MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-04-22 19:14:33 -07:00
Code Issues Packages Projects Releases Wiki Activity

refactor(memory): replace MemoryManagerAgent with prompt-driven memory editing across four tiers (#25716)

Browse Source
This commit is contained in:
Sandy Tao
2026-04-21 18:21:55 -07:00
committed by GitHub
parent ffb28c772b
commit 6edfba481f
24 changed files with 772 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files
evals/save_memory.eval.ts
+291 -21
View File
@@ -283,7 +283,7 @@ describe('save_memory', () => {
name: proactiveMemoryFromLongSession,
params: {
settings: {
experimental: { memoryManager: true },
experimental: { memoryV2: true },
},
},
messages: [
@@ -341,29 +341,75 @@ describe('save_memory', () => {
prompt:
'Please save any persistent preferences or facts about me from our conversation to memory.',
assert: async (rig, result) => {
const wasToolCalled = await rig.waitForToolCall(
'invoke_agent',
undefined,
(args) => /save_memory/i.test(args) && /vitest/i.test(args),
);
// Under experimental.memoryV2, the agent persists memories by
// editing markdown files directly with write_file or replace — not via
// a save_memory subagent. The user said "I always prefer Vitest over
// Jest for testing in all my projects" — that matches the new
// cross-project cue phrase ("across all my projects"), so under the
// 4-tier model the correct destination is the global personal memory
// file (~/.gemini/GEMINI.md). It must NOT land in a committed project
// GEMINI.md (that tier is for team conventions) or the per-project
// private memory folder (that tier is for project-specific personal
// notes). The chat history mixes this durable preference with
// transient debugging chatter, so the eval also verifies the agent
// picks out the persistent fact among the noise.
await rig.waitForToolCall('write_file').catch(() => {});
const writeCalls = rig
.readToolLogs()
.filter((log) =>
['write_file', 'replace'].includes(log.toolRequest.name),
);
const wroteVitestToGlobal = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/GEMINI\.md/i.test(args) &&
!/tmp\/[^/]+\/memory/i.test(args) &&
/vitest/i.test(args)
);
});
expect(
wasToolCalled,
'Expected invoke_agent to be called with save_memory agent and the Vitest preference from the conversation history',
wroteVitestToGlobal,
'Expected the cross-project Vitest preference to be written to the global personal memory file (~/.gemini/GEMINI.md) via write_file or replace',
).toBe(true);
const leakedToCommittedProject = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/GEMINI\.md/i.test(args) &&
!/\.gemini\//i.test(args) &&
/vitest/i.test(args)
);
});
expect(
leakedToCommittedProject,
'Cross-project Vitest preference must NOT be mirrored into a committed project ./GEMINI.md (that tier is for team-shared conventions only)',
).toBe(false);
const leakedToPrivateProject = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/tmp\/[^/]+\/memory\//i.test(args) && /vitest/i.test(args)
);
});
expect(
leakedToPrivateProject,
'Cross-project Vitest preference must NOT be mirrored into the private project memory folder (that tier is for project-specific personal notes only)',
).toBe(false);
assertModelHasOutput(result);
},
});
const memoryManagerRoutingPreferences =
'Agent routes global and project preferences to memory';
const memoryV2RoutesTeamConventionsToProjectGemini =
'Agent routes team-shared project conventions to ./GEMINI.md';
evalTest('USUALLY_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: memoryManagerRoutingPreferences,
name: memoryV2RoutesTeamConventionsToProjectGemini,
params: {
settings: {
experimental: { memoryManager: true },
experimental: { memoryV2: true },
},
},
messages: [
@@ -372,7 +418,7 @@ describe('save_memory', () => {
type: 'user',
content: [
{
text: 'I always use dark mode in all my editors and terminals.',
text: 'For this project, the team always runs tests with `npm run test` — please remember that as our project convention.',
},
],
timestamp: '2026-01-01T00:00:00Z',
@@ -380,7 +426,9 @@ describe('save_memory', () => {
{
id: 'msg-2',
type: 'gemini',
content: [{ text: 'Got it, I will keep that in mind!' }],
content: [
{ text: 'Got it, I will keep `npm run test` in mind for tests.' },
],
timestamp: '2026-01-01T00:00:05Z',
},
{
@@ -404,16 +452,238 @@ describe('save_memory', () => {
],
prompt: 'Please save the preferences I mentioned earlier to memory.',
assert: async (rig, result) => {
const wasToolCalled = await rig.waitForToolCall(
'invoke_agent',
undefined,
(args) => /save_memory/i.test(args),
);
// Under experimental.memoryV2, the prompt enforces an explicit
// one-tier-per-fact rule: team-shared project conventions (the team's
// test command, project-wide indentation rules) belong in the
// committed project-root ./GEMINI.md and must NOT be mirrored or
// cross-referenced into the private project memory folder
// (~/.gemini/tmp/<hash>/memory/). The global ~/.gemini/GEMINI.md must
// never be touched in this mode either.
await rig.waitForToolCall('write_file').catch(() => {});
const writeCalls = rig
.readToolLogs()
.filter((log) =>
['write_file', 'replace'].includes(log.toolRequest.name),
);
const wroteToProjectRoot = (factPattern: RegExp) =>
writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/GEMINI\.md/i.test(args) &&
!/\.gemini\//i.test(args) &&
factPattern.test(args)
);
});
expect(
wasToolCalled,
'Expected invoke_agent to be called with save_memory agent',
wroteToProjectRoot(/npm run test/i),
'Expected the team test-command convention to be written to the project-root ./GEMINI.md',
).toBe(true);
expect(
wroteToProjectRoot(/2[- ]space/i),
'Expected the project-wide "2-space indentation" convention to be written to the project-root ./GEMINI.md',
).toBe(true);
const leakedToPrivateMemory = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/tmp\/[^/]+\/memory\//i.test(args) &&
(/npm run test/i.test(args) || /2[- ]space/i.test(args))
);
});
expect(
leakedToPrivateMemory,
'Team-shared project conventions must NOT be mirrored into the private project memory folder (~/.gemini/tmp/<hash>/memory/) — each fact lives in exactly one tier.',
).toBe(false);
const leakedToGlobal = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/GEMINI\.md/i.test(args) &&
!/tmp\/[^/]+\/memory/i.test(args)
);
});
expect(
leakedToGlobal,
'Project preferences must NOT be written to the global ~/.gemini/GEMINI.md',
).toBe(false);
assertModelHasOutput(result);
},
});
const memoryV2RoutesUserProject =
'Agent routes personal-to-user project notes to user-project memory';
evalTest('USUALLY_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: memoryV2RoutesUserProject,
params: {
settings: {
experimental: { memoryV2: true },
},
},
prompt: `Please remember my personal local dev setup for THIS project's Postgres database. This is private to my machine — do NOT commit it to the repo.
Connection details:
- Host: localhost
- Port: 6543 (non-standard, I run multiple Postgres instances)
- Database: myproj_dev
- User: sandy_local
- Password: read from the SANDY_PG_LOCAL_PASS env var in my shell
How I start it locally:
1. Run \`brew services start postgresql@15\` to bring the server up.
2. Run \`./scripts/seed-local-db.sh\` from the repo root to load my personal seed data.
3. Verify with \`psql -h localhost -p 6543 -U sandy_local myproj_dev -c '\\dt'\`.
Quirks to remember:
- The migrations runner sometimes hangs on my machine if I forget step 1; kill it with Ctrl+C and rerun.
- I keep an extra \`scratch\` schema for ad-hoc experiments — never reference it from project code.`,
assert: async (rig, result) => {
// Under experimental.memoryV2 with the Private Project Memory bullet
// surfaced in the prompt, a fact that is project-specific AND
// personal-to-the-user (must not be committed) should land in the
// private project memory folder under ~/.gemini/tmp/<hash>/memory/. The
// detailed note should be written to a sibling markdown file, with
// MEMORY.md updated as the index. It must NOT go to committed
// ./GEMINI.md or the global ~/.gemini/GEMINI.md.
await rig.waitForToolCall('write_file').catch(() => {});
const writeCalls = rig
.readToolLogs()
.filter((log) =>
['write_file', 'replace'].includes(log.toolRequest.name),
);
const wroteUserProjectDetail = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/tmp\/[^/]+\/memory\/(?!MEMORY\.md)[^"]+\.md/i.test(args) &&
/6543/.test(args)
);
});
expect(
wroteUserProjectDetail,
'Expected the personal-to-user project note to be written to a private project memory detail file (~/.gemini/tmp/<hash>/memory/*.md)',
).toBe(true);
const wroteUserProjectIndex = writeCalls.some((log) => {
const args = log.toolRequest.args;
return /\.gemini\/tmp\/[^/]+\/memory\/MEMORY\.md/i.test(args);
});
expect(
wroteUserProjectIndex,
'Expected the personal-to-user project note to update the private project memory index (~/.gemini/tmp/<hash>/memory/MEMORY.md)',
).toBe(true);
// Defensive: should NOT have written this private note to the
// committed project GEMINI.md or the global GEMINI.md.
const leakedToCommittedProject = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\/GEMINI\.md/i.test(args) &&
!/\.gemini\//i.test(args) &&
/6543/.test(args)
);
});
expect(
leakedToCommittedProject,
'Personal-to-user note must NOT be written to the committed project GEMINI.md',
).toBe(false);
const leakedToGlobal = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/GEMINI\.md/i.test(args) &&
!/tmp\/[^/]+\/memory/i.test(args) &&
/6543/.test(args)
);
});
expect(
leakedToGlobal,
'Personal-to-user project note must NOT be written to the global ~/.gemini/GEMINI.md',
).toBe(false);
assertModelHasOutput(result);
},
});
const memoryV2RoutesCrossProjectToGlobal =
'Agent routes cross-project personal preferences to ~/.gemini/GEMINI.md';
evalTest('USUALLY_PASSES', {
suiteName: 'default',
suiteType: 'behavioral',
name: memoryV2RoutesCrossProjectToGlobal,
params: {
settings: {
experimental: { memoryV2: true },
},
},
prompt:
'Please remember this about me in general: across all my projects I always prefer Prettier with single quotes and trailing commas, and I always prefer tabs over spaces for indentation. These are my personal coding-style defaults that follow me into every workspace.',
assert: async (rig, result) => {
// Under experimental.memoryV2 with the Global Personal Memory
// tier surfaced in the prompt, a fact that explicitly applies to the
// user "across all my projects" / "in every workspace" must land in
// the global ~/.gemini/GEMINI.md (the cross-project tier). It must
// NOT be mirrored into a committed project-root ./GEMINI.md (that
// tier is for team-shared conventions) or into the per-project
// private memory folder (that tier is for project-specific personal
// notes). Each fact lives in exactly one tier across all four tiers.
await rig.waitForToolCall('write_file').catch(() => {});
const writeCalls = rig
.readToolLogs()
.filter((log) =>
['write_file', 'replace'].includes(log.toolRequest.name),
);
const wroteToGlobal = (factPattern: RegExp) =>
writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/GEMINI\.md/i.test(args) &&
!/tmp\/[^/]+\/memory/i.test(args) &&
factPattern.test(args)
);
});
expect(
wroteToGlobal(/Prettier/i),
'Expected the cross-project Prettier preference to be written to the global personal memory file (~/.gemini/GEMINI.md)',
).toBe(true);
expect(
wroteToGlobal(/tabs/i),
'Expected the cross-project "tabs over spaces" preference to be written to the global personal memory file (~/.gemini/GEMINI.md)',
).toBe(true);
const leakedToCommittedProject = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/GEMINI\.md/i.test(args) &&
!/\.gemini\//i.test(args) &&
(/Prettier/i.test(args) || /tabs/i.test(args))
);
});
expect(
leakedToCommittedProject,
'Cross-project personal preferences must NOT be mirrored into a committed project ./GEMINI.md (that tier is for team-shared conventions only)',
).toBe(false);
const leakedToPrivateProject = writeCalls.some((log) => {
const args = log.toolRequest.args;
return (
/\.gemini\/tmp\/[^/]+\/memory\//i.test(args) &&
(/Prettier/i.test(args) || /tabs/i.test(args))
);
});
expect(
leakedToPrivateProject,
'Cross-project personal preferences must NOT be mirrored into the private project memory folder (that tier is for project-specific personal notes only)',
).toBe(false);
assertModelHasOutput(result);
},
});