benchmark: measure R@5 improvement
|
||||
4. Cross-session memory persistence
|
||||
224
gateway/config_validator.py
Normal file
224
gateway/config_validator.py
Normal file
@@ -0,0 +1,224 @@
|
||||
"""
|
||||
Gateway Config Validator & Fallback Fix — #892.
|
||||
|
||||
Validates gateway configuration and provides sensible defaults
|
||||
for missing keys to prevent fallback chain breaks.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Dict, Any, List, Optional
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ConfigIssue:
|
||||
"""A configuration issue found during validation."""
|
||||
key: str
|
||||
severity: str # error, warning, info
|
||||
message: str
|
||||
fix: str
|
||||
|
||||
|
||||
@dataclass
|
||||
class ConfigValidation:
|
||||
"""Result of config validation."""
|
||||
valid: bool
|
||||
issues: List[ConfigIssue] = field(default_factory=list)
|
||||
warnings: int = 0
|
||||
errors: int = 0
|
||||
|
||||
|
||||
# Required keys and their defaults
|
||||
REQUIRED_KEYS = {
|
||||
"OPENROUTER_API_KEY": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "warning",
|
||||
"message": "OPENROUTER_API_KEY not set - fallback chain may break",
|
||||
"fix": "Set OPENROUTER_API_KEY in .env for OpenRouter provider",
|
||||
},
|
||||
"API_SERVER_KEY": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "warning",
|
||||
"message": "API_SERVER_KEY not configured",
|
||||
"fix": "Set API_SERVER_KEY in .env for API server auth",
|
||||
},
|
||||
"GITEA_TOKEN": {
|
||||
"required": False,
|
||||
"default": "",
|
||||
"severity": "info",
|
||||
"message": "GITEA_TOKEN not set - Gitea features disabled",
|
||||
"fix": "Set GITEA_TOKEN in .env for Gitea integration",
|
||||
},
|
||||
}
|
||||
|
||||
# Config validation rules
|
||||
VALIDATION_RULES = [
|
||||
{
|
||||
"key": "idle_minutes",
|
||||
"validate": lambda v: isinstance(v, (int, float)) and v > 0,
|
||||
"message": "Invalid idle_minutes={v} - must be > 0",
|
||||
"fix": "Set idle_minutes to positive integer (default: 30)",
|
||||
},
|
||||
{
|
||||
"key": "max_skills_discord",
|
||||
"validate": lambda v: isinstance(v, int) and v <= 100,
|
||||
"message": "Discord slash command limit reached ({v}/100) - skills not registered",
|
||||
"fix": "Reduce skills or paginate registration",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def validate_config(config: Dict[str, Any]) -> ConfigValidation:
|
||||
"""
|
||||
Validate gateway configuration.
|
||||
|
||||
Args:
|
||||
config: Configuration dictionary
|
||||
|
||||
Returns:
|
||||
ConfigValidation with issues found
|
||||
"""
|
||||
issues = []
|
||||
|
||||
# Check required keys
|
||||
for key, spec in REQUIRED_KEYS.items():
|
||||
value = config.get(key) or os.environ.get(key) or spec["default"]
|
||||
if spec["required"] and not value:
|
||||
issues.append(ConfigIssue(
|
||||
key=key,
|
||||
severity=spec["severity"],
|
||||
message=spec["message"],
|
||||
fix=spec["fix"],
|
||||
))
|
||||
elif not value and spec["severity"] != "error":
|
||||
issues.append(ConfigIssue(
|
||||
key=key,
|
||||
severity=spec["severity"],
|
||||
message=spec["message"],
|
||||
fix=spec["fix"],
|
||||
))
|
||||
|
||||
# Check validation rules
|
||||
for rule in VALIDATION_RULES:
|
||||
value = config.get(rule["key"])
|
||||
if value is not None:
|
||||
if not rule["validate"](value):
|
||||
issues.append(ConfigIssue(
|
||||
key=rule["key"],
|
||||
severity="error",
|
||||
message=rule["message"].format(v=value),
|
||||
fix=rule["fix"],
|
||||
))
|
||||
|
||||
errors = sum(1 for i in issues if i.severity == "error")
|
||||
warnings = sum(1 for i in issues if i.severity == "warning")
|
||||
|
||||
return ConfigValidation(
|
||||
valid=errors == 0,
|
||||
issues=issues,
|
||||
warnings=warnings,
|
||||
errors=errors,
|
||||
)
|
||||
|
||||
|
||||
def apply_defaults(config: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Apply default values for missing config keys.
|
||||
|
||||
Args:
|
||||
config: Configuration dictionary
|
||||
|
||||
Returns:
|
||||
Config with defaults applied
|
||||
"""
|
||||
result = dict(config)
|
||||
|
||||
for key, spec in REQUIRED_KEYS.items():
|
||||
if key not in result or not result[key]:
|
||||
default = os.environ.get(key) or spec["default"]
|
||||
if default:
|
||||
result[key] = default
|
||||
logger.debug("Applied default for %s", key)
|
||||
|
||||
# Apply validation defaults
|
||||
if "idle_minutes" not in result or not result["idle_minutes"] or result["idle_minutes"] <= 0:
|
||||
result["idle_minutes"] = 30
|
||||
logger.debug("Applied default idle_minutes=30")
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def fix_discord_skill_limit(skills: List[str], max_skills: int = 95) -> List[str]:
|
||||
"""
|
||||
Fix Discord slash command limit by reducing skills.
|
||||
|
||||
Args:
|
||||
skills: List of skill names
|
||||
max_skills: Maximum skills to register (default 95, leaving room for built-ins)
|
||||
|
||||
Returns:
|
||||
Reduced skill list
|
||||
"""
|
||||
if len(skills) <= max_skills:
|
||||
return skills
|
||||
|
||||
logger.warning(
|
||||
"Discord skill limit: %d skills exceeds %d limit, truncating",
|
||||
len(skills), max_skills
|
||||
)
|
||||
|
||||
# Keep first max_skills (alphabetical priority)
|
||||
return sorted(skills)[:max_skills]
|
||||
|
||||
|
||||
def validate_provider_config(provider: str, config: Dict[str, Any]) -> ConfigIssue:
|
||||
"""
|
||||
Validate provider-specific configuration.
|
||||
|
||||
Args:
|
||||
provider: Provider name
|
||||
config: Provider config
|
||||
|
||||
Returns:
|
||||
ConfigIssue if invalid, None if valid
|
||||
"""
|
||||
if provider == "local-llama.cpp":
|
||||
# Check if llama.cpp is configured
|
||||
if not config.get("model_path") and not config.get("base_url"):
|
||||
return ConfigIssue(
|
||||
key=f"provider.{provider}",
|
||||
severity="warning",
|
||||
message=f"{provider} provider not configured - fallback fails",
|
||||
fix=f"Configure {provider} model_path or base_url, or remove from provider list",
|
||||
)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def format_validation_report(validation: ConfigValidation) -> str:
|
||||
"""Format validation results as a report."""
|
||||
lines = [
|
||||
"=" * 50,
|
||||
"GATEWAY CONFIG VALIDATION",
|
||||
"=" * 50,
|
||||
"",
|
||||
f"Status: {'VALID' if validation.valid else 'INVALID'}",
|
||||
f"Errors: {validation.errors}",
|
||||
f"Warnings: {validation.warnings}",
|
||||
"",
|
||||
]
|
||||
|
||||
if validation.issues:
|
||||
lines.append("Issues:")
|
||||
for issue in validation.issues:
|
||||
icon = "❌" if issue.severity == "error" else "⚠️" if issue.severity == "warning" else "ℹ️"
|
||||
lines.append(f" {icon} [{issue.key}] {issue.message}")
|
||||
lines.append(f" Fix: {issue.fix}")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
@@ -44,34 +44,6 @@ from typing import Dict, Any, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _format_error(
|
||||
message: str,
|
||||
skill_name: str = None,
|
||||
file_path: str = None,
|
||||
suggestion: str = None,
|
||||
context: dict = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""Format an error with rich context for better debugging."""
|
||||
parts = [message]
|
||||
if skill_name:
|
||||
parts.append(f"Skill: {skill_name}")
|
||||
if file_path:
|
||||
parts.append(f"File: {file_path}")
|
||||
if suggestion:
|
||||
parts.append(f"Suggestion: {suggestion}")
|
||||
if context:
|
||||
for key, value in context.items():
|
||||
parts.append(f"{key}: {value}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": " | ".join(parts),
|
||||
"skill_name": skill_name,
|
||||
"file_path": file_path,
|
||||
"suggestion": suggestion,
|
||||
}
|
||||
|
||||
|
||||
# Import security scanner — agent-created skills get the same scrutiny as
|
||||
# community hub installs.
|
||||
try:
|
||||
|
||||
Reference in New Issue
Block a user