Open in the interactive docs · markdown for agents: https://neuraldeep.tech/docs/agent-config.md
Agent settings
Pick a plan, options and an agent, then copy the file to the path shown.
How the numbers are derived:
- agent streams - about three quarters of
parallel, the rest is left for other requests with the same key; - gap between requests - 60 seconds divided by chat RPM;
- request timeout - two thirds of the gateway ceiling;
- stream silence - 60 seconds;
- three retries; long session/week windows cannot be waited out by retrying.
Not every agent can express all of these numbers in its file; the notes under the config say what was applied.
Reference sections (markdown for agents)
- Start · key, errors, quotas
- Text · chat
- Vectorization
- Reranking
- Transcription
- Image recognition
- Structured output
- Clients · agents
- Remaining limits · Limits API
- Search · Search API
- OCR · documents
- Images · Image API
- Music · Music API
- PII anonymization · PII Guard
- SpeechCore · STT
- Speech synthesis · TTS API
- Who spoke when · diarization
- Text decisions · FRIDA-Decisions, clef-flash
- Drift · overview
- Files + sandbox preview
- Your own tools, skills, MCP
- Tasks · proactive
- Memory · memory
- Isolation and security
- Agent settings
- Limits · errors
- Book · search and MCP
- Streaming
- SDK · Python / JS
- Privacy