lucasacchi/LogWhispererAI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
d0f530f757b12a781e37b08e043be5b794a59fb4
LogWhispererAI/CHANGELOG.md
Luca Sacchi Ricciardi d0f530f757 docs: update AI Pipeline spec to use OpenRouter instead of OpenAI direct 
Migrated from OpenAI direct API to OpenRouter for multiple advantages:

Cost Optimization:
- Reduced cost by ~25%: /bin/bash.00015/call (vs /bin/bash.0002/call OpenAI)
- Monthly estimate: ~/bin/bash.15 for 1000 calls (vs /bin/bash.20)

Provider Benefits:
- Access to 300+ AI models (OpenAI, Anthropic, Google, etc.)
- Automatic fallback between providers for 99.9% uptime
- Single API key for all providers
- Unified API interface

Technical Changes:
- Updated endpoint: api.openai.com → openrouter.ai/api/v1
- Model format: gpt-4o-mini → openai/gpt-4o-mini
- Added required headers: HTTP-Referer, X-Title
- Environment variables: OPENAI_API_KEY → OPENROUTER_API_KEY
  + OPENROUTER_SITE_URL (for OpenRouter ranking)
  + OPENROUTER_APP_NAME

Added Sections:
- 3.1 Why OpenRouter? (benefits comparison)
- 3.5 Model Fallback (automatic provider switching)
- Updated all code examples with OpenRouter integration
- Updated test cases (openai_client → openrouter_client)
- Updated cost estimates throughout document

References updated to OpenRouter documentation.

Refs: OpenRouter docs https://openrouter.ai/docs
2026-04-02 19:31:04 +02:00

5.4 KiB
Raw Blame History

Changelog

All notable changes to this project will be documented in this file.

The format is based on Common Changelog, and this project adheres to Semantic Versioning.

[Unreleased]

Added

  • feat: Create n8n workflow LogWhisperer_Ingest for secure log ingestion

    • Webhook trigger on POST /webhook/logwhisperer/ingest
    • HMAC-SHA256 signature validation with anti-replay protection
    • Data validation (UUID, severity levels, non-empty raw_log)
    • PostgreSQL storage with automatic table creation
    • Conditional AI processing for critical severity logs
    • JSON export at workflows/logwhisperer_ingest.json
    • Test suite at workflows/test_workflow.sh
    • Integration guide at workflows/INTEGRATION.md
    • Documentation at workflows/README.md
    • Implements Metodo Sacchi: Safety First, Little Often, Double Check

  • feat: Configure MCP servers for enhanced AI capabilities

    • sequential-thinking MCP for structured problem solving
    • context7 MCP for contextual library documentation retrieval
    • n8n MCP for workflow automation integration

  • docs: Add agent-specific configurations in .opencode/agents/

    • @n8n_specialist_agent for n8n workflow management
    • @context_auditor_agent for documentation alignment checks

  • docs: Add skill playbooks in .opencode/skills/

    • TDD_Python_Specialist: Test-driven development workflow
    • Git_and_Changelog: Conventional commits and changelog standards
    • n8n_automation_mastery: n8n workflow best practices
    • context7_documentation_retrivial: Context-aware documentation lookup

  • docs: Add requirements.txt with Python dependencies (pytest, requests)

  • docs: Add AI Pipeline technical specification

    • System prompt with Metodo Sacchi integration (Safety First, Little Often, Double Check)
    • OpenRouter configuration (migrated from OpenAI direct)
      • 25% cost savings (~$0.00015/call vs ~$0.0002/call)
      • Multi-provider fallback (300+ models available)
      • Automatic failover if primary provider down
    • Complete n8n Code Node JavaScript implementation
      • OpenRouter endpoint: https://openrouter.ai/api/v1
      • Required headers: HTTP-Referer, X-Title for ranking
      • Model format: provider/model (e.g., openai/gpt-4o-mini)
    • JSON output schema with severity mapping (critical/medium/low)
    • Error handling with circuit breaker pattern
    • Security guidelines (data sanitization, rate limiting)
    • 10 acceptance criteria defined
    • 5 test scenarios with expected input/output
    • 5 real-world examples (OOM, disk full, connection refused, etc.)
    • Implementation checklist for developers

Changed

  • docs: Update README.md with complete project structure
    • Add MCP configuration section
    • Document all agent configurations
    • Include skill playbooks in project tree
    • Update setup instructions with requirements.txt
  • docs: Refactor setup documentation structure (moved to docs/1.setup_procedure/)

[0.1.1] - 2026-04-02

Added

  • docs: Project Review Sprint 1 complete analysis
    • Product Manager review: UVP alignment (7.05/10)
    • Tech Lead review: Architecture assessment (7.5/10)
    • Security Auditor review: Risk analysis (5.75/10)
    • Comprehensive recommendations for Sprint 2

Changed

  • docs: Major README.md refactoring with badges and improved navigation
  • docs: Updated all sprint documentation to "Completed" status

[0.1.0] - 2026-04-02

Added

  • feat: Implement log ingestion script (logwhisperer.sh) for monitoring system logs

    • Monitor multiple log sources: syslog, nginx, postgresql
    • Pattern matching for critical errors (FATAL, ERROR, OOM, segfault, disk full)
    • JSON payload generation with severity levels (low, medium, critical)
    • Rate limiting to prevent alert flooding (30s per source/pattern)
    • Offset tracking for each log file to avoid reprocessing
    • HTTP POST dispatch to configurable webhook with retry logic
    • Dry-run mode for testing pattern matching without sending webhooks
    • Configuration file support (/etc/logwhisperer/config.env)
    • Command-line flags: --help, --validate, --config, --dry-run, --test-line

  • feat: Create installation script (install.sh)

    • Interactive configuration wizard
    • UUID v4 generation for CLIENT_ID
    • Systemd service creation (when run as root)
    • Support for both system-wide and user-local installation
    • Prerequisite checking (bash, curl)
    • Connectivity test to webhook URL

  • test: Add comprehensive test suite (tests/test_logwhisperer.py)

    • Script existence and executable validation
    • Configuration validation tests
    • Pattern matching tests (FATAL, OOM, ERROR patterns)
    • JSON payload structure validation
    • Severity mapping verification

  • docs: Create technical specification for Feature 1 (Log Ingestion)

    • Architecture diagram and component description
    • Requirements (functional and non-functional)
    • Safety guidelines (Metodo Sacchi)
    • Acceptance criteria

  • docs: Create Sprint 1 verification report (docs/sprint1_verification.md)

    • Complete verification of all Sprint 1 deliverables
    • Test results summary (12/12 tests passed)
    • Acceptance criteria checklist
    • Security audit results
    • Code quality assessment

Security

  • Configuration files created with restrictive permissions (600)
  • No hardcoded credentials in scripts
  • HTTPS validation for webhook URLs (warning for non-HTTPS)
  • Read-only access to log files (no modifications)
Reference in New Issue View Git Blame Copy Permalink