ElenaRevicheva/AIPA_AITCF

> **Web Data UNLOCKED hackathon submission (May 2026):** Track 1 — GTM Intelligence. Four Bright Data products in production (Web Unlocker, SERP API, Scraping Browser, MCP Server) + autonomous Claude tool-use loop exposing them as /research_company, /research_employer, /research_competitor Telegram commands. See Live Web Data Layer below.
Single TypeScript service that:
- Automatically reviews every PR and push
- Routes between LLMs based on criticality
- Persists technical memory in Oracle Autonomous DB
- Exposes technical Q&A via API and Telegram
Deployed on Oracle Cloud. PM2-managed. **Elena Revicheva** · AIdeazz · LinkedIn
---
Screenshots
| | |
|:---:|:---:|
| **1. Architecture or health** — System overview or GET / response | **2. PR review** — GitHub PR or commit with CTO review comment |
| | |
| **3. Telegram** — CTO bot menu or /ask / /daily response | **4. Atuona** — /create or /visualize output |
*Add images to docs/assets/ (see docs/assets/README.md).*
PR and commit reviews are triggered by the GitHub webhook to CTO AIPA.
---
Architecture (high level)
- **Triggers:** GitHub webhook, Telegram (Grammy), HTTP POST /ask-cto.
- **Service:** Single process. Deterministic rules run first; then model router; then LLM. Results persisted to Oracle (and file for Atuona).
- **Persistence:** Oracle Autonomous DB (mTLS) for CTO memory, tech debt, context; JSON file for Atuona creative state.
---
Orchestration flow (bullet pipeline)
**Code review (PR or push):**
1. GitHub sends webhook → Express receives.
2. Fetch diff; run **deterministic** checks (security, complexity, architecture patterns).
3. **Route:** If critical (security/payment/keywords) or explicit override → Claude Opus 4; else → Groq Llama 3.3 70B.
4. Build prompt with diff + rule results + last N memories from Oracle.
5. LLM returns review text → post comment on PR/commit.
6. Save to aipa_memory (Oracle); notify CMO webhook (non-blocking).
**Ask CTO (API or Telegram):**
1. Request (JSON or message) → load conversation context from Oracle.
2. **Route:** Always Claude Opus 4 for strategic Q&A.
3. LLM returns answer → save to aipa_memory and conversation context; respond to client.
**Atuona (Telegram):**
1. Message/voice → Whisper for transcription if voice.
2. Load atuona-state.json (mood, creative memory); select mood; inject knowledge + anti-repetition lists.
3. Claude Opus 4 generates → extractAndTrackFromResponse() updates creative memory → save state; reply.
---
Model routing logic
| Trigger / task | Model | Reason |
|----------------|--------|--------|
| Code review, **critical** (security, payment, or useClaudeForCritical) | Claude Opus 4 | Best for security and architecture reasoning. |
| Code review, **standard** | Groq Llama 3.3 70B | Fast, free tier; sufficient for routine style/complexity. |
| Ask CTO (API or Telegram) | Claude Opus 4 | Strategic and multi-repo context. |
| Voice message (Telegram) | Whisper (Groq) → then Claude Opus 4 | Transcription then same as text. |
| Atuona (all text/creative) | Claude Opus 4 | Consistency and creative quality. |
| Atuona image/video | Replicate / Runway / Luma / DALL·E | Per-request availability. |
Configurable via env: CRITICAL_MODEL, STRATEGIC_MODEL, STANDARD_MODEL.
---
Why deterministic + LLM split
- **Deterministic rules** handle everything that must be consistent and cheap: regex/pattern checks for SQL injection, hardcoded secrets, XSS, eval, debug code; line-count and nesting for complexity; detection of patterns (async/await, try-catch, types). No token cost, no flakiness, instant. The LLM then gets a structured summary (e.g. “3 high, 2 low”) and the diff, and focuses on synthesis and advice.
- **LLM** is used only where reasoning or language is needed: review narrative, answer to “How should I structure auth?”, dialogue, creative text. We avoid using the model for things that can be computed.
- **Result:** Lower cost (Groq for most reviews), predictable security/complexity signals, and a single place to tune “when to use Claude” (critical path and config).
---
Data lifecycle (how memory tables are used)
| Store | Written when | Read when |
|-------|----------------|-----------|
| **aipa_memory** | After every code review and every Ask CTO answer. | Before review (last N for this repo/action); before Ask CTO (recent Q&A). |
| **tech_debt** | When user or CTO records tech debt via Telegram/API. | When listing or resolving debt. |
| **arch_decisions** | When a decision is recorded. | When listing decisions for context. |