chore: update contract feature docs

pages/developers/decentralized-applications/genlayer-js.mdx

@@ -49,7 +49,7 @@ npm install genlayer-js
 
 Here’s how to initialize the client and connect to the GenLayer Studio:
 
-- **[Reading a transaction](../intelligent-contracts/advanced-features/contract-to-contract-interaction)**: Understand how to query transactions on the GenLayer network.
+- **[Reading a transaction](../intelligent-contracts/features/interacting-with-intelligent-contracts)**: Understand how to query transactions on the GenLayer network.
 - **[Reading a contract](/developers/decentralized-applications/reading-data)**: Discover how to read data from intelligent contracts on GenLayer.
 - **[Writing a contract](../intelligent-contracts/tools/genlayer-studio/contract-state)**: Learn how to write data to intelligent contracts on GenLayer.
 

pages/developers/intelligent-contracts/_meta.json

@@ -1,5 +1,6 @@
 {
   "introduction": "Introduction to Intelligent Contracts",
+  "features": "Feature List",
   "tooling-setup": "Tooling Setup",
   "first-contract": "Your First Contract",
   "types": "Types",
@@ -9,7 +10,6 @@
   "debugging": "Debugging",
   "deploying": "Deploying",
   "crafting-prompts": "Crafting Prompts",
-  "advanced-features": "Advanced Features",
   "security-and-best-practices": "Security and Best Practices",
   "examples": "Examples",
   "tools": "Tools",

pages/developers/intelligent-contracts/features/_meta.json

@@ -0,0 +1,16 @@
+{
+    "features": "Features",
+    "storage": "Storage",
+    "error-handling": "Error Handling",
+    "upgradability": "Upgradability",
+    "balances": "Balances",
+    "interacting-with-intelligent-contracts": "Interacting with Intelligent Contracts",
+    "interacting-with-evm-contracts": "Interacting with EVM Contracts",
+    "vector-storage": "Vector Storage",
+    "debugging": "Debugging",
+    "special-methods": "Special Methods",
+    "random": "Random",
+    "non-determinism": "Non-determinism",
+    "calling-llms": "Calling LLMs",
+    "web-access": "Web Access"
+}

pages/developers/intelligent-contracts/features/balances.mdx

@@ -0,0 +1,45 @@
+import { Callout } from "nextra-theme-docs";
+
+# Balances
+
+## Getting Contract Balance
+
+Access your contract's balance using `self.balance` within contract methods:
+
+```python
+class Contract(gl.Contract):
+    @gl.public.view
+    def get_balance(self):
+        return self.balance  # Shows contract's current balance
+```
+
+## Getting Another Contract's Balance
+
+Get any contract's balance by address:
+
+```python
+other_contract = gl.get_contract_at(contract_address)
+print(other_contract.balance)
+```
+
+## Transferring Funds
+
+Transfer funds from sender to current contract:
+
+```python
+other_contract = gl.get_contract_at(gl.message.sender_address)
+other_contract.emit_transfer(value=u256(5))
+other_contract.emit(value=u256(5), on='finalized').transfer(Address("0x..."))
+```
+
+## Balance Context
+
+Balance behavior depends on execution context:
+- In `write` methods: `self.balance` reflects actual contract balance after state changes
+- In `view` methods: Balance shows current state without modifications
+- Transfers can only occur in write context
+
+<Callout type="warning">
+  If message is emitted on acceptance and previous transaction gets successfully appealed after the emit,
+  the balance will be decremented nonetheless
+</Callout>

pages/developers/intelligent-contracts/features/calling-llms.mdx

@@ -0,0 +1,77 @@
+import { Callout } from 'nextra-theme-docs'
+
+# Calling LLMs
+
+## Basic LLM Calls
+
+Execute prompts using large language models:
+
+```python
+def llm_call():
+    response = gl.nondet.exec_prompt("Answer this question")
+    return response.strip().lower()
+
+# Consensus ensures consistent LLM responses
+answer = gl.eq_principle.strict_eq(llm_call)
+```
+
+## JSON Response Format
+
+Request structured responses from LLMs:
+
+```python
+def structured_llm_call():
+    prompt = """
+    Return a JSON object with these keys:
+    - "score": random integer from 1 to 100
+    - "status": either "active" or "inactive"
+    """
+    return gl.nondet.exec_prompt(prompt, response_format='json')
+
+result = gl.eq_principle.strict_eq(structured_llm_call)
+score = result['score']  # Access JSON fields
+```
+
+This approach guarantees that `exec_prompt` returns a valid JSON object, however
+correspondence to the specified format depends on the underlying LLM.
+
+## Image Processing
+
+Process images with vision models:
+
+```python
+def vision_analysis():
+    prompt = "Describe what you see in this image"
+    image_data = b"\x89PNG..."
+    return gl.nondet.exec_prompt(
+        prompt,
+        images=[image_data]
+    )
+
+description = gl.eq_principle.strict_eq(vision_analysis)
+```
+
+<Callout type="warning">
+    Limit of images is two
+</Callout>
+
+
+## Response Validation
+
+Validate and process LLM responses:
+
+```python
+def validated_call():
+    response = gl.nondet.exec_prompt(
+        "Generate a number between 1 and 100",
+        response_format='json'
+    )
+
+    # Validate the response
+    if response['number'] < 1 or response['number'] > 100:
+        raise Exception(f"Invalid number: {response['number']}")
+
+    return response['number']
+
+result = gl.eq_principle.strict_eq(validated_call)
+```

pages/developers/intelligent-contracts/features/debugging.mdx

@@ -0,0 +1,31 @@
+import { Callout } from "nextra-theme-docs";
+
+# Debugging
+
+## Print Statements
+
+Use `print` calls for basic debugging, which will be present in node or studio output.
+
+Use `gl.trace` to include time stamps in the output (it will be written to genvm_log instead of stdout)
+
+## Profiling
+
+There is also `gl.trace_time_micro` which returns timestamp in the GenVM debug mode. Default bootloader includes
+possibility to enable profiling by setting environment variable `GENLAYER_ENABLE_PROFILER=true`.
+
+```python
+# {
+#   "Seq": [
+#     { "SetEnv": { "name": "GENLAYER_ENABLE_PROFILER", "value": "true" } },
+#     { "Depends": "py-genlayer:test" }
+#   ]
+# }
+```
+
+This will output base-64 encoded gzip-compressed profiling data to stderr after every single VM execution
+
+## Attaching a Debugger
+
+<Callout type="warning" emoji="🏗️">
+  Unfortunately, attaching a debugger to a running Intelligent Contract is not supported yet
+</Callout>