ayder-cli 1.6.9__tar.gz → 1.8.3__tar.gz

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ayder-cli
-Version: 1.6.9
+Version: 1.8.3
 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
@@ -19,7 +19,7 @@ Requires-Dist: google-genai
 Requires-Dist: httpx
 Requires-Dist: libcst>=1.0.0
 Requires-Dist: loguru
-Requires-Dist: ollama>=0.6.1
+Requires-Dist: ollama>=0.6.2
 Requires-Dist: openai
 Requires-Dist: python-dotenv>=1.0.0
 Requires-Dist: rich>=13.0.0
@@ -54,39 +54,11 @@ Most AI coding assistants require cloud APIs, subscriptions, or heavy IDE plugin
 - **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.
-
-### Tested Providers with Models
-
-| Provider | Location | Model |
-| -------- | -------- | ----- |
-| ollama | Cloud | deepseek-v3.2:cloud |
-| ollama | Cloud | gemini-3-pro-preview:latest |
-| ollama | Local | glm-4.7-flash:latest |
-| ollama | Cloud | glm-4.7:cloud |
-| ollama | Cloud | glm-5:cloud |
-| ollama | Local | glm-ocr:latest |
-| ollama | Cloud | gpt-oss:120b-cloud |
-| ollama | Cloud | kimi-k2.5:cloud |
-| ollama | Cloud | minimax-m2.5:cloud |
-| ollama | Local | ministral-3:14b |
-| ollama | Cloud | qwen3-coder-next:cloud |
-| ollama | Cloud | qwen3-coder:480b-cloud |
-| ollama | Local | qwen3-coder:latest |
-| anthropic | Cloud | claude-opus-4-6 |
-| anthropic | Cloud | claude-sonnet-4-5-20250929 |
-| anthropic | Cloud | claude-haiku-4-5-20251001 |
-| openai | Cloud | GPT-5.3-Codex |
-| openai | Cloud | GPT-5.3-Codex-Spark |
-| openai | Cloud | GPT-5.2 |
-| openai | Cloud | GPT-5 |
-| gemini | Cloud | gemini-3-deep-think |
-| gemini | Cloud | gemini-3-pro |
-| gemini | Cloud | gemini-3-flash |
+- **Batteries included** -- the OpenAI, Anthropic, Google, and Ollama SDKs all ship with ayder-cli, so every provider works out of the box. The terminal UI is built on Rich and Textual.
 
 ### Tools
 
-LLMs on their own can only generate text. To be a useful coding assistant, the model needs to *act* on your codebase. ayder-cli provides 25 tools across 10 categories that the model can call:
+LLMs on their own can only generate text. To be a useful coding assistant, the model needs to *act* on your codebase. ayder-cli ships 16 built-in tools that the model can call, plus optional plugin toolsets (see [Plugins](#plugins)):
 
 Each tool has an OpenAI-compatible JSON schema so models that support function calling can use them natively. For models that don't, ayder-cli also parses a custom XML-like syntax (`<function=name><parameter=key>value</parameter></function>`) as a fallback.
 
@@ -134,26 +106,16 @@ export OLLAMA_FLASH_ATTENTION=true
 export OLLAMA_MAX_LOADED_MODELS=1
 ```
 
-### Anthropic setup (optional)
+### Cloud providers (Anthropic, OpenAI, Gemini)
 
-```bash
-# Install the Anthropic SDK
-pip install anthropic
-
-# Set your API key in ~/.ayder/config.toml (see Configuration below)
-# Then switch provider:
-#   /provider anthropic
-```
-
-### Gemini setup (optional)
+The Anthropic, OpenAI, and Google SDKs ship with ayder-cli — no extra installs.
+Just add an API key to a profile in `~/.ayder/config.toml` (see Configuration
+below) and switch provider in the TUI:
 
 ```bash
-# Install the Google Generative AI SDK
-pip install google-generativeai
+/provider anthropic   # or: openai, gemini
 ```
 
-Set your API key in `~/.ayder/config.toml`, then switch provider: `/provider gemini`
-
 ### Configuration: Profiles and Drivers
 
 ayder-cli uses a flexible profile-based configuration system. On the first run, it creates a config file at `~/.ayder/config.toml`.
@@ -218,7 +180,7 @@ rotation = "10 MB"
 retention = "7 days"
 
 [context_manager]
-enabled = false
+enabled = true
 max_context_tokens = 8192
 
 [temporal]
@@ -316,12 +278,14 @@ ayder --implement-all
 
 By default, every tool call requires user confirmation. Use permission flags to auto-approve tool categories:
 
-| Flag | Category | Tools |
-| ---- | -------- | ----- |
-| `-r` | Read | `file_explorer`, `read_file`, `search_codebase`, `get_project_structure`, `load_memory`, `get_background_output`, `list_background_processes`, `list_tasks`, `show_task`, `list_virtualenvs`, `activate_virtualenv` |
-| `-w` | Write | `file_editor`, `create_note`, `save_memory`, `manage_environment_vars`, `python_editor`, `temporal_workflow` |
-| `-x` | Execute | `run_shell_command`, `run_background_process`, `kill_background_process`, `create_virtualenv`, `install_requirements`, `remove_virtualenv` |
-| `--http` | Web/Network | `fetch_web`, `dbs_tool` |
+| Flag | Category | Built-in tools |
+| ---- | -------- | -------------- |
+| `-r` | Read | `file_explorer`, `read_file`, `search_codebase`, `get_project_structure`, `get_background_output`, `list_background_processes`, `list_tasks`, `show_task` |
+| `-w` | Write | `file_editor`, `context`, `create_note`, `manage_environment_vars` |
+| `-x` | Execute | `run_shell_command`, `run_background_process`, `kill_background_process` |
+| `--http` | Web/Network | `fetch_web` |
+
+Installed plugins extend these categories (e.g. `python_editor` → write, virtualenv tools → execute, `dbs_tool` → web).
 
 ```bash
 # Auto-approve read-only tools
@@ -370,7 +334,7 @@ The context manager is configured under `[context_manager]` in `config.toml`:
 | `max_tool_result_length` | `2048` | Maximum character length for a compressed tool result. |
 | `compress_tool_results` | `true` | Enable automatic tool result compression. |
 
-You can also manually manage context with `/save-memory`, `/load-memory`, and `/compact`.
+You can also manually manage context with the `context` tool and its slash-command shortcuts: `/save-context`, `/load-context`, `/list-contexts`, `/context-stats`, and `/compact`.
 
 ### Slash Commands
 
@@ -390,9 +354,11 @@ You can also manually manage context with `/save-memory`, `/load-memory`, and `/
 | `/skill` | Activate a domain skill from `.ayder/skills/` |
 | `/verbose` | Toggle verbose mode |
 | `/logging` | Set log level for current session (NONE, ERROR, WARNING, INFO, DEBUG) |
-| `/compact` | Summarize conversation, save to memory, clear, and reload context |
-| `/save-memory` | Summarize conversation and save to memory (no clear) |
-| `/load-memory` | Load memory and restore context |
+| `/compact` | Summarize conversation, save a context snapshot, clear, and reload |
+| `/save-context` | Summarize conversation and save it to a named context slot (no clear) |
+| `/load-context` | Load a saved context slot and restore it |
+| `/list-contexts` | List saved context slots |
+| `/context-stats` | Show current token and KV-cache usage |
 | `/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 |
@@ -436,7 +402,7 @@ The standard mode for general coding and chat. Uses the system prompt.
 > create a fibonacci function
 ```
 
-Available tools: File read/write, shell commands, search, memory, notes, tasks.
+Available tools: file read/write, shell commands, search, context, notes, tasks.
 
 ### Planning Mode (`/plan`)
 
@@ -486,24 +452,23 @@ The tool system:
 - Supports tag-based filtering for dynamic enable/disable
 - Injects tool-specific system prompts when enabled
 
-**Current tool categories (25 tools):**
+**Built-in tools (16):**
 
 | Category | Tools |
 |----------|-------|
 | **Filesystem** | `file_explorer`, `read_file`, `file_editor` |
 | **Search** | `search_codebase`, `get_project_structure` |
 | **Shell** | `run_shell_command` |
-| **Python Editor** | `python_editor` (CST-based structural code manipulation) |
-| **Memory** | `save_memory`, `load_memory` |
+| **Context** | `context` (save / load / list / stats / clear session context slots) |
 | **Notes** | `create_note` |
 | **Background Processes** | `run_background_process`, `get_background_output`, `kill_background_process`, `list_background_processes` |
 | **Tasks** | `list_tasks`, `show_task` |
 | **Environment** | `manage_environment_vars` |
-| **Virtual Environments** | `create_virtualenv`, `install_requirements`, `list_virtualenvs`, `activate_virtualenv`, `remove_virtualenv` |
 | **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) |
+
+When agents are configured, the `call_agent` tool is also registered so the main LLM can dispatch them (see [Multi-Agent System](#multi-agent-system)).
+
+**Plugin tools** — `python_editor`, `dbs_tool`, `temporal_workflow`, virtualenv tools, and MCP integrations ship as optional plugins in the [ayder/ayder-plugins](https://github.com/ayder/ayder-plugins) repo (see [Plugins](#plugins)). Once installed they are auto-discovered exactly like built-ins.
 
 ## Multi-Agent System
 

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/README.md

@@ -25,39 +25,11 @@ Most AI coding assistants require cloud APIs, subscriptions, or heavy IDE plugin
 - **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.
-
-### Tested Providers with Models
-
-| Provider | Location | Model |
-| -------- | -------- | ----- |
-| ollama | Cloud | deepseek-v3.2:cloud |
-| ollama | Cloud | gemini-3-pro-preview:latest |
-| ollama | Local | glm-4.7-flash:latest |
-| ollama | Cloud | glm-4.7:cloud |
-| ollama | Cloud | glm-5:cloud |
-| ollama | Local | glm-ocr:latest |
-| ollama | Cloud | gpt-oss:120b-cloud |
-| ollama | Cloud | kimi-k2.5:cloud |
-| ollama | Cloud | minimax-m2.5:cloud |
-| ollama | Local | ministral-3:14b |
-| ollama | Cloud | qwen3-coder-next:cloud |
-| ollama | Cloud | qwen3-coder:480b-cloud |
-| ollama | Local | qwen3-coder:latest |
-| anthropic | Cloud | claude-opus-4-6 |
-| anthropic | Cloud | claude-sonnet-4-5-20250929 |
-| anthropic | Cloud | claude-haiku-4-5-20251001 |
-| openai | Cloud | GPT-5.3-Codex |
-| openai | Cloud | GPT-5.3-Codex-Spark |
-| openai | Cloud | GPT-5.2 |
-| openai | Cloud | GPT-5 |
-| gemini | Cloud | gemini-3-deep-think |
-| gemini | Cloud | gemini-3-pro |
-| gemini | Cloud | gemini-3-flash |
+- **Batteries included** -- the OpenAI, Anthropic, Google, and Ollama SDKs all ship with ayder-cli, so every provider works out of the box. The terminal UI is built on Rich and Textual.
 
 ### Tools
 
-LLMs on their own can only generate text. To be a useful coding assistant, the model needs to *act* on your codebase. ayder-cli provides 25 tools across 10 categories that the model can call:
+LLMs on their own can only generate text. To be a useful coding assistant, the model needs to *act* on your codebase. ayder-cli ships 16 built-in tools that the model can call, plus optional plugin toolsets (see [Plugins](#plugins)):
 
 Each tool has an OpenAI-compatible JSON schema so models that support function calling can use them natively. For models that don't, ayder-cli also parses a custom XML-like syntax (`<function=name><parameter=key>value</parameter></function>`) as a fallback.
 
@@ -105,26 +77,16 @@ export OLLAMA_FLASH_ATTENTION=true
 export OLLAMA_MAX_LOADED_MODELS=1
 ```
 
-### Anthropic setup (optional)
+### Cloud providers (Anthropic, OpenAI, Gemini)
 
-```bash
-# Install the Anthropic SDK
-pip install anthropic
-
-# Set your API key in ~/.ayder/config.toml (see Configuration below)
-# Then switch provider:
-#   /provider anthropic
-```
-
-### Gemini setup (optional)
+The Anthropic, OpenAI, and Google SDKs ship with ayder-cli — no extra installs.
+Just add an API key to a profile in `~/.ayder/config.toml` (see Configuration
+below) and switch provider in the TUI:
 
 ```bash
-# Install the Google Generative AI SDK
-pip install google-generativeai
+/provider anthropic   # or: openai, gemini
 ```
 
-Set your API key in `~/.ayder/config.toml`, then switch provider: `/provider gemini`
-
 ### Configuration: Profiles and Drivers
 
 ayder-cli uses a flexible profile-based configuration system. On the first run, it creates a config file at `~/.ayder/config.toml`.
@@ -189,7 +151,7 @@ rotation = "10 MB"
 retention = "7 days"
 
 [context_manager]
-enabled = false
+enabled = true
 max_context_tokens = 8192
 
 [temporal]
@@ -287,12 +249,14 @@ ayder --implement-all
 
 By default, every tool call requires user confirmation. Use permission flags to auto-approve tool categories:
 
-| Flag | Category | Tools |
-| ---- | -------- | ----- |
-| `-r` | Read | `file_explorer`, `read_file`, `search_codebase`, `get_project_structure`, `load_memory`, `get_background_output`, `list_background_processes`, `list_tasks`, `show_task`, `list_virtualenvs`, `activate_virtualenv` |
-| `-w` | Write | `file_editor`, `create_note`, `save_memory`, `manage_environment_vars`, `python_editor`, `temporal_workflow` |
-| `-x` | Execute | `run_shell_command`, `run_background_process`, `kill_background_process`, `create_virtualenv`, `install_requirements`, `remove_virtualenv` |
-| `--http` | Web/Network | `fetch_web`, `dbs_tool` |
+| Flag | Category | Built-in tools |
+| ---- | -------- | -------------- |
+| `-r` | Read | `file_explorer`, `read_file`, `search_codebase`, `get_project_structure`, `get_background_output`, `list_background_processes`, `list_tasks`, `show_task` |
+| `-w` | Write | `file_editor`, `context`, `create_note`, `manage_environment_vars` |
+| `-x` | Execute | `run_shell_command`, `run_background_process`, `kill_background_process` |
+| `--http` | Web/Network | `fetch_web` |
+
+Installed plugins extend these categories (e.g. `python_editor` → write, virtualenv tools → execute, `dbs_tool` → web).
 
 ```bash
 # Auto-approve read-only tools
@@ -341,7 +305,7 @@ The context manager is configured under `[context_manager]` in `config.toml`:
 | `max_tool_result_length` | `2048` | Maximum character length for a compressed tool result. |
 | `compress_tool_results` | `true` | Enable automatic tool result compression. |
 
-You can also manually manage context with `/save-memory`, `/load-memory`, and `/compact`.
+You can also manually manage context with the `context` tool and its slash-command shortcuts: `/save-context`, `/load-context`, `/list-contexts`, `/context-stats`, and `/compact`.
 
 ### Slash Commands
 
@@ -361,9 +325,11 @@ You can also manually manage context with `/save-memory`, `/load-memory`, and `/
 | `/skill` | Activate a domain skill from `.ayder/skills/` |
 | `/verbose` | Toggle verbose mode |
 | `/logging` | Set log level for current session (NONE, ERROR, WARNING, INFO, DEBUG) |
-| `/compact` | Summarize conversation, save to memory, clear, and reload context |
-| `/save-memory` | Summarize conversation and save to memory (no clear) |
-| `/load-memory` | Load memory and restore context |
+| `/compact` | Summarize conversation, save a context snapshot, clear, and reload |
+| `/save-context` | Summarize conversation and save it to a named context slot (no clear) |
+| `/load-context` | Load a saved context slot and restore it |
+| `/list-contexts` | List saved context slots |
+| `/context-stats` | Show current token and KV-cache usage |
 | `/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 |
@@ -407,7 +373,7 @@ The standard mode for general coding and chat. Uses the system prompt.
 > create a fibonacci function
 ```
 
-Available tools: File read/write, shell commands, search, memory, notes, tasks.
+Available tools: file read/write, shell commands, search, context, notes, tasks.
 
 ### Planning Mode (`/plan`)
 
@@ -457,24 +423,23 @@ The tool system:
 - Supports tag-based filtering for dynamic enable/disable
 - Injects tool-specific system prompts when enabled
 
-**Current tool categories (25 tools):**
+**Built-in tools (16):**
 
 | Category | Tools |
 |----------|-------|
 | **Filesystem** | `file_explorer`, `read_file`, `file_editor` |
 | **Search** | `search_codebase`, `get_project_structure` |
 | **Shell** | `run_shell_command` |
-| **Python Editor** | `python_editor` (CST-based structural code manipulation) |
-| **Memory** | `save_memory`, `load_memory` |
+| **Context** | `context` (save / load / list / stats / clear session context slots) |
 | **Notes** | `create_note` |
 | **Background Processes** | `run_background_process`, `get_background_output`, `kill_background_process`, `list_background_processes` |
 | **Tasks** | `list_tasks`, `show_task` |
 | **Environment** | `manage_environment_vars` |
-| **Virtual Environments** | `create_virtualenv`, `install_requirements`, `list_virtualenvs`, `activate_virtualenv`, `remove_virtualenv` |
 | **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) |
+
+When agents are configured, the `call_agent` tool is also registered so the main LLM can dispatch them (see [Multi-Agent System](#multi-agent-system)).
+
+**Plugin tools** — `python_editor`, `dbs_tool`, `temporal_workflow`, virtualenv tools, and MCP integrations ship as optional plugins in the [ayder/ayder-plugins](https://github.com/ayder/ayder-plugins) repo (see [Plugins](#plugins)). Once installed they are auto-discovered exactly like built-ins.
 
 ## Multi-Agent System
 

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/docs/PROJECT_STRUCTURE.md

@@ -219,7 +219,7 @@ cli.py:main()
 | `tui/adapter.py` | Adapter glue between `AyderApp` and `ChatLoop` | callback wiring helpers |
 | `tui/commands.py` | Slash command handlers | `COMMAND_MAP`, `handle_*()` |
 | `tui/widgets.py` | Custom widgets | `ChatView`, `ToolPanel`, `CLIInputBar`, `StatusBar`, `AutoCompleteInput` |
-| `tui/screens.py` | Modal screens | `CLIConfirmScreen`, `CLIHelpScreen`, `CLIPermissionScreen`, `CLISafeModeScreen`, `CLISelectScreen`, `TaskEditScreen` |
+| `tui/screens.py` | Modal screens | `AgentListScreen`, `CLIConfirmScreen`, `CLIHelpScreen`, `CLIMultiSelectScreen`, `CLIPermissionScreen`, `CLISafeModeScreen`, `CLISelectScreen`, `TaskEditScreen` |
 | `tui/parser.py` | TUI-specific parsing | `content_processor()` |
 | `tui/helpers.py` | UI helpers | `create_tui_banner()` |
 | `tui/keybindings.py` | Keybinding declarations | `BINDINGS` |
@@ -289,7 +289,7 @@ the design rationale.
 | `tools/builtins/filesystem.py` | File system tool impls | `file_explorer()`, `read_file()`, `file_editor()` |
 | `tools/builtins/search.py` | Search tool impls | `search_codebase()`, `get_project_structure()` |
 | `tools/builtins/shell.py` | Shell execution impl | `run_shell_command()` |
-| `tools/builtins/memory.py` | Long-term memory tools | `save_memory`, `load_memory`, `save_context_memory`, `load_context_memory` |
+| `tools/builtins/context.py` | Session context snapshots | `context` |
 | `tools/builtins/notes.py` | Note-taking tool | `create_note()` |
 | `tools/builtins/tasks.py` | Task-management tools | `list_tasks()`, `show_task()` |
 | `tools/builtins/web.py` | HTTP fetch tool | `fetch_web()` |
@@ -642,11 +642,11 @@ Schema-driven tool definitions with auto-discovery:
 - **Schema generation**: `to_openai_schema()` returns the OpenAI function-calling dict
 - **Plugin loading**: `tools/plugin_manager.py` can augment `TOOL_DEFINITIONS` at runtime from local or GitHub-sourced plugins
 
-19 built-in tools across 9 definition files:
+16 built-in tools across 9 definition files:
 - Filesystem (3): `file_explorer`, `read_file`, `file_editor`
 - Search (2): `search_codebase`, `get_project_structure`
 - Shell (1): `run_shell_command`
-- Memory (4): `save_memory`, `load_memory`, `save_context_memory`, `load_context_memory`
+- Context (1): `context`
 - Notes (1): `create_note`
 - Background Processes (4): `run_background_process`, `get_background_output`, `kill_background_process`, `list_background_processes`
 - Tasks (2): `list_tasks`, `show_task`

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ayder-cli"
-version = "1.6.9"
+version = "1.8.3"
 description = "AI agent for any LLMs"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -23,7 +23,7 @@ dependencies = [
     "openai",
     "anthropic",
     "google-genai",
-    "ollama>=0.6.1",
+    "ollama>=0.6.2",
     "loguru",
     "httpx",
     "rich>=13.0.0",

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/src/ayder_cli/agents/callbacks.py

@@ -41,6 +41,7 @@ class AgentCallbacks:
         self._cancel_event = cancel_event
         self._on_progress = on_progress
         self.last_content: str = ""
+        self.last_system_error: str | None = None
 
     def _emit(self, event: str, data: Any = None) -> None:
         if self._on_progress:
@@ -87,6 +88,11 @@ class AgentCallbacks:
         self._emit("tools_cleanup")
 
     def on_system_message(self, text: str) -> None:
+        # ChatLoop reports stream/tool failures here. Capture them so the
+        # runner can promote them into AgentSummary.error instead of returning
+        # a misleading "completed" status with no content.
+        if isinstance(text, str) and text.lstrip().lower().startswith("error"):
+            self.last_system_error = text
         self._emit("system_message", text)
 
     async def request_confirmation(

ayder_cli-1.8.3/src/ayder_cli/agents/config.py

@@ -0,0 +1,74 @@
+"""AgentConfig — Pydantic model for agent definitions."""
+
+from typing import Any
+
+from pydantic import BaseModel, ConfigDict, model_validator
+
+
+class AgentConfig(BaseModel):
+    """Configuration for a single agent, parsed from [agents.<name>] TOML sections.
+
+    Connection-level fields (base_url, api_key, num_ctx, temperature, think,
+    driver) are optional; when set they override the values pulled from the
+    parent provider profile. This lets one agent target an entirely different
+    endpoint than the main session without needing a separate [llm.<name>]
+    profile.
+    """
+
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    name: str
+    provider: str | None = None
+    model: str | None = None
+    system_prompt: str = ""
+
+    base_url: str | None = None
+    api_key: str | None = None
+    driver: str | None = None
+    num_ctx: int | None = None
+    temperature: float | None = None
+    max_output_tokens: int | None = None
+    think: str | None = None
+
+    @model_validator(mode="before")
+    @classmethod
+    def _coerce_aliases(cls, data: Any) -> Any:
+        """Accept ``thinking`` as an alias for ``think`` and coerce numeric strings."""
+        if not isinstance(data, dict):
+            return data
+        new_data = dict(data)
+        if "thinking" in new_data and "think" not in new_data:
+            new_data["think"] = new_data.pop("thinking")
+        for key in ("temperature",):
+            val = new_data.get(key)
+            if isinstance(val, str) and val.strip():
+                try:
+                    new_data[key] = float(val)
+                except ValueError:
+                    pass
+        for key in ("num_ctx", "max_output_tokens"):
+            val = new_data.get(key)
+            if isinstance(val, str) and val.strip():
+                try:
+                    new_data[key] = int(val)
+                except ValueError:
+                    pass
+        return new_data
+
+    def overrides(self) -> dict[str, Any]:
+        """Return non-None connection-level fields suitable for cfg.model_copy()."""
+        out: dict[str, Any] = {}
+        for field in (
+            "model",
+            "base_url",
+            "api_key",
+            "driver",
+            "num_ctx",
+            "temperature",
+            "max_output_tokens",
+            "think",
+        ):
+            value = getattr(self, field)
+            if value is not None:
+                out[field] = value
+        return out

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/src/ayder_cli/agents/registry.py

@@ -79,39 +79,42 @@ class AgentRegistry:
         """Count of currently active instances of the named agent."""
         return sum(1 for r in self._active.values() if r.agent_name == name)
 
+    def list_agents(self) -> list[dict[str, Any]]:
+        """Return configured agents with live status information."""
+        parent_model = getattr(self._parent_config, "model", None)
+        agents: list[dict[str, Any]] = []
+        for name, cfg in self.agents.items():
+            description = cfg.system_prompt[:200] if cfg.system_prompt else ""
+            resolved_model = cfg.model or parent_model
+            model = resolved_model if isinstance(resolved_model, str) else ""
+            agents.append({
+                "name": name,
+                "description": description,
+                "model": model,
+                "status": self.get_status(name) or "unknown",
+                "running_count": self.get_running_count(name),
+            })
+        return agents
+
     def get_capability_prompts(self) -> str:
-        """Generate capability prompt text for the main LLM's system prompt."""
+        """Generate generic agent capability guidance for the system prompt."""
         if not self.agents:
             return ""
 
-        agent_names = list(self.agents.keys())
-
         lines = [
-            "\n## Registered Agents",
-            "",
-            "You have specialized agents available. To use them, call the `call_agent` tool",
-            f"with the `name` parameter set to one of: {', '.join(repr(n) for n in agent_names)}.",
+            "\n## Agent Delegation",
             "",
+            "Configured specialized agents may be available.",
+            "Use the `list_agents` tool to discover exact names and descriptions before `call_agent`.",
             "Each agent runs in the background with its own LLM and tools.",
             "You will receive the agent's summary when it completes.",
-            "",
-            "When asked to list agents, list the names below — do NOT search the codebase.",
-            "",
-        ]
-        for name, cfg in self.agents.items():
-            provider = cfg.provider or "(inherited)"
-            model = cfg.model or "(inherited)"
-            desc = cfg.system_prompt[:150] if cfg.system_prompt else "(no description)"
-            lines.append(f"- **{name}** (provider: {provider}, model: {model}): {desc}")
-
-        lines.extend([
             "",
             "**Usage rules:**",
             "- You CAN dispatch the same agent multiple times with different tasks.",
             "- Only use the agent whose specialty matches the task. Do NOT use unrelated agents.",
             "- Batch behavior: you will receive all agent summaries after all agents complete.",
             "- On agent failure, handle the task yourself. Do NOT re-dispatch failed agents.",
-        ])
+        ]
 
         return "\n".join(lines)
 
@@ -122,7 +125,17 @@ class AgentRegistry:
         """
         if name not in self.agents:
             logger.debug("dispatch rejected: agent '%s' not found", name)
-            return f"Error: Agent '{name}' not found in configured agents"
+            available = ", ".join(sorted(self.agents))
+            if available:
+                return (
+                    f"Error: Agent '{name}' not found. "
+                    f"Available agents: {available}. "
+                    f"Call list_agents for descriptions."
+                )
+            return (
+                f"Error: Agent '{name}' not found. "
+                f"No agents are configured. Call list_agents to verify availability."
+            )
         # Re-dispatch guard: block agents that failed in this cycle
         if name in self._settled and self._settled[name] in ("error", "timeout"):
             logger.debug(
@@ -185,7 +198,19 @@ class AgentRegistry:
         if self._loop is None:
             self._active.pop(run_id, None)
             return "Error: Agent registry not initialized (event loop not set)"
-        asyncio.run_coroutine_threadsafe(_run_and_queue(), self._loop)
+
+        coro = _run_and_queue()
+        try:
+            asyncio.run_coroutine_threadsafe(coro, self._loop)
+        except Exception as exc:
+            # If scheduling fails (for example because the loop was closed),
+            # the coroutine object will never be awaited unless explicitly
+            # closed. Also remove the runner from active state so status does
+            # not remain stuck on "running".
+            coro.close()
+            self._active.pop(run_id, None)
+            logger.exception("failed to schedule agent run: agent='%s' run_id=%d", name, run_id)
+            return f"Error: Failed to schedule agent '{name}': {exc}"
 
         return run_id
 

{ayder_cli-1.6.9 → ayder_cli-1.8.3}/src/ayder_cli/agents/runner.py

@@ -139,6 +139,23 @@ class AgentRunner:
                     error=f"Agent exceeded {self._timeout}s timeout",
                 )
 
+            # ChatLoop swallows stream/tool failures via on_system_message
+            # and returns normally. Promote any captured error into a real
+            # error AgentSummary so callers see the cause instead of a
+            # placeholder "completed with no summary".
+            if callbacks.last_system_error and not callbacks.last_content.strip():
+                self.status = "error"
+                logger.debug(
+                    "run failed (captured via on_system_message): agent='%s' run_id=%d error='%s'",
+                    self.agent_name, self.run_id, callbacks.last_system_error[:200],
+                )
+                return AgentSummary(
+                    agent_name=self.agent_name,
+                    status="error",
+                    summary="Agent failed before producing output.",
+                    error=callbacks.last_system_error,
+                )
+
             # Completed successfully
             self.status = "completed"
             summary_text = self._parse_summary(callbacks.last_content)