Skip to content
HotKVDocs

Ask the HotKV docs

Answers come only from these docs and can be wrong; check the linked pages before you rely on them.

AMEM.CONV.WINDOW

Last updated 
AMEM.CONV.WINDOW session_id count
Group
Agent memory
Complexity
O(count)
Arity
3 (exactly, counting the command name)
Flags
read-only, fast
Keys
first 1, last 1, step 1
HotKV Cloud
Performance and Scale
On-Premise
requires the agent-memory license feature

Agent memory gives AI agents four kinds of memory. Conversation memory keeps the recent turns of a chat session as a bounded sliding window: when a session holds its maximum number of turns, appending a new turn drops the oldest. AMEM.CONV.WINDOW returns the last count turns, oldest first, which is the shape you usually feed back into a model prompt. If the session holds fewer turns, you get all of them.

Return value

Section titled “Return value”
Case RESP2 RESP3
Always Array of turns, oldest first. Each turn is a flat array: "role", the role, "content", the content (all bulk strings). Empty for an unknown session or a count of 0. Same

Errors:

  • ERR invalid count if count is not a non-negative integer.
  • ERR wrong number of arguments for 'amem.conv.window' command if the argument count is wrong.
  • NOLICENSE agent-memory requires a HotKV license. Contact sales@hotkv.com if your license does not include the agent-memory feature.

Examples

Section titled “Examples”
127.0.0.1:6379> AMEM.CONV.WINDOW agent-42 1
1) 1) "role"
   2) "assistant"
   3) "content"
   4) "I'll check the weather for you."

Compatibility

Section titled “Compatibility”

HotKV-only command. Redis and Valkey have no equivalent.

See also

Section titled “See also”

AMEM.CONV.CREATE, AMEM.CONV.APPEND, AMEM.CONV.GET, AMEM.CONV.CLEAR, AMEM.CONV.DROP, AI features guide