fix(dream): stop duplicating SOUL/USER/MEMORY into the Dream prompt (#5622)

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: chengyongru <chengyongru.ai@gmail.com>
This commit is contained in:
Wind.D
2026-09-01 17:17:35 +08:00
committed by GitHub
co-authored by Claude Sonnet 5 chengyongru
parent eebe3ca292
commit dda67286f9
3 changed files with 64 additions and 53 deletions
+2 -34
View File
@@ -62,10 +62,6 @@ class MemoryStore:
# Deliberately excludes memory/.dream_cursor so progress bookkeeping never # Deliberately excludes memory/.dream_cursor so progress bookkeeping never
# appears as a durable-memory edit in the audit record. # appears as a durable-memory edit in the audit record.
_DREAM_CONTENT_PATHS = ("SOUL.md", "USER.md", "memory/MEMORY.md") _DREAM_CONTENT_PATHS = ("SOUL.md", "USER.md", "memory/MEMORY.md")
# Per-file cap when embedding current contents into the Dream prompt. The
# durable files are tiny in practice (~5 KB total), but a runaway file must
# not unbounded the prompt.
_DREAM_FILE_EMBED_CAP = 8000
_LEGACY_ENTRY_START_RE = re.compile(r"^\[(\d{4}-\d{2}-\d{2}[^\]]*)\]\s*") _LEGACY_ENTRY_START_RE = re.compile(r"^\[(\d{4}-\d{2}-\d{2}[^\]]*)\]\s*")
_LEGACY_TIMESTAMP_RE = re.compile(r"^\[(\d{4}-\d{2}-\d{2} \d{2}:\d{2})\]\s*") _LEGACY_TIMESTAMP_RE = re.compile(r"^\[(\d{4}-\d{2}-\d{2} \d{2}:\d{2})\]\s*")
_LEGACY_RAW_MESSAGE_RE = re.compile( _LEGACY_RAW_MESSAGE_RE = re.compile(
@@ -549,9 +545,7 @@ class MemoryStore:
Returns ``(prompt, last_cursor)`` or ``None`` if nothing to process. Returns ``(prompt, last_cursor)`` or ``None`` if nothing to process.
The current contents of the durable memory files (SOUL.md, USER.md, The current contents of the durable memory files (SOUL.md, USER.md,
memory/MEMORY.md) are embedded so the model edits the real files rather memory/MEMORY.md) reach Dream through the normal agent system context.
than a stale mental model — eliminating a class of failed/out-of-bounds
edits that previously produced hallucinated audit records.
""" """
last_cursor = self.get_last_dream_cursor() last_cursor = self.get_last_dream_cursor()
entries = self.read_unprocessed_history(since_cursor=last_cursor) entries = self.read_unprocessed_history(since_cursor=last_cursor)
@@ -564,35 +558,9 @@ class MemoryStore:
for e in batch for e in batch
) )
template = self._dream_template() template = self._dream_template()
files_section = self._render_current_memory_files() prompt = f"{template}\n\n## Conversation History\n{history_text}"
prompt = (
f"{template}\n\n{files_section}\n\n"
f"## Conversation History\n{history_text}"
)
return (prompt, batch[-1]["cursor"]) return (prompt, batch[-1]["cursor"])
def _render_current_memory_files(self) -> str:
"""Render the durable memory files' current contents for the Dream prompt.
Missing files render as ``(empty)``; oversized files are capped. The
section is the ground truth the model must edit against.
"""
files = [
("SOUL.md", self.soul_file),
("USER.md", self.user_file),
("memory/MEMORY.md", self.memory_file),
]
blocks: list[str] = []
for label, path in files:
try:
content = path.read_text(encoding="utf-8") if path.exists() else ""
except OSError:
content = ""
if len(content) > self._DREAM_FILE_EMBED_CAP:
content = truncate_text(content, self._DREAM_FILE_EMBED_CAP) + "\n...[truncated]"
blocks.append(f"### {label}\n{content}" if content.strip() else f"### {label}\n(empty)")
return "## Current Memory Files\n" + "\n\n".join(blocks)
def dream_content_diff(self) -> str: def dream_content_diff(self) -> str:
"""Structured summary of uncommitted changes to the durable memory files. """Structured summary of uncommitted changes to the durable memory files.
+1 -1
View File
@@ -99,7 +99,7 @@ For [SKILL] entries:
- Skills are instruction sets with concrete values, commands, and examples. MEMORY.md keeps strategic context and high-level facts only. - Skills are instruction sets with concrete values, commands, and examples. MEMORY.md keeps strategic context and high-level facts only.
## Editing ## Editing
- Current contents of SOUL.md, USER.md, and memory/MEMORY.md are embedded in this prompt under "Current Memory Files". Edit those files directly; do not rely on a remembered version of a file. - Current contents of SOUL.md, USER.md, and memory/MEMORY.md are provided by the agent system context. Edit those files directly; do not rely on a remembered version of a file.
- Batch changes into as few calls as possible. Surgical edits only. - Batch changes into as few calls as possible. Surgical edits only.
## Verification ## Verification
+61 -18
View File
@@ -62,28 +62,14 @@ class TestBuildDreamPrompt:
prompt, _ = result prompt, _ = result
assert "skill-creator" in prompt assert "skill-creator" in prompt
def test_prompt_embeds_current_memory_file_contents(self, store): def test_prompt_does_not_duplicate_current_memory_file_contents(self, store):
"""Dream must see the real current file contents (Tier 4) so it edits the
files, not a stale mental model."""
store.append_history("hello") store.append_history("hello")
result = store.build_dream_prompt() result = store.build_dream_prompt()
assert result is not None assert result is not None
prompt, _ = result prompt, _ = result
assert "## Current Memory Files" in prompt assert "## Current Memory Files" not in prompt
assert "### SOUL.md" in prompt assert "Project X active" not in prompt
assert "### USER.md" in prompt assert "Helpful" not in prompt
assert "### memory/MEMORY.md" in prompt
# Real current contents are embedded verbatim.
assert "Project X active" in prompt
assert "Helpful" in prompt
def test_prompt_renders_missing_files_as_empty(self, tmp_path):
store = MemoryStore(tmp_path) # no durable files written
store.append_history("hello")
result = store.build_dream_prompt()
assert result is not None
prompt, _ = result
assert "(empty)" in prompt
def test_workspace_dream_prompt_overrides_default(self, store): def test_workspace_dream_prompt_overrides_default(self, store):
store.dream_prompt_file.parent.mkdir(parents=True) store.dream_prompt_file.parent.mkdir(parents=True)
@@ -625,6 +611,63 @@ class TestEphemeralDirect:
assert "entry-21" not in request_text assert "entry-21" not in request_text
assert "entry-60" not in request_text assert "entry-60" not in request_text
async def test_dream_turn_injects_memory_files_once_and_persists_session(self, tmp_path):
"""Dream gets durable files from system context without losing its session record."""
from unittest.mock import MagicMock
from nanobot.agent.loop import AgentLoop
from nanobot.bus.queue import MessageBus
markers = {
"SOUL.md": "DREAM_SOUL_MARKER",
"USER.md": "DREAM_USER_MARKER",
"memory/MEMORY.md": "DREAM_MEMORY_MARKER",
}
store = MemoryStore(tmp_path)
store.write_soul(markers["SOUL.md"])
store.write_user(markers["USER.md"])
store.write_memory(markers["memory/MEMORY.md"])
store.append_history("history-marker")
(tmp_path / "AGENTS.md").write_text("DREAM_AGENTS_MARKER", encoding="utf-8")
result = store.build_dream_prompt()
assert result is not None
prompt, _ = result
captured: dict[str, list[dict]] = {}
provider = MagicMock()
provider.get_default_model.return_value = "test-model"
provider.supports_tools = True
provider.generation = MagicMock(max_tokens=4096)
async def chat_with_retry(**kwargs):
captured["messages"] = kwargs["messages"]
return LLMResponse(content="done", finish_reason="stop")
provider.chat_with_retry = chat_with_retry
loop = AgentLoop(
bus=MessageBus(),
provider=provider,
workspace=tmp_path,
context_window_tokens=32_000,
)
session_key = "dream:single-memory-copy"
await loop.process_direct(
prompt,
session_key=session_key,
ephemeral=True,
tools=store.build_dream_tools(),
)
messages = captured["messages"]
system_prompt = str(messages[0]["content"])
request_text = "\n".join(str(message.get("content", "")) for message in messages)
for marker in [*markers.values(), "DREAM_AGENTS_MARKER"]:
assert marker in system_prompt
assert request_text.count(marker) == 1
assert loop.sessions._get_session_path(session_key).exists()
class TestEphemeralHooks: class TestEphemeralHooks:
"""When ephemeral=True, extra hooks must not fire.""" """When ephemeral=True, extra hooks must not fire."""