Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.51ultron.com/llms.txt

Use this file to discover all available pages before exploring further.

Every Ultron session is persisted. Transcripts are saved turn-by-turn as JSONL. Sessions can be resumed exactly where they left off.

​
Context injection at session start

Before you type your first message, Ultron loads context in a specific order: 
Session start — context assembly
├── 1. Static system instructions    — Ultron behavior rules, tool use guidelines, quality gates
├── 2. User profile                  — business name, ICP, voice tone, competitors, platforms
├── 3. Connected integrations         — list of active services (Gmail, Stripe, HubSpot, etc.)
├── 4. Relevant memories              — max 5 entries selected by Sonnet-powered recall
└── 5. Current date                  — injected as system reminder
This order is intentional. Static content at the top enables cache sharing across sessions (lower latency, lower cost). Dynamic content at the bottom gets fresh context every time.

​
Session persistence

  • Transcripts saved as JSONL — one JSON object per message turn
  • Includes: message content, tool calls, tool results, token counts, timestamps
  • Resume at any time — context is fully reconstructed from the transcript
  • Cost tracking accumulated per session and per-turn

​
Automatic compression

As conversations grow, the compression engine manages context automatically. You never need to manually summarize or restart a session:
  1. MicroCompact fires first — removes stale tool outputs from old turns (no API call)
  2. Session Memory Compact — uses stored memories as compression baseline (no API call)
  3. API Digest — full LLM summary via fast model (last resort)
After each compression, a boundary marker is inserted. All subsequent processing only touches messages after that boundary, preventing repeated compression of already-compressed content.

​
Cost tracking

What’s trackedWhere to see it
Input tokens per turnSettings → Usage
Output tokens per turnSettings → Usage
Model used per callSettings → Usage
Total session costSettings → Usage
Long research sessions with many tool calls accumulate tokens quickly. Check usage after complex sessions to calibrate which tasks to run in API mode vs sandbox mode.