mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
Add comprehensive code review specifications and templates
- Introduced best practices requirements specification covering code quality, performance, maintainability, error handling, and documentation standards. - Established quality standards with overall quality metrics and mandatory checks for security, code quality, performance, and maintainability. - Created security requirements specification aligned with OWASP Top 10 and CWE Top 25, detailing checks and patterns for common vulnerabilities. - Developed templates for documenting best practice findings, security findings, and generating reports, including structured markdown and JSON formats. - Updated dependencies in the project, ensuring compatibility and stability. - Added test files and README documentation for vector indexing tests.
This commit is contained in:
catlog22
@@ -430,6 +430,7 @@ def search(
|
||||
query: str = typer.Argument(..., help="Search query."),
|
||||
path: Path = typer.Option(Path("."), "--path", "-p", help="Directory to search from."),
|
||||
limit: int = typer.Option(20, "--limit", "-n", min=1, max=500, help="Max results."),
|
||||
offset: int = typer.Option(0, "--offset", min=0, help="Pagination offset - skip first N results."),
|
||||
depth: int = typer.Option(-1, "--depth", "-d", help="Search depth (-1 = unlimited, 0 = current only)."),
|
||||
files_only: bool = typer.Option(False, "--files-only", "-f", help="Return only file paths without content snippets."),
|
||||
method: str = typer.Option("dense_rerank", "--method", "-m", help="Search method: 'dense_rerank' (semantic, default), 'fts' (exact keyword)."),
|
||||
|
||||
@@ -161,9 +161,15 @@ class Config:
|
||||
# Multi-endpoint configuration for litellm backend
|
||||
embedding_endpoints: List[Dict[str, Any]] = field(default_factory=list)
|
||||
# List of endpoint configs: [{"model": "...", "api_key": "...", "api_base": "...", "weight": 1.0}]
|
||||
embedding_pool_enabled: bool = False # Enable high availability pool for embeddings
|
||||
embedding_strategy: str = "latency_aware" # round_robin, latency_aware, weighted_random
|
||||
embedding_cooldown: float = 60.0 # Default cooldown seconds for rate-limited endpoints
|
||||
|
||||
# Reranker multi-endpoint configuration
|
||||
reranker_pool_enabled: bool = False # Enable high availability pool for reranker
|
||||
reranker_strategy: str = "latency_aware" # round_robin, latency_aware, weighted_random
|
||||
reranker_cooldown: float = 60.0 # Default cooldown seconds for rate-limited endpoints
|
||||
|
||||
# API concurrency settings
|
||||
api_max_workers: int = 4 # Max concurrent API calls for embedding/reranking
|
||||
api_batch_size: int = 8 # Batch size for API requests
|
||||
@@ -254,12 +260,13 @@ class Config:
|
||||
"backend": self.embedding_backend,
|
||||
"model": self.embedding_model,
|
||||
"use_gpu": self.embedding_use_gpu,
|
||||
"pool_enabled": self.embedding_pool_enabled,
|
||||
"strategy": self.embedding_strategy,
|
||||
"cooldown": self.embedding_cooldown,
|
||||
}
|
||||
# Include multi-endpoint config if present
|
||||
if self.embedding_endpoints:
|
||||
embedding_config["endpoints"] = self.embedding_endpoints
|
||||
embedding_config["strategy"] = self.embedding_strategy
|
||||
embedding_config["cooldown"] = self.embedding_cooldown
|
||||
|
||||
settings = {
|
||||
"embedding": embedding_config,
|
||||
@@ -274,6 +281,9 @@ class Config:
|
||||
"backend": self.reranker_backend,
|
||||
"model": self.reranker_model,
|
||||
"top_k": self.reranker_top_k,
|
||||
"pool_enabled": self.reranker_pool_enabled,
|
||||
"strategy": self.reranker_strategy,
|
||||
"cooldown": self.reranker_cooldown,
|
||||
},
|
||||
"cascade": {
|
||||
"strategy": self.cascade_strategy,
|
||||
@@ -317,6 +327,8 @@ class Config:
|
||||
# Load multi-endpoint configuration
|
||||
if "endpoints" in embedding:
|
||||
self.embedding_endpoints = embedding["endpoints"]
|
||||
if "pool_enabled" in embedding:
|
||||
self.embedding_pool_enabled = embedding["pool_enabled"]
|
||||
if "strategy" in embedding:
|
||||
self.embedding_strategy = embedding["strategy"]
|
||||
if "cooldown" in embedding:
|
||||
@@ -351,6 +363,12 @@ class Config:
|
||||
self.reranker_model = reranker["model"]
|
||||
if "top_k" in reranker:
|
||||
self.reranker_top_k = reranker["top_k"]
|
||||
if "pool_enabled" in reranker:
|
||||
self.reranker_pool_enabled = reranker["pool_enabled"]
|
||||
if "strategy" in reranker:
|
||||
self.reranker_strategy = reranker["strategy"]
|
||||
if "cooldown" in reranker:
|
||||
self.reranker_cooldown = reranker["cooldown"]
|
||||
|
||||
# Load cascade settings
|
||||
cascade = settings.get("cascade", {})
|
||||
@@ -394,9 +412,15 @@ class Config:
|
||||
Supported variables:
|
||||
EMBEDDING_MODEL: Override embedding model/profile
|
||||
EMBEDDING_BACKEND: Override embedding backend (fastembed/litellm)
|
||||
EMBEDDING_POOL_ENABLED: Enable embedding high availability pool
|
||||
EMBEDDING_STRATEGY: Load balance strategy for embedding
|
||||
EMBEDDING_COOLDOWN: Rate limit cooldown for embedding
|
||||
RERANKER_MODEL: Override reranker model
|
||||
RERANKER_BACKEND: Override reranker backend
|
||||
RERANKER_ENABLED: Override reranker enabled state (true/false)
|
||||
RERANKER_POOL_ENABLED: Enable reranker high availability pool
|
||||
RERANKER_STRATEGY: Load balance strategy for reranker
|
||||
RERANKER_COOLDOWN: Rate limit cooldown for reranker
|
||||
"""
|
||||
from .env_config import load_global_env
|
||||
|
||||
@@ -417,6 +441,26 @@ class Config:
|
||||
else:
|
||||
log.warning("Invalid EMBEDDING_BACKEND in .env: %r", backend)
|
||||
|
||||
if "EMBEDDING_POOL_ENABLED" in env_vars:
|
||||
value = env_vars["EMBEDDING_POOL_ENABLED"].lower()
|
||||
self.embedding_pool_enabled = value in {"true", "1", "yes", "on"}
|
||||
log.debug("Overriding embedding_pool_enabled from .env: %s", self.embedding_pool_enabled)
|
||||
|
||||
if "EMBEDDING_STRATEGY" in env_vars:
|
||||
strategy = env_vars["EMBEDDING_STRATEGY"].lower()
|
||||
if strategy in {"round_robin", "latency_aware", "weighted_random"}:
|
||||
self.embedding_strategy = strategy
|
||||
log.debug("Overriding embedding_strategy from .env: %s", strategy)
|
||||
else:
|
||||
log.warning("Invalid EMBEDDING_STRATEGY in .env: %r", strategy)
|
||||
|
||||
if "EMBEDDING_COOLDOWN" in env_vars:
|
||||
try:
|
||||
self.embedding_cooldown = float(env_vars["EMBEDDING_COOLDOWN"])
|
||||
log.debug("Overriding embedding_cooldown from .env: %s", self.embedding_cooldown)
|
||||
except ValueError:
|
||||
log.warning("Invalid EMBEDDING_COOLDOWN in .env: %r", env_vars["EMBEDDING_COOLDOWN"])
|
||||
|
||||
# Reranker overrides
|
||||
if "RERANKER_MODEL" in env_vars:
|
||||
self.reranker_model = env_vars["RERANKER_MODEL"]
|
||||
@@ -435,6 +479,26 @@ class Config:
|
||||
self.enable_cross_encoder_rerank = value in {"true", "1", "yes", "on"}
|
||||
log.debug("Overriding reranker_enabled from .env: %s", self.enable_cross_encoder_rerank)
|
||||
|
||||
if "RERANKER_POOL_ENABLED" in env_vars:
|
||||
value = env_vars["RERANKER_POOL_ENABLED"].lower()
|
||||
self.reranker_pool_enabled = value in {"true", "1", "yes", "on"}
|
||||
log.debug("Overriding reranker_pool_enabled from .env: %s", self.reranker_pool_enabled)
|
||||
|
||||
if "RERANKER_STRATEGY" in env_vars:
|
||||
strategy = env_vars["RERANKER_STRATEGY"].lower()
|
||||
if strategy in {"round_robin", "latency_aware", "weighted_random"}:
|
||||
self.reranker_strategy = strategy
|
||||
log.debug("Overriding reranker_strategy from .env: %s", strategy)
|
||||
else:
|
||||
log.warning("Invalid RERANKER_STRATEGY in .env: %r", strategy)
|
||||
|
||||
if "RERANKER_COOLDOWN" in env_vars:
|
||||
try:
|
||||
self.reranker_cooldown = float(env_vars["RERANKER_COOLDOWN"])
|
||||
log.debug("Overriding reranker_cooldown from .env: %s", self.reranker_cooldown)
|
||||
except ValueError:
|
||||
log.warning("Invalid RERANKER_COOLDOWN in .env: %r", env_vars["RERANKER_COOLDOWN"])
|
||||
|
||||
@classmethod
|
||||
def load(cls) -> "Config":
|
||||
"""Load config with settings from file."""
|
||||
|
||||
@@ -27,11 +27,17 @@ ENV_VARS = {
|
||||
"RERANKER_API_KEY": "API key for reranker service (SiliconFlow/Cohere/Jina)",
|
||||
"RERANKER_API_BASE": "Base URL for reranker API (overrides provider default)",
|
||||
"RERANKER_PROVIDER": "Reranker provider: siliconflow, cohere, jina",
|
||||
"RERANKER_POOL_ENABLED": "Enable reranker high availability pool: true/false",
|
||||
"RERANKER_STRATEGY": "Reranker load balance strategy: round_robin, latency_aware, weighted_random",
|
||||
"RERANKER_COOLDOWN": "Reranker rate limit cooldown in seconds",
|
||||
# Embedding configuration (overrides settings.json)
|
||||
"EMBEDDING_MODEL": "Embedding model/profile name (overrides settings.json)",
|
||||
"EMBEDDING_BACKEND": "Embedding backend: fastembed, litellm",
|
||||
"EMBEDDING_API_KEY": "API key for embedding service",
|
||||
"EMBEDDING_API_BASE": "Base URL for embedding API",
|
||||
"EMBEDDING_POOL_ENABLED": "Enable embedding high availability pool: true/false",
|
||||
"EMBEDDING_STRATEGY": "Embedding load balance strategy: round_robin, latency_aware, weighted_random",
|
||||
"EMBEDDING_COOLDOWN": "Embedding rate limit cooldown in seconds",
|
||||
# LiteLLM configuration
|
||||
"LITELLM_API_KEY": "API key for LiteLLM",
|
||||
"LITELLM_API_BASE": "Base URL for LiteLLM",
|
||||
|
||||
@@ -1338,8 +1338,9 @@ class ChainSearchEngine:
|
||||
(d for cid, d, _ in coarse_candidates if cid == chunk_id),
|
||||
1.0
|
||||
)
|
||||
# Convert cosine distance to score
|
||||
score = 1.0 - distance
|
||||
# Convert cosine distance to score (clamp to [0, 1] for Pydantic validation)
|
||||
# Cosine distance can be > 1 for anti-correlated vectors, causing negative scores
|
||||
score = max(0.0, 1.0 - distance)
|
||||
|
||||
content = chunk.get("content", "")
|
||||
result = SearchResult(
|
||||
|
||||
Reference in New Issue
Block a user