nexus-agentos 0.99.0__tar.gz

nexus_agentos-0.99.0/PKG-INFO

@@ -0,0 +1,219 @@
+Metadata-Version: 2.4
+Name: nexus-agentos
+Version: 0.99.0
+Summary: Agent Operating System — Production-ready multi-model agent framework with TokenCounter, SemanticMemoryRetriever, ConfigPresets, ToolRegistry, WorkflowTemplate, ResponseCache, AgentGraph, StreamingAgent, ConversationMemory, AsyncAgentLoop, SwarmPatterns, CI/CD pipeline, and 30+ production modules
+Author: AgentOS Team
+License: MIT
+Project-URL: Homepage, https://github.com/agentos/agentos
+Project-URL: Documentation, https://docs.agentos.dev
+Project-URL: Repository, https://github.com/agentos/agentos.git
+Keywords: agent,llm,ai,framework,multi-agent
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: openai>=1.0.0
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: aiosqlite>=0.20.0
+Requires-Dist: langsmith>=0.1.0
+Requires-Dist: fastapi>=0.110.0
+Requires-Dist: uvicorn[standard]>=0.29.0
+Requires-Dist: numpy>=1.26.0
+Provides-Extra: full
+Requires-Dist: faiss-cpu>=1.8.0; extra == "full"
+Requires-Dist: chromadb>=0.5.0; extra == "full"
+Requires-Dist: sentence-transformers>=3.0.0; extra == "full"
+Requires-Dist: opentelemetry-api>=1.20.0; extra == "full"
+Requires-Dist: docker>=7.0.0; extra == "full"
+Requires-Dist: mcp>=1.0.0; extra == "full"
+Provides-Extra: test
+Requires-Dist: pytest>=8.0; extra == "test"
+Requires-Dist: pytest-asyncio>=0.23.0; extra == "test"
+
+# AgentOS v0.99
+
+**Agent Operating System** — Production-ready multi-model agent framework.
+
+## Overview
+
+AgentOS is a modular, twelve-layered framework for building, orchestrating, and deploying AI agents. It supports OpenAI, Anthropic, Google Gemini, and open-source models through a unified routing layer.
+
+## Quick Start
+
+```bash
+pip install agentos
+
+# Create a new project
+agentos init my-agent
+
+# Start the API server
+agentos serve --preset production
+```
+
+```python
+from agentos import AgentLoop, LoopConfig, ModelRouter
+
+loop = AgentLoop(
+    config=LoopConfig(model="gpt-4o", max_iterations=10),
+    router=ModelRouter(),
+)
+result = loop.run("Summarize the key features of AgentOS.")
+print(result.output)
+```
+
+## Architecture
+
+```
+agentos/
+├── agents/         Agent marketplace & skill registry
+├── api/            REST API server, middleware, streaming, versioning
+├── benchmarks/     Benchmarking & performance testing
+├── cache/          LLM cache, response cache, embedding cache
+├── cli/            CLI scaffolding & serve commands
+├── comm/           Inter-agent communication (blackboard, event bus)
+├── config/         Configuration loader, validator, presets
+├── core/           Agent loop, state machine, async loop, streaming
+├── cost/           Cost tracking, token counting
+├── deployment/     Docker & Kubernetes deployment
+├── docs/           API documentation generator
+├── errors/         Error formatting & handling
+├── evaluation/     Scoring & evaluation metrics
+├── experiments/    A/B experiment runner
+├── feedback/       User feedback collection & learning
+├── health/         Health checks & monitoring
+├── logging/        Structured logging
+├── memory/         Short-term, long-term, working memory, summarizer, retriever
+├── models/         Model router, resilience, backends (Gemini)
+├── monitoring/     Alerting & metrics
+├── multimodal/     Image, audio, document processing
+├── observability/  Cost analytics, metrics, tracing
+├── orchestration/  DAG orchestrator, agent graph execution
+├── plugins/        Plugin system & lifecycle
+├── prompts/        Prompt registry & templates
+├── protocols/      Agent contracts & MCP
+├── queue/          Task queue & rate limiter
+├── security/       Guardrails, auditor, sandbox
+├── server/         MCP server
+├── storage/        Storage backend abstraction
+├── subagent/       Sub-agent management
+├── swarm/          Swarm coordination & patterns
+├── testing/        Test fixtures & mocks
+├── tools/          Tool registry, function calling, orchestrator, generator
+├── vectorstore/    Vector database abstraction
+└── workflows/      Workflow engine & templates
+```
+
+## Key Features
+
+### v0.99 New
+| Module | Description |
+|--------|-------------|
+| `TokenCounter` | Model-aware token counting + cost estimation for OpenAI/Anthropic/Gemini/Llama |
+| `SemanticMemoryRetriever` | Hybrid memory search (semantic + BM25 keyword) across conversation & long-term memory |
+| `ConfigPresets` | 8 ready-to-use config profiles: development, production, testing, budget, creative, deep_research, gemini_fast, gemini_pro |
+
+### Core Features (v0.95 - v0.98)
+| Module | Description |
+|--------|-------------|
+| `ToolRegistry` | Function calling pipeline with JSON Schema validation & batch execution |
+| `WorkflowTemplate` | Declarative workflow templates (YAML/JSON) with 6 step types |
+| `ResponseCache` | TTL cache with LRU eviction & 3 key strategies |
+| `AgentGraph` | DAG execution engine with Mermaid export |
+| `StreamingAgent` | SSE real-time streaming with session management |
+| `ConversationMemory` | 4 window strategies: Sliding, TokenAware, Importance, Hybrid |
+| `AsyncAgentLoop` | Async concurrent execution with p50/p95/p99 latency stats |
+| `SwarmPatterns` | 5 collaboration topologies: Broadcast, Pipeline, Hierarchical, Consensus, RoundRobin |
+
+### Infrastructure (v0.50 - v0.95)
+- **Model Router**: Unified routing across OpenAI, Anthropic, Gemini, Llama
+- **Guardrails**: Content safety, PII sanitization, content hashing
+- **Rate Limiter**: Token bucket, sliding window, concurrency limiter
+- **Circuit Breaker**: Resilience patterns with configurable retry
+- **Cost Analytics**: Budget alerts, cost breakdown, session tracking
+- **Health Checks**: OpenAI connectivity, vector store, disk space, memory
+- **Security Auditor**: Full security audit with severity-based findings
+- **Docker/K8s**: Auto-generate Dockerfile + docker-compose
+- **CI/CD**: GitHub Actions with multi-OS, 3 Python versions, lint, bandit security scan
+
+## Config Presets
+
+```python
+from agentos import get_preset, list_presets
+
+# List all presets
+for name in list_presets():
+    p = get_preset(name)
+    print(f"{p.name}: {p.model} (T={p.temperature})")
+
+# Apply a preset
+config = {"max_iterations": 15}
+from agentos import apply_preset
+apply_preset("production", config)  # Overrides with prod defaults
+```
+
+| Preset | Model | Temp | Use Case |
+|--------|-------|------|----------|
+| `development` | gpt-4o-mini | 0.8 | Local dev, fast iteration |
+| `production` | gpt-4o | 0.3 | Deployed services |
+| `testing` | gpt-4o-mini | 0.0 | CI/CD tests |
+| `budget` | gpt-4o-mini | 0.5 | Cost-sensitive |
+| `creative` | claude-3.5-sonnet | 0.95 | Creative writing |
+| `deep_research` | claude-3-opus | 0.4 | Research & analysis |
+| `gemini_fast` | gemini-2.0-flash | 0.7 | High throughput |
+| `gemini_pro` | gemini-1.5-pro | 0.5 | 2M context window |
+
+## Token Counting
+
+```python
+from agentos import TokenCounter
+
+counter = TokenCounter()
+tokens = counter.count("Hello, agent world!", model="gpt-4o")
+print(f"Tokens: {counter.format_tokens(tokens)}")
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Explain quantum computing in 3 sentences."},
+]
+total = counter.count_messages(messages, model="gpt-4o")
+cost = counter.estimate_cost(total)
+print(f"Cost: {counter.format_cost(cost)}")
+```
+
+## Memory Retrieval
+
+```python
+from agentos import SemanticMemoryRetriever, RetrievalStrategy, MemoryEntry
+
+retriever = SemanticMemoryRetriever()
+
+# Index memories
+retriever.index([
+    MemoryEntry(id="1", content="Deployed to production at 3pm UTC", source="long_term"),
+    MemoryEntry(id="2", content="User asked about GDPR compliance", source="conversation"),
+    MemoryEntry(id="3", content="Database migration scheduled for Friday", source="conversation"),
+])
+
+# Hybrid search (semantic + keyword)
+results = retriever.retrieve("When is the next deployment?")
+for r in results:
+    print(f"[{r.score:.2f}] {r.entry.content}")
+```
+
+## Requirements
+
+- Python >= 3.11
+- openai >= 1.0.0
+- httpx >= 0.27.0
+- pyyaml >= 6.0
+- pydantic >= 2.0
+- fastapi >= 0.110.0 (optional, for API server)
+
+## License
+
+MIT

nexus_agentos-0.99.0/README.md

@@ -0,0 +1,182 @@
+# AgentOS v0.99
+
+**Agent Operating System** — Production-ready multi-model agent framework.
+
+## Overview
+
+AgentOS is a modular, twelve-layered framework for building, orchestrating, and deploying AI agents. It supports OpenAI, Anthropic, Google Gemini, and open-source models through a unified routing layer.
+
+## Quick Start
+
+```bash
+pip install agentos
+
+# Create a new project
+agentos init my-agent
+
+# Start the API server
+agentos serve --preset production
+```
+
+```python
+from agentos import AgentLoop, LoopConfig, ModelRouter
+
+loop = AgentLoop(
+    config=LoopConfig(model="gpt-4o", max_iterations=10),
+    router=ModelRouter(),
+)
+result = loop.run("Summarize the key features of AgentOS.")
+print(result.output)
+```
+
+## Architecture
+
+```
+agentos/
+├── agents/         Agent marketplace & skill registry
+├── api/            REST API server, middleware, streaming, versioning
+├── benchmarks/     Benchmarking & performance testing
+├── cache/          LLM cache, response cache, embedding cache
+├── cli/            CLI scaffolding & serve commands
+├── comm/           Inter-agent communication (blackboard, event bus)
+├── config/         Configuration loader, validator, presets
+├── core/           Agent loop, state machine, async loop, streaming
+├── cost/           Cost tracking, token counting
+├── deployment/     Docker & Kubernetes deployment
+├── docs/           API documentation generator
+├── errors/         Error formatting & handling
+├── evaluation/     Scoring & evaluation metrics
+├── experiments/    A/B experiment runner
+├── feedback/       User feedback collection & learning
+├── health/         Health checks & monitoring
+├── logging/        Structured logging
+├── memory/         Short-term, long-term, working memory, summarizer, retriever
+├── models/         Model router, resilience, backends (Gemini)
+├── monitoring/     Alerting & metrics
+├── multimodal/     Image, audio, document processing
+├── observability/  Cost analytics, metrics, tracing
+├── orchestration/  DAG orchestrator, agent graph execution
+├── plugins/        Plugin system & lifecycle
+├── prompts/        Prompt registry & templates
+├── protocols/      Agent contracts & MCP
+├── queue/          Task queue & rate limiter
+├── security/       Guardrails, auditor, sandbox
+├── server/         MCP server
+├── storage/        Storage backend abstraction
+├── subagent/       Sub-agent management
+├── swarm/          Swarm coordination & patterns
+├── testing/        Test fixtures & mocks
+├── tools/          Tool registry, function calling, orchestrator, generator
+├── vectorstore/    Vector database abstraction
+└── workflows/      Workflow engine & templates
+```
+
+## Key Features
+
+### v0.99 New
+| Module | Description |
+|--------|-------------|
+| `TokenCounter` | Model-aware token counting + cost estimation for OpenAI/Anthropic/Gemini/Llama |
+| `SemanticMemoryRetriever` | Hybrid memory search (semantic + BM25 keyword) across conversation & long-term memory |
+| `ConfigPresets` | 8 ready-to-use config profiles: development, production, testing, budget, creative, deep_research, gemini_fast, gemini_pro |
+
+### Core Features (v0.95 - v0.98)
+| Module | Description |
+|--------|-------------|
+| `ToolRegistry` | Function calling pipeline with JSON Schema validation & batch execution |
+| `WorkflowTemplate` | Declarative workflow templates (YAML/JSON) with 6 step types |
+| `ResponseCache` | TTL cache with LRU eviction & 3 key strategies |
+| `AgentGraph` | DAG execution engine with Mermaid export |
+| `StreamingAgent` | SSE real-time streaming with session management |
+| `ConversationMemory` | 4 window strategies: Sliding, TokenAware, Importance, Hybrid |
+| `AsyncAgentLoop` | Async concurrent execution with p50/p95/p99 latency stats |
+| `SwarmPatterns` | 5 collaboration topologies: Broadcast, Pipeline, Hierarchical, Consensus, RoundRobin |
+
+### Infrastructure (v0.50 - v0.95)
+- **Model Router**: Unified routing across OpenAI, Anthropic, Gemini, Llama
+- **Guardrails**: Content safety, PII sanitization, content hashing
+- **Rate Limiter**: Token bucket, sliding window, concurrency limiter
+- **Circuit Breaker**: Resilience patterns with configurable retry
+- **Cost Analytics**: Budget alerts, cost breakdown, session tracking
+- **Health Checks**: OpenAI connectivity, vector store, disk space, memory
+- **Security Auditor**: Full security audit with severity-based findings
+- **Docker/K8s**: Auto-generate Dockerfile + docker-compose
+- **CI/CD**: GitHub Actions with multi-OS, 3 Python versions, lint, bandit security scan
+
+## Config Presets
+
+```python
+from agentos import get_preset, list_presets
+
+# List all presets
+for name in list_presets():
+    p = get_preset(name)
+    print(f"{p.name}: {p.model} (T={p.temperature})")
+
+# Apply a preset
+config = {"max_iterations": 15}
+from agentos import apply_preset
+apply_preset("production", config)  # Overrides with prod defaults
+```
+
+| Preset | Model | Temp | Use Case |
+|--------|-------|------|----------|
+| `development` | gpt-4o-mini | 0.8 | Local dev, fast iteration |
+| `production` | gpt-4o | 0.3 | Deployed services |
+| `testing` | gpt-4o-mini | 0.0 | CI/CD tests |
+| `budget` | gpt-4o-mini | 0.5 | Cost-sensitive |
+| `creative` | claude-3.5-sonnet | 0.95 | Creative writing |
+| `deep_research` | claude-3-opus | 0.4 | Research & analysis |
+| `gemini_fast` | gemini-2.0-flash | 0.7 | High throughput |
+| `gemini_pro` | gemini-1.5-pro | 0.5 | 2M context window |
+
+## Token Counting
+
+```python
+from agentos import TokenCounter
+
+counter = TokenCounter()
+tokens = counter.count("Hello, agent world!", model="gpt-4o")
+print(f"Tokens: {counter.format_tokens(tokens)}")
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Explain quantum computing in 3 sentences."},
+]
+total = counter.count_messages(messages, model="gpt-4o")
+cost = counter.estimate_cost(total)
+print(f"Cost: {counter.format_cost(cost)}")
+```
+
+## Memory Retrieval
+
+```python
+from agentos import SemanticMemoryRetriever, RetrievalStrategy, MemoryEntry
+
+retriever = SemanticMemoryRetriever()
+
+# Index memories
+retriever.index([
+    MemoryEntry(id="1", content="Deployed to production at 3pm UTC", source="long_term"),
+    MemoryEntry(id="2", content="User asked about GDPR compliance", source="conversation"),
+    MemoryEntry(id="3", content="Database migration scheduled for Friday", source="conversation"),
+])
+
+# Hybrid search (semantic + keyword)
+results = retriever.retrieve("When is the next deployment?")
+for r in results:
+    print(f"[{r.score:.2f}] {r.entry.content}")
+```
+
+## Requirements
+
+- Python >= 3.11
+- openai >= 1.0.0
+- httpx >= 0.27.0
+- pyyaml >= 6.0
+- pydantic >= 2.0
+- fastapi >= 0.110.0 (optional, for API server)
+
+## License
+
+MIT

nexus_agentos-0.99.0/agentos/__init__.py

@@ -0,0 +1,180 @@
+"""
+AgentOS v0.99 — 多模型通用 Agent 框架。
+
+十二层架构 + 生产就绪增强 + CI/CD 发布管线。
+v0.99新增: TokenCounter(模型感知Token计数+成本估算+多Provider定价) + SemanticMemoryRetriever(语义记忆检索+BM25关键词+混合搜索) + ConfigPresets(8种场景预设配置: Development/Production/Budget/Creative/Research等)。
+v0.98基线: ToolRegistry + WorkflowTemplate + ResponseCache。
+"""
+
+__version__ = "0.99.0"
+
+from agentos.core.loop import AgentLoop, AgentResult, LoopConfig, LoopState, MaxIterationsExceeded, StepTimeoutError, ReflectionResult, HumanInterruptNeeded, StepResult
+from agentos.cost.tracker import CostTracker, PRICING
+from agentos.agents.market import AgentMarket, AgentSkill, AgentCategory
+from agentos.prompts.manager import PromptRegistry, PromptTemplate, DEFAULT_PROMPTS
+from agentos.feedback.learner import FeedbackCollector, FeedbackRecord, FeedbackType, PreferenceLearner
+from agentos.vectorstore.db import FAISSVectorStore, ChromaVectorStore, VectorEntry
+from agentos.api.server import AgentAPI
+from agentos.swarm.coordinator import SwarmCoordinator, SwarmTopology, AgentRole, SwarmTask, TaskResult, SwarmResult, MessageBus
+from agentos.comm.layer import CommunicationLayer, AgentMessage, ChannelType, Blackboard, EventBus, AgentMailbox
+from agentos.server.mcp_server import MCPServer, MCPClient, MCPServerConfig, MCPTool, MCPResource, MCPPrompt
+from agentos.queue.task_queue import TaskQueue, ScheduledTask, TaskState, TaskPriority, MemoryQueue
+from agentos.cache.llm_cache import LLMCache, LRUCache, SemanticCache, CacheStats
+from agentos.multimodal.manager import MultimodalManager, MultimodalBlock, Modality, ImageProcessor, AudioProcessor, DocumentParser
+from agentos.experiments.runner import ExperimentRunner, ExperimentConfig, ExperimentReport, PromptVariant, TrialResult, Evaluator
+from agentos.models.router import ModelRouter, ModelConfig, ModelSpec, ModelResponse, RECOMMENDED_CONFIG
+from agentos.tools.generator import OpenAPIToolGenerator, GeneratedTool
+from agentos.cache.embedder import BaseEmbedder, OpenAIEmbedder, LocalEmbedder, CohereEmbedder, get_embedder, cosine_similarity
+from agentos.security.guard import Guardrails, GuardResult, ContentRisk, PIISanitizer, ContentHasher
+from agentos.queue.rate_limiter import RateLimiter, RateLimitConfig, TokenBucket, SlidingWindow, ConcurrencyLimiter, QuotaManager
+from agentos.core.state_machine import AgentStateMachine, AgentState, StateMachineConfig, StateTransition
+from agentos.memory.summarizer import MemorySummarizer, MemoryChunk, ConversationMemory, ImportanceScorer
+from agentos.models.resilience import CircuitBreaker, CircuitBreakerConfig, RetryConfig, retry_with_backoff, ResilientCall
+from agentos.config.loader import (
+    AgentOSConfig, ModelConfig, LoopCfg, MemoryCfg,
+    SecurityCfg, ObservabilityCfg, ReflectionCfg, CostCfg,
+    FeedbackCfg, APICfg, SwarmCfg, QueueCfg, CacheCfg,
+    ExperimentCfg, MultimodalCfg, MCPServerCfg,
+    GuardrailsCfg, RateLimitCfg, StateMachineCfg, ResilienceCfg,
+    PluginsCfg, GeminiCfg, ContractsCfg, OrchestratorCfg, ScorerCfg,
+    BenchmarkCfg, HealthCfg, AuditCfg, DeployCfg, MiddlewareCfg,
+    load_config,
+)
+
+# v0.70 新增模块
+from agentos.observability.cost_analytics import CostAnalytics, BudgetAlert, CostBreakdown, CostSession
+from agentos.observability.metrics import MetricsCollector, MetricSnapshot, Counter, Gauge, Histogram
+from agentos.plugins.registry import PluginRegistry, PluginManifest, RegisteredPlugin
+from agentos.plugins.loader import PluginLoader, PluginLoadError
+from agentos.plugins.lifecycle import LifecyclePlugin, LifecycleManager, PluginHealth
+from agentos.tools.orchestrator import ToolOrchestrator, DAGSpec, DAGBuilder, DAGResult, NodeResult, NodeState, RetryPolicy, chain_builder, parallel_then_merge, if_then_else
+from agentos.protocols.contracts import ContractRegistry, AgentContract, AgentCapability, CapabilityDomain, CapabilityMatcher, MatchScore, QoSLevel
+from agentos.evaluation.scorers import CompositeScorer, ScoringStrategy, ScoreResult, rouge_l, bleu, semantic_similarity, STRATEGY_CODE_GEN, STRATEGY_QA, STRATEGY_SUMMARY, STRATEGY_TRANSLATION
+
+# v0.80 模块
+from agentos.errors.handler import HumanError, ErrorFormatter, ErrorContext, ErrorCategory, format_error, friendly_error
+from agentos.docs.generator import DocGenerator, DocConfig as DocGenConfig, generate_api_docs, generate_quickstart
+from agentos.cli.init import scaffold
+from agentos.cli.serve import ServeConfig, start_api_server
+from agentos.benchmarks.runner import BenchmarkRunner, BenchmarkConfig, BenchmarkReport, BenchmarkScenario, run_benchmark
+
+# v0.90 新增模块
+from agentos.security.auditor import SecurityAuditor, AuditReport, AuditFinding, AuditSeverity, full_audit
+from agentos.deployment.docker import DockerConfig, ComposeConfig, ComposeService, generate_dockerfile, generate_docker_compose, write_deployment_files
+from agentos.api.middleware import MiddlewareStack, CORSMiddleware, CORSConfig, AuthMiddleware, AuthConfig, RequestLogMiddleware, RequestIDMiddleware, RequestContext
+from agentos.api.versioning import VersionNegotiator, VersionConfig, APIVersion, VersionStrategy
+from agentos.monitoring import Alert, AlertEvaluator, AlertRule, AlertSeverity, AlertState, MonitoringConfig, WebhookConfig, WebhookDispatcher
+from agentos.config.validator import ValidationResult, ValidationIssue, ValidationLevel, validate_config, validate_config_file
+from agentos.health import HealthChecker, HealthStatus, HealthCheck, CheckResult, create_default_health_checker, check_openai_connectivity, check_vectorstore_health, check_disk_space, check_memory
+from agentos.logging import JSONFormatter, TraceContext, setup_structured_logging, get_logger, audit_log
+
+# v0.95 测试基础设施
+from agentos.testing import MockLLMClient, MockLLMResponse, mock_openai_client, mock_model_response, sample_config, sample_loop_config, temp_workspace, mock_memory_store, sample_agent_state, sample_audit_report, sample_health_status, sample_docker_config, sample_middleware_stack, sample_alert_config
+
+# v0.96 异步核心 + 增强协作
+from agentos.core.async_loop import AsyncAgentLoop, AsyncLoopConfig, AsyncInvocationResult, AsyncContextManager
+from agentos.swarm.patterns import SwarmPatterns, CollaborationConfig, CollaborationResult, MemberResult, Topology
+
+# v0.97 Graph执行 + 流式 + 对话记忆
+from agentos.orchestration.graph_executor import AgentGraph, GraphNode, GraphResult, GraphNodeState, GraphRecipe
+from agentos.api.streaming import StreamingAgent, StreamEvent, StreamSession
+from agentos.memory.conversation import ConversationMemory, WindowConfig, WindowStrategy, ConversationTurn
+
+# v0.98 函数调用 + 工作流模板 + 响应缓存
+from agentos.tools.function_calling import ToolRegistry, ToolSchema, ToolCall, ToolResult
+from agentos.workflows.templates import WorkflowTemplate, WorkflowStep, StepType, RetryPolicy, BUILTIN_TEMPLATES
+from agentos.cache.response_cache import ResponseCache, CacheEntry, CacheStats, CacheKeyStrategy
+
+# v0.99 Token计数 + 语义记忆检索 + 配置预设
+from agentos.cost.token_counter import TokenCounter, TokenCount, CostEstimate, ModelFamily
+from agentos.memory.retriever import SemanticMemoryRetriever, RetrievalStrategy, RetrievalResult, MemoryEntry as MemEntry
+from agentos.config.presets import AgentOSPreset, PRESETS, get_preset, list_presets, get_preset_names, apply_preset
+
+__all__ = [
+    "__version__",
+    "AgentLoop", "AgentResult", "LoopConfig", "LoopState",
+    "MaxIterationsExceeded", "StepTimeoutError", "ReflectionResult", "HumanInterruptNeeded", "StepResult",
+    "CostTracker", "PRICING",
+    "AgentMarket", "AgentSkill", "AgentCategory",
+    "PromptRegistry", "PromptTemplate", "DEFAULT_PROMPTS",
+    "FeedbackCollector", "FeedbackRecord", "FeedbackType", "PreferenceLearner",
+    "FAISSVectorStore", "ChromaVectorStore", "VectorEntry",
+    "AgentAPI",
+    # v0.40
+    "SwarmCoordinator", "SwarmTopology", "AgentRole", "SwarmTask", "TaskResult", "SwarmResult", "MessageBus",
+    "CommunicationLayer", "AgentMessage", "ChannelType", "Blackboard", "EventBus", "AgentMailbox",
+    "MCPServer", "MCPClient", "MCPServerConfig", "MCPTool", "MCPResource", "MCPPrompt",
+    "TaskQueue", "ScheduledTask", "TaskState", "TaskPriority", "MemoryQueue",
+    "LLMCache", "LRUCache", "SemanticCache", "CacheStats",
+    "MultimodalManager", "MultimodalBlock", "Modality", "ImageProcessor", "AudioProcessor", "DocumentParser",
+    "ExperimentRunner", "ExperimentConfig", "ExperimentReport", "PromptVariant", "TrialResult", "Evaluator",
+    # v0.50
+    "ModelRouter", "ModelConfig", "ModelSpec", "ModelResponse", "RECOMMENDED_CONFIG",
+    "OpenAPIToolGenerator", "GeneratedTool",
+    "BaseEmbedder", "OpenAIEmbedder", "LocalEmbedder", "CohereEmbedder", "get_embedder", "cosine_similarity",
+    # v0.60
+    "Guardrails", "GuardResult", "ContentRisk", "PIISanitizer", "ContentHasher",
+    "RateLimiter", "RateLimitConfig", "TokenBucket", "SlidingWindow", "ConcurrencyLimiter", "QuotaManager",
+    "AgentStateMachine", "AgentState", "StateMachineConfig", "StateTransition",
+    "MemorySummarizer", "MemoryChunk", "ConversationMemory", "ImportanceScorer",
+    "CircuitBreaker", "CircuitBreakerConfig", "RetryConfig", "retry_with_backoff", "ResilientCall",
+    "AgentOSConfig", "LoopCfg", "MemoryCfg",
+    "SecurityCfg", "ObservabilityCfg", "ReflectionCfg", "CostCfg",
+    "FeedbackCfg", "APICfg", "SwarmCfg", "QueueCfg", "CacheCfg",
+    "ExperimentCfg", "MultimodalCfg", "MCPServerCfg",
+    "GuardrailsCfg", "RateLimitCfg", "StateMachineCfg", "ResilienceCfg",
+    # v0.70 config
+    "PluginsCfg", "GeminiCfg", "ContractsCfg", "OrchestratorCfg", "ScorerCfg",
+    "BenchmarkCfg",
+    "HealthCfg", "AuditCfg", "DeployCfg", "MiddlewareCfg",
+    "load_config",
+    # v0.70 modules
+    "CostAnalytics", "BudgetAlert", "CostBreakdown", "CostSession",
+    "MetricsCollector", "MetricSnapshot", "Counter", "Gauge", "Histogram",
+    "PluginRegistry", "PluginManifest", "RegisteredPlugin",
+    "PluginLoader", "PluginLoadError",
+    "LifecyclePlugin", "LifecycleManager", "PluginHealth",
+    "ToolOrchestrator", "DAGSpec", "DAGBuilder", "DAGResult", "NodeResult", "NodeState", "RetryPolicy",
+    "chain_builder", "parallel_then_merge", "if_then_else",
+    "ContractRegistry", "AgentContract", "AgentCapability", "CapabilityDomain", "CapabilityMatcher", "MatchScore", "QoSLevel",
+    "CompositeScorer", "ScoringStrategy", "ScoreResult",
+    "rouge_l", "bleu", "semantic_similarity",
+    "STRATEGY_CODE_GEN", "STRATEGY_QA", "STRATEGY_SUMMARY", "STRATEGY_TRANSLATION",
+    # v0.80 modules
+    "HumanError", "ErrorFormatter", "ErrorContext", "ErrorCategory",
+    "format_error", "friendly_error",
+    "DocGenerator", "DocGenConfig", "generate_api_docs", "generate_quickstart",
+    "scaffold",
+    "ServeConfig", "start_api_server",
+    "BenchmarkRunner", "BenchmarkConfig", "BenchmarkReport", "BenchmarkScenario", "run_benchmark",
+    # v0.90 modules
+    "SecurityAuditor", "AuditReport", "AuditFinding", "AuditSeverity", "full_audit",
+    "DockerConfig", "ComposeConfig", "ComposeService", "generate_dockerfile", "generate_docker_compose", "write_deployment_files",
+    "MiddlewareStack", "CORSMiddleware", "CORSConfig", "AuthMiddleware", "AuthConfig", "RequestLogMiddleware", "RequestIDMiddleware", "RequestContext",
+    "VersionNegotiator", "VersionConfig", "APIVersion", "VersionStrategy",
+    "Alert", "AlertEvaluator", "AlertRule", "AlertSeverity", "AlertState", "MonitoringConfig", "WebhookConfig", "WebhookDispatcher",
+    "ValidationResult", "ValidationIssue", "ValidationLevel", "validate_config", "validate_config_file",
+    "HealthChecker", "HealthStatus", "HealthCheck", "CheckResult", "create_default_health_checker",
+    "check_openai_connectivity", "check_vectorstore_health", "check_disk_space", "check_memory",
+    "JSONFormatter", "TraceContext", "setup_structured_logging", "get_logger", "audit_log",
+    # v0.95 testing
+    "MockLLMClient", "MockLLMResponse", "mock_openai_client", "mock_model_response",
+    "sample_config", "sample_loop_config", "temp_workspace", "mock_memory_store",
+    "sample_agent_state", "sample_audit_report", "sample_health_status",
+    "sample_docker_config", "sample_middleware_stack", "sample_alert_config",
+    # v0.96 async + swarm patterns
+    "AsyncAgentLoop", "AsyncLoopConfig", "AsyncInvocationResult", "AsyncContextManager",
+    "SwarmPatterns", "CollaborationConfig", "CollaborationResult", "MemberResult", "Topology",
+    # v0.97 graph + streaming + conversation
+    "AgentGraph", "GraphNode", "GraphResult", "GraphNodeState", "GraphRecipe",
+    "StreamingAgent", "StreamEvent", "StreamSession",
+    "ConversationMemory", "WindowConfig", "WindowStrategy", "ConversationTurn",
+    # v0.98 function calling + workflow templates + response cache
+    "ToolRegistry", "ToolSchema", "ToolCall", "ToolResult",
+    "WorkflowTemplate", "WorkflowStep", "StepType", "RetryPolicy", "BUILTIN_TEMPLATES",
+    "ResponseCache", "CacheEntry", "CacheKeyStrategy",
+    # v0.99 token counter + semantic retriever + config presets
+    "TokenCounter", "TokenCount", "CostEstimate", "ModelFamily",
+    "SemanticMemoryRetriever", "RetrievalStrategy", "RetrievalResult", "MemEntry",
+    "AgentOSPreset", "PRESETS", "get_preset", "list_presets", "get_preset_names", "apply_preset",
+]