docs: fix typos and inconsistencies in LLM Chat documentation

- Fix typo: "tempurature" → "temperature" in README
- Fix wrong default model: "granite3b" → "ibm/granite-13b-chat-v2"
- Fix model_id type: int → string
- Fix duplicate in variable name: LLMCHAT_SESSION_SESSION_TTL → LLMCHAT_SESSION_TTL
- Fix incorrect defaults for Redis settings (CHAT_HISTORY_TTL: 0.2 → 3600, CHAT_HISTORY_MAX_MESSAGES: 0.2 → 50)
- Add missing LLMCHAT_ prefix to env vars in llm-chat.md to match config.py
- Improve table formatting for consistency

Signed-off-by: Mihai Criveti <[email protected]>

Author: crivetimihai

README.md

@@ -1239,13 +1239,13 @@ The LLM Chat MCP Client allows you to interact with MCP servers using conversati
 
 
 **IBM WatsonX AI**
-| Setting                 | Description                     | Default      | Options         |
-| ----------------------- | --------------------------------| ------------ | ----------------|
-| `WATSONX_URL`           | watsonx url                     | (none)       | string          |
-| `WATSONX_APIKEY`        | API key                         | (none)       | string          |
-| `WATSONX_PROJECT_ID`    | Project Id for WatsonX          | (none)       | string          |
-| `WATSONX_MODEL_ID`      | Watsonx model id                | `granite3b`  | int             |
-| `WATSONX_TEMPERATURE`   | tempurature (optional)          | `0.7`        | float (0.0-1.0) |
+| Setting                 | Description                     | Default                        | Options         |
+| ----------------------- | --------------------------------| ------------------------------ | ----------------|
+| `WATSONX_URL`           | watsonx url                     | (none)                         | string          |
+| `WATSONX_APIKEY`        | API key                         | (none)                         | string          |
+| `WATSONX_PROJECT_ID`    | Project Id for WatsonX          | (none)                         | string          |
+| `WATSONX_MODEL_ID`      | Watsonx model id                | `ibm/granite-13b-chat-v2`      | string          |
+| `WATSONX_TEMPERATURE`   | temperature (optional)          | `0.7`                          | float (0.0-1.0) |
 
 
 **Ollama Configuration:**
@@ -1277,12 +1277,12 @@ The LLM Chat MCP Client allows you to interact with MCP servers using conversati
 
 | Setting                              | Description                                | Default | Options |
 | -------------------------------------| -------------------------------------------| ------- | ------- |
-| `LLMCHAT_SESSION_SESSION_TTL`        | Seconds for active_session key TTL         | `300`   | int     |
+| `LLMCHAT_SESSION_TTL`                | Seconds for active_session key TTL         | `300`   | int     |
 | `LLMCHAT_SESSION_LOCK_TTL`           | Seconds for lock expiry                    | `30`    | int     |
 | `LLMCHAT_SESSION_LOCK_RETRIES`       | How many times to poll while waiting       | `10`    | int     |
 | `LLMCHAT_SESSION_LOCK_WAIT`          | Seconds between polls                      | `0.2`   | float   |
-| `LLMCHAT_CHAT_HISTORY_TTL`           | Seconds for chat history expiry            | `0.2`   | float   |
-| `LLMCHAT_CHAT_HISTORY_MAX_MESSAGES`  | Maximum message history to store per user  | `0.2`   | float   |
+| `LLMCHAT_CHAT_HISTORY_TTL`           | Seconds for chat history expiry            | `3600`  | int     |
+| `LLMCHAT_CHAT_HISTORY_MAX_MESSAGES`  | Maximum message history to store per user  | `50`    | int     |
 
 **Documentation:**
 - [LLM Chat Guide](https://ibm.github.io/mcp-context-forge/using/clients/llm-chat) - Complete LLM Chat setup and provider configuration

docs/docs/using/clients/llm-chat.md

@@ -87,33 +87,33 @@ OLLAMA_TEMPERATURE=0.7
 
 ```bash
 # ===== Redis Connection =====
-CACHE_TYPE=redis                          # Enable Redis 
+CACHE_TYPE=redis                          # Enable Redis
 REDIS_URL=redis://localhost:6379/0       # Redis connection string
 
 # ===== Session Management =====
-SESSION_TTL=300                           # Active session ownership TTL (seconds)
+LLMCHAT_SESSION_TTL=300                   # Active session ownership TTL (seconds)
 # Default: 300 (5 minutes)
 # Higher values: More stable sessions, slower failover
 # Lower values: Faster failover, more frequent TTL refreshes
 
 # ===== Lock Configuration =====
-SESSION_LOCK_TTL=30                       # Lock expiry time (seconds)
+LLMCHAT_SESSION_LOCK_TTL=30               # Lock expiry time (seconds)
 # Default: 30 seconds
 # Should be > typical initialization time
 
-SESSION_LOCK_RETRIES=10                   # Lock acquisition retry attempts
+LLMCHAT_SESSION_LOCK_RETRIES=10           # Lock acquisition retry attempts
 # Default: 10 attempts
 # Total wait time = RETRIES × WAIT
 
-SESSION_LOCK_WAIT=0.2                     # Wait between retry attempts (seconds)
+LLMCHAT_SESSION_LOCK_WAIT=0.2             # Wait between retry attempts (seconds)
 # Default: 0.2 seconds (200ms)
 # Total max wait: 10 × 0.2 = 2 seconds
 
 # ===== Chat History =====
-CHAT_HISTORY_TTL=3600                     # History expiry time (seconds)
+LLMCHAT_CHAT_HISTORY_TTL=3600             # History expiry time (seconds)
 # Default: 3600 (1 hour)
 
-CHAT_HISTORY_MAX_MESSAGES=50              # Maximum messages per user
+LLMCHAT_CHAT_HISTORY_MAX_MESSAGES=50      # Maximum messages per user
 # Default: 50
 # Older messages automatically trimmed
 ```
@@ -153,7 +153,7 @@ After selecting a server, expand the **LLM Configuration** section and choose yo
 5. IBM watsonx.ai
 6. Ollama
 
-Select your preferred provider. If you’ve already configured LLM details like API key, URL, etc., in the environment variables, you can leave the next fields blank.
+Select your preferred provider. If you've already configured LLM details like API key, URL, etc., in the environment variables, you can leave the next fields blank.
 
 
 ### Step 3: 🔗 Connect to the Chat Session