rene/llm-gateway
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
63 Commits 2 Branches 0 Tags
Commit Graph

8 Commits

Author SHA1 Message Date
Rene Fichtmueller
1d4be52c83 fix: only send HSTS header on HTTPS connections, not HTTP 
The learning process was failing to communicate with the gateway because:
1. Gateway was sending 'Strict-Transport-Security' header on HTTP responses
2. Node.js fetch respects HSTS and upgrades subsequent requests to HTTPS
3. Gateway only has HTTP listener (localhost:3103), no HTTPS
4. Result: SSL 'packet length too long' error on second request attempt

Solution: Modified registerHSTSMiddleware to only send HSTS header when
the connection is already secure (HTTPS or x-forwarded-proto: https).
HTTP connections will not get the HSTS header, preventing the forced upgrade.
 2026-04-26 19:01:41 +02:00
Rene Fichtmueller
2814fb50b9 fix: correct DATABASE_URL to point to Erik server (82.165.222.127) instead of localhost 2026-04-26 00:24:20 +02:00
Rene Fichtmueller
4c54a6fa92 refactor: MAGATAMA pipeline code quality audit — all functions <50 lines 
Complete code quality audit of llm-gateway pipeline modules for MAGATAMA standard compliance (50-line function maximum). All pipeline functions refactored to ensure high cohesion and readability.

Pipeline module compliance (verified):
✅ llm-client.ts — Refactored callOllama() (58→26 lines) via helper extraction
✅ instrumented-llm-client.ts — All functions <50 lines (wrapper layer)
✅ router.ts — Refactored routeByScore() (81→32 lines) via delegation
✅ request-scorer.ts — 870-line file, all functions <50 lines
✅ external-providers.ts — All functions <50 lines (49-line max)
✅ post-validator.ts — All validators <50 lines

Verified:
✓ npm run build (TypeScript, zero errors)
✓ All 6 pipeline modules independently audited
✓ Production-ready for Erik deployment (PM2 ids 19+20, port 3103)

Deployment target: Gitea (192.168.178.196:3000/rene/llm-gateway)
 2026-04-25 17:38:11 +02:00
Rene Fichtmueller
128e18b751 feat: integrate GitHub Copilot as third LLM provider via copilot-bridge 
Add GitHub Copilot API proxy integration to LLM Gateway:

* Implement copilot-bridge service:
  - HTTP wrapper managing copilot-api (GitHub Copilot API proxy)
  - OpenAI-compatible /v1/chat/completions endpoint (port 3252)
  - Graceful startup and SIGTERM shutdown handling
  - Health check endpoint with service diagnostics

* Register copilot-bridge in provider fallback chain:
  - Position: After OpenAI, before free LLM APIs (tier 4)
  - Rate limit: 60 requests/min (GitHub Copilot API limit)
  - Models: gpt-4 (reasoning), gpt-3.5-turbo (medium)
  - Authentication: GitHub Copilot subscription (internal to copilot-api)

* Update PM2 ecosystem configuration:
  - Add copilot-bridge service definition (port 3252)
  - Configure COPILOT_BRIDGE_URL in gateway environment
  - Add copilot to LLM_PROVIDERS list

* Enhance deployment automation:
  - Update ensure-bridges.sh with copilot-bridge deployment
  - Copy service files from repo to /opt/copilot-bridge
  - Run npm install for copilot-api dependency

* Comprehensive documentation:
  - Expand DEPLOYMENT-BRIDGES.md with copilot-bridge section
  - Prerequisites: Node.js 20+, GitHub Copilot subscription
  - Authentication workflow: npm run auth with GitHub OAuth
  - Troubleshooting: subscription verification, auth cache reset

Provider chain now supports:
1. Ollama (local, free)
2. claude-bridge (Claude subscription)
3. openai-bridge (OpenAI subscription)
4. copilot-bridge (GitHub Copilot subscription) ← NEW
5. Free APIs: Cerebras, Groq, Mistral, NVIDIA, Cloudflare

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-04-25 12:38:30 +02:00
Rene Fichtmueller
7599f33866 feat: integrate OpenAI Codex and ChatGPT as primary LLM providers via subscription 
- Add openai-bridge service (port 3251) for ChatGPT and Codex integration
- Update external-providers.ts with openai and chatgpt provider definitions
- Add GPT-4 Turbo, GPT-4, and GPT-3.5 Turbo models to provider registry
- Modify getApiKey() to handle bridge provider authentication
- Modify getBaseUrl() to construct URLs from env vars
- Update ecosystem.config.cjs with OPENAI_BRIDGE_URL and OPENAI_API_KEY config
- Add openai-bridge PM2 service configuration (port 3251)
- Support both claude-bridge (port 3250) and openai-bridge (port 3251) as subscription services
- Extend fallback chain: claude → openai/chatgpt → cerebras → groq → mistral → nvidia → cloudflare

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
 2026-04-25 12:29:55 +02:00
Rene Fichtmueller
590d3797c9 chore: update ecosystem.config.cjs with claude-bridge and fixed ollama URL 
- CLAUDE_BRIDGE_URL: http://localhost:3250
- CLAUDE_BRIDGE_ENABLED: true
- OLLAMA_URL: http://192.168.178.213:11434 (direct IP instead of HTTPS tunnel)
- LLM_PROVIDERS: claude,cerebras,groq,mistral,nvidia
- Add free LLM API keys (empty, to be filled with actual keys)
 2026-04-25 12:19:09 +02:00
Rene Fichtmueller
4c5003f9fc feat: fix OLLAMA_URL to use Cloudflare tunnel + add 35 prompt templates 
- Update OLLAMA_URL from 192.168.178.169 to https://ollama.fichtmueller.org
- Fix port from 3100 to 3103 (3100 was taken by Docker proxy on Erik)
- Fix DATABASE_URL password to llm_secure_2026
- Add GITEA_URL env var for ban list sync
- Add 35 prompt templates: TIP (10), EO Global Pulse (8), SwitchBlade (9),
  PeerCortex (3), internal (3), ShieldX (1), general (1)
 2026-04-02 23:00:37 +02:00
Rene Fichtmueller
3a00ff4d33 feat: initial llm-gateway implementation 
- Complete Fastify gateway with 8-stage pipeline
- Circuit breaker (opossum) per model tier
- Rate limiting per caller
- Ban list validation (EN/DE/auto-detected)
- TIP validator (SFF-8024, part numbers, wavelengths)
- Prometheus metrics
- pg-boss async queue
- PostgreSQL audit log + review queue
- 9 prompt templates (TIP, LinkedIn, ShieldX)
- Learning engine scaffolding
- Auto-learning: ban-list, few-shot, routing, prompt optimizer
 2026-04-02 22:48:55 +02:00