docs: update documentation for v1.4.0 features

Author: Pomilon

README.md

@@ -103,6 +103,7 @@ Detailed guides are available in the `docs/` directory:
 - [Getting Started](docs/getting_started.md)
 - [Slash Command Reference](docs/COMMANDS.md)
 - [Tool Reference](docs/tools.md)
+- [Memory Management](docs/memory.md)
 - [Sandbox Environment](docs/sandbox.md)
 - [Configuring Providers](docs/configuration.md)
 

docs/configuration.md

@@ -48,3 +48,18 @@ You can manage your providers without leaving the TUI using slash commands:
 ```bash
 /config reorder "Groq Backup" up
 ```
+
+## Economics & Budgeting
+
+Plexir tracks real-time token usage and estimates costs based on the active provider's pricing. 
+
+### Set a session budget
+To prevent unexpected costs during long sessions, you can set a maximum dollar amount for the current session. If exceeded, Plexir will stop generating and notify you.
+```bash
+/config budget 0.50
+```
+*Set to `0` to disable the limit.*
+
+### View current usage
+Usage metrics (Tokens and Estimated Cost) are always visible in the **System Status** sidebar.
+

docs/memory.md

@@ -0,0 +1,31 @@
+# Memory & Context Management
+
+Plexir uses advanced techniques to manage long-running conversations, ensuring the model remains coherent even as the history grows.
+
+## 🔄 Rolling Summarization
+
+When a conversation history becomes too large (exceeding 40 messages), Plexir automatically triggers **Rolling Summarization**. 
+
+1. **How it works**: Plexir identifies older, unpinned messages and uses the primary LLM to condense them into a concise "BACKGROUND SUMMARY."
+2. **Context Preservation**: This summary is injected at the start of the conversation, allowing the model to remember high-level decisions and context while clearing out detailed token-heavy noise.
+3. **Automatic**: This happens in the background without user intervention.
+
+## 📌 Message Pinning
+
+You can manually protect critical messages from being summarized or pruned using **Context Pinning**.
+
+### Pin a message
+Use the `/session pin` command followed by the message number (visible in the history or logs).
+```bash
+/session pin 5
+```
+*Pinned messages will be highlighted and are exempt from the summarization process.*
+
+### Unpin a message
+```bash
+/session unpin 5
+```
+
+## 🧠 Distillation (Failover)
+
+During a **Provider Failover** (e.g., Gemini Primary hitting a quota), Plexir uses a "Distillation" process to transfer only the most essential recent context to the backup provider. This ensures a smooth transition with minimal latency and token waste.

docs/tools.md

@@ -32,9 +32,18 @@ Plexir agents are equipped with a powerful set of tools to interact with the sys
 
 ## MCP & Extensibility
 
-| Tool | Description | Critical? |
-| :--- | :--- | :--- |
-| `mcp_<server>_resources` | List or read resources (schemas, logs, etc.) from an MCP server. | No |
+Plexir dynamically integrates with Model Context Protocol (MCP) servers.
+
+| Tool | Description |
+| :--- | :--- |
+| `mcp_<server>_resources` | List or read static resources and dynamic URI templates from the server. |
+| `mcp_<server>_prompts` | List and retrieve reusable prompt templates (expert configurations) from the server. |
+
+### How it works
+When you add an MCP server via `/config add`, Plexir automatically queries its capabilities and registers these tools if supported by the server. 
+- **Resources**: Can be database schemas, log files, or internal documentation.
+- **Prompts**: Pre-defined system instructions optimized for specific tasks like code review or documentation generation.
+
 
 ## Web & Information