mirror of
https://github.com/supermemoryai/supermemory.git
synced 2026-10-22 05:26:17 +00:00
82ef13e720
When a customId is configured, the chat-completions path hands addMemoryTool the messages plus API credentials, so the save routes through /v4/conversations with the internal "conversation:" prefix stripped back off. The Responses path built the same prefixed memoryCustomId but passed neither messages nor credentials, so the conversation branch never ran and the save fell through to client.add() with "conversation:<id>" as the stored customId — a value customId validation rejects (alphanumeric/hyphen/underscore only). The error is swallowed by design (memory saves must not break the user's API call), which means every Responses API call with a customId silently saved nothing. Hand the input over as a single user message together with the credentials, mirroring the chat path, so conversation grouping works for the Responses API too. Also strip the internal prefix in the client.add fallback so the routing marker can never leak into a stored customId on any path (previously the chat path had the same leak whenever SUPERMEMORY_API_KEY was unset). Covered with mocked-SDK middleware tests: a customId save routes through addConversation with the un-prefixed conversation id and never touches client.add; the fallback stores the user's configured id, not the prefixed marker; and the no-customId path is unchanged. Two of the three tests fail against the previous implementation. |
||
|---|---|---|
| .. | ||
| agent-framework-python | ||
| ai-sdk | ||
| cartesia-sdk-python | ||
| docs-test | ||
| hooks | ||
| lib | ||
| memory-graph | ||
| openai-sdk-python | ||
| pipecat-sdk-python | ||
| tools | ||
| ui | ||
| validation | ||