feat(dream): per-line age annotations + dedup-aware prompt + max_iter=15
Three improvements to Dream's memory consolidation: 1. Per-line git-blame age annotations: MEMORY.md lines get `← Nd` suffixes (N>14) from dulwich annotate. SOUL.md/USER.md excluded as permanent. LLM uses content judgment, not just age, to decide what to prune. 2. Dedup-aware Phase 1 prompt: reframed as dual-task (extract facts + deduplicate existing files) with explicit redundancy patterns to scan for. Validated through 20 experiments (exp-002 prompt + max_iter=15 was best, averaging -1643 chars/5.4% compression per run). 3. Phase 1 analysis as commit body: dream git commits now include the full Phase 1 analysis for transparency via /dream-log. 4. max_iterations raised from 10 to 15: 30% improvement over 10 with no risk; 20 showed diminishing returns (exp-020: -701 vs exp-017: -1643).
This commit is contained in:
chengyongru
Xubin Ren
@@ -123,3 +123,55 @@ class TestDreamRun:
|
||||
assert "Successfully wrote" in result
|
||||
assert (store.workspace / "skills" / "test-skill" / "SKILL.md").exists()
|
||||
|
||||
async def test_phase1_prompt_includes_line_age_annotations(self, dream, mock_provider, mock_runner, store):
|
||||
"""Phase 1 prompt should have per-line age suffixes in MEMORY.md when git is available."""
|
||||
store.append_history("some event")
|
||||
mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
|
||||
mock_runner.run = AsyncMock(return_value=_make_run_result())
|
||||
|
||||
# Init git so line_ages works
|
||||
store.git.init()
|
||||
store.git.auto_commit("initial memory state")
|
||||
|
||||
await dream.run()
|
||||
|
||||
# The MEMORY.md section should not crash and should contain the memory content
|
||||
call_args = mock_provider.chat_with_retry.call_args
|
||||
user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
|
||||
assert "## Current MEMORY.md" in user_msg
|
||||
|
||||
async def test_phase1_annotates_only_memory_not_soul_or_user(self, dream, mock_provider, mock_runner, store):
|
||||
"""SOUL.md and USER.md should never have age annotations — they are permanent."""
|
||||
store.append_history("some event")
|
||||
mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
|
||||
mock_runner.run = AsyncMock(return_value=_make_run_result())
|
||||
|
||||
store.git.init()
|
||||
store.git.auto_commit("initial state")
|
||||
|
||||
await dream.run()
|
||||
|
||||
call_args = mock_provider.chat_with_retry.call_args
|
||||
user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
|
||||
# The ← suffix should only appear in MEMORY.md section
|
||||
memory_section = user_msg.split("## Current MEMORY.md")[1].split("## Current SOUL.md")[0]
|
||||
soul_section = user_msg.split("## Current SOUL.md")[1].split("## Current USER.md")[0]
|
||||
user_section = user_msg.split("## Current USER.md")[1]
|
||||
# SOUL and USER should not contain age arrows
|
||||
assert "\u2190" not in soul_section
|
||||
assert "\u2190" not in user_section
|
||||
|
||||
async def test_phase1_prompt_works_without_git(self, dream, mock_provider, mock_runner, store):
|
||||
"""Phase 1 should work fine even if git is not initialized (no age annotations)."""
|
||||
store.append_history("some event")
|
||||
mock_provider.chat_with_retry.return_value = MagicMock(content="[SKIP]")
|
||||
mock_runner.run = AsyncMock(return_value=_make_run_result())
|
||||
|
||||
await dream.run()
|
||||
|
||||
# Should still succeed — just without age annotations
|
||||
mock_provider.chat_with_retry.assert_called_once()
|
||||
call_args = mock_provider.chat_with_retry.call_args
|
||||
user_msg = call_args.kwargs.get("messages", call_args[1].get("messages"))[1]["content"]
|
||||
assert "## Current MEMORY.md" in user_msg
|
||||
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
"""Tests for GitStore — line_ages() and core git operations."""
|
||||
|
||||
import time
|
||||
from datetime import datetime, timezone, timedelta
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from nanobot.utils.gitstore import GitStore
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def git(tmp_path):
|
||||
"""Create an initialized GitStore with tracked MEMORY.md."""
|
||||
g = GitStore(tmp_path, tracked_files=["MEMORY.md", "SOUL.md"])
|
||||
g.init()
|
||||
return g
|
||||
|
||||
|
||||
class TestLineAges:
|
||||
def test_returns_empty_when_not_initialized(self, tmp_path):
|
||||
"""line_ages should return [] if the git repo is not initialized."""
|
||||
git = GitStore(tmp_path, tracked_files=["MEMORY.md"])
|
||||
assert git.line_ages("MEMORY.md") == []
|
||||
|
||||
def test_returns_empty_for_missing_file(self, git):
|
||||
"""line_ages should return [] for a file that doesn't exist."""
|
||||
assert git.line_ages("SOUL.md") == []
|
||||
|
||||
def test_returns_empty_for_empty_file(self, git, tmp_path):
|
||||
"""line_ages should return [] for an empty tracked file."""
|
||||
(tmp_path / "SOUL.md").write_text("", encoding="utf-8")
|
||||
git.auto_commit("empty soul")
|
||||
assert git.line_ages("SOUL.md") == []
|
||||
|
||||
def test_one_age_per_line(self, git, tmp_path):
|
||||
"""line_ages should return one entry per line in the file."""
|
||||
content = "# Memory\n\n## Section A\n- item 1\n"
|
||||
(tmp_path / "MEMORY.md").write_text(content, encoding="utf-8")
|
||||
git.auto_commit("initial")
|
||||
ages = git.line_ages("MEMORY.md")
|
||||
assert len(ages) == len(content.splitlines())
|
||||
|
||||
def test_fresh_lines_have_age_zero(self, git, tmp_path):
|
||||
"""Lines committed today should have age_days=0."""
|
||||
(tmp_path / "MEMORY.md").write_text("## A\n- x\n", encoding="utf-8")
|
||||
git.auto_commit("initial")
|
||||
ages = git.line_ages("MEMORY.md")
|
||||
assert all(a.age_days == 0 for a in ages)
|
||||
|
||||
def test_age_differentiates_across_days(self, git, tmp_path):
|
||||
"""Lines committed today should show correct age when 'now' is mocked forward."""
|
||||
(tmp_path / "MEMORY.md").write_text("## A\n- x\n", encoding="utf-8")
|
||||
git.auto_commit("initial")
|
||||
|
||||
future_now = datetime.now(tz=timezone.utc) + timedelta(days=30)
|
||||
with patch("nanobot.utils.gitstore.datetime") as mock_dt:
|
||||
mock_dt.now.return_value = future_now
|
||||
mock_dt.fromtimestamp = datetime.fromtimestamp
|
||||
ages = git.line_ages("MEMORY.md")
|
||||
|
||||
assert len(ages) == 2
|
||||
assert all(a.age_days == 30 for a in ages)
|
||||
|
||||
def test_annotate_failure_returns_empty(self, tmp_path):
|
||||
"""If annotate fails, line_ages should return [] gracefully."""
|
||||
git = GitStore(tmp_path, tracked_files=["MEMORY.md"])
|
||||
# Don't init — annotate will fail
|
||||
assert git.line_ages("MEMORY.md") == []
|
||||
|
||||
def test_partial_edit_only_updates_changed_lines(self, git, tmp_path):
|
||||
"""Only modified lines should reflect the new commit's timestamp."""
|
||||
(tmp_path / "MEMORY.md").write_text(
|
||||
"# Memory\n\n## A\n- old\n\n## B\n- keep\n", encoding="utf-8"
|
||||
)
|
||||
git.auto_commit("commit1")
|
||||
time.sleep(1.1)
|
||||
|
||||
# Only modify section A
|
||||
(tmp_path / "MEMORY.md").write_text(
|
||||
"# Memory\n\n## A\n- new\n\n## B\n- keep\n", encoding="utf-8"
|
||||
)
|
||||
git.auto_commit("commit2")
|
||||
|
||||
ages = git.line_ages("MEMORY.md")
|
||||
lines = (tmp_path / "MEMORY.md").read_text(encoding="utf-8").splitlines()
|
||||
# All lines are from today, but verify line-level tracking works
|
||||
assert len(ages) == len(lines)
|
||||
# "- new" line and "- keep" line both age=0 (same day), but
|
||||
# the key point is we get per-line results
|
||||
assert len(ages) == 7
|
||||
Reference in New Issue
Block a user