Short-term memory is the conversation context of messages, replies and tool results. Learn its structure, key settings, multi-stage compression on overflow, and commands to inspect or clear it.
Conversation context is the Agent’s short-term memory, containing all messages in the current session (user input, Agent replies, tool calls and results). Proper context management is critical for the Agent’s reasoning quality and cost control.
Context Structure
Each conversation turn consists of:
User message → Agent thinking → Tool call → Tool result → ... → Agent final reply
A single turn may include multiple tool calls (controlled by agent_max_steps). All tool calls and results are retained in context until compressed or trimmed.
Key Configuration
Parameter
Description
Default
agent_max_context_tokens
Maximum context token budget
200000
agent_max_context_turns
Maximum conversation turns in context
30
agent_max_steps
Maximum decision steps per turn (tool call count)
100
Configurable via config.json or the /config chat command.
Compression Strategy
When context exceeds limits, the system automatically compresses to free space. The process has multiple stages:
1. Tool Result Truncation
Before each decision loop, the system checks tool call results in historical turns. Results exceeding 20,000 characters are truncated, keeping only the beginning and end with a truncation notice. Current turn results are not affected.
2. Turn Trimming
When conversation turns exceed agent_max_context_turns:
The oldest half of complete turns is trimmed (preserving tool call chain integrity)
Trimmed messages are summarized by LLM and written to the daily memory file
Once the LLM summary is ready, it is also injected into the first user message of the retained context, helping the model maintain conversational continuity
Summary injection runs asynchronously in the background and takes effect from the next turn onward
3. Token Budget Trimming
After turn trimming, if tokens still exceed the budget:
Fewer than 5 turns: All turns undergo text compression — each turn keeps only the first user text and last Agent reply, removing intermediate tool call chains
5 or more turns: The first half of turns is trimmed again, with discarded content written to memory and a context summary injected
4. Overflow Emergency Handling
When the model API returns a context overflow error:
All current messages are summarized and written to memory
Aggressive trimming is applied (tool results limited to 10K chars, user text to 10K, max 5 turns)
If still overflowing, the entire conversation context is cleared
5. Manual Compaction
Besides the automatic strategies above, you can compact context on demand with the /compact command. It reuses the same logic as automatic trimming — older turns are summarized by the LLM and injected into the retained context, while the most recent turns are kept intact. Unlike auto-trim, it runs immediately regardless of current token usage, which is handy for freeing context before a long task.
Session Persistence
Conversation messages are persisted to a local database, automatically restored after service restart. Restore strategy:
Restores the most recent max(3, max_context_turns / 6) turns
Only retains each turn’s user text and Agent final reply, not intermediate tool call chains
Sessions older than 30 days are automatically cleaned up
Commands
Use these commands in chat to manage context:
Command
Description
/context
View current context statistics (message count, role distribution, total characters)
/clear
Clear current session context (/context clear still works as an alias)
/compact
Summarize older turns to free up context, keeping recent turns intact
/config agent_max_context_tokens 80000
Adjust context token budget
/config agent_max_context_turns 30
Adjust context turn limit
After clearing context, the Agent “forgets” previous conversation content. Content that was already written to long-term memory can still be retrieved via memory search.