docs: update provider lists and add Chat Mode documentation

Problem: Documentation was missing new providers (Ollama Cloud, Z.AI) and
Chat Mode feature that were added in recent sessions.

Solution:
- Update provider counts from 10 to 13 across docs
- Add Ollama Cloud and Z.AI to all provider lists
- Add Ollama Cloud setup section to PROVIDERS.md
- Add Chat Mode documentation to FEATURES.md
- Add Chat Mode to SANDBOX.md and USER_GUIDE.md

Testing: Syntax checks pass on all modified files

Author: fewtarius

README.md

@@ -91,7 +91,7 @@ CLIO is part of the [Synthetic Autonomic Mind (SAM)](https://github.com/Syntheti
 | **Todos** | Manage tasks within your workflow |
 | **Web** | Fetch and analyze web content |
 | **MCP** | Connect to external tool servers via [Model Context Protocol](docs/MCP.md) |
-| **AI Providers** | GitHub Copilot, OpenAI, Google Gemini, DeepSeek, OpenRouter, MiniMax, llama.cpp, LM Studio, SAM |
+| **AI Providers** | GitHub Copilot, OpenAI, Google Gemini, DeepSeek, OpenRouter, Ollama Cloud, MiniMax, Z.AI, llama.cpp, LM Studio, SAM |
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 

docs/ARCHITECTURE.md

@@ -6,7 +6,7 @@
 
 ## Quick Overview
 
-CLIO is a **terminal-first AI code assistant** built in Perl. It integrates AI models (GitHub Copilot, OpenAI, Google, OpenRouter) with local tools (file operations, git, terminal) to help developers work more effectively.
+CLIO is a **terminal-first AI code assistant** built in Perl. It integrates AI models (GitHub Copilot, OpenAI, Google, OpenRouter, Ollama Cloud, MiniMax, Z.AI) with local tools (file operations, git, terminal) to help developers work more effectively.
 
 **Core concept:** User types → CLIO thinks → CLIO uses tools → Results displayed
 
@@ -97,7 +97,7 @@ Terminal Output
 | Logger | `Logger.pm` | Debug and trace output |
 
 **How it works:**
-1. APIManager connects to AI provider (GitHub Copilot, OpenAI, Google, OpenRouter)
+1. APIManager connects to AI provider (GitHub Copilot, OpenAI, Google, OpenRouter, MiniMax, Z.AI, Ollama Cloud, etc.)
 2. WorkflowOrchestrator manages complex interactions, including:
    - Proactive context trimming before each API call (keeps messages at ≤75% of context)
    - Reactive trimming with 3-attempt escalation when the API rejects due to token overflow
@@ -531,7 +531,7 @@ clio --new           # First run
 
 ```
 lib/CLIO/
-  Providers.pm             # AI provider registry (GitHub Copilot, OpenAI, Google, etc.)
+  Providers.pm             # AI provider registry (GitHub Copilot, OpenAI, Ollama, Z.AI, etc.)
   Update.pm                # Self-update system
   UI/                      # Terminal interface
       Chat.pm              # Main interactive loop

docs/FEATURES.md

@@ -117,6 +117,24 @@ CLIO uses conservative sampling defaults tuned for reliable tool use. When worki
 
 Overrides are saved globally and visible in `/api show`. Provider-recommended defaults (e.g. MiniMax's `temperature=1.0`) are applied automatically when no override is set - you only need to set these if you want to change from the provider recommendation.
 
+### Chat Mode
+
+For conversational AI without file modifications, use chat mode:
+
+```
+clio --chat --new
+```
+
+Chat mode:
+- Auto-enables sandbox mode for safety
+- Restricts tools to: web, file read, memory, interact, todos
+- Uses a lighter system prompt optimized for chat
+
+This is useful for:
+- Quick questions without modifying code
+- Web searches and research
+- Explaining concepts or debugging help
+
 ### Iteration and Error Recovery
 
 When something goes wrong - a syntax error, a failed test, an unexpected file structure - CLIO doesn't stop. It reads the error, adjusts its approach, and tries again. In interactive mode CLIO has no iteration limit. In non-interactive mode (scripting, sub-agents) a default of 75 iterations applies. Both are configurable.
@@ -241,7 +259,7 @@ Connect to external tool servers via the Model Context Protocol. See [MCP Integr
 
 ## 3. AI Providers
 
-CLIO supports 10 AI providers out of the box. Switch between them at any time - even mid-session.
+CLIO supports 13 AI providers out of the box. Switch between them at any time - even mid-session.
 
 | Provider | Type | Authentication |
 |----------|------|---------------|
@@ -250,7 +268,10 @@ CLIO supports 10 AI providers out of the box. Switch between them at any time -
 | **Google Gemini** | Cloud | API key |
 | **DeepSeek** | Cloud | API key |
 | **OpenRouter** | Cloud | API key |
+| **Ollama Cloud** | Cloud | API key |
 | **MiniMax** | Cloud | API key (Token Plan support) |
+| **Z.AI** | Cloud | API key |
+| **Z.AI Coding Plan** | Cloud | API key |
 | **llama.cpp** | Local | None |
 | **LM Studio** | Local | None |
 | **SAM** | Local | API key (optional) |

docs/PROVIDERS.md

@@ -13,6 +13,7 @@
 | **Google Gemini** | `google` | API Key |
 | **DeepSeek** | `deepseek` | API Key |
 | **OpenRouter** | `openrouter` | API Key |
+| **Ollama Cloud** | `ollama_cloud` | API Key |
 | **MiniMax** | `minimax` | API Key |
 | **MiniMax Token Plan** | `minimax_token` | API Key |
 | **Z.AI** | `zai` | API Key |
@@ -187,6 +188,39 @@ Models use the `provider/model` format:
 
 ---
 
+### Ollama Cloud
+
+**Best for:** Access to open-source models (Qwen, Gemma, DeepSeek, etc.) with API convenience
+
+**Get API Key:**
+1. Create account at [ollama.com](https://ollama.com)
+2. Go to your account settings
+3. Create an API key
+
+**Configure CLIO:**
+```bash
+clio --new
+/api set provider ollama_cloud
+/api set key <your-api-key>
+/config save
+```
+
+**Available model families:** Qwen, Gemma, DeepSeek, Mistral, Llama, and more. Use `/api models` for the current list.
+
+**Features:**
+- Supports tools/function calling
+- Streaming responses
+- Reasoning models (for thinking-enabled models)
+
+**Example models:**
+| Model | Size | Best For |
+|-------|------|----------|
+| gemma4:31b | 31B | Balanced performance |
+| qwen3:8b | 8B | Fast, low memory |
+| deepseek-v3.2 | - | Coding, reasoning |
+
+---
+
 ### MiniMax
 
 **Best for:** High-throughput coding, large output windows, interleaved reasoning

docs/SANDBOX.md

@@ -120,6 +120,7 @@ This handles:
 
 | Scenario | Recommendation |
 |----------|----------------|
+| Conversational AI, quick questions | `--chat` flag |
 | Trusted local environment | No sandbox needed |
 | Exploring unfamiliar codebase | `--sandbox` flag |
 | Working on sensitive project | `--sandbox` flag |

docs/USER_GUIDE.md

@@ -2001,6 +2001,30 @@ clio --sandbox --new
 - Version control: limited to project repository
 - Terminal operations: NOT restricted
 
+### Chat Mode (`--chat` flag)
+
+A conversational AI mode optimized for quick questions and web access. Chat mode:
+
+- Auto-enables sandbox mode for safety
+- Restricts tools to: web, file read, memory, interact, todos
+- Uses a lighter system prompt optimized for chat
+
+```bash
+clio --chat --new
+```
+
+**When to use Chat Mode:**
+- Quick questions without modifying code
+- Web searches and research
+- Explaining concepts or code
+- General debugging help
+
+**When to use Agent Mode (default):**
+- Making changes to files
+- Running commands
+- Multi-step refactoring
+- Autonomous task completion
+
 ### Container Sandbox (Docker)
 
 For complete isolation, run CLIO in a container: