feat(skills): Add write_to_csv skill for data export workflows

.adl-ignore

@@ -17,6 +17,7 @@ skills/take_screenshot.go
 skills/execute_script.go
 skills/handle_authentication.go
 skills/wait_for_condition.go
+skills/write_to_csv.go
 internal/playwright/playwright.go
 
 # Go dependency files

AGENTS.md

@@ -75,7 +75,7 @@ Your automation solutions should be maintainable, efficient, and production-read
 ## Skills
 
 
-This agent provides 8 skills:
+This agent provides 9 skills:
 
 
 ### navigate_to_url
@@ -134,6 +134,13 @@ This agent provides 8 skills:
 - **Output Schema**: Defined in agent configuration
 
 
+### write_to_csv
+- **Description**: Write structured data to CSV files with support for custom headers and file paths
+- **Tags**: export, csv, data, file
+- **Input Schema**: Defined in agent configuration
+- **Output Schema**: Defined in agent configuration
+
+
 
 
 ## Server Configuration
@@ -239,6 +246,11 @@ curl -X POST http://localhost:8080/skills/wait_for_condition \
   -H "Content-Type: application/json" \
   -d '{"input": "your_input_here"}'
 
+# Execute write_to_csv skill
+curl -X POST http://localhost:8080/skills/write_to_csv \
+  -H "Content-Type: application/json" \
+  -d '{"input": "your_input_here"}'
+
 
 ```
 
@@ -286,6 +298,8 @@ docker run -p 8080:8080 browser-agent
 
 │   └── wait_for_condition.go   # Wait for specific conditions before proceeding with automation
 
+│   └── write_to_csv.go   # Write structured data to CSV files with support for custom headers and file paths
+
 ├── .well-known/         # Agent configuration
 │   └── agent.json       # Agent metadata
 ├── go.mod               # Go module definition

CLAUDE.md

@@ -10,7 +10,7 @@ browser-agent is an A2A (Agent-to-Agent) server implementing the [A2A Protocol](
 
 ### ADL-Generated Structure
 
-The codebase is generated using ADL CLI 0.21.4 and follows a strict generation pattern:
+The codebase is generated using ADL CLI 0.21.5 and follows a strict generation pattern:
 - **Generated Files**: Marked with `DO NOT EDIT` headers - manual changes will be overwritten
 - **Configuration Source**: `agent.yaml` - defines agent capabilities, skills, and metadata
 - **Server Implementation**: Built on the ADK (Agent Development Kit) framework from `github.com/inference-gateway/adk`
@@ -82,6 +82,7 @@ The following skills are currently defined:
 - **execute_script**: Execute custom JavaScript code in the browser context
 - **handle_authentication**: Handle various authentication scenarios including basic auth, OAuth, and custom login forms
 - **wait_for_condition**: Wait for specific conditions before proceeding with automation
+- **write_to_csv**: Write structured data to CSV files with support for custom headers and file paths
 
 To modify skills:
 1. Update `agent.yaml` with skill definitions
@@ -117,7 +118,7 @@ Activate with: `flox activate` (if Flox is installed)
 
 - **Generated Files**: Never manually edit files with "DO NOT EDIT" headers
 - **Configuration Changes**: Always modify `agent.yaml` and regenerate
-- **ADL Version**: Ensure ADL CLI 0.21.4 or compatible version for regeneration
+- **ADL Version**: Ensure ADL CLI 0.21.5 or compatible version for regeneration
 - **Port Configuration**: Default 8080, configurable via `A2A_PORT` or `A2A_SERVER_PORT`
 
 ## Debugging Tips

README.md

@@ -49,6 +49,7 @@ docker run -p 8080:8080 browser-agent
 | `execute_script` | Execute custom JavaScript code in the browser context |args, return_value, script |
 | `handle_authentication` | Handle various authentication scenarios including basic auth, OAuth, and custom login forms |login_url, password, password_selector, submit_selector, type, username, username_selector |
 | `wait_for_condition` | Wait for specific conditions before proceeding with automation |condition, custom_function, selector, state, timeout |
+| `write_to_csv` | Write structured data to CSV files with support for custom headers and file paths |append, data, filename, headers, include_headers |
 
 ## Configuration
 
@@ -61,13 +62,13 @@ The following custom configuration variables are available:
 | Category | Variable | Description | Default |
 |----------|----------|-------------|---------|
 | **Browser** | `BROWSER_ARGS` | Args configuration | `[--disable-blink-features=AutomationControlled --disable-features=VizDisplayCompositor --no-first-run --disable-default-apps --disable-extensions --disable-plugins --disable-sync --disable-translate --hide-scrollbars --mute-audio --no-zygote --disable-background-timer-throttling --disable-backgrounding-occluded-windows --disable-renderer-backgrounding --disable-ipc-flooding-protection]` |
+| **Browser** | `BROWSER_DATA_DIR` | Data_dir configuration | `/tmp/playwright/artifacts` |
 | **Browser** | `BROWSER_HEADER_ACCEPT` | Header_accept configuration | `text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7` |
 | **Browser** | `BROWSER_HEADER_ACCEPT_ENCODING` | Header_accept_encoding configuration | `gzip, deflate, br` |
 | **Browser** | `BROWSER_HEADER_ACCEPT_LANGUAGE` | Header_accept_language configuration | `en-US,en;q=0.9` |
 | **Browser** | `BROWSER_HEADER_CONNECTION` | Header_connection configuration | `keep-alive` |
 | **Browser** | `BROWSER_HEADER_DNT` | Header_dnt configuration | `1` |
 | **Browser** | `BROWSER_HEADER_UPGRADE_INSECURE_REQUESTS` | Header_upgrade_insecure_requests configuration | `1` |
-| **Browser** | `BROWSER_SCREENSHOTS_DIR` | Screenshots_dir configuration | `/tmp/screenshots` |
 | **Browser** | `BROWSER_USER_AGENT` | User_agent configuration | `Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36` |
 | **Browser** | `BROWSER_VIEWPORT_HEIGHT` | Viewport_height configuration | `1080` |
 | **Browser** | `BROWSER_VIEWPORT_WIDTH` | Viewport_width configuration | `1920` |

agent.yaml

@@ -20,7 +20,7 @@ spec:
       header_dnt: "1"
       header_connection: "keep-alive"
       header_upgrade_insecure_requests: "1"
-      screenshots_dir: "/tmp/screenshots"
+      data_dir: "/tmp/playwright/artifacts"
       args:
         - "--disable-blink-features=AutomationControlled"
         - "--disable-features=VizDisplayCompositor"
@@ -310,6 +310,44 @@ spec:
       inject:
         - logger
         - playwright
+    - id: write_to_csv
+      name: write_to_csv
+      description: Write structured data to CSV files with support for custom headers and file paths
+      tags:
+        - export
+        - csv
+        - data
+        - file
+      schema:
+        type: object
+        properties:
+          data:
+            type: array
+            items:
+              type: object
+            description: Array of objects to write to CSV, each object represents a row
+          filename:
+            type: string
+            description: Name of the CSV file (without path, will be saved to configured data directory)
+          headers:
+            type: array
+            items:
+              type: string
+            description: Custom column headers for the CSV file (optional, will use object keys if not provided)
+          append:
+            type: boolean
+            description: Whether to append to existing file or create new file
+            default: false
+          include_headers:
+            type: boolean
+            description: Whether to include headers in the CSV output
+            default: true
+        required:
+          - data
+          - filename
+      inject:
+        - logger
+        - playwright
   agent:
     provider: ""
     model: ""

example/.env.example

@@ -0,0 +1,7 @@
+# Inference Gateway
+DEEPSEEK_API_KEY=
+GOOGLE_API_KEY=
+
+# Agent
+A2A_AGENT_CLIENT_PROVIDER=deepseek
+A2A_AGENT_CLIENT_MODEL=deepseek-chat

example/README.md

@@ -6,7 +6,7 @@ This script demonstrates how to use the Playwright automation framework to perfo
 Configure the environment variables as needed:
 
 ```bash
-cp .env.gateway.example .env.gateway
+cp .env.example .env
 ```
 
 ** Add at least two providers, in this example Google and DeepSeek.

example/docker-compose.yaml

@@ -8,9 +8,8 @@ services:
     ports:
       - "8080:8080"
     volumes:
-      - ./screenshots:/tmp/screenshots
+      - ./artifacts:/tmp/playwright/artifacts
     environment:
-      BROWSER_SCREENSHOTS_DIR: /tmp/screenshots
       BROWSER_USER_AGENT: "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
       BROWSER_VIEWPORT_WIDTH: "1920"
       BROWSER_VIEWPORT_HEIGHT: "1080"
@@ -45,8 +44,8 @@ services:
       A2A_SERVER_IDLE_TIMEOUT: 120s
       A2A_SERVER_DISABLE_HEALTHCHECK_LOG: true
       A2A_AGENT_CARD_FILE_PATH: .well-known/agent.json
-      A2A_AGENT_CLIENT_PROVIDER: google
-      A2A_AGENT_CLIENT_MODEL: models/gemini-2.5-flash
+      A2A_AGENT_CLIENT_PROVIDER: ${A2A_AGENT_CLIENT_PROVIDER}
+      A2A_AGENT_CLIENT_MODEL: ${A2A_AGENT_CLIENT_MODEL}
       A2A_AGENT_CLIENT_API_KEY: ""
       A2A_AGENT_CLIENT_BASE_URL: http://inference-gateway:8080/v1
       A2A_AGENT_CLIENT_TIMEOUT: 30s
@@ -72,13 +71,14 @@ services:
     image: ghcr.io/inference-gateway/inference-gateway:latest
     container_name: inference-gateway
     environment:
+      DEEPSEEK_API_KEY: ${DEEPSEEK_API_KEY}
+      GOOGLE_API_KEY: ${GOOGLE_API_KEY}
       ENVIRONMENT: development
       SERVER_READ_TIMEOUT: 530s
       SERVER_WRITE_TIMEOUT: 530s
       CLIENT_TIMEOUT: 530s
-      CLIENT_IDLE_CONN_TIMEOUT: 30s
-    env_file:
-      .env.gateway
+      CLIENT_IDLE_CONN_TIMEOUT: 130s
+      CLIENT_RESPONSE_HEADER_TIMEOUT: 120s
     networks:
       - a2a-network
 
@@ -89,23 +89,10 @@ services:
       INFER_LOGGING_DEBUG: true
       INFER_GATEWAY_URL: http://inference-gateway:8080
       INFER_A2A_ENABLED: true
-      INFER_TOOLS_ENABLED: true
-      INFER_TOOLS_QUERY_ENABLED: true
-      INFER_TOOLS_TASK_ENABLED:  true
-      INFER_TOOLS_BASH_ENABLED: false
-      INFER_TOOLS_TODO_WRITE_ENABLED: false
-      INFER_TOOLS_WRITE_ENABLED: false
-      INFER_TOOLS_READ_ENABLED: false
-      INFER_TOOLS_DELETE_ENABLED: false
-      INFER_TOOLS_EDIT_ENABLED: false
-      INFER_TOOLS_GREP_ENABLED: false
-      INFER_TOOLS_TREE_ENABLED: false
-      INFER_TOOLS_WEB_FETCH_ENABLED: false
-      INFER_TOOLS_WEB_SEARCH_ENABLED: false
-      INFER_TOOLS_GITHUB_ENABLED: false
+      INFER_TOOLS_ENABLED: false
       INFER_AGENT_MODEL: deepseek/deepseek-chat
-      INFER_A2A_AGENTS: 'http://agent:8080'
-      INFER_A2A_CACHE_ENABLED: false
+      INFER_A2A_AGENTS: |
+        http://agent:8080
     command:
       - chat
     networks:

example/integration_demo.md

@@ -0,0 +1,76 @@
+# CSV Export Integration Demo
+
+This document demonstrates how to use the new `write_to_csv` skill in combination with the existing `extract_data` skill for complete data collection workflows.
+
+## Workflow Example
+
+1. **Navigate to a webpage**:
+   ```json
+   {
+     "skill": "navigate_to_url",
+     "args": {
+       "url": "https://example.com/products"
+     }
+   }
+   ```
+
+2. **Extract data from the page**:
+   ```json
+   {
+     "skill": "extract_data",
+     "args": {
+       "extractors": [
+         {
+           "name": "product_name",
+           "selector": ".product-title",
+           "multiple": true
+         },
+         {
+           "name": "price",
+           "selector": ".product-price",
+           "multiple": true
+         },
+         {
+           "name": "rating",
+           "selector": ".product-rating",
+           "attribute": "data-rating",
+           "multiple": true
+         }
+       ],
+       "format": "json"
+     }
+   }
+   ```
+
+3. **Write the extracted data to CSV**:
+   ```json
+   {
+     "skill": "write_to_csv",
+     "args": {
+       "data": [
+         {"product_name": "Product A", "price": "$29.99", "rating": "4.5"},
+         {"product_name": "Product B", "price": "$39.99", "rating": "4.2"},
+         {"product_name": "Product C", "price": "$19.99", "rating": "4.8"}
+       ],
+       "file_path": "/tmp/products.csv",
+       "headers": ["product_name", "price", "rating"],
+       "include_headers": true
+     }
+   }
+   ```
+
+## Features Supported
+
+- **Custom Headers**: Specify column order and names
+- **Append Mode**: Add to existing CSV files without overwriting
+- **Flexible Data**: Handles arrays, objects, and primitive values
+- **Error Handling**: Validates data format and file operations
+- **Directory Creation**: Automatically creates parent directories
+
+## Use Cases
+
+- **E-commerce Data Collection**: Extract product information, prices, and reviews
+- **News Aggregation**: Collect headlines, dates, and article links
+- **Financial Data**: Gather stock prices, market data, and trading volumes
+- **Contact Information**: Extract business details from directory sites
+- **Event Listings**: Collect event names, dates, venues, and prices