chnjinlei/hive
1
0
Fork 0
Code Issues Pull Requests Actions 39 Packages Projects Releases Wiki Activity

chore: architecture

Browse Source
This commit is contained in:
Timothy
2026-02-22 17:54:12 -08:00
parent 564b1bb752
commit 13cc93c334
3 changed files with 404 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/architecture/README.md
+164 -14
View File
@@ -1,5 +1,148 @@
# Hive Agent Framework: Triangulated Verification for Reliable Goal-Driven Agents
## System Architecture Overview
The Hive framework is organized around five core subsystems that collaborate to execute goal-driven agents reliably. The following diagram shows how these subsystems connect:
```mermaid
flowchart TB
%% Main Entity
User([User])
%% =========================================
%% EXTERNAL EVENT SOURCES
%% =========================================
subgraph ExtEventSource [External Event Source]
E_Sch["Schedulers"]
E_WH["Webhook"]
E_SSE["SSE"]
end
%% =========================================
%% SYSTEM NODES
%% =========================================
subgraph EventLoopNode [Event Loop Node]
ELN_L["listener"]
ELN_SP["System Prompt<br/>(Task)"]
ELN_EL["Event loop"]
ELN_C["Conversation"]
end
subgraph WorkerBees [Worker Bees]
WB_C["Conversation"]
WB_SP["System prompt"]
subgraph Graph [Graph]
direction TB
N1["Node"] --> N2["Node"] --> N3["Node"]
N1 -.-> AN["Active Node"]
N2 -.-> AN
N3 -.-> AN
end
end
subgraph JudgeNode [Judge]
J_C["Criteria"]
J_P["Principles"]
J_EL["Event loop"] <--> J_S["Scheduler"]
end
subgraph QueenBee [Queen Bee]
QB_SP["System prompt"]
QB_EL["Event loop"]
QB_C["Conversation"]
end
subgraph Infra [Infra]
SA["Sub Agent"]
TR["Tool Registry"]
WTM["Write through Conversation Memory<br/>(Logs/RAM/Harddrive)"]
SM["Shared Memory<br/>(State/Harddrive)"]
EB["Event Bus<br/>(RAM)"]
CS["Credential Store<br/>(Harddrive/Cloud)"]
end
subgraph PC [PC]
B["Browser"]
CB["Codebase<br/>v 0.0.x ... v n.n.n"]
end
%% =========================================
%% CONNECTIONS & DATA FLOW
%% =========================================
%% External Event Routing
E_Sch --> ELN_L
E_WH --> ELN_L
E_SSE --> ELN_L
ELN_L -->|"triggers"| ELN_EL
%% User Interactions
User -->|"Talk"| WB_C
User -->|"Talk"| QB_C
User -->|"Read/Write Access"| CS
%% Inter-System Logic
ELN_C <-->|"Mirror"| WB_C
WB_C -->|"Focus"| AN
WorkerBees -->|"Inquire"| JudgeNode
JudgeNode -->|"Approve"| WorkerBees
%% Judge Alignments
J_C <-.->|"aligns"| WB_SP
J_P <-.->|"aligns"| QB_SP
%% Escalate path
J_EL -->|"Report (Escalate)"| QB_EL
%% Pub/Sub Logic
AN -->|"publish"| EB
EB -->|"subscribe"| QB_C
%% Infra and Process Spawning
ELN_EL -->|"Spawn"| SA
SA -->|"Inform"| ELN_EL
SA -->|"Starts"| B
B -->|"Report"| ELN_EL
TR -->|"Assigned"| EventLoopNode
CB -->|"Modify Worker Bee"| WorkerBees
%% =========================================
%% SHARED MEMORY & LOGS ACCESS
%% =========================================
%% Worker Bees Access
Graph <-->|"Read/Write"| WTM
Graph <-->|"Read/Write"| SM
%% Queen Bee Access
QB_C <-->|"Read/Write"| WTM
QB_EL <-->|"Read/Write"| SM
%% Credentials Access
CS -->|"Read Access"| QB_C
```
### Key Subsystems
| Subsystem | Role | Description |
| --- | --- | --- |
| **Event Loop Node** | Entry point | Listens for external events (schedulers, webhooks, SSE), triggers the event loop, and spawns sub-agents. Its conversation mirrors the Worker Bees conversation for context continuity. |
| **Worker Bees** | Execution | A graph of nodes that execute the actual work. Each node in the graph can become the Active Node. Workers maintain their own conversation and system prompt, and read/write to shared memory. |
| **Judge** | Evaluation | Evaluates Worker Bee output against criteria (aligned with Worker system prompt) and principles (aligned with Queen Bee system prompt). Runs on a scheduled event loop and escalates to the Queen Bee when needed. |
| **Queen Bee** | Oversight | The orchestration layer. Subscribes to Active Node events via the Event Bus, receives escalation reports from the Judge, and has read/write access to shared memory and credentials. Users can talk directly to the Queen Bee. |
| **Infra** | Services | Shared infrastructure: Tool Registry (assigned to Event Loop Nodes), Write-through Conversation Memory (logs across RAM and disk), Shared Memory (state on disk), Event Bus (pub/sub in RAM), Credential Store (encrypted on disk or cloud), and Sub Agents. |
### Data Flow Patterns
- **External triggers**: Schedulers, Webhooks, and SSE events flow into the Event Loop Node's listener, which triggers the event loop to spawn sub-agents or start browser-based tasks.
- **User interaction**: Users talk directly to Worker Bees (for task execution) or the Queen Bee (for oversight). Users also have read/write access to the Credential Store.
- **Worker-Judge loop**: Worker Bees inquire with the Judge after completing work. The Judge approves the output or escalates to the Queen Bee.
- **Pub/Sub**: The Active Node publishes events to the Event Bus. The Queen Bee subscribes for real-time visibility.
- **Adaptiveness**: The Codebase modifies Worker Bees, enabling the framework to evolve agent graphs across versions.
---
## The Core Problem: The Ground Truth Crisis in Agentic Systems
Modern agent frameworks face a fundamental epistemological challenge: **there is no reliable oracle**.
@@ -324,30 +467,35 @@ High Confidence ─────────────────────
## The Complete Picture
The system architecture (see diagram above) maps onto four logical layers. The **Goal Layer** defines what the Queen Bee and Judge align on. The **Execution Layer** is the Worker Bees graph. The **Verification Layer** is the Judge with its triangulated signals. The **Reflexion Layer** is the feedback loop between Worker Bees and Judge.
```
┌─────────────────────────────────────────────────────────────────────┐
│ HIVE AGENT FRAMEWORK │
├─────────────────────────────────────────────────────────────────────┤
│ │
│ ┌─────────────────────────────────────────────────────────────┐ │
│ │ GOAL LAYER │ │
│ │ GOAL LAYER (Queen Bee) │ │
│ │ • Success criteria (weighted, multi-metric) │ │
│ │ • Constraints (hard/soft boundaries) │ │
│ │ • Principles aligned with Queen Bee system prompt │ │
│ │ • Context (domain knowledge, preferences) │ │
│ └─────────────────────────────────────────────────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────────────────────────┐ │
│ │ EXECUTION LAYER │ │
│ │ EXECUTION LAYER (Worker Bees) │ │
│ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │
│ │ │ Graph │───►│ Worker │───►│ Shared │ │ │
│ │ │ Graph │───►│ Active │───►│ Shared │ │ │
│ │ │ Executor │ │ Node │ │ Memory │ │ │
│ │ └──────────┘ └──────────┘ └──────────┘ │ │
│ │ Event Loop Node triggers │ Sub Agents, Browser tasks │ │
│ │ Tool Registry provides tools │ Event Bus publishes events │ │
│ └─────────────────────────────────────────────────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────────────────────────┐ │
│ │ TRIANGULATED VERIFICATION │ │
│ │ TRIANGULATED VERIFICATION (Judge) │ │
│ │ │ │
│ │ Signal 1 Signal 2 Signal 3 │ │
│ │ ┌────────┐ ┌──────────┐ ┌─────────┐ │ │
@@ -356,9 +504,9 @@ High Confidence ─────────────────────
│ │ └────────┘ └──────────┘ └─────────┘ │ │
│ │ │ │ │ │ │
│ │ └────────────────┴──────────────────┘ │ │
│ │ │ │ │
│ │ ▼ │ │
│ │ Confidence from Agreement │ │
│ │ Criteria aligned with Worker Bee system prompt │ │
│ │ Principles aligned with Queen Bee system prompt │ │
│ │ Confidence from agreement across signals │ │
│ └─────────────────────────────────────────────────────────────┘ │
│ │ │
│ ▼ │
@@ -367,7 +515,7 @@ High Confidence ─────────────────────
│ │ • ACCEPT: Proceed with confidence │ │
│ │ • RETRY: Learn from failure, try again │ │
│ │ • REPLAN: Strategy failed, change approach │ │
│ │ • ESCALATE: Uncertainty too high, ask human │ │
│ │ • ESCALATE: Report to Queen Bee, ask human │ │
│ └─────────────────────────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────────┘
@@ -628,17 +776,19 @@ class SignalWeights:
## Summary
The Hive Agent Framework addresses the fundamental reliability crisis in agentic systems through **Triangulated Verification** and a roadmap toward **Online Learning**:
The Hive Agent Framework addresses the fundamental reliability crisis in agentic systems through a layered architecture of **Event Loop Nodes**, **Worker Bees**, **Judges**, and a **Queen Bee**, unified by **Triangulated Verification** and a roadmap toward **Online Learning**:
1. **The Problem**: No single evaluation signal is trustworthy. Tests can be gamed, model confidence is miscalibrated, LLM judges hallucinate.
1. **The Architecture**: External events enter through Event Loop Nodes, which trigger Worker Bees to execute graph-based tasks. A Judge evaluates output using triangulated signals. A Queen Bee provides oversight, receives escalations, and subscribes to events via the Event Bus. Shared infrastructure (memory, credentials, tool registry) connects all subsystems.
2. **The Solution**: Confidence emerges from agreement across multiple independent signals—deterministic rules, semantic evaluation, and human judgment.
2. **The Problem**: No single evaluation signal is trustworthy. Tests can be gamed, model confidence is miscalibrated, LLM judges hallucinate.
3. **The Foundation**: Goal-driven architecture ensures we're optimizing for user intent, not metric gaming. The reflexion loop enables learning from failure without expensive search.
3. **The Solution**: Confidence emerges from agreement across multiple independent signals—deterministic rules, semantic evaluation, and human judgment. The Judge's criteria align with Worker Bee prompts; its principles align with the Queen Bee.
4. **The Learning Path**: Human escalations aren't just fallbacks—they're training signals. Confidence calibration tunes thresholds automatically. Rule generation transforms repeated human decisions into deterministic automation.
4. **The Foundation**: Goal-driven architecture ensures we're optimizing for user intent, not metric gaming. The reflexion loop between Worker Bees and Judge enables learning from failure without expensive search.
5. **The Result**: Agents that are reliable not because they're always right, but because they **know when they don't know**—and get smarter every time they ask for help.
5. **The Learning Path**: Human escalations aren't just fallbacks—they're training signals. Confidence calibration tunes thresholds automatically. Rule generation transforms repeated human decisions into deterministic automation.
6. **The Result**: Agents that are reliable not because they're always right, but because they **know when they don't know**—and get smarter every time they ask for help.
---
docs/roadmap.md
+225 -175
View File
@@ -3,93 +3,122 @@
Aden Agent Framework aims to help developers build outcome-oriented, self-adaptive agents. Please find our roadmap here
```mermaid
flowchart TD
subgraph Foundation
direction LR
subgraph arch["Architecture"]
a1["Node-Based Architecture"]:::done
a2["Python SDK"]:::done
a3["LLM Integration"]:::done
a4["Communication Protocol"]:::done
end
subgraph ca["Coding Agent"]
b1["Goal Creation Session"]:::done
b2["Worker Agent Creation"]
b3["MCP Tools"]:::done
end
subgraph wa["Worker Agent"]
c1["Human-in-the-Loop"]:::done
c2["Callback Handlers"]:::done
c3["Intervention Points"]:::done
c4["Streaming Interface"]
end
subgraph cred["Credentials"]
d1["Setup Process"]:::done
d2["Pluggable Sources"]:::done
d3["Enterprise Secrets"]
d4["Integration Tools"]:::done
end
subgraph tools["Tools"]
e1["File Use"]:::done
e2["Memory STM/LTM"]:::done
e3["Web Search/Scraper"]:::done
e4["CSV/PDF"]:::done
e5["Excel/Email"]
end
subgraph core["Core"]
f1["Eval System"]
f2["Pydantic Validation"]:::done
f3["Documentation"]:::done
f4["Adaptiveness"]
f5["Sample Agents"]
end
end
flowchart TB
%% Main Entity
User([User])
subgraph Expansion
direction LR
subgraph intel["Intelligence"]
g1["Guardrails"]
g2["Streaming Mode"]
g3["Image Generation"]
g4["Semantic Search"]
%% =========================================
%% EXTERNAL EVENT SOURCES
%% =========================================
subgraph ExtEventSource [External Event Source]
E_Sch["Schedulers"]
E_WH["Webhook"]
E_SSE["SSE"]
end
subgraph mem["Memory Iteration"]
h1["Message Model & Sessions"]
h2["Storage Migration"]
h3["Context Building"]
h4["Proactive Compaction"]
h5["Token Tracking"]
end
subgraph evt["Event System"]
i1["Event Bus for Nodes"]
end
subgraph cas["Coding Agent Support"]
j1["Claude Code"]
j2["Cursor"]
j3["Opencode"]
j4["Antigravity"]
j5["Codex CLI"]
end
subgraph plat["Platform"]
k1["JavaScript/TypeScript SDK"]
k2["Custom Tool Integrator"]
k3["Windows Support"]
end
subgraph dep["Deployment"]
l1["Self-Hosted"]
l2["Cloud Services"]
l3["CI/CD Pipeline"]
end
subgraph tmpl["Templates"]
m1["Sales Agent"]
m2["Marketing Agent"]
m3["Analytics Agent"]
m4["Training Agent"]
m5["Smart Form Agent"]
end
end
classDef done fill:#9e9e9e,color:#fff,stroke:#757575
%% =========================================
%% SYSTEM NODES
%% =========================================
subgraph EventLoopNode [Event Loop Node]
ELN_L["listener"]
ELN_SP["System Prompt<br/>(Task)"]
ELN_EL["Event loop"]
ELN_C["Conversation"]
end
subgraph WorkerBees [Worker Bees]
WB_C["Conversation"]
WB_SP["System prompt"]
subgraph Graph [Graph]
direction TB
N1["Node"] --> N2["Node"] --> N3["Node"]
N1 -.-> AN["Active Node"]
N2 -.-> AN
N3 -.-> AN
end
end
subgraph JudgeNode [Judge]
J_C["Criteria"]
J_P["Principles"]
J_EL["Event loop"] <--> J_S["Scheduler"]
end
subgraph QueenBee [Queen Bee]
QB_SP["System prompt"]
QB_EL["Event loop"]
QB_C["Conversation"]
end
subgraph Infra [Infra]
SA["Sub Agent"]
TR["Tool Registry"]
WTM["Write through Conversation Memory<br/>(Logs/RAM/Harddrive)"]
SM["Shared Memory<br/>(State/Harddrive)"]
EB["Event Bus<br/>(RAM)"]
CS["Credential Store<br/>(Harddrive/Cloud)"]
end
subgraph PC [PC]
B["Browser"]
CB["Codebase<br/>v 0.0.x ... v n.n.n"]
end
%% =========================================
%% CONNECTIONS & DATA FLOW
%% =========================================
%% External Event Routing
E_Sch --> ELN_L
E_WH --> ELN_L
E_SSE --> ELN_L
ELN_L -->|"triggers"| ELN_EL
%% User Interactions
User -->|"Talk"| WB_C
User -->|"Talk"| QB_C
User -->|"Read/Write Access"| CS
%% Inter-System Logic
ELN_C <-->|"Mirror"| WB_C
WB_C -->|"Focus"| AN
WorkerBees -->|"Inquire"| JudgeNode
JudgeNode -->|"Approve"| WorkerBees
%% Judge Alignments
J_C <-.->|"aligns"| WB_SP
J_P <-.->|"aligns"| QB_SP
%% Escalate path
J_EL -->|"Report (Escalate)"| QB_EL
%% Pub/Sub Logic
AN -->|"publish"| EB
EB -->|"subscribe"| QB_C
%% Infra and Process Spawning
ELN_EL -->|"Spawn"| SA
SA -->|"Inform"| ELN_EL
SA -->|"Starts"| B
B -->|"Report"| ELN_EL
TR -->|"Assigned"| EventLoopNode
CB -->|"Modify Worker Bee"| WorkerBees
%% =========================================
%% SHARED MEMORY & LOGS ACCESS
%% =========================================
%% Worker Bees Access
Graph <-->|"Read/Write"| WTM
Graph <-->|"Read/Write"| SM
%% Queen Bee Access
QB_C <-->|"Read/Write"| WTM
QB_EL <-->|"Read/Write"| SM
%% Credentials Access
CS -->|"Read Access"| QB_C
```
---
@@ -97,92 +126,97 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
## Phase 1: Foundation
### Backbone Architecture
- [ ] **Node-Based Architecture (Agent as a node)**
- [x] Object schema definition
- [x] Node wrapper SDK
- [x] Shared memory access
- [ ] Default monitoring hooks
- [x] Tool access layer
- [x] LLM integration layer (Natively supports all mainstream LLMs through LiteLLM)
- [x] Anthropic
- [x] OpenAI
- [x] Google
- [x] Object schema definition
- [x] Node wrapper SDK
- [x] Shared memory access
- [ ] Default monitoring hooks
- [x] Tool access layer
- [x] LLM integration layer (Natively supports all mainstream LLMs through LiteLLM)
- [x] Anthropic
- [x] OpenAI
- [x] Google
- [x] **Communication protocol between nodes**
- [x] **[Coding Agent] Goal Creation Session** (separate from coding session)
- [x] Instruction back and forth
- [x] Goal Object schema definition
- [x] Being able to generate the test cases
- [x] Test case validation for worker agent (Outcome driven)
- [x] Instruction back and forth
- [x] Goal Object schema definition
- [x] Being able to generate the test cases
- [x] Test case validation for worker agent (Outcome driven)
- [ ] **[Coding Agent] Worker Agent Creation**
- [x] Coding Agent tools
- [ ] Use Template Agent as a start
- [x] Use our MCP tools
- [x] Coding Agent tools
- [ ] Use Template Agent as a start
- [x] Use our MCP tools
- [ ] **[Worker Agent] Human-in-the-Loop**
- [x] Worker Agents request with questions and options
- [x] Callback Handler System to receive events throughout execution
- [x] Tool-Based Intervention Points (tool to pause execution and request human input)
- [x] Multiple entrypoint for different event source (e.g. Human input, webhook)
- [ ] Streaming Interface for Real-time Monitoring
- [x] Request State Management
- [x] Worker Agents request with questions and options
- [x] Callback Handler System to receive events throughout execution
- [x] Tool-Based Intervention Points (tool to pause execution and request human input)
- [x] Multiple entrypoint for different event source (e.g. Human input, webhook)
- [ ] Streaming Interface for Real-time Monitoring
- [x] Request State Management
### Credential Management
- [x] **Credentials Setup Process**
- [x] Install Credential MCP
- [x] Install Credential MCP
- [x] **Pluggable Credential Sources**
- [x] **Abstraction & Local Sources**
- [x] Introduce `CredentialSource` base class
- [x] Refactor existing logic into `EnvVarSource`
- [x] Implementation of Source Priority Chain mechanism
- [ ] Foundation unit tests
- [ ] **Enterprise Secret Managers**
- [x] `VaultSource` (HashiCorp Vault)
- [ ] `AWSSecretsSource` (AWS Secrets Manager)
- [ ] `AzureKeyVaultSource` (Azure Key Vault)
- [ ] Management of optional provider dependencies
- [ ] **Advanced Features**
- [x] Credential expiration and auto-refresh
- [ ] Audit logging for compliance/tracking
- [ ] Per-environment configuration support
- [ ] **Documentation & DX**
- [ ] Comprehensive source documentation
- [ ] Example configurations for all providers
- [x] **Integration as tools coverage**
- [x] Gsuite Tools
- [x] Social Media
- [ ] Twitter(X)
- [x] Github
- [ ] Instagram
- [ ] SAAS
- [ ] Hubspot
- [ ] Slack
- [ ] Teams
- [ ] Zoom
- [ ] Stripe
- [ ] Salesforce
- [x] **Abstraction & Local Sources**
- [x] Introduce `CredentialSource` base class
- [x] Refactor existing logic into `EnvVarSource`
- [x] Implementation of Source Priority Chain mechanism
- [ ] Foundation unit tests
- [ ] **Enterprise Secret Managers**
- [x] `VaultSource` (HashiCorp Vault)
- [ ] `AWSSecretsSource` (AWS Secrets Manager)
- [ ] `AzureKeyVaultSource` (Azure Key Vault)
- [ ] Management of optional provider dependencies
- [ ] **Advanced Features**
- [x] Credential expiration and auto-refresh
- [ ] Audit logging for compliance/tracking
- [ ] Per-environment configuration support
- [ ] **Documentation & DX**
- [ ] Comprehensive source documentation
- [ ] Example configurations for all providers
- [x] **Integration as tools coverage**
- [x] Gsuite Tools
- [x] Social Media
- [ ] Twitter(X)
- [x] Github
- [ ] Instagram
- [ ] SAAS
- [ ] Hubspot
- [ ] Slack
- [ ] Teams
- [ ] Zoom
- [ ] Stripe
- [ ] Salesforce
> [!IMPORTANT]
> **Community Contribution Wanted**: We appreciate help from the community to expand the "Integration as tools" capability. Leave an issue of the integration you want to support via Hive!
### Essential Tools
- [x] **File Use Tool Kit**
- [X] **Memory Tools**
- [x] STM Layer Tool (state-based short-term memory)
- [x] LTM Layer Tool (RLM - long-term memory)
- [x] **Memory Tools**
- [x] STM Layer Tool (state-based short-term memory)
- [x] LTM Layer Tool (RLM - long-term memory)
- [ ] **Infrastructure Tools**
- [x] Runtime Log Tool (logs for coding agent)
- [x] Web Search
- [x] Web Scraper
- [x] CSV tools
- [x] PDF tools
- [ ] Excel tools
- [ ] Email Tools
- [ ] Recipe for "Add your own tools"
- [x] Runtime Log Tool (logs for coding agent)
- [x] Web Search
- [x] Web Scraper
- [x] CSV tools
- [x] PDF tools
- [ ] Excel tools
- [ ] Email Tools
- [ ] Recipe for "Add your own tools"
### Memory & File System
- [x] DB for long-term persistent memory (Filesystem as durable scratchpad pattern)
- [x] Session Local memory isolation
### Eval System (Basic)
- [x] Test Driven - Run test case for all agent iteration
- [ ] Failure recording mechanism
- [ ] SDK for defining failure conditions
@@ -190,27 +224,31 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
- [ ] User-driven log analysis (OSS approach)
### Data Validation
- [x] Natively Support data validation of LLMs output with Pydantic
### Developer Experience
- [ ] **MVP Features**
- [ ] Debugging mode
- [ ] CLI tools for memory management
- [ ] CLI tools for credential management
- [ ] Debugging mode
- [ ] CLI tools for memory management
- [ ] CLI tools for credential management
- [ ] **MVP Resources & Documentation**
- [x] Quick start guide
- [x] Goal creation guide
- [x] Agent creation guide
- [x] GitHub Page setup
- [x] README with examples
- [x] Contributing guidelines
- [ ] Introduction Video
- [x] Quick start guide
- [x] Goal creation guide
- [x] Agent creation guide
- [x] GitHub Page setup
- [x] README with examples
- [x] Contributing guidelines
- [ ] Introduction Video
### Adaptiveness
- [ ] Runtime data feedback loop
- [ ] Instant Developer Feedback for improvement
### Sample Agents
- [ ] Knowledge Agent
- [ ] Blog Writer Agent
- [ ] SDR Agent
@@ -220,37 +258,42 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
## Phase 2: Expansion
### Basic Guardrails
- [ ] Support Basic Monitoring from Agent node SDK
- [ ] SDK guardrail implementation (in node)
- [ ] Guardrail type support (Determined Condition as Guardrails)
### Agent Capability
- [ ] Streaming mode support
- [ ] Image Generation support
- [ ] Take end user input Image and flatfile understand capability
### Event-loop For Nodes (Opencode-style)
- [ ] **Event bus**
### Memory System Iteration
- [ ] **Message Model & Session Management**
- [ ] Introduce `Message` class with structured content types
- [ ] Implement `Session` classes for conversation state
- [ ] Introduce `Message` class with structured content types
- [ ] Implement `Session` classes for conversation state
- [ ] **Storage Migration**
- [ ] Implement granular per-message file persistence (`/message/[agentID]/...`)
- [ ] Migrate from monolithic run storage
- [ ] Implement granular per-message file persistence (`/message/[agentID]/...`)
- [ ] Migrate from monolithic run storage
- [ ] **Context Building & Conversation Loop**
- [ ] Implement `Message.stream(sessionID)`
- [ ] Update `EventLoopNode.execute()` for full context building
- [ ] Implement `Message.toModelMessages()` conversion
- [ ] Implement `Message.stream(sessionID)`
- [ ] Update `EventLoopNode.execute()` for full context building
- [ ] Implement `Message.toModelMessages()` conversion
- [ ] **Proactive Compaction**
- [ ] Implement proactive overflow detection
- [ ] Develop backward-scanning pruning strategy (e.g., clearing old tool outputs)
- [ ] Implement proactive overflow detection
- [ ] Develop backward-scanning pruning strategy (e.g., clearing old tool outputs)
- [ ] **Enhanced Token Tracking**
- [ ] Extend `LLMResponse` to track reasoning and cache tokens
- [ ] Integrate granular token metrics into compaction logic
- [ ] Extend `LLMResponse` to track reasoning and cache tokens
- [ ] Integrate granular token metrics into compaction logic
### Coding Agent Support
- [ ] Claude Code
- [ ] Cursor
- [ ] Opencode
@@ -258,18 +301,21 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
- [ ] Codex CLI (in progress)
### File System Enhancement
- [ ] Semantic Search integration
- [ ] Interactive File System in product (frontend integration)
### More Worker Tools
- [ ] Custom Tool Integrator
- [ ] Integration as a tool (Credential Store & Support)
- [ ] **Core Agent Tools**
- [ ] Node Discovery Tool (find other agents in the graph)
- [ ] HITL Tool (pause execution for human approval)
- [ ] Wake-up Tool (resume agent tasks)
- [ ] Node Discovery Tool (find other agents in the graph)
- [ ] HITL Tool (pause execution for human approval)
- [ ] Wake-up Tool (resume agent tasks)
### Deployment (Self-Hosted)
- [ ] Worker agent docker container standardization
- [ ] Headless backend execution
- [ ] Exposed API for frontend attachment
@@ -277,19 +323,22 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
- [ ] Basic lifecycle APIs (Start, Stop, Pause, Resume)
### Deployment (Cloud)
- [ ] Cloud Service Options
- [ ] Support deployment to 3rd-party platforms
- [ ] Self-deploy + orchestrator connection
- [ ] **CI/CD Pipeline**
- [ ] Automated test execution
- [ ] Agent version control
- [ ] All tests must pass for deployment
- [ ] Automated test execution
- [ ] Agent version control
- [ ] All tests must pass for deployment
### Developer Experience Enhancement
- [ ] Tool usage documentation
- [ ] Discord Support Channel
### More Agent Templates
- [ ] GTM Sales Agent (workflow)
- [ ] GTM Marketing Agent (workflow)
- [ ] Analytics Agent
@@ -297,5 +346,6 @@ classDef done fill:#9e9e9e,color:#fff,stroke:#757575
- [ ] Smart Entry / Form Agent (self-evolution emphasis)
### Cross-Platform
- [ ] JavaScript / TypeScript Version SDK
- [ ] Better windows support
uv.lock
Generated
+15
View File
@@ -3269,6 +3269,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/81/0d/13d1d239a25cbfb19e740db83143e95c772a1fe10202dda4b76792b114dd/starlette-0.52.1-py3-none-any.whl", hash = "sha256:0029d43eb3d273bc4f83a08720b4912ea4b071087a3b48db01b7c839f7954d74", size = 74272, upload-time = "2026-01-18T13:34:09.188Z" },
]
[[package]]
name = "stripe"
version = "14.3.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "requests" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/49/67/8a38222a57fc2ba359c4dcb66528d94c00d803c7fde8f8d8470ad6bdccbb/stripe-14.3.0.tar.gz", hash = "sha256:4c76137d741bd43e8bb433a596c198ca20f4cdf17a8fe04604faf37c74b01978", size = 1463618, upload-time = "2026-01-28T21:20:29.856Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/9e/4b/0b7d5920f2be5e42d72bdfc44a9fae57b422668bfc8dacdf2f74886f6daa/stripe-14.3.0-py3-none-any.whl", hash = "sha256:3e36b68b256c8970e99b703e195d947e2a2919095758788c7074ac4485ac255e", size = 2106980, upload-time = "2026-01-28T21:20:27.566Z" },
]
[[package]]
name = "textual"
version = "7.5.0"
@@ -3386,6 +3399,7 @@ dependencies = [
{ name = "pypdf" },
{ name = "python-dotenv" },
{ name = "resend" },
{ name = "stripe" },
]
[package.optional-dependencies]
@@ -3456,6 +3470,7 @@ requires-dist = [
{ name = "resend", specifier = ">=2.0.0" },
{ name = "restrictedpython", marker = "extra == 'all'", specifier = ">=7.0" },
{ name = "restrictedpython", marker = "extra == 'sandbox'", specifier = ">=7.0" },
{ name = "stripe", specifier = ">=14.3.0" },
]
provides-extras = ["dev", "sandbox", "ocr", "excel", "sql", "bigquery", "all"]