ayder-cli 1.0__tar.gz → 1.1.0__tar.gz

{ayder_cli-1.0 → ayder_cli-1.1.0}/.gitignore

@@ -17,6 +17,9 @@ htmlcov/
 # macOS files
 .DS_Store
 
+# Git worktrees
+.worktrees/
+
 # Virtual environments
 .venv
 TODO

{ayder_cli-1.0 → ayder_cli-1.1.0}/AGENTS.md

@@ -61,16 +61,26 @@ ayder-cli/
 │   │   ├── context.py          # ProjectContext (path sandboxing)
 │   │   └── result.py           # ToolSuccess/ToolError types
 │   │
+│   ├── agents/                 # Multi-agent system
+│   │   ├── __init__.py         # Package exports
+│   │   ├── callbacks.py        # AgentCallbacks (ChatCallbacks for agents)
+│   │   ├── config.py           # AgentConfig (Pydantic model)
+│   │   ├── registry.py         # AgentRegistry (lifecycle management)
+│   │   ├── runner.py           # AgentRunner (isolated ChatLoop execution)
+│   │   ├── summary.py          # AgentSummary (structured result)
+│   │   └── tool.py             # call_agent tool definition + handler
+│   │
 │   ├── application/            # Shared application layer (CLI + TUI)
 │   │   ├── execution_policy.py         # ExecutionPolicy, PermissionDeniedError
 │   │   ├── message_contract.py         # LLM message format contracts
-│   │   ├── runtime_factory.py          # create_runtime() composition root
+│   │   ├── runtime_factory.py          # create_runtime() + create_agent_runtime()
 │   │   ├── temporal_contract.py        # Temporal workflow contracts
 │   │   ├── temporal_metadata.py        # Temporal metadata types
 │   │   └── validation.py              # ValidationAuthority, SchemaValidator
 │   │
-│   ├── loops/                  # Shared agent loop base
+│   ├── loops/                  # Shared agent loop + base classes
 │   │   ├── base.py             # AgentLoopBase (iteration, checkpoint, routing)
+│   │   ├── chat_loop.py        # ChatLoop (async LLM + tool execution loop)
 │   │   └── config.py           # Shared LoopConfig dataclass
 │   │
 │   ├── providers/              # LLM provider implementations
@@ -108,12 +118,15 @@ ayder-cli/
 │   │       ├── utils_tools.py  # manage_environment_vars
 │   │       ├── web.py          # fetch_web
 │   │       ├── dbs_tool.py     # DBS RAG API tool
-│   │       └── temporal.py     # Temporal workflow tool
+│   │       ├── temporal.py     # Temporal workflow tool
+│   │       ├── tasks.py        # Task management (.ayder/tasks/)
+│   │       ├── notes.py        # Note management (.ayder/notes/)
+│   │       └── memory.py       # Cross-session memory storage
 │   │
 │   ├── tui/                    # Textual TUI (main interface)
 │   │   ├── __init__.py         # run_tui() entry point
 │   │   ├── app.py              # AyderApp main application
-│   │   ├── chat_loop.py        # TUI async chat loop (TuiChatLoop)
+│   │   ├── chat_loop.py        # Backward-compat re-exports → loops/chat_loop.py
 │   │   ├── commands.py         # Slash command handlers (19 commands)
 │   │   ├── helpers.py          # TUI helper functions
 │   │   ├── adapter.py          # TUIInteractionSink (verbose debug)
@@ -128,12 +141,9 @@ ayder-cli/
 │   │   ├── claude.py           # Claude theme CSS
 │   │   └── original.py         # Original theme CSS
 │   │
-│   ├── memory.py               # Cross-session memory storage
-│   ├── notes.py                # Note management (.ayder/notes/)
 │   ├── parser.py               # XML/JSON tool call parser
 │   ├── process_manager.py      # Background process management
 │   ├── prompts.py              # System prompt templates
-│   ├── tasks.py                # Task management (.ayder/tasks/)
 │   └── ui.py                   # Rich terminal UI helpers
 │
 ├── tests/                      # Test suite (998+ tests)
@@ -158,7 +168,8 @@ ayder-cli/
 | `cli.py` | Entry point, argument parsing |
 | `tui/app.py` | Main TUI application (AyderApp) |
 | `tui/commands.py` | Slash command handlers (19 commands) |
-| `tui/chat_loop.py` | Async LLM loop for TUI (TuiChatLoop + TuiCallbacks protocol) |
+| `loops/chat_loop.py` | Async LLM + tool execution loop (ChatLoop + ChatCallbacks protocol) |
+| `tui/chat_loop.py` | Backward-compat re-exports (TuiChatLoop → ChatLoop aliases) |
 | `cli_runner.py` | CLI command execution + sync agent loop |
 | `application/runtime_factory.py` | `create_runtime()` — single composition root for CLI + TUI |
 | `application/execution_policy.py` | Shared permission + tool execution policy |

{ayder_cli-1.0 → ayder_cli-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ayder-cli
-Version: 1.0
+Version: 1.1.0
 Summary: AI agent for any LLMs
 Project-URL: Homepage, https://github.com/ayder/ayder-cli
 Project-URL: Repository, https://github.com/ayder/ayder-cli.git
@@ -54,6 +54,7 @@ Most AI coding assistants require cloud APIs, subscriptions, or heavy IDE plugin
 - **7 native drivers** -- Ollama, OpenAI, Anthropic, Gemini, DeepSeek, Qwen (DashScope), and GLM (ZhipuAI). Each driver guarantees native tool calling and streaming support.
 - **Fully local or cloud** -- run locally with Ollama, or connect to any cloud provider.
 - **Agentic workflow** -- the LLM reads files, edits code, runs shell commands, and iterates autonomously with configurable iteration limits per message.
+- **Multi-agent** -- define specialized sub-agents in `config.toml`. Each agent runs independently with its own LLM, model, and context. Results are injected back into the main conversation when complete.
 - **Textual TUI** -- an inline terminal interface with chat view, tool panel, thinking block toggle, slash command auto-completion, permission toggles, and tool confirmation modals with diff previews.
 - **Minimal dependencies** -- OpenAI SDK, Rich, and Textual. Other provider SDKs are optional.
 
@@ -210,6 +211,7 @@ max_output_tokens = 4096      # Max tokens in LLM response
 max_history_messages = 30     # Messages kept in history
 prompt = "STANDARD"           # System prompt tier: MINIMAL, STANDARD, EXTENDED
 tool_tags = ["core", "metadata"]  # Enabled tool tags (see /plugin)
+agent_timeout = 300           # Seconds before a background agent is cancelled
 
 [logging]
 file_enabled = true
@@ -383,6 +385,9 @@ For small local models (7B-14B), lower `max_context_tokens` to match the model's
 | `/load-memory` | Load memory and restore context |
 | `/archive-completed-tasks` | Move completed tasks to `.ayder/task_archive/` |
 | `/temporal` | Start/status Temporal queue worker |
+| `/agent list` | List configured agents and their current status |
+| `/agent <name> <task>` | Dispatch an agent to run a task in the background |
+| `/agent cancel <name>` | Cancel a running agent |
 
 ### Logging
 
@@ -488,6 +493,144 @@ The tool system:
 | **Web** | `fetch_web` |
 | **DBS** | `dbs_tool` (RAG API for DBS-related queries) |
 | **Workflow** | `temporal_workflow` |
+| **Agents** | `call_agent` (dispatch a named agent to run a task in the background) |
+
+## Multi-Agent System
+
+ayder-cli supports user-defined **specialized agents**: each agent is an independent AI loop with its own LLM provider, model, system prompt, and context window. Agents run as background tasks — they never block the main conversation and their results are automatically injected back when they complete.
+
+### How Agents Work
+
+```
+Main LLM (your conversation)
+    │
+    ├─ calls `call_agent` tool  ─────────────────────────────────┐
+    │   OR you type `/agent <name> <task>`                       │
+    │                                                            ▼
+    │                                            AgentRunner (background asyncio task)
+    │                                            ┌─────────────────────────────────┐
+    │                                            │  Isolated ChatLoop              │
+    │                                            │  • own LLM provider + model     │
+    │                                            │  • own context window           │
+    │                                            │  • own ToolRegistry             │
+    │                                            │  • auto-approves all tools      │
+    │                                            │  • produces <agent-summary>     │
+    │                                            └────────────────┬────────────────┘
+    │                                                             │ completes
+    │                                                             ▼
+    │                                            AgentSummary → _summary_queue
+    │
+    ▼ (next main LLM turn)
+pre_iteration_hook drains queue
+    └─ injects AgentSummary as system message into main context
+         └─ main LLM sees: "[Agent 'reviewer' completed] FINDINGS: ..."
+```
+
+Key properties:
+- **Separate context** — agents have no access to the main conversation history. They receive only their system prompt and the task description.
+- **Non-blocking** — dispatching an agent returns immediately. Both `/agent` and `call_agent` are fire-and-forget.
+- **Concurrent** — multiple agents can run simultaneously, each in its own async task.
+- **Summary injection** — when an agent finishes, its structured `<agent-summary>` block is injected as a system message into the main LLM's context at the start of the next turn.
+- **Timeout** — agents are automatically cancelled after `agent_timeout` seconds (default: 300).
+
+### Configuring Agents
+
+Add `[agents.<name>]` sections to your `~/.ayder/config.toml`:
+
+```toml
+[app]
+provider = "ollama"
+agent_timeout = 300           # Global timeout for all agents (seconds)
+
+[llm.ollama]
+driver = "ollama"
+model = "qwen3-coder:latest"
+num_ctx = 65536
+
+[llm.anthropic]
+driver = "anthropic"
+api_key = "sk-ant-..."
+model = "claude-sonnet-4-5-20250929"
+num_ctx = 200000
+
+# --- Agents ---
+
+[agents.code-reviewer]
+system_prompt = """You are a senior code reviewer. Review the code for bugs,
+security issues, and style violations. Be concise and actionable."""
+provider = "anthropic"         # Optional: use a different provider than main
+model = "claude-sonnet-4-5-20250929"  # Optional: use a different model
+
+[agents.test-writer]
+system_prompt = """You are a test engineer. Write comprehensive pytest tests
+for the code provided. Follow existing test patterns in the codebase."""
+# No provider/model → inherits from [app] provider
+
+[agents.doc-writer]
+system_prompt = """You are a technical writer. Write clear, concise docstrings
+and inline comments for the code provided."""
+```
+
+Each agent field:
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `system_prompt` | Yes | The agent's role and instructions |
+| `provider` | No | LLM provider profile name (inherits from `[app]` if omitted) |
+| `model` | No | Model name override (inherits from provider profile if omitted) |
+
+### Using Agents
+
+**From the TUI (slash commands):**
+
+```
+# List configured agents and their status
+/agent list
+
+# Dispatch an agent to review your authentication module
+/agent code-reviewer Review src/auth.py for security issues
+
+# Dispatch the test writer for a specific module
+/agent test-writer Write tests for src/api/users.py
+
+# Cancel a running agent
+/agent cancel code-reviewer
+```
+
+**Via the main LLM (automatic):**
+
+When agents are configured, the main LLM is told about them via its system prompt and can call `call_agent` autonomously:
+
+```
+You: Review the authentication module and write tests for it.
+
+LLM: I'll dispatch two agents to handle this in parallel.
+     [calls call_agent: name="code-reviewer", task="Review src/auth.py..."]
+     [calls call_agent: name="test-writer", task="Write tests for src/auth.py..."]
+
+     Both agents are running in the background. I'll incorporate
+     their findings when they complete.
+
+... (agents run independently) ...
+
+LLM: [next turn, after agents complete]
+     The code-reviewer found 2 issues: ...
+     The test-writer produced 8 new tests: ...
+```
+
+**Agent summary format:**
+
+Agents end their final response with a structured block that ayder-cli parses:
+
+```
+<agent-summary>
+FINDINGS: Found a SQL injection vulnerability in login() and missing input validation in register()
+FILES_CHANGED: none
+RECOMMENDATIONS: Parameterize all DB queries; add Pydantic validators to all endpoints
+</agent-summary>
+```
+
+This summary is injected into the main LLM's context as a system message so the main agent can act on it, summarize it for you, or chain it to further work.
 
 ## License
 

{ayder_cli-1.0 → ayder_cli-1.1.0}/README.md

@@ -23,6 +23,7 @@ Most AI coding assistants require cloud APIs, subscriptions, or heavy IDE plugin
 - **7 native drivers** -- Ollama, OpenAI, Anthropic, Gemini, DeepSeek, Qwen (DashScope), and GLM (ZhipuAI). Each driver guarantees native tool calling and streaming support.
 - **Fully local or cloud** -- run locally with Ollama, or connect to any cloud provider.
 - **Agentic workflow** -- the LLM reads files, edits code, runs shell commands, and iterates autonomously with configurable iteration limits per message.
+- **Multi-agent** -- define specialized sub-agents in `config.toml`. Each agent runs independently with its own LLM, model, and context. Results are injected back into the main conversation when complete.
 - **Textual TUI** -- an inline terminal interface with chat view, tool panel, thinking block toggle, slash command auto-completion, permission toggles, and tool confirmation modals with diff previews.
 - **Minimal dependencies** -- OpenAI SDK, Rich, and Textual. Other provider SDKs are optional.
 
@@ -179,6 +180,7 @@ max_output_tokens = 4096      # Max tokens in LLM response
 max_history_messages = 30     # Messages kept in history
 prompt = "STANDARD"           # System prompt tier: MINIMAL, STANDARD, EXTENDED
 tool_tags = ["core", "metadata"]  # Enabled tool tags (see /plugin)
+agent_timeout = 300           # Seconds before a background agent is cancelled
 
 [logging]
 file_enabled = true
@@ -352,6 +354,9 @@ For small local models (7B-14B), lower `max_context_tokens` to match the model's
 | `/load-memory` | Load memory and restore context |
 | `/archive-completed-tasks` | Move completed tasks to `.ayder/task_archive/` |
 | `/temporal` | Start/status Temporal queue worker |
+| `/agent list` | List configured agents and their current status |
+| `/agent <name> <task>` | Dispatch an agent to run a task in the background |
+| `/agent cancel <name>` | Cancel a running agent |
 
 ### Logging
 
@@ -457,6 +462,144 @@ The tool system:
 | **Web** | `fetch_web` |
 | **DBS** | `dbs_tool` (RAG API for DBS-related queries) |
 | **Workflow** | `temporal_workflow` |
+| **Agents** | `call_agent` (dispatch a named agent to run a task in the background) |
+
+## Multi-Agent System
+
+ayder-cli supports user-defined **specialized agents**: each agent is an independent AI loop with its own LLM provider, model, system prompt, and context window. Agents run as background tasks — they never block the main conversation and their results are automatically injected back when they complete.
+
+### How Agents Work
+
+```
+Main LLM (your conversation)
+    │
+    ├─ calls `call_agent` tool  ─────────────────────────────────┐
+    │   OR you type `/agent <name> <task>`                       │
+    │                                                            ▼
+    │                                            AgentRunner (background asyncio task)
+    │                                            ┌─────────────────────────────────┐
+    │                                            │  Isolated ChatLoop              │
+    │                                            │  • own LLM provider + model     │
+    │                                            │  • own context window           │
+    │                                            │  • own ToolRegistry             │
+    │                                            │  • auto-approves all tools      │
+    │                                            │  • produces <agent-summary>     │
+    │                                            └────────────────┬────────────────┘
+    │                                                             │ completes
+    │                                                             ▼
+    │                                            AgentSummary → _summary_queue
+    │
+    ▼ (next main LLM turn)
+pre_iteration_hook drains queue
+    └─ injects AgentSummary as system message into main context
+         └─ main LLM sees: "[Agent 'reviewer' completed] FINDINGS: ..."
+```
+
+Key properties:
+- **Separate context** — agents have no access to the main conversation history. They receive only their system prompt and the task description.
+- **Non-blocking** — dispatching an agent returns immediately. Both `/agent` and `call_agent` are fire-and-forget.
+- **Concurrent** — multiple agents can run simultaneously, each in its own async task.
+- **Summary injection** — when an agent finishes, its structured `<agent-summary>` block is injected as a system message into the main LLM's context at the start of the next turn.
+- **Timeout** — agents are automatically cancelled after `agent_timeout` seconds (default: 300).
+
+### Configuring Agents
+
+Add `[agents.<name>]` sections to your `~/.ayder/config.toml`:
+
+```toml
+[app]
+provider = "ollama"
+agent_timeout = 300           # Global timeout for all agents (seconds)
+
+[llm.ollama]
+driver = "ollama"
+model = "qwen3-coder:latest"
+num_ctx = 65536
+
+[llm.anthropic]
+driver = "anthropic"
+api_key = "sk-ant-..."
+model = "claude-sonnet-4-5-20250929"
+num_ctx = 200000
+
+# --- Agents ---
+
+[agents.code-reviewer]
+system_prompt = """You are a senior code reviewer. Review the code for bugs,
+security issues, and style violations. Be concise and actionable."""
+provider = "anthropic"         # Optional: use a different provider than main
+model = "claude-sonnet-4-5-20250929"  # Optional: use a different model
+
+[agents.test-writer]
+system_prompt = """You are a test engineer. Write comprehensive pytest tests
+for the code provided. Follow existing test patterns in the codebase."""
+# No provider/model → inherits from [app] provider
+
+[agents.doc-writer]
+system_prompt = """You are a technical writer. Write clear, concise docstrings
+and inline comments for the code provided."""
+```
+
+Each agent field:
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `system_prompt` | Yes | The agent's role and instructions |
+| `provider` | No | LLM provider profile name (inherits from `[app]` if omitted) |
+| `model` | No | Model name override (inherits from provider profile if omitted) |
+
+### Using Agents
+
+**From the TUI (slash commands):**
+
+```
+# List configured agents and their status
+/agent list
+
+# Dispatch an agent to review your authentication module
+/agent code-reviewer Review src/auth.py for security issues
+
+# Dispatch the test writer for a specific module
+/agent test-writer Write tests for src/api/users.py
+
+# Cancel a running agent
+/agent cancel code-reviewer
+```
+
+**Via the main LLM (automatic):**
+
+When agents are configured, the main LLM is told about them via its system prompt and can call `call_agent` autonomously:
+
+```
+You: Review the authentication module and write tests for it.
+
+LLM: I'll dispatch two agents to handle this in parallel.
+     [calls call_agent: name="code-reviewer", task="Review src/auth.py..."]
+     [calls call_agent: name="test-writer", task="Write tests for src/auth.py..."]
+
+     Both agents are running in the background. I'll incorporate
+     their findings when they complete.
+
+... (agents run independently) ...
+
+LLM: [next turn, after agents complete]
+     The code-reviewer found 2 issues: ...
+     The test-writer produced 8 new tests: ...
+```
+
+**Agent summary format:**
+
+Agents end their final response with a structured block that ayder-cli parses:
+
+```
+<agent-summary>
+FINDINGS: Found a SQL injection vulnerability in login() and missing input validation in register()
+FILES_CHANGED: none
+RECOMMENDATIONS: Parameterize all DB queries; add Pydantic validators to all endpoints
+</agent-summary>
+```
+
+This summary is injected into the main LLM's context as a system message so the main agent can act on it, summarize it for you, or chain it to further work.
 
 ## License
 

{ayder_cli-1.0 → ayder_cli-1.1.0}/docs/PROJECT_STRUCTURE.md

@@ -50,7 +50,6 @@ ayder-cli is an AI agent chat client with a modular, layered architecture:
 │  │            Shared Application Modules                     │  │
 │  │  application/execution_policy.py   (ExecutionPolicy)      │  │
 │  │  application/validation.py         (ValidationAuthority)  │  │
-│  │  application/checkpoint_orchestrator.py (orchestration)   │  │
 │  │  application/runtime_factory.py    (create_runtime())     │  │
 │  │  loops/base.py                     (AgentLoopBase)        │  │
 │  └───────────────────────────────────────────────────────────┘  │
@@ -92,7 +91,7 @@ ayder-cli is an AI agent chat client with a modular, layered architecture:
 1. **Layered Architecture**: Clear separation between entry → app → service → core → tools
 2. **Protocol-Based**: `TuiCallbacks` protocol decouples TUI from business logic; `InteractionSink`/`ConfirmationPolicy` decouple `ToolExecutor` from UI
 3. **Single Composition Root**: `application/runtime_factory.create_runtime()` assembles all dependencies — no duplicated wiring between CLI and TUI
-4. **Shared Loop Base**: `AgentLoopBase` (in `loops/base.py`) owns iteration counting, checkpoint trigger detection, and tool-call routing; both `ChatLoop` and `TuiChatLoop` extend it
+4. **Shared Loop Base**: `AgentLoopBase` (in `loops/base.py`) owns tool-call routing and escalation detection; `ChatLoop` (in `loops/chat_loop.py`) extends it with the full async LLM + tool execution loop
 5. **Single Execution Path**: `ExecutionPolicy.execute_with_registry()` is the sole tool execution entry point; validation → permission → execute, no inline policy in loop code
 6. **Single Validation Path**: `ValidationAuthority → SchemaValidator` is the only validation stage; schema derived from live `TOOL_DEFINITIONS` registry (no hardcoded lists)
 7. **Sandboxed Paths**: All file operations go through `ProjectContext` for security
@@ -158,7 +157,27 @@ cli.py:main()
 | `cli.py` | Entry point, argument parsing | `main()`, `create_parser()` |
 | `client.py` | LLM client and chat session | `ChatSession`, `Agent`, `call_llm_async()` |
 | `cli_runner.py` | Command execution | `CommandRunner`, `TaskRunner`, `run_command()` |
-| `chat_loop.py` | Sync CLI agent loop | `ChatLoop`, `LoopConfig`, `ToolCallHandler` |
+
+
+### Agent System Modules (`agents/`)
+
+| Module | Purpose |
+|--------|---------|
+| `agents/config.py` | `AgentConfig` Pydantic model for `[agents.*]` TOML sections |
+| `agents/summary.py` | `AgentSummary` dataclass — structured result of agent runs |
+| `agents/callbacks.py` | `AgentCallbacks` — `ChatCallbacks` for autonomous agents |
+| `agents/runner.py` | `AgentRunner` — wraps one `ChatLoop` per agent dispatch |
+| `agents/registry.py` | `AgentRegistry` — dispatch, cancel, status, capability prompts |
+| `agents/tool.py` | `call_agent` tool definition + handler factory |
+
+**Agent dispatch flow (Approach A — all non-blocking):**
+1. Config parsed → `AgentConfig` objects in `Config.agents`
+2. `AyderApp.__init__` creates `AgentRegistry` if agents configured
+3. LLM calls `call_agent` tool → `registry.dispatch()` (sync, fire-and-forget)
+4. User runs `/agent <name> <task>` → same `registry.dispatch()`
+5. Agent runs `ChatLoop` with isolated runtime + `AgentCallbacks` in background
+6. Summary parsed from `<agent-summary>` block → `AgentSummary` → `_summary_queue`
+7. `pre_iteration_hook` drains queue → injects summaries as system messages
 
 ### Shared Application Modules (`application/`)
 
@@ -166,15 +185,14 @@ cli.py:main()
 |--------|---------|----------------------|
 | `application/execution_policy.py` | Shared tool permission + execution policy | `ExecutionPolicy`, `PermissionDeniedError`, `ToolRequest`, `ConfirmationRequirement` |
 | `application/validation.py` | Single validation path (schema only) | `ValidationAuthority`, `SchemaValidator`, `ToolRequest` |
-| `application/checkpoint_orchestrator.py` | Shared checkpoint orchestration | `CheckpointOrchestrator`, `CheckpointTrigger`, `RuntimeContext`, `EngineState` |
-| `application/runtime_factory.py` | Single composition root | `create_runtime()`, `RuntimeComponents` |
+| `application/runtime_factory.py` | Single composition root | `create_runtime()`, `create_agent_runtime()`, `RuntimeComponents` |
 | `application/message_contract.py` | LLM message format contracts | DTOs for message interchange |
 
 ### Shared Loop Modules (`loops/`)
 
 | Module | Purpose | Key Classes/Functions |
 |--------|---------|----------------------|
-| `loops/base.py` | Shared agent loop base class | `AgentLoopBase` — iteration, checkpoint, tool routing, escalation |
+| `loops/base.py` | Shared agent loop base class | `AgentLoopBase` — iteration, tool routing, escalation |
 | `loops/config.py` | Shared loop configuration | `LoopConfig` dataclass |
 
 ### TUI Modules (Textual-based)
@@ -182,7 +200,7 @@ cli.py:main()
 | Module | Purpose | Key Classes/Functions |
 |--------|---------|----------------------|
 | `tui/app.py` | Main TUI application | `AyderApp`, `AppCallbacks` |
-| `tui/chat_loop.py` | TUI chat loop logic | `TuiChatLoop`, `TuiLoopConfig` |
+| `tui/chat_loop.py` | Backward-compat re-exports | `TuiChatLoop` → `ChatLoop`, `TuiLoopConfig` → `ChatLoopConfig` |
 | `tui/commands.py` | Slash command handlers | `COMMAND_MAP`, `handle_*()` |
 | `tui/widgets.py` | Custom widgets | `ChatView`, `ToolPanel`, `CLIInputBar` |
 | `tui/screens.py` | Modal screens | `CLIConfirmScreen`, `CLISelectScreen` |
@@ -216,10 +234,6 @@ cli.py:main()
 
 | Module | Purpose | Key Classes/Functions |
 |--------|---------|----------------------|
-| `tasks.py` | Task management | `list_tasks()`, `show_task()` |
-| `memory.py` | Cross-session memory | `MemoryManager`, `save_memory()`, `load_memory()` |
-| `notes.py` | Note creation | `create_note()` |
-| `checkpoint_manager.py` | Memory checkpoints | `CheckpointManager` |
 | `process_manager.py` | Background processes | `ProcessManager`, `run_background_process()` |
 | `prompts.py` | System prompts | `SYSTEM_PROMPT`, `PLANNING_PROMPT_TEMPLATE` |
 | `parser.py` | XML parsing | `parse_custom_tool_calls()` |
@@ -289,7 +303,7 @@ User Input → CLIInputBar
 
 ### TuiCallbacks Protocol
 
-The `TuiCallbacks` protocol in `tui/chat_loop.py` decouples `TuiChatLoop` from all UI concerns:
+The `ChatCallbacks` protocol in `loops/chat_loop.py` (aliased as `TuiCallbacks` in `tui/chat_loop.py`) decouples `ChatLoop` from all UI concerns:
 
 ```python
 @runtime_checkable
@@ -386,8 +400,7 @@ Use `TYPE_CHECKING` for type-only imports:
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from ayder_cli.memory import MemoryManager
-    from ayder_cli.checkpoint_manager import CheckpointManager
+    from ayder_cli.core.context import ProjectContext
 ```
 
 ### Protocol-Based Imports
@@ -395,10 +408,10 @@ if TYPE_CHECKING:
 The TUI uses protocols to avoid circular imports:
 
 ```python
-# tui/chat_loop.py
+# loops/chat_loop.py (aliased as TuiCallbacks in tui/chat_loop.py)
 from typing import Protocol
 
-class TuiCallbacks(Protocol):
+class ChatCallbacks(Protocol):
     ...
 
 # tui/app.py
@@ -445,7 +458,7 @@ registry.execute("read_file", {"file_path": "main.py"})
 ## File Organization Tips
 
 1. **New Tools**: Create `tools/builtins/<domain>_definitions.py` with a `TOOL_DEFINITIONS` tuple + implement in `tools/builtins/<domain>.py`. Auto-discovery handles the rest — no edits to `definition.py` needed.
-2. **New Application-Layer Shared Logic**: Add to `application/` and import from both `chat_loop.py` and `tui/chat_loop.py`.
+2. **New Application-Layer Shared Logic**: Add to `application/` and import from `loops/chat_loop.py`.
 3. **New TUI Commands**: Add to `tui/commands.py`, add to `COMMAND_MAP`.
 4. **New Widgets**: Add to `tui/widgets.py`, import in `tui/app.py`.
 5. **New Screens**: Add to `tui/screens.py`, push via `app.push_screen()`.
@@ -482,12 +495,11 @@ It exposes key components like AyderApp, widgets (ChatView, ToolPanel), and scre
 AyderApp is the main Textual application implementing a chat-style interface:
 - **Layout**: Banner, ChatView, ToolPanel, ActivityBar, CLIInputBar, StatusBar
 - **Keybindings**: Ctrl+Q (quit), Ctrl+C/X (cancel), Ctrl+L (clear), Ctrl+O (toggle tools)
-- **Features**: 
+- **Features**:
   - Async processing with worker threads
   - Tool confirmation with diff previews
   - Activity animations and status updates
   - Safe mode with middleware checks
-  - Memory checkpoint system integration
 - **Architecture**: Uses AppCallbacks to implement TuiCallbacks protocol, decoupling business logic from UI
 
 The application manages:
@@ -495,14 +507,13 @@ The application manages:
 - Tool registry initialization with middleware
 - System prompt construction with project structure
 - Process manager for background operations
-- Checkpoint and memory managers
 
-### TUI Chat Loop Summary (src/ayder_cli/tui/chat_loop.py)
+### Chat Loop Summary (src/ayder_cli/loops/chat_loop.py)
 
-`TuiChatLoop` (extends `AgentLoopBase`) implements the core async agentic process:
+`ChatLoop` (extends `AgentLoopBase`) implements the core async agentic process:
 - Handles repeated LLM calls with tool execution until completion
 - Supports multiple tool call formats: OpenAI native (`tool_calls`), XML custom, JSON fallback
-- Manages iteration counting via `AgentLoopBase._increment_iteration()` with checkpoint system
+- Manages iteration counting via `AgentLoopBase._increment_iteration()`
 - Communicates with UI exclusively through `TuiCallbacks` protocol (no Textual imports)
 - Extracts and emits `<think>` blocks separately from display content
 
@@ -510,7 +521,6 @@ Key features:
 - Auto-approved tools run in parallel (`asyncio.gather`); confirmation-required tools run sequentially
 - Confirmation gate applies to **both** OpenAI-format and XML/JSON custom tool calls
 - `ExecutionPolicy.execute_with_registry()` is the single execution entry (validate → permission → execute)
-- Memory checkpoint creation/restore to prevent context-window overflow
 - Token usage tracking and iteration limiting
 - Graceful cancellation via `is_cancelled()`
 
@@ -579,10 +589,9 @@ Schema-driven tool definitions with auto-discovery:
 
 ### Phase — Shared Agent Loop Base (`loops/base.py`)
 
-`AgentLoopBase` extracted to `loops/base.py`. Both `ChatLoop` and `TuiChatLoop` extend it:
+`AgentLoopBase` extracted to `loops/base.py`. `ChatLoop` (in `loops/chat_loop.py`) extends it:
 
 - `_increment_iteration()` / `_reset_iterations()` — shared iteration counting
-- `_should_trigger_checkpoint()` — delegates to `CheckpointTrigger`
 - `_route_tool_calls()` — shared OpenAI / XML / JSON / none routing logic
 - `_is_escalation()` — shared escalation detection
 
@@ -596,7 +605,7 @@ Schema-driven tool definitions with auto-discovery:
 
 | Bug | Fix |
 |-----|-----|
-| Double `on_thinking_stop()` on LLM exception | Removed from `except` blocks in `run()` and `_handle_checkpoint()`; kept only in `finally` |
+| Double `on_thinking_stop()` on LLM exception | Removed from `except` blocks in `run()`; kept only in `finally` |
 | Stale loop variable in `_discover_definitions()` | Collect `(definition, source_module)` tuples; unpack in duplicate-check loop |
 | XML tool calls bypass confirmation gate | `_execute_custom_tool_calls()` now calls `_tool_needs_confirmation()` before `execute_with_registry()` |
 | Silent post-execute callback failure | Added `logger.warning()` in `registry.py` post-execute exception handler |

{ayder_cli-1.0 → ayder_cli-1.1.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ayder-cli"
-version = "1.0"
+version = "1.1.0"
 description = "AI agent for any LLMs"
 readme = "README.md"
 requires-python = ">=3.12"

ayder_cli-1.1.0/src/ayder_cli/agents/__init__.py

@@ -0,0 +1,8 @@
+"""Multi-agent system: config, registry, runner, and tool."""
+
+from ayder_cli.agents.config import AgentConfig
+from ayder_cli.agents.summary import AgentSummary
+from ayder_cli.agents.runner import AgentRunner
+from ayder_cli.agents.registry import AgentRegistry
+
+__all__ = ["AgentConfig", "AgentSummary", "AgentRunner", "AgentRegistry"]