fix: stop pass-1 narration leaking + remove PII masking + lower thres…#14
Conversation
…hold - Buffer supervisor pass-1 tokens and discard if memory_agent fires (prevents DeepSeek narration text leaking to user on tool calls) - Add CRITICAL output rule to supervisor prompt (no text before tool_call) - Remove PII masking from memory pipeline (Presidio was breaking embeddings) - Lower cosine similarity threshold from 0.6 to 0.35 for better recall - Add tool_use SSE event type with pulsing Database indicator in ChatWindow - Populate content_masked column with plaintext (masking removed)
|
Warning Rate limit exceeded
To continue reviewing without waiting, purchase usage credits in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (8)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
@copilot pregledaj tozi kod molq te |
…shold default Agent-Logs-Url: https://github.com/Krasimir-Hristov/AXON/sessions/bba8361d-8f1c-423d-8eb8-e46d11e5da93 Co-authored-by: Krasimir-Hristov <102061932+Krasimir-Hristov@users.noreply.github.com>
Agent-Logs-Url: https://github.com/Krasimir-Hristov/AXON/sessions/bba8361d-8f1c-423d-8eb8-e46d11e5da93 Co-authored-by: Krasimir-Hristov <102061932+Krasimir-Hristov@users.noreply.github.com>
Прегледах целия PR. Ето обобщение: ✅ Правилно имплементирано:
🐛 Бъгове, намерени и оправени (commit
🔧 Малки подобрения (commit
CodeQL: 0 нови alerts. ✅ |
|
@copilot как точно работеше PII masking s Presidio |
PII masking-ът работеше така (код в Библиотеки: Microsoft Presidio ( Какво засичаше: Write path (запис на памет): Embedding-ът се изчисляваше върху маскирания текст, а в DB се пазеше оригиналният шифрован текст. Search path (търсене): Защо се счупи: spaCy-то е English-only ( Сегашното решение: embed директно от plaintext — семантиката е запазена, multilingual работи, retrieval-ът е коректен. Оригиналният plaintext продължава да се криптира в |
|
@copilot koj model iypolyvam ya embedding |
Използваш Конфигурацията е в embedding_model: str = "openai/text-embedding-3-large"
embedding_dimensions: int = 1536Именно затова threshold-ът е 0.35 — |
…hold