feat(evolution): add self-evolution subsystem

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).

agent/evolution/__init__.py

@@ -0,0 +1,19 @@
+"""
+Self-evolution subsystem for CowAgent.
+
+Runs a lightweight, isolated review pass after a conversation goes idle to
+decide whether anything is worth durably learning (memory / skill) or whether
+an unfinished task can be pushed forward. Conservative by design: most
+conversations should produce no change at all.
+
+Public entry points:
+    from agent.evolution import get_evolution_config
+    from agent.evolution.trigger import start_evolution_trigger, note_user_turn
+"""
+
+from agent.evolution.config import EvolutionConfig, get_evolution_config
+
+__all__ = [
+    "EvolutionConfig",
+    "get_evolution_config",
+]

agent/evolution/backup.py

@@ -0,0 +1,102 @@
+"""File backup / rollback support for self-evolution.
+
+Before the evolution agent edits MEMORY.md or a skill file, we snapshot the
+current state into ``memory/.evolution_backups/<backup_id>/`` so a later "undo"
+can restore it. File-level restore only — simple and reliable.
+"""
+
+from __future__ import annotations
+
+import json
+import shutil
+import time
+from datetime import datetime
+from pathlib import Path
+from typing import List, Optional
+
+from common.log import logger
+
+_BACKUP_DIRNAME = ".evolution_backups"
+_MANIFEST_NAME = "manifest.json"
+# Keep only the most recent N backups to bound disk usage.
+_MAX_BACKUPS = 10
+
+
+def _backups_root(workspace_dir: Path) -> Path:
+    return Path(workspace_dir) / "memory" / _BACKUP_DIRNAME
+
+
+def create_backup(workspace_dir: Path, files: List[Path]) -> Optional[str]:
+    """Snapshot ``files`` (those that exist) under a new backup id.
+
+    Returns the backup_id, or None when there is nothing to back up.
+    """
+    existing = [Path(f) for f in files if Path(f).exists()]
+    if not existing:
+        return None
+
+    backup_id = datetime.now().strftime("%Y%m%d-%H%M%S-") + str(int(time.time() * 1000) % 1000)
+    root = _backups_root(workspace_dir)
+    target = root / backup_id
+    try:
+        target.mkdir(parents=True, exist_ok=True)
+        ws = Path(workspace_dir)
+        manifest = []
+        for idx, src in enumerate(existing):
+            # Store under a flat index plus the relative path so restore knows
+            # where it came from, even for nested skill files.
+            try:
+                rel = str(src.relative_to(ws))
+            except ValueError:
+                rel = src.name
+            dst = target / f"{idx}.bak"
+            shutil.copy2(src, dst)
+            manifest.append({"rel": rel, "bak": f"{idx}.bak"})
+        (target / _MANIFEST_NAME).write_text(
+            json.dumps(manifest, ensure_ascii=False, indent=2), encoding="utf-8"
+        )
+        _prune_old_backups(root)
+        # Caller logs a combined backup+review line; keep this at debug.
+        logger.debug(f"[Evolution] Created backup {backup_id} ({len(manifest)} file(s))")
+        return backup_id
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to create backup: {e}")
+        return None
+
+
+def restore_backup(workspace_dir: Path, backup_id: str) -> bool:
+    """Restore all files captured under ``backup_id``. Returns success."""
+    if not backup_id:
+        return False
+    target = _backups_root(workspace_dir) / backup_id
+    manifest_path = target / _MANIFEST_NAME
+    if not manifest_path.exists():
+        logger.warning(f"[Evolution] Backup not found: {backup_id}")
+        return False
+    try:
+        manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
+        ws = Path(workspace_dir)
+        for entry in manifest:
+            bak = target / entry["bak"]
+            dst = ws / entry["rel"]
+            if bak.exists():
+                dst.parent.mkdir(parents=True, exist_ok=True)
+                shutil.copy2(bak, dst)
+        logger.info(f"[Evolution] Restored backup {backup_id} ({len(manifest)} file(s))")
+        return True
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to restore backup {backup_id}: {e}")
+        return False
+
+
+def _prune_old_backups(root: Path) -> None:
+    """Drop the oldest backups beyond _MAX_BACKUPS (sorted by name = chronological)."""
+    try:
+        dirs = sorted(
+            [d for d in root.iterdir() if d.is_dir()],
+            key=lambda p: p.name,
+        )
+        for old in dirs[:-_MAX_BACKUPS]:
+            shutil.rmtree(old, ignore_errors=True)
+    except Exception as e:
+        logger.debug(f"[Evolution] Backup prune skipped: {e}")

agent/evolution/config.py

@@ -0,0 +1,76 @@
+"""Configuration for the self-evolution subsystem.
+
+Reads flat ``self_evolution_*`` keys from config.json. All fields have safe
+defaults so the feature degrades gracefully when keys are absent.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any
+
+
+# Defaults — conservative (see executor module docstring). Disabled by default
+# until release; enable via ``self_evolution_enabled``.
+DEFAULT_ENABLED = False
+DEFAULT_IDLE_MINUTES = 15
+DEFAULT_MIN_TURNS = 6
+# Max review steps for the isolated evolution agent. Kept small (not exposed as
+# config): the review is meant to be cheap and focused, not a long autonomous run.
+DEFAULT_MAX_STEPS = 12
+
+
+@dataclass
+class EvolutionConfig:
+    """Resolved self-evolution settings."""
+
+    enabled: bool = DEFAULT_ENABLED
+    idle_minutes: int = DEFAULT_IDLE_MINUTES
+    min_turns: int = DEFAULT_MIN_TURNS
+    max_steps: int = DEFAULT_MAX_STEPS
+
+    @property
+    def idle_seconds(self) -> int:
+        return max(60, self.idle_minutes * 60)
+
+
+def _as_bool(value: Any, fallback: bool) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        v = value.strip().lower()
+        if v in ("true", "1", "yes", "on"):
+            return True
+        if v in ("false", "0", "no", "off"):
+            return False
+    return fallback
+
+
+def _as_pos_int(value: Any, fallback: int) -> int:
+    try:
+        n = int(value)
+        return n if n > 0 else fallback
+    except (TypeError, ValueError):
+        return fallback
+
+
+def get_evolution_config() -> EvolutionConfig:
+    """Build EvolutionConfig from the live config.json ``self_evolution_*`` keys."""
+    try:
+        from config import conf
+        c = conf()
+    except Exception:
+        c = {}
+
+    def _get(key, default):
+        try:
+            return c.get(key, default)
+        except Exception:
+            return default
+
+    return EvolutionConfig(
+        enabled=_as_bool(_get("self_evolution_enabled", None), DEFAULT_ENABLED),
+        idle_minutes=_as_pos_int(_get("self_evolution_idle_minutes", None), DEFAULT_IDLE_MINUTES),
+        min_turns=_as_pos_int(_get("self_evolution_min_turns", None), DEFAULT_MIN_TURNS),
+        max_steps=DEFAULT_MAX_STEPS,
+    )

agent/evolution/executor.py

@@ -0,0 +1,449 @@
+"""Self-evolution executor.
+
+Runs an isolated review agent over an idle conversation's transcript and, if a
+clear signal is found, lets it edit memory / skills via a restricted toolset.
+Conservative by design: most runs return ``[SILENT]`` and change nothing.
+
+Flow:
+    1. Build a transcript from the session's new (since last pass) messages.
+    2. Snapshot MEMORY.md + daily file + editable skills (for undo) -> backup_id.
+    3. Run an isolated agent (same model, restricted tools, evolution prompt).
+    4. If output is [SILENT], or no workspace file actually changed -> done.
+    5. Otherwise -> record to the evolution log, inject an [EVOLUTION] note into
+       the user session (so the main agent can honor "undo"), and push the
+       summary to the user's channel.
+
+Reuses existing infrastructure (AgentBridge.create_agent, ToolManager,
+remember_scheduled_output, channel_factory) rather than introducing a fork.
+"""
+
+from __future__ import annotations
+
+import threading
+from datetime import datetime
+from pathlib import Path
+from typing import List, Optional
+
+from common.log import logger
+
+from agent.evolution.backup import create_backup
+from agent.evolution.config import get_evolution_config
+from agent.evolution.prompts import (
+    EVOLUTION_MARKER,
+    EVOLUTION_SYSTEM_PROMPT,
+    SILENT_TOKEN,
+    build_review_user_message,
+)
+from agent.evolution.record import append_session_evolution
+
+# Tools the isolated evolution agent is allowed to use. Everything else is
+# withheld so a review pass can only read context and edit memory/skill files.
+_ALLOWED_TOOLS = {"read", "write", "edit", "ls", "memory_search", "memory_get"}
+
+# Cap concurrent evolution passes so a burst of idle sessions can't spawn many
+# background model runs at once. Extra sessions simply wait for the next scan.
+_MAX_CONCURRENT = 2
+_running_lock = threading.Lock()
+_running_count = 0
+
+
+def _builtin_skill_names() -> set:
+    """Names of skills shipped with the product (project-root ``skills/``).
+
+    These are protected: the evolution agent must never edit them, even though
+    a same-named copy exists in the workspace at runtime. The project dir is the
+    authoritative list of what counts as built-in.
+    """
+    try:
+        # executor.py -> agent/evolution -> agent -> project root
+        project_root = Path(__file__).resolve().parents[2]
+        builtin_dir = project_root / "skills"
+        if not builtin_dir.is_dir():
+            return set()
+        names = set()
+        for entry in builtin_dir.iterdir():
+            if entry.is_dir() and not entry.name.startswith("."):
+                names.add(entry.name)
+        return names
+    except Exception:
+        return set()
+
+
+def _build_transcript(messages: List[dict], max_chars: int = 12000) -> str:
+    """Render the session messages into a compact text transcript."""
+    lines: List[str] = []
+    for msg in messages:
+        role = msg.get("role", "")
+        if role not in ("user", "assistant"):
+            continue
+        content = msg.get("content", "")
+        text = _extract_text(content)
+        if not text.strip():
+            continue
+        speaker = "User" if role == "user" else "Assistant"
+        lines.append(f"{speaker}: {text.strip()}")
+    transcript = "\n".join(lines)
+    # Keep the most RECENT context if oversized (tail is most relevant).
+    if len(transcript) > max_chars:
+        transcript = "...(earlier omitted)...\n" + transcript[-max_chars:]
+    return transcript
+
+
+def _extract_text(content) -> str:
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        parts = []
+        for block in content:
+            if isinstance(block, dict) and block.get("type") == "text":
+                parts.append(block.get("text", ""))
+            elif isinstance(block, str):
+                parts.append(block)
+        return "\n".join(parts)
+    return ""
+
+
+def _select_tools(all_tools: list) -> list:
+    return [t for t in all_tools if getattr(t, "name", None) in _ALLOWED_TOOLS]
+
+
+# Tools whose writes must be confined to the workspace during evolution.
+_WRITE_TOOLS = {"write", "edit"}
+
+
+class _WorkspaceWriteGuard:
+    """Wraps a write/edit tool so it can ONLY write inside the workspace.
+
+    Hard engineering guard (not prompt-based): any write resolving outside the
+    workspace — e.g. the project's bundled ``skills/`` dir — is rejected. This
+    protects built-in skills regardless of what the model attempts.
+    """
+
+    def __init__(self, inner, workspace_dir: str):
+        self._inner = inner
+        self._ws = Path(workspace_dir).resolve()
+        # Mirror the attributes the agent runtime reads off a tool.
+        self.name = inner.name
+        self.description = inner.description
+        self.params = inner.params
+
+    def __getattr__(self, item):
+        return getattr(self._inner, item)
+
+    def execute_tool(self, params):
+        # The agent runtime calls execute_tool (not execute); route it through
+        # our guarded execute so the path checks always run.
+        try:
+            return self.execute(params)
+        except Exception as e:
+            logger.error(f"[Evolution] guarded tool error: {e}")
+            from agent.tools.base_tool import ToolResult
+            return ToolResult.fail(f"Error: {e}")
+
+    def execute(self, args):
+        path = (args.get("path") or "").strip()
+        if path:
+            try:
+                resolved = Path(self._inner._resolve_path(path)).resolve()
+                from agent.tools.base_tool import ToolResult
+                # Confine writes to the workspace. This protects the product's
+                # bundled skills (which live outside the workspace) from ever
+                # being modified, no matter what path the model attempts.
+                if self._ws not in resolved.parents and resolved != self._ws:
+                    return ToolResult.fail(
+                        "Error: evolution may only write inside the workspace; "
+                        f"path '{path}' is outside and was blocked."
+                    )
+            except Exception:
+                pass
+        return self._inner.execute(args)
+
+
+def _guard_tools(tools: list, workspace_dir: str) -> list:
+    """Wrap write/edit tools with the workspace guard; leave others as-is."""
+    guarded = []
+    for t in tools:
+        if getattr(t, "name", None) in _WRITE_TOOLS:
+            guarded.append(_WorkspaceWriteGuard(t, workspace_dir))
+        else:
+            guarded.append(t)
+    return guarded
+
+
+# Workspace subtrees worth watching for evolution-induced changes.
+_WATCH_SUBDIRS = ("MEMORY.md", "skills", "knowledge", "output")
+# Subpaths under memory/ to ignore: evolution's own bookkeeping + the nightly
+# dream diary, none of which count as a user-facing change signal.
+_MEMORY_IGNORE = (".evolution_backups", "dreams", "evolution")
+
+
+def _workspace_snapshot(workspace_dir) -> dict:
+    """Map relative path -> (mtime, size) for watched files. Cheap, no reads."""
+    ws = Path(workspace_dir)
+    snap: dict = {}
+    for name in _WATCH_SUBDIRS:
+        root = ws / name
+        if root.is_file():
+            try:
+                st = root.stat()
+                snap[name] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+            continue
+        if not root.is_dir():
+            continue
+        for p in root.rglob("*"):
+            if not p.is_file():
+                continue
+            try:
+                st = p.stat()
+                snap[str(p.relative_to(ws))] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+
+    # Watch the daily memory files (memory/*.md and per-user dailies) since
+    # evolution now records learnings there. Skip backups/dreams bookkeeping.
+    mem_dir = ws / "memory"
+    if mem_dir.is_dir():
+        for p in mem_dir.rglob("*.md"):
+            rel_parts = p.relative_to(mem_dir).parts
+            if rel_parts and rel_parts[0] in _MEMORY_IGNORE:
+                continue
+            try:
+                st = p.stat()
+                snap[str(p.relative_to(ws))] = (st.st_mtime, st.st_size)
+            except OSError:
+                pass
+    return snap
+
+
+def _workspace_changed(workspace_dir, pre: dict) -> bool:
+    """True if any watched file was added, removed, or modified since ``pre``."""
+    return _workspace_snapshot(workspace_dir) != pre
+
+
+def run_evolution_for_session(
+    agent_bridge,
+    session_id: str,
+    channel_type: str = "",
+    receiver: str = "",
+    user_id: Optional[str] = None,
+    idle_minutes: float = 0.0,
+) -> bool:
+    """Run one evolution pass for a session. Returns True if it changed anything.
+
+    Safe to call from a background thread. All failures are swallowed and
+    logged — evolution must never disrupt the main pipeline.
+    """
+    cfg = get_evolution_config()
+    if not cfg.enabled:
+        return False
+
+    # Concurrency gate: bound how many evolution passes run at once.
+    global _running_count
+    with _running_lock:
+        if _running_count >= _MAX_CONCURRENT:
+            logger.info(
+                f"[Evolution] busy ({_running_count}/{_MAX_CONCURRENT} running); "
+                f"skipping session={session_id} this scan"
+            )
+            return False
+        _running_count += 1
+
+    try:
+        agent = agent_bridge.agents.get(session_id) or agent_bridge.default_agent
+        if not agent:
+            return False
+
+        with agent.messages_lock:
+            all_messages = list(agent.messages)
+        total_msgs = len(all_messages)
+        # In-memory evolution cursor: only review messages added since the last
+        # pass so a long session doesn't re-judge (and re-write) old content.
+        # Stored on the agent instance; lost on restart (acceptable — at worst
+        # one redundant pass right after a restart, gated by the file-change
+        # check downstream so it won't double-write identical memory).
+        done = int(getattr(agent, "_evo_done_msg_count", 0))
+        if done > total_msgs:
+            done = 0  # history was trimmed/reset; start fresh
+        new_messages = all_messages[done:]
+        transcript = _build_transcript(new_messages)
+        if not transcript.strip():
+            logger.info(f"[Evolution] session={session_id}: no new messages, skip")
+            # Advance the cursor anyway so we don't re-scan the same tail.
+            agent._evo_done_msg_count = total_msgs
+            return False
+
+        logger.info(
+            f"[Evolution] ▶ Reviewing session={session_id} "
+            f"(idle {idle_minutes:.1f}min, {len(new_messages)} new/{total_msgs} msgs, "
+            f"~{len(transcript)} chars)"
+        )
+
+        # Resolve workspace + files to snapshot for undo.
+        from agent.memory.config import get_default_memory_config
+        mem_cfg = get_default_memory_config()
+        workspace_dir = mem_cfg.get_workspace()
+        if user_id:
+            memory_file = Path(workspace_dir) / "memory" / "users" / user_id / "MEMORY.md"
+        else:
+            memory_file = Path(workspace_dir) / "MEMORY.md"
+        skills_dir = mem_cfg.get_skills_dir()
+
+        # Snapshot MEMORY.md + every NON-protected skill's SKILL.md. Protected
+        # built-in skills are excluded from backup because they must never be
+        # edited in the first place.
+        protected_names = _builtin_skill_names()
+        # Back up both MEMORY.md and today's daily file: evolution now writes to
+        # the daily file, but MEMORY.md is cheap to snapshot and keeps undo safe
+        # if the model ever edits it.
+        today_daily = Path(workspace_dir) / "memory" / (
+            datetime.now().strftime("%Y-%m-%d") + ".md"
+        )
+        if user_id:
+            today_daily = Path(workspace_dir) / "memory" / "users" / user_id / (
+                datetime.now().strftime("%Y-%m-%d") + ".md"
+            )
+        backup_files = [Path(memory_file), today_daily]
+        if skills_dir.exists():
+            for skill_md in skills_dir.rglob("SKILL.md"):
+                # The skill dir is the SKILL.md's parent (or an ancestor for
+                # collections); guard by checking the immediate top-level dir.
+                try:
+                    top = skill_md.relative_to(skills_dir).parts[0]
+                except (ValueError, IndexError):
+                    continue
+                if top in protected_names:
+                    continue
+                backup_files.append(skill_md)
+        backup_id = create_backup(workspace_dir, backup_files)
+        _backup_n = sum(1 for f in backup_files if Path(f).exists())
+
+        # Snapshot the whole workspace (path -> mtime/size) so we can reliably
+        # detect ANY file change — including new output files written when
+        # finishing an unfinished task, which are not in backup_files.
+        pre_snapshot = _workspace_snapshot(workspace_dir)
+
+        # Build the isolated review agent: same model, restricted tools, with a
+        # hard guard that confines all writes to the workspace (protects the
+        # project's bundled skills from ever being modified).
+        review_tools = _guard_tools(
+            _select_tools(list(getattr(agent, "tools", []) or [])),
+            str(workspace_dir),
+        )
+        review_agent = agent_bridge.create_agent(
+            system_prompt=EVOLUTION_SYSTEM_PROMPT,
+            tools=review_tools,
+            description="Self-evolution review agent",
+            max_steps=cfg.max_steps,
+            workspace_dir=str(workspace_dir),
+            skill_manager=getattr(agent, "skill_manager", None),
+            memory_manager=getattr(agent, "memory_manager", None),
+            enable_skills=False,
+        )
+        # Reuse the live model so it follows the user's configured model.
+        review_agent.model = agent.model
+
+        logger.info(
+            f"[Evolution] backup {backup_id} ({_backup_n} files) → running review agent"
+        )
+        user_msg = build_review_user_message(transcript, protected_skills=list(protected_names))
+        result = review_agent.run_stream(user_msg, clear_history=True)
+        result = (result or "").strip()
+
+        # These messages are now reviewed; advance the cursor so the next pass
+        # only looks at messages added after this point (silent or not).
+        agent._evo_done_msg_count = total_msgs
+
+        if not result or SILENT_TOKEN in result:
+            logger.info(f"[Evolution] ✗ No change for session={session_id} ([SILENT])")
+            return False
+
+        # Hard gate: an evolution only counts (and only notifies) if a workspace
+        # file ACTUALLY changed. If the model did real work (wrote memory /
+        # patched a skill / finished a task) the user is told; if it merely
+        # produced text without changing anything, we stay silent. This is the
+        # key anti-nag rule — no notification unless something was actually done.
+        if not _workspace_changed(workspace_dir, pre_snapshot):
+            logger.info(
+                f"[Evolution] ✗ session={session_id}: model produced text but "
+                f"changed no file — treating as silent"
+            )
+            return False
+
+        logger.info(f"[Evolution] ✓ session={session_id} evolved:\n{result}")
+        append_session_evolution(workspace_dir, result, backup_id=backup_id, user_id=user_id)
+        # Inject an [EVOLUTION] note so the main agent can honor "undo".
+        _inject_evolution_record(agent_bridge, session_id, channel_type, result, backup_id)
+
+        # Push the summary to the user's channel. The "did a file actually
+        # change" gate above is the only throttle we need: real evolutions are
+        # rare, so no extra opt-in switch or daily-count limit is required.
+        if channel_type and receiver:
+            _notify_user(channel_type, receiver, result)
+
+        return True
+
+    except Exception as e:
+        logger.warning(f"[Evolution] Run failed for session={session_id}: {e}")
+        return False
+    finally:
+        with _running_lock:
+            _running_count -= 1
+
+
+def _inject_evolution_record(
+    agent_bridge, session_id: str, channel_type: str, summary: str, backup_id: Optional[str]
+) -> None:
+    """Add an [EVOLUTION] note to the user session so the main agent can undo."""
+    try:
+        note = f"{EVOLUTION_MARKER} {summary}"
+        if backup_id:
+            note += f"\n(backup_id: {backup_id}; to undo, restore this backup)"
+        # Reuse the scheduler-output injection path: isolated execution, only a
+        # compact record lands in the user session.
+        agent_bridge.remember_scheduled_output(
+            session_id=session_id,
+            content=note,
+            channel_type=channel_type,
+            task_description="self-evolution",
+        )
+    except Exception as e:
+        logger.debug(f"[Evolution] Failed to inject evolution record: {e}")
+
+
+def _notify_user(channel_type: str, receiver: str, summary: str) -> None:
+    """Push the evolution summary to the user's channel as a new message."""
+    try:
+        from bridge.context import Context, ContextType
+        from bridge.reply import Reply, ReplyType
+        from channel.channel_factory import create_channel
+
+        context = Context(ContextType.TEXT, summary)
+        context["receiver"] = receiver
+        context["isgroup"] = False
+        context["session_id"] = receiver
+        # Channels that reply to an original message need msg=None for a fresh push.
+        if channel_type in ("feishu", "dingtalk", "wecom_bot", "qq"):
+            context["msg"] = None
+        if channel_type == "feishu":
+            context["receive_id_type"] = "open_id"
+
+        channel = create_channel(channel_type)
+        if not channel:
+            return
+
+        # Web is request-response: a background push needs a synthetic request_id
+        # plus a request->session mapping so the channel can route the message to
+        # the user's polling queue (same approach the scheduler uses).
+        if channel_type == "web":
+            import uuid
+            request_id = f"evolution_{uuid.uuid4().hex[:8]}"
+            context["request_id"] = request_id
+            if hasattr(channel, "request_to_session"):
+                channel.request_to_session[request_id] = receiver
+
+        channel.send(Reply(ReplyType.TEXT, summary), context)
+        logger.info(f"[Evolution] Notified user via {channel_type}")
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to notify user: {e}")

agent/evolution/prompts.py

@@ -0,0 +1,163 @@
+"""Prompts for the self-evolution review agent.
+
+The system prompt is intentionally English-only: it governs the agent's
+internal reasoning and is more stable / cheaper to maintain in one language.
+The user-facing summary the agent produces should follow the user's own
+language (instructed at the end of the prompt).
+
+Design goals (see ref/hermes-agent background_review for inspiration):
+  - Default to doing NOTHING. Evolution is the exception, not the rule.
+  - Three signal types: memory, skill, unfinished task.
+  - An explicit "do NOT capture" list to avoid self-poisoning over time.
+  - Generic examples only — never bake in domain-specific business terms.
+"""
+
+# Sentinel the agent emits when there is nothing worth evolving.
+SILENT_TOKEN = "[SILENT]"
+
+# Marker prefix for the evolution record injected into the user session, so the
+# main chat agent can recognize past evolutions and honor an "undo" request.
+EVOLUTION_MARKER = "[EVOLUTION]"
+
+
+EVOLUTION_SYSTEM_PROMPT = """You are a self-evolution review agent for an AI assistant.
+
+You are given a transcript of a conversation that just went idle. Your job is to
+decide whether anything from it is worth durably learning so future
+conversations go better — and if so, to make that change.
+
+# Top principle: default to doing NOTHING
+
+Most ordinary conversations need no evolution. Only act when there is a CLEAR
+signal below. If there is none, reply with exactly `[SILENT]` and stop. Staying
+silent is the normal, correct outcome — not a failure.
+
+Greetings, small talk, acknowledgements ("ok", "thanks", "got it"), and casual
+chat are NOT signals. For these, output exactly `[SILENT]` immediately — do not
+explore files, do not write a summary, do not be polite. Just `[SILENT]`.
+
+IMPORTANT: A summary is only allowed if you ACTUALLY made a file change via a
+tool (write/edit) in this pass. If you did not change any file, you MUST output
+exactly `[SILENT]` — never describe a change you only intended to make.
+
+# Signals worth acting on (act only if at least one clearly appears)
+
+SKILL and UNFINISHED TASK are your PRIMARY value — no other mechanism handles
+them. When their signal is clear, act; do not be shy here.
+
+1. SKILL — two cases:
+   a) PATCH an existing skill: a skill used here showed a STRUCTURAL problem (a
+      missing step/section, a wrong or outdated detail, an error in its
+      content), or its OUTPUT repeatedly misses something the user flagged. Read
+      the relevant skill file under the skills directory and make a small
+      incremental edit so it never recurs.
+   b) CREATE a new skill: a clearly reusable, repeatable workflow emerged that
+      no existing skill covers and the user is likely to want again. To create
+      one, follow the `skill-creator` skill's conventions (read its SKILL.md for
+      the required structure) and write the new skill under the workspace
+      `skills/` directory. Only create when the workflow is genuinely reusable —
+      not for a one-off task.
+
+   CRITICAL — fix the SOURCE, do not just remember the symptom: when the root
+   cause of a problem lives IN a skill file itself (its instructions, content,
+   or configuration are wrong/outdated), the correct action is to EDIT that
+   skill so the problem cannot recur. Recording the corrected fact in memory
+   does NOT prevent recurrence — only fixing the skill does. Never log "skill X
+   has wrong detail Y" as a memory note in place of editing skill X.
+
+2. UNFINISHED TASK — a specific deliverable you promised but didn't produce,
+   AND you already have everything needed to finish it. DO IT now with the
+   available tools and produce the result (e.g. write the file you said you'd
+   write). If key info is missing, or the task is merely waiting on the user's
+   reply/decision, do NOTHING and stay [SILENT] — do not nag or ping the user.
+   You only ever notify the user as a side effect of having actually done work.
+
+3. MEMORY — LAST resort, and you are only a SAFETY NET here, not the primary
+   writer. The main assistant already writes memory DURING the conversation, and
+   a nightly pass consolidates daily notes into long-term memory. Prefer fixing
+   a skill (above) over writing memory whenever the fact belongs in a skill.
+   Act ONLY on something the main assistant clearly MISSED that does not belong
+   in any skill.
+   - MEMORY.md is the curated long-term index, auto-loaded into EVERY future
+     conversation. Treat it as precious: writing here is RARE and reserved for
+     CORRECTING a wrong fact already in MEMORY.md (edit that line in place).
+     Do NOT append new entries to MEMORY.md — that is the nightly pass's job.
+   - For a genuinely important NEW durable fact the chat missed, append ONE
+     short bullet to today's `memory/YYYY-MM-DD.md` (not MEMORY.md). When unsure,
+     the daily file is the safe place — but first ask whether this really
+     belongs in a skill instead.
+   - Keep it to ONE short bullet. Never write paragraphs, never re-summarize the
+     conversation, never copy what the main assistant already recorded.
+   - If it is already captured anywhere (check MEMORY.md AND the daily file
+     first), do NOTHING.
+
+# Do NOT capture (these poison future behavior)
+
+- Environment failures: missing binaries, unset credentials, uninstalled
+  packages, "command not found". The user can fix these; they are not durable
+  rules.
+- Negative claims about tools or features ("tool X does not work"). These
+  harden into refusals the agent cites against itself later.
+- One-off task narratives (e.g. summarizing today's content). Not a class of
+  reusable work.
+- Transient errors that resolved on retry within the conversation.
+
+# Execution constraints
+
+- Before changing memory or a skill, READ the current content first and make a
+  small INCREMENTAL edit. Never fabricate, never rewrite large sections.
+- AVOID DUPLICATES. Before writing memory, READ both MEMORY.md AND today's
+  daily file `memory/YYYY-MM-DD.md`. If the fact/preference is already recorded
+  in EITHER (even if worded differently), do NOT add it again. The main
+  assistant likely already wrote it during the chat — only add what is
+  genuinely new or a correction not yet reflected anywhere.
+- You may only edit files inside the workspace. Built-in skills shipped with
+  the product live outside it and are write-protected; do not try to edit them.
+- Make at most the few edits the signals justify; do not go looking for work.
+
+# Output
+
+- Nothing worth evolving -> output exactly `[SILENT]` and nothing else.
+- Otherwise, after performing the edits, output a short user-facing summary in
+  the SAME LANGUAGE the user used in the conversation. Tell the user, briefly:
+    1) that you just did a self-learning pass,
+    2) what you learned and what you changed (in plain terms — no need to cite
+       exact file paths; "remembered X" / "improved the weekly-report skill" is
+       enough).
+  Keep it to 1-3 lines. Generic shape (do not copy domain words):
+    "I just did a self-learning pass.
+     - Learned: <what you learned>
+     - Changed: <remembered it / improved the <name> skill / finished <task>>
+     Reply 'undo the last learning' if this is wrong."
+"""
+
+
+def build_review_user_message(transcript: str, protected_skills: list = None) -> str:
+    """Wrap the conversation transcript as the review agent's user message.
+
+    ``protected_skills`` lists skill names that must never be edited (built-in
+    skills shipped with the product). Surfaced so the agent avoids them.
+    """
+    from datetime import datetime
+    today = datetime.now().strftime("%Y-%m-%d")
+
+    protected_note = ""
+    if protected_skills:
+        names = ", ".join(sorted(protected_skills))
+        protected_note = (
+            "\n\nPROTECTED skills (built-in — never edit these): "
+            f"{names}\n"
+        )
+    return (
+        "Here is the conversation transcript that just went idle. Review it per "
+        "your instructions and act on any clear signal. Prefer fixing a skill at "
+        "its source over writing memory whenever the fact belongs in a skill.\n"
+        f"Today is {today}. Only if a fact genuinely belongs in memory (and not "
+        f"in a skill): append one short bullet to the daily file "
+        f"`memory/{today}.md` for a new fact, or edit MEMORY.md in place to "
+        f"correct an existing wrong fact."
+        f"{protected_note}\n"
+        "<transcript>\n"
+        f"{transcript}\n"
+        "</transcript>"
+    )

agent/evolution/record.py

@@ -0,0 +1,55 @@
+"""Self-evolution record log.
+
+Session-level evolutions are appended to their OWN per-day file under
+``memory/evolution/YYYY-MM-DD.md`` (separate from the nightly Deep Dream diary
+in ``memory/dreams/``). Each day's file accumulates one short section per
+evolution pass — tagged with a timestamp and a backup id for undo — so the
+memory UI can surface "what the agent learned/changed today" on one timeline
+without ever mixing into the dream diary or the main conversation memory.
+"""
+
+from __future__ import annotations
+
+from datetime import datetime
+from pathlib import Path
+from typing import Optional
+
+from common.log import logger
+
+
+def _evolution_dir(workspace_dir: Path, user_id: Optional[str] = None) -> Path:
+    base = Path(workspace_dir) / "memory"
+    if user_id:
+        return base / "users" / user_id / "evolution"
+    return base / "evolution"
+
+
+def append_session_evolution(
+    workspace_dir: Path,
+    summary: str,
+    backup_id: Optional[str] = None,
+    user_id: Optional[str] = None,
+) -> None:
+    """Append a session-evolution entry to today's evolution log."""
+    if not summary or not summary.strip():
+        return
+    try:
+        evo_dir = _evolution_dir(workspace_dir, user_id)
+        evo_dir.mkdir(parents=True, exist_ok=True)
+        today = datetime.now().strftime("%Y-%m-%d")
+        log_file = evo_dir / f"{today}.md"
+
+        ts = datetime.now().strftime("%H:%M")
+        header = f"## {ts}"
+        body = summary.strip()
+        if backup_id:
+            body += f"\n\n_backup_id: {backup_id}_"
+
+        # Create with a title if the file is new, otherwise append a section.
+        if not log_file.exists():
+            log_file.write_text(f"# Self-Evolution: {today}\n\n", encoding="utf-8")
+        with open(log_file, "a", encoding="utf-8") as f:
+            f.write(f"\n{header}\n\n{body}\n")
+        logger.info(f"[Evolution] Recorded session evolution to {log_file.name}")
+    except Exception as e:
+        logger.warning(f"[Evolution] Failed to record session evolution: {e}")

agent/evolution/trigger.py

@@ -0,0 +1,133 @@
+"""Idle-based evolution trigger.
+
+A single background thread periodically scans live agent sessions and runs an
+evolution pass for any session that is idle for >= idle_minutes AND has enough
+accumulated signal, where "enough signal" is EITHER:
+  - >= min_turns user turns since the last evolution, OR
+  - the live context has grown past _CONTEXT_RATIO of the agent's token budget
+    (mirrors how OpenClacky / Claude Code consolidate under context pressure).
+
+Turn counting is per user turn (not per message), measured from the last
+evolution (or session start). After a pass runs, the baseline resets so a long
+session can evolve multiple times without re-judging old content.
+
+Per-session evolution state is stored on the agent instance via lightweight
+attributes set by AgentBridge.agent_reply (see _note_user_turn).
+"""
+
+from __future__ import annotations
+
+import threading
+import time
+
+from common.log import logger
+
+from agent.evolution.config import get_evolution_config
+from agent.evolution.executor import run_evolution_for_session
+
+_SCAN_INTERVAL_SECONDS = 60
+
+# Context-pressure trigger: evolve once the live context exceeds this fraction
+# of the agent's token budget, even if min_turns hasn't been reached. Kept as a
+# module constant (not user config) for now. Fallback budget matches
+# agent_initializer / config.py (agent_max_context_tokens default = 50000).
+_CONTEXT_RATIO = 0.8
+_FALLBACK_CONTEXT_BUDGET = 50000
+
+
+def _context_pressure_reached(agent) -> bool:
+    """True if the agent's live context exceeds _CONTEXT_RATIO of its budget.
+
+    Uses the agent's own (estimated) token accounting so behavior matches the
+    existing context-trimming path. Best-effort: any error -> False.
+    """
+    try:
+        with agent.messages_lock:
+            messages = list(agent.messages)
+        if not messages:
+            return False
+        est = sum(agent._estimate_message_tokens(m) for m in messages)
+        budget = getattr(agent, "max_context_tokens", None) or _FALLBACK_CONTEXT_BUDGET
+        return est / budget > _CONTEXT_RATIO
+    except Exception:
+        return False
+
+
+def note_user_turn(agent, channel_type: str = "", receiver: str = "") -> None:
+    """Record activity for a session's agent. Called once per real user turn.
+
+    Maintains, on the agent instance:
+      _evo_last_active   : epoch seconds of the last user turn
+      _evo_turns         : user turns since the last evolution
+      _evo_channel_type  : originating channel (for later notify)
+      _evo_receiver      : push target for notify
+    """
+    try:
+        agent._evo_last_active = time.time()
+        agent._evo_turns = int(getattr(agent, "_evo_turns", 0)) + 1
+        if channel_type:
+            agent._evo_channel_type = channel_type
+        if receiver:
+            agent._evo_receiver = receiver
+    except Exception:
+        pass
+
+
+def start_evolution_trigger(agent_bridge) -> None:
+    """Start the idle-scan thread once per process (idempotent)."""
+    if getattr(agent_bridge, "_evolution_trigger_started", False):
+        return
+    agent_bridge._evolution_trigger_started = True
+
+    t = threading.Thread(
+        target=_scan_loop, args=(agent_bridge,), daemon=True, name="evolution-trigger"
+    )
+    t.start()
+    logger.info("[Evolution] Idle trigger started")
+
+
+def _scan_loop(agent_bridge) -> None:
+    while True:
+        try:
+            time.sleep(_SCAN_INTERVAL_SECONDS)
+            cfg = get_evolution_config()
+            if not cfg.enabled:
+                continue
+            _scan_once(agent_bridge, cfg)
+        except Exception as e:
+            logger.warning(f"[Evolution] Scan loop error: {e}")
+            time.sleep(_SCAN_INTERVAL_SECONDS)
+
+
+def _scan_once(agent_bridge, cfg) -> None:
+    now = time.time()
+    # Snapshot to avoid holding the dict while running long evolutions.
+    sessions = list(getattr(agent_bridge, "agents", {}).items())
+    for session_id, agent in sessions:
+        try:
+            last_active = getattr(agent, "_evo_last_active", 0)
+            turns = int(getattr(agent, "_evo_turns", 0))
+            # Enough signal = enough turns OR enough context pressure.
+            enough_signal = turns >= cfg.min_turns or _context_pressure_reached(agent)
+            if not enough_signal:
+                continue
+            idle = now - last_active if last_active > 0 else -1
+            if last_active <= 0 or idle < cfg.idle_seconds:
+                continue
+
+            channel_type = getattr(agent, "_evo_channel_type", "") or ""
+            receiver = getattr(agent, "_evo_receiver", "") or ""
+
+            # Reset baseline BEFORE running so a long pass / new messages during
+            # it don't double-trigger; turns accrue fresh from here.
+            agent._evo_turns = 0
+
+            run_evolution_for_session(
+                agent_bridge,
+                session_id=session_id,
+                channel_type=channel_type,
+                receiver=receiver,
+                idle_minutes=(now - last_active) / 60 if last_active > 0 else 0.0,
+            )
+        except Exception as e:
+            logger.warning(f"[Evolution] Failed to evaluate session={session_id}: {e}")