kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-17 11:07:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(evolution): add self-evolution subsystem

Browse Source 
Add a self-evolution subsystem that reviews idle conversations in an
isolated agent and durably learns from them — patching/creating skills,
finishing unfinished tasks, and backfilling missed memory.

- Trigger: background idle scan, fires when a session is idle >= N min AND
  (>= N turns OR context usage > 80%). In-memory cursor reviews only new
  messages so a session never re-learns old content.
- Isolated review agent: same model, restricted toolset, hard write-guard
  confining edits to the workspace (built-in skills are protected).
- Safety: file-level backup before edits + evolution_undo tool; notify the
  user ONLY when a workspace file actually changed (no-nag rule); capped
  concurrency.
- Records to memory/evolution/<date>.md, surfaced in the memory UI's
  renamed "Self-Evolution" tab (merged with dream diaries).
- Hide internal [SCHEDULED]/[EVOLUTION]/backup_id markers from chat history
  display (also fixes scheduler marker leakage) while keeping them in stored
  content for undo.
- Flat config: self_evolution_enabled (default off until release),
  self_evolution_idle_minutes (15), self_evolution_min_turns (6).
- Tests: tests/test_evolution.py (stub + real model modes, 7 scenarios).
This commit is contained in:
zhayujie
2026-06-07 18:55:33 +08:00
parent 0e4da1d1c5
commit ba777ed706
19 changed files with 1856 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
agent/memory/conversation_store.py
View File

@@ -13,6 +13,7 @@ Storage path: ~/cow/sessions/conversations.db
from __future__ import annotations
import json
import re
import sqlite3
import threading
import time
@@ -109,6 +110,43 @@ def _extract_display_text(content: Any) -> str:
return ""
# Internal markers written into the session for the agent's own bookkeeping
# (scheduler injection / self-evolution undo). They must stay in the stored
# content (the LLM reads them, e.g. to find a backup_id for undo) but should
# never be shown verbatim to the user in the chat history UI.
_SCHEDULED_DISPLAY_MARKERS = ("[SCHEDULED]", "Scheduled task")
_EVOLUTION_DISPLAY_MARKER = "[EVOLUTION]"
def _is_internal_user_marker(text: str) -> bool:
"""True if a user-turn text is an internal injection marker (hide from UI)."""
t = (text or "").lstrip()
return any(t.startswith(m) for m in _SCHEDULED_DISPLAY_MARKERS)
def _clean_display_text(text: str) -> str:
"""Strip internal markers from assistant text for user-facing display.
Removes a leading ``[EVOLUTION]`` tag and a trailing ``(backup_id: ...)``
undo hint. The raw stored message is untouched, so undo + LLM context still
work; only the rendered chat bubble is cleaned.
"""
if not text:
return text
cleaned = text
stripped = cleaned.lstrip()
if stripped.startswith(_EVOLUTION_DISPLAY_MARKER):
cleaned = stripped[len(_EVOLUTION_DISPLAY_MARKER):].lstrip()
# Drop a trailing backup_id undo hint line, e.g.
# "(backup_id: 20260607-...; to undo, restore this backup)"
cleaned = re.sub(
r"\n*\(backup_id:[^\)]*\)\s*$",
"",
cleaned,
).rstrip()
return cleaned
def _extract_tool_calls(content: Any) -> List[Dict[str, Any]]:
"""
Extract tool_use blocks from an assistant message content.
@@ -210,7 +248,10 @@ def _group_into_display_turns(
if user_row:
content, created_at, _u_extras = user_row
text = _extract_display_text(content)
if text:
# Hide internal injection markers (scheduler / self-evolution) so the
# user never sees a synthetic "[SCHEDULED] self-evolution" bubble;
# the assistant reply that follows is still rendered.
if text and not _is_internal_user_marker(text):
turns.append({"role": "user", "content": text, "created_at": created_at})
# Build an ordered list of steps preserving the original sequence:
@@ -265,6 +306,14 @@ def _group_into_display_turns(
step["result"] = tr.get("result", "")
step["is_error"] = tr.get("is_error", False)
# Clean internal markers from the user-facing assistant text. Applies to
# both the final content and the mirrored content step so the rendered
# bubble shows clean text while the stored message keeps the markers.
final_text = _clean_display_text(final_text)
for step in steps:
if step.get("type") == "content":
step["content"] = _clean_display_text(step.get("content", ""))
if steps or final_text:
turn = {
"role": "assistant",

38
agent/memory/service.py
View File

@@ -34,13 +34,18 @@ class MemoryService:
# ------------------------------------------------------------------
def list_files(self, page: int = 1, page_size: int = 20, category: str = "memory") -> dict:
"""
List memory or dream files with metadata (without content).
List memory, dream, or evolution files with metadata (without content).
Args:
category: ``"memory"`` (default) — MEMORY.md + daily files;
``"dream"`` — dream diary files from memory/dreams/
``"dream"`` — dream diary files from memory/dreams/;
``"evolution"`` — self-evolution logs from memory/evolution/
merged with the nightly dream diaries, so
one tab shows everything the agent learned.
"""
if category == "dream":
if category == "evolution":
files = self._list_evolution_files()
elif category == "dream":
files = self._list_dream_files()
else:
files = self._list_memory_files()
@@ -93,6 +98,26 @@ class MemoryService:
return files
def _list_evolution_files(self) -> List[dict]:
"""Self-evolution logs (memory/evolution/*.md) merged with the nightly
dream diaries (memory/dreams/*.md), newest first.
Both are surfaced under the unified "Self-Evolution" tab. A file's
``type`` records its origin so the reader can resolve the right dir.
"""
files: List[dict] = []
for sub, ftype in (("evolution", "evolution"), ("dreams", "dream")):
sub_dir = os.path.join(self.memory_dir, sub)
if not os.path.isdir(sub_dir):
continue
for name in os.listdir(sub_dir):
full = os.path.join(sub_dir, name)
if os.path.isfile(full) and name.endswith(".md"):
files.append(self._file_info(full, name, ftype))
# Sort newest first by filename (date-named); ties favor evolution.
files.sort(key=lambda f: (f["filename"], f["type"] != "evolution"), reverse=True)
return files
# ------------------------------------------------------------------
# content — read a single file
# ------------------------------------------------------------------
@@ -101,7 +126,7 @@ class MemoryService:
Read the full content of a memory or dream file.
:param filename: File name, e.g. ``MEMORY.md``, ``2026-02-20.md``
:param category: ``"memory"`` or ``"dream"``
:param category: ``"memory"``, ``"dream"`` or ``"evolution"``
:return: dict with ``filename`` and ``content``
:raises FileNotFoundError: if the file does not exist
"""
@@ -125,7 +150,7 @@ class MemoryService:
Dispatch a memory management action.
:param action: ``list`` or ``content``
:param payload: action-specific payload (supports ``category``: ``"memory"`` | ``"dream"``)
:param payload: action-specific payload (supports ``category``: ``"memory"`` | ``"dream"`` | ``"evolution"``)
:return: protocol-compatible response dict
"""
payload = payload or {}
@@ -166,6 +191,7 @@ class MemoryService:
- ``MEMORY.md`` → ``{workspace_root}/MEMORY.md``
- ``2026-02-20.md`` (memory) → ``{workspace_root}/memory/2026-02-20.md``
- ``2026-02-20.md`` (dream) → ``{workspace_root}/memory/dreams/2026-02-20.md``
- ``2026-02-20.md`` (evolution) → ``{workspace_root}/memory/evolution/2026-02-20.md``
Raises ValueError if the resolved path escapes the allowed directory.
"""
@@ -173,6 +199,8 @@ class MemoryService:
base_dir = self.workspace_root
elif category == "dream":
base_dir = os.path.join(self.memory_dir, "dreams")
elif category == "evolution":
base_dir = os.path.join(self.memory_dir, "evolution")
else:
base_dir = self.memory_dir