feat: MCP: add minimal response mode#27
Merged
spokV merged 3 commits intoagentic-box:devfrom Mar 13, 2026
Merged
Conversation
Add an optional response_mode argument to memory_create so callers can request a token-efficient response that returns only the created memory id. The default full payload remains unchanged. - validate response_mode against full|minimal - return only the created memory id in minimal mode - cover the minimal contract with a small fixture-based pytest Co-Authored-By: OpenAI Codex <noreply@openai.com>
Keep minimal memory_create responses compact while preserving similar-memory details when suggest_similar=true. Add focused pytest coverage for the id-only case, the preserved similar payload, and the disabled-suggestions path. Co-Authored-By: OpenAI Codex <noreply@openai.com>
spokV
approved these changes
Mar 13, 2026
Collaborator
spokV
left a comment
spokV
left a comment
There was a problem hiding this comment.
LGTM — clean implementation. Minimal response mode preserves important signals (duplicate warnings, similar memories) while cutting payload size. Good test coverage.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Helps with token efficiency when used as an MCP server.
Response payloads were hitting ~1k characters when metadata was relatively large.
tests/conftest.py: shared with #28