mempalace--mempalace
wehub-resource-sync
c3749daf48
Tests / test-linux (3.13) (push) Failing after 0s
Tests / test-linux (3.11) (push) Failing after 1s
Tests / lint (push) Failing after 0s
Tests / test-linux (3.9) (push) Failing after 1s
Docker / build (push) Failing after 1s
Docker / build-gpu (push) Failing after 2s
Tests / test-windows (push) Has been cancelled
Tests / test-macos (push) Has been cancelled
21 行
1.0 KiB
Plaintext
21 行
1.0 KiB
Plaintext
---
|
|
description: When the user asks about past work, prior decisions, people, projects, or events that may be filed in MemPalace, call mempalace_search (or mempalace_kg_query for relational or time-bound facts) before answering from model memory. Return stored content verbatim; never guess when the palace might know.
|
|
alwaysApply: false
|
|
---
|
|
|
|
# MemPalace recall
|
|
|
|
Before answering anything that may already be in the user's memory
|
|
palace — past work, prior decisions, a person, a project, or "what did
|
|
we do / decide / discuss last time?" — search the palace first:
|
|
|
|
1. Call `mempalace_search` with a short keyword query. Use
|
|
`mempalace_kg_query` for relational or time-bound facts.
|
|
2. Quote the drawer's **verbatim** text. Never summarize or paraphrase
|
|
stored content.
|
|
3. If results are empty, say so — do not invent an answer. If the MCP
|
|
server is unavailable, surface the error; do not fall back to guessing.
|
|
|
|
Skip recall for pure greenfield work with no memory relevance (renaming
|
|
a variable, fixing a typo). Recall is question-driven, not reflexive.
|