Files
spring-ai/chat-memory/output/02-advisor-conversations.txt
Claude 823f6fac5b Add chat-memory module: MessageWindowChatMemory, JDBC and Redis repositories, per-user conversation IDs
Real PostgreSQL 16 and Redis Stack 7.4; 24 tests write output/01-24. Covers the 20-message
default window with no property, the 36-character conversation_id, tool messages dropped by
JdbcChatMemoryRepository, concurrent add() on one conversation, a 1.x table under the 2.0
repository, the Redis repository silently backing off for a custom ChatMemory, and the
removal of PromptChatMemoryAdvisor.

Co-Authored-By: Claude Sonnet 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Ja4jkzrbQ4LQZBNrb5mkZE
2026-09-24 15:56:47 +00:00

20 lines
728 B
Plaintext

# MessageChatMemoryAdvisor: what the model is sent
conv-A, call 1: "My name is Priya"
reply: Nice to meet you, Priya.
model was sent: S:You are a terse assistant. | U:My name is Priya
conv-A, call 2: "What is my name?"
reply: Your name is Priya.
model was sent: S:You are a terse assistant. | U:My name is Priya | A:Nice to meet you, Priya. | U:What is my name?
conv-B, call 1: "What is my name?" (different conversation ID)
reply: I do not know your name yet.
model was sent: S:You are a terse assistant. | U:What is my name?
Stored for conv-A afterwards:
USER My name is Priya
ASSISTANT Nice to meet you, Priya.
USER What is my name?
ASSISTANT Your name is Priya.