Files
nanobot/nanobot/config/loader.py
T
d1a94dae8a refactor(dream): replace two-phase Dream class with simple cron + process_direct (#3990)
* refactor(dream): replace two-phase Dream class with simple cron + process_direct

- Remove the heavyweight Dream class (AgentRunner-based two-phase system)
  from nanobot/agent/memory.py
- Delete dream_phase1.md and dream_phase2.md templates
- New dream.md template serves as the consolidation prompt
- Cron callback uses agent.process_direct(prompt, session_key=\"dream\")
  instead of agent.dream.run()
- Always performs git auto_commit after execution
- /dream command updated to use process_direct + git commit
- DreamConfig kept for backward compatibility; deprecated fields
  (model_override, max_batch_size, max_iterations, annotate_line_ages)
  are ignored but accepted in config
- interval_h remains configurable via agents.defaults.dream.interval_h
- Update tests and webui settings to match new architecture

* feat(loop): add ephemeral mode to process_direct, skip history writes for Dream

When ephemeral=True, _state_save skips enforce_file_cap (which calls
raw_archive -> append_history) and consolidator.maybe_consolidate_by_tokens.
This prevents Dream sessions from creating a positive feedback loop where
they process their own output. The session IS still saved to disk.

* fix(loop): skip extra hooks for ephemeral sessions (Dream)

* feat(dream): per-run timestamped sessions with rotation for WebUI

* test(config): restore DreamConfig schedule and alias tests

* fix(dream): include LLM response summary in git auto-commit message

The old two-phase Dream class included the Phase 1 analysis in the git
commit message body. The new single-phase version lost this. Restore it
by extracting resp.content from the process_direct return value and
appending it to the commit message in both the cron handler and the
/dream command.

* fix(test): accept ephemeral kwarg in test_openai_api fake_process

* refactor(dream): merge dream_session.py into MemoryStore

The standalone dream_session.py module only contained three small helpers
that all revolve around MemoryStore concerns (session keys, commit messages,
file pruning). Fold them into MemoryStore as @staticmethod to reduce
indirection and avoid a 35-line module with no independent reason to exist.

* fix(test): address code review — patch correct instance, use actual function

- Fix test_ephemeral_skips_raw_archive to patch loop.context.memory
  instead of the fixture's separate MemoryStore instance
- Fix TestDreamCommitMessage to call MemoryStore.build_dream_commit_message
  instead of reimplementing the logic inline
- Move Dream helpers in memory.py above the Consolidator section comment
  to avoid misleading visual boundary

* fix(dream): gate cursor advancement and restrict tools

maintainer edit: Dream now processes backlog from the oldest unprocessed entries, only advances the cursor after a completed ephemeral run, and uses a restricted file-only tool registry for background consolidation.

* fix(dream): skip idle compact for dream sessions

Dream runs use internal dream:* sessions that are pruned by Dream retention. Exclude them from AutoCompact scheduling, archive execution, and summary injection so idle-session compaction cannot truncate Dream transcripts.

* fix(dream): keep batched history isolated

* feat(dream): tag archived memory for single-phase Dream

---------

Co-authored-by: Xubin Ren <52506698+Re-bin@users.noreply.github.com>
2026-06-02 22:46:47 +08:00

178 lines
5.9 KiB
Python

"""Configuration loading utilities."""
import json
import os
import re
from pathlib import Path
from typing import Any
import pydantic
from loguru import logger
from pydantic import BaseModel
from nanobot.config.schema import Config, _resolve_tool_config_refs
# Global variable to store current config path (for multi-instance support)
_current_config_path: Path | None = None
_schema_refs_ready = False
def set_config_path(path: Path) -> None:
"""Set the current config path (used to derive data directory)."""
global _current_config_path
_current_config_path = path
def get_config_path() -> Path:
"""Get the configuration file path."""
if _current_config_path:
return _current_config_path
return Path.home() / ".nanobot" / "config.json"
def load_config(config_path: Path | None = None) -> Config:
"""
Load configuration from file or create default.
Args:
config_path: Optional path to config file. Uses default if not provided.
Returns:
Loaded configuration object.
"""
global _schema_refs_ready
if not _schema_refs_ready:
_resolve_tool_config_refs()
_schema_refs_ready = True
path = config_path or get_config_path()
config = Config()
if path.exists():
try:
with open(path, encoding="utf-8") as f:
data = json.load(f)
data = _migrate_config(data)
config = Config.model_validate(data)
except (json.JSONDecodeError, ValueError, pydantic.ValidationError) as e:
logger.warning("Failed to load config from {}: {}", path, e)
logger.warning("Using default configuration.")
_apply_ssrf_whitelist(config)
return config
def _apply_ssrf_whitelist(config: Config) -> None:
"""Apply SSRF whitelist from config to the network security module."""
from nanobot.security.network import configure_ssrf_whitelist
configure_ssrf_whitelist(config.tools.ssrf_whitelist)
def save_config(config: Config, config_path: Path | None = None) -> None:
"""
Save configuration to file.
Args:
config: Configuration to save.
config_path: Optional path to save to. Uses default if not provided.
"""
path = config_path or get_config_path()
path.parent.mkdir(parents=True, exist_ok=True)
data = config.model_dump(mode="json", by_alias=True)
with open(path, "w", encoding="utf-8") as f:
json.dump(data, f, indent=2, ensure_ascii=False)
_ENV_REF_PATTERN = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
def resolve_config_env_vars(config: Config) -> Config:
"""Return *config* with ``${VAR}`` env-var references resolved.
Walks in place so fields declared with ``exclude=True`` survive;
returns the same instance when no references are present.
Raises ``ValueError`` if a referenced variable is not set.
"""
return _resolve_in_place(config)
def _resolve_in_place(obj: Any) -> Any:
if isinstance(obj, str):
new = _ENV_REF_PATTERN.sub(_env_replace, obj)
return new if new != obj else obj
if isinstance(obj, BaseModel):
updates: dict[str, Any] = {}
for name in type(obj).model_fields:
old = getattr(obj, name)
new = _resolve_in_place(old)
if new is not old:
updates[name] = new
extras = obj.__pydantic_extra__
new_extras: dict[str, Any] | None = None
if extras:
resolved = {k: _resolve_in_place(v) for k, v in extras.items()}
if any(resolved[k] is not extras[k] for k in extras):
new_extras = resolved
if not updates and new_extras is None:
return obj
copy = obj.model_copy(update=updates) if updates else obj.model_copy()
if new_extras is not None:
copy.__pydantic_extra__ = new_extras
return copy
if isinstance(obj, dict):
resolved = {k: _resolve_in_place(v) for k, v in obj.items()}
return resolved if any(resolved[k] is not obj[k] for k in obj) else obj
if isinstance(obj, list):
resolved = [_resolve_in_place(v) for v in obj]
return resolved if any(nv is not ov for nv, ov in zip(resolved, obj)) else obj
return obj
def _resolve_env_vars(obj: object) -> object:
"""Recursively resolve ``${VAR}`` patterns in plain strings/dicts/lists."""
if isinstance(obj, str):
return _ENV_REF_PATTERN.sub(_env_replace, obj)
if isinstance(obj, dict):
return {k: _resolve_env_vars(v) for k, v in obj.items()}
if isinstance(obj, list):
return [_resolve_env_vars(v) for v in obj]
return obj
def _env_replace(match: re.Match[str]) -> str:
name = match.group(1)
value = os.environ.get(name)
if value is None:
raise ValueError(
f"Environment variable '{name}' referenced in config is not set"
)
return value
def _migrate_config(data: dict) -> dict:
"""Migrate old config formats to current."""
# Move tools.exec.restrictToWorkspace → tools.restrictToWorkspace
tools = data.get("tools", {})
exec_cfg = tools.get("exec", {})
if "restrictToWorkspace" in exec_cfg and "restrictToWorkspace" not in tools:
tools["restrictToWorkspace"] = exec_cfg.pop("restrictToWorkspace")
# Move tools.myEnabled / tools.mySet → tools.my.{enable, allowSet}.
# The old flat keys shipped in the initial MyTool landing; wrapping them in a
# sub-config keeps `web` / `exec` / `my` symmetric and gives room to grow.
if "myEnabled" in tools or "mySet" in tools:
my_cfg = tools.setdefault("my", {})
if "myEnabled" in tools and "enable" not in my_cfg:
my_cfg["enable"] = tools.pop("myEnabled")
else:
tools.pop("myEnabled", None)
if "mySet" in tools and "allowSet" not in my_cfg:
my_cfg["allowSet"] = tools.pop("mySet")
else:
tools.pop("mySet", None)
return data