mirror of
https://github.com/HKUDS/nanobot.git
synced 2026-04-05 02:42:41 +00:00
feat(memory): add git-backed version control for dream memory files
- Add GitStore class wrapping dulwich for memory file versioning - Auto-commit memory changes during Dream consolidation - Add /dream-log and /dream-restore commands for history browsing - Pass tracked_files as constructor param, generate .gitignore dynamically
This commit is contained in:
parent
a9e01bf838
commit
f824a629a8
156
docs/DREAM.md
Normal file
156
docs/DREAM.md
Normal file
@ -0,0 +1,156 @@
|
||||
# Dream: Two-Stage Memory Consolidation
|
||||
|
||||
Dream is nanobot's memory management system. It automatically extracts key information from conversations and persists it as structured knowledge files.
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
Consolidator (per-turn) Dream (cron-scheduled) GitStore (version control)
|
||||
+----------------------------+ +----------------------------+ +---------------------------+
|
||||
| token over budget → LLM | | Phase 1: analyze history | | dulwich-backed .git repo |
|
||||
| summarize evicted messages |──────▶| vs existing memory files | | auto_commit on Dream run |
|
||||
| → history.jsonl | | Phase 2: AgentRunner | | /dream-log: view changes |
|
||||
| (plain text, no tool_call) | | + read_file/edit_file | | /dream-restore: rollback |
|
||||
+----------------------------+ | → surgical incremental | +---------------------------+
|
||||
| edit of memory files |
|
||||
+----------------------------+
|
||||
```
|
||||
|
||||
### Consolidator
|
||||
|
||||
Lightweight, triggered on-demand after each conversation turn. When a session's estimated prompt tokens exceed 50% of the context window, the Consolidator sends the oldest message slice to the LLM for summarization and appends the result to `history.jsonl`.
|
||||
|
||||
Key properties:
|
||||
- Uses plain-text LLM calls (no `tool_choice`), compatible with all providers
|
||||
- Cuts messages at user-turn boundaries to avoid truncating multi-turn conversations
|
||||
- Up to 5 consolidation rounds until the token budget drops below the safety threshold
|
||||
|
||||
### Dream
|
||||
|
||||
Heavyweight, triggered by a cron schedule (default: every 2 hours). Two-phase processing:
|
||||
|
||||
| Phase | Description | LLM call |
|
||||
|-------|-------------|----------|
|
||||
| Phase 1 | Compare `history.jsonl` against existing memory files, output `[FILE] atomic fact` lines | Plain text, no tools |
|
||||
| Phase 2 | Based on the analysis, use AgentRunner with `read_file` / `edit_file` for incremental edits | With filesystem tools |
|
||||
|
||||
Key properties:
|
||||
- Incremental edits — never rewrites entire files
|
||||
- Cursor always advances to prevent re-processing
|
||||
- Phase 2 failure does not block cursor advancement (prevents infinite loops)
|
||||
|
||||
### GitStore
|
||||
|
||||
Pure-Python git implementation backed by [dulwich](https://github.com/jelmer/dulwich), providing version control for memory files.
|
||||
|
||||
- Auto-commits after each Dream run
|
||||
- Auto-generated `.gitignore` that only tracks memory files
|
||||
- Supports log viewing, diff comparison, and rollback
|
||||
|
||||
## Data Files
|
||||
|
||||
```
|
||||
workspace/
|
||||
├── SOUL.md # Bot personality and communication style (managed by Dream)
|
||||
├── USER.md # User profile and preferences (managed by Dream)
|
||||
└── memory/
|
||||
├── MEMORY.md # Long-term facts and project context (managed by Dream)
|
||||
├── history.jsonl # Consolidator summary output (append-only)
|
||||
├── .cursor # Last message index processed by Consolidator
|
||||
├── .dream_cursor # Last history.jsonl cursor processed by Dream
|
||||
└── .git/ # GitStore repository
|
||||
```
|
||||
|
||||
### history.jsonl Format
|
||||
|
||||
Each line is a JSON object:
|
||||
|
||||
```json
|
||||
{"cursor": 42, "timestamp": "2026-04-03 00:02", "content": "- User prefers dark mode\n- Decided to use PostgreSQL"}
|
||||
```
|
||||
|
||||
Searching history:
|
||||
|
||||
```bash
|
||||
# Python (cross-platform)
|
||||
python -c "import json; [print(json.loads(l).get('content','')) for l in open('memory/history.jsonl','r',encoding='utf-8') if l.strip() and 'keyword' in l.lower()][-20:]"
|
||||
|
||||
# grep
|
||||
grep -i "keyword" memory/history.jsonl
|
||||
```
|
||||
|
||||
### Compaction
|
||||
|
||||
When `history.jsonl` exceeds 1000 entries, it automatically drops entries that Dream has already processed (keeping only unprocessed entries).
|
||||
|
||||
## Configuration
|
||||
|
||||
Configure under `agents.defaults.dream` in `~/.nanobot/config.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"agents": {
|
||||
"defaults": {
|
||||
"dream": {
|
||||
"cron": "0 */2 * * *",
|
||||
"model": null,
|
||||
"max_batch_size": 20,
|
||||
"max_iterations": 10
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
| Field | Type | Default | Description |
|
||||
|-------|------|---------|-------------|
|
||||
| `cron` | string | `0 */2 * * *` | Cron expression for Dream run interval |
|
||||
| `model` | string\|null | null | Optional model override for Dream |
|
||||
| `max_batch_size` | int | 20 | Max history entries processed per run |
|
||||
| `max_iterations` | int | 10 | Max tool calls in Phase 2 |
|
||||
|
||||
Dependency: `pip install dulwich`
|
||||
|
||||
## Commands
|
||||
|
||||
| Command | Description |
|
||||
|---------|-------------|
|
||||
| `/dream` | Manually trigger a Dream run |
|
||||
| `/dream-log` | Show the latest Dream changes (git diff) |
|
||||
| `/dream-log <sha>` | Show changes from a specific commit |
|
||||
| `/dream-restore` | List the 10 most recent Dream commits |
|
||||
| `/dream-restore <sha>` | Revert a specific commit (restore to its parent state) |
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Dream produces no changes
|
||||
|
||||
Check whether `history.jsonl` has entries and whether `.dream_cursor` has caught up:
|
||||
|
||||
```bash
|
||||
# Check recent history entries
|
||||
tail -5 memory/history.jsonl
|
||||
|
||||
# Check Dream cursor
|
||||
cat memory/.dream_cursor
|
||||
|
||||
# Compare: the last entry's cursor in history.jsonl should be > .dream_cursor
|
||||
```
|
||||
|
||||
### Memory files contain inaccurate information
|
||||
|
||||
1. Use `/dream-log` to inspect what Dream changed
|
||||
2. Use `/dream-restore <sha>` to roll back to a previous state
|
||||
3. If the information is still wrong after rollback, manually edit the memory files — Dream will preserve your edits on the next run (it skips facts that already match)
|
||||
|
||||
### Git-related issues
|
||||
|
||||
```bash
|
||||
# Check if GitStore is initialized
|
||||
ls workspace/.git
|
||||
|
||||
# If missing, restart the gateway to auto-initialize
|
||||
|
||||
# View commit history manually (requires git)
|
||||
cd workspace && git log --oneline
|
||||
```
|
||||
307
nanobot/agent/git_store.py
Normal file
307
nanobot/agent/git_store.py
Normal file
@ -0,0 +1,307 @@
|
||||
"""Git-backed version control for memory files, using dulwich."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from loguru import logger
|
||||
|
||||
|
||||
@dataclass
|
||||
class CommitInfo:
|
||||
sha: str # Short SHA (8 chars)
|
||||
message: str
|
||||
timestamp: str # Formatted datetime
|
||||
|
||||
def format(self, diff: str = "") -> str:
|
||||
"""Format this commit for display, optionally with a diff."""
|
||||
header = f"## {self.message.splitlines()[0]}\n`{self.sha}` — {self.timestamp}\n"
|
||||
if diff:
|
||||
return f"{header}\n```diff\n{diff}\n```"
|
||||
return f"{header}\n(no file changes)"
|
||||
|
||||
|
||||
class GitStore:
|
||||
"""Git-backed version control for memory files."""
|
||||
|
||||
def __init__(self, workspace: Path, tracked_files: list[str]):
|
||||
self._workspace = workspace
|
||||
self._tracked_files = tracked_files
|
||||
|
||||
def is_initialized(self) -> bool:
|
||||
"""Check if the git repo has been initialized."""
|
||||
return (self._workspace / ".git").is_dir()
|
||||
|
||||
# -- init ------------------------------------------------------------------
|
||||
|
||||
def init(self) -> bool:
|
||||
"""Initialize a git repo if not already initialized.
|
||||
|
||||
Creates .gitignore and makes an initial commit.
|
||||
Returns True if a new repo was created, False if already exists.
|
||||
"""
|
||||
if self.is_initialized():
|
||||
return False
|
||||
|
||||
try:
|
||||
from dulwich import porcelain
|
||||
|
||||
porcelain.init(str(self._workspace))
|
||||
|
||||
# Write .gitignore
|
||||
gitignore = self._workspace / ".gitignore"
|
||||
gitignore.write_text(self._build_gitignore(), encoding="utf-8")
|
||||
|
||||
# Ensure tracked files exist (touch them if missing) so the initial
|
||||
# commit has something to track.
|
||||
for rel in self._tracked_files:
|
||||
p = self._workspace / rel
|
||||
p.parent.mkdir(parents=True, exist_ok=True)
|
||||
if not p.exists():
|
||||
p.write_text("", encoding="utf-8")
|
||||
|
||||
# Initial commit
|
||||
porcelain.add(str(self._workspace), paths=[".gitignore"] + self._tracked_files)
|
||||
porcelain.commit(
|
||||
str(self._workspace),
|
||||
message=b"init: nanobot memory store",
|
||||
author=b"nanobot <nanobot@dream>",
|
||||
committer=b"nanobot <nanobot@dream>",
|
||||
)
|
||||
logger.info("Git store initialized at {}", self._workspace)
|
||||
return True
|
||||
except Exception:
|
||||
logger.warning("Git store init failed for {}", self._workspace)
|
||||
return False
|
||||
|
||||
# -- daily operations ------------------------------------------------------
|
||||
|
||||
def auto_commit(self, message: str) -> str | None:
|
||||
"""Stage tracked memory files and commit if there are changes.
|
||||
|
||||
Returns the short commit SHA, or None if nothing to commit.
|
||||
"""
|
||||
if not self.is_initialized():
|
||||
return None
|
||||
|
||||
try:
|
||||
from dulwich import porcelain
|
||||
|
||||
# .gitignore excludes everything except tracked files,
|
||||
# so any staged/unstaged change must be in our files.
|
||||
st = porcelain.status(str(self._workspace))
|
||||
if not st.unstaged and not any(st.staged.values()):
|
||||
return None
|
||||
|
||||
msg_bytes = message.encode("utf-8") if isinstance(message, str) else message
|
||||
porcelain.add(str(self._workspace), paths=self._tracked_files)
|
||||
sha_bytes = porcelain.commit(
|
||||
str(self._workspace),
|
||||
message=msg_bytes,
|
||||
author=b"nanobot <nanobot@dream>",
|
||||
committer=b"nanobot <nanobot@dream>",
|
||||
)
|
||||
if sha_bytes is None:
|
||||
return None
|
||||
sha = sha_bytes.hex()[:8]
|
||||
logger.debug("Git auto-commit: {} ({})", sha, message)
|
||||
return sha
|
||||
except Exception:
|
||||
logger.warning("Git auto-commit failed: {}", message)
|
||||
return None
|
||||
|
||||
# -- internal helpers ------------------------------------------------------
|
||||
|
||||
def _resolve_sha(self, short_sha: str) -> bytes | None:
|
||||
"""Resolve a short SHA prefix to the full SHA bytes."""
|
||||
try:
|
||||
from dulwich.repo import Repo
|
||||
|
||||
with Repo(str(self._workspace)) as repo:
|
||||
try:
|
||||
sha = repo.refs[b"HEAD"]
|
||||
except KeyError:
|
||||
return None
|
||||
|
||||
while sha:
|
||||
if sha.hex().startswith(short_sha):
|
||||
return sha
|
||||
commit = repo[sha]
|
||||
if commit.type_name != b"commit":
|
||||
break
|
||||
sha = commit.parents[0] if commit.parents else None
|
||||
return None
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _build_gitignore(self) -> str:
|
||||
"""Generate .gitignore content from tracked files."""
|
||||
dirs: set[str] = set()
|
||||
for f in self._tracked_files:
|
||||
parent = str(Path(f).parent)
|
||||
if parent != ".":
|
||||
dirs.add(parent)
|
||||
lines = ["/*"]
|
||||
for d in sorted(dirs):
|
||||
lines.append(f"!{d}/")
|
||||
for f in self._tracked_files:
|
||||
lines.append(f"!{f}")
|
||||
lines.append("!.gitignore")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
# -- query -----------------------------------------------------------------
|
||||
|
||||
def log(self, max_entries: int = 20) -> list[CommitInfo]:
|
||||
"""Return simplified commit log."""
|
||||
if not self.is_initialized():
|
||||
return []
|
||||
|
||||
try:
|
||||
from dulwich.repo import Repo
|
||||
|
||||
entries: list[CommitInfo] = []
|
||||
with Repo(str(self._workspace)) as repo:
|
||||
try:
|
||||
head = repo.refs[b"HEAD"]
|
||||
except KeyError:
|
||||
return []
|
||||
|
||||
sha = head
|
||||
while sha and len(entries) < max_entries:
|
||||
commit = repo[sha]
|
||||
if commit.type_name != b"commit":
|
||||
break
|
||||
ts = time.strftime(
|
||||
"%Y-%m-%d %H:%M",
|
||||
time.localtime(commit.commit_time),
|
||||
)
|
||||
msg = commit.message.decode("utf-8", errors="replace").strip()
|
||||
entries.append(CommitInfo(
|
||||
sha=sha.hex()[:8],
|
||||
message=msg,
|
||||
timestamp=ts,
|
||||
))
|
||||
sha = commit.parents[0] if commit.parents else None
|
||||
|
||||
return entries
|
||||
except Exception:
|
||||
logger.warning("Git log failed")
|
||||
return []
|
||||
|
||||
def diff_commits(self, sha1: str, sha2: str) -> str:
|
||||
"""Show diff between two commits."""
|
||||
if not self.is_initialized():
|
||||
return ""
|
||||
|
||||
try:
|
||||
from dulwich import porcelain
|
||||
|
||||
full1 = self._resolve_sha(sha1)
|
||||
full2 = self._resolve_sha(sha2)
|
||||
if not full1 or not full2:
|
||||
return ""
|
||||
|
||||
out = io.BytesIO()
|
||||
porcelain.diff(
|
||||
str(self._workspace),
|
||||
commit=full1,
|
||||
commit2=full2,
|
||||
outstream=out,
|
||||
)
|
||||
return out.getvalue().decode("utf-8", errors="replace")
|
||||
except Exception:
|
||||
logger.warning("Git diff_commits failed")
|
||||
return ""
|
||||
|
||||
def find_commit(self, short_sha: str, max_entries: int = 20) -> CommitInfo | None:
|
||||
"""Find a commit by short SHA prefix match."""
|
||||
for c in self.log(max_entries=max_entries):
|
||||
if c.sha.startswith(short_sha):
|
||||
return c
|
||||
return None
|
||||
|
||||
def show_commit_diff(self, short_sha: str, max_entries: int = 20) -> tuple[CommitInfo, str] | None:
|
||||
"""Find a commit and return it with its diff vs the parent."""
|
||||
commits = self.log(max_entries=max_entries)
|
||||
for i, c in enumerate(commits):
|
||||
if c.sha.startswith(short_sha):
|
||||
if i + 1 < len(commits):
|
||||
diff = self.diff_commits(commits[i + 1].sha, c.sha)
|
||||
else:
|
||||
diff = ""
|
||||
return c, diff
|
||||
return None
|
||||
|
||||
# -- restore ---------------------------------------------------------------
|
||||
|
||||
def revert(self, commit: str) -> str | None:
|
||||
"""Revert (undo) the changes introduced by the given commit.
|
||||
|
||||
Restores all tracked memory files to the state at the commit's parent,
|
||||
then creates a new commit recording the revert.
|
||||
|
||||
Returns the new commit SHA, or None on failure.
|
||||
"""
|
||||
if not self.is_initialized():
|
||||
return None
|
||||
|
||||
try:
|
||||
from dulwich.repo import Repo
|
||||
|
||||
full_sha = self._resolve_sha(commit)
|
||||
if not full_sha:
|
||||
logger.warning("Git revert: SHA not found: {}", commit)
|
||||
return None
|
||||
|
||||
with Repo(str(self._workspace)) as repo:
|
||||
commit_obj = repo[full_sha]
|
||||
if commit_obj.type_name != b"commit":
|
||||
return None
|
||||
|
||||
if not commit_obj.parents:
|
||||
logger.warning("Git revert: cannot revert root commit {}", commit)
|
||||
return None
|
||||
|
||||
# Use the parent's tree — this undoes the commit's changes
|
||||
parent_obj = repo[commit_obj.parents[0]]
|
||||
tree = repo[parent_obj.tree]
|
||||
|
||||
restored: list[str] = []
|
||||
for filepath in self._tracked_files:
|
||||
content = self._read_blob_from_tree(repo, tree, filepath)
|
||||
if content is not None:
|
||||
dest = self._workspace / filepath
|
||||
dest.write_text(content, encoding="utf-8")
|
||||
restored.append(filepath)
|
||||
|
||||
if not restored:
|
||||
return None
|
||||
|
||||
# Commit the restored state
|
||||
msg = f"revert: undo {commit}"
|
||||
return self.auto_commit(msg)
|
||||
except Exception:
|
||||
logger.warning("Git revert failed for {}", commit)
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _read_blob_from_tree(repo, tree, filepath: str) -> str | None:
|
||||
"""Read a blob's content from a tree object by walking path parts."""
|
||||
parts = Path(filepath).parts
|
||||
current = tree
|
||||
for part in parts:
|
||||
try:
|
||||
entry = current[part.encode()]
|
||||
except KeyError:
|
||||
return None
|
||||
obj = repo[entry[1]]
|
||||
if obj.type_name == b"blob":
|
||||
return obj.data.decode("utf-8", errors="replace")
|
||||
if obj.type_name == b"tree":
|
||||
current = obj
|
||||
else:
|
||||
return None
|
||||
return None
|
||||
@ -15,6 +15,7 @@ from nanobot.utils.helpers import ensure_dir, estimate_message_tokens, estimate_
|
||||
|
||||
from nanobot.agent.runner import AgentRunSpec, AgentRunner
|
||||
from nanobot.agent.tools.registry import ToolRegistry
|
||||
from nanobot.agent.git_store import GitStore
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from nanobot.providers.base import LLMProvider
|
||||
@ -38,9 +39,15 @@ class MemoryStore:
|
||||
self.history_file = self.memory_dir / "history.jsonl"
|
||||
self.soul_file = workspace / "SOUL.md"
|
||||
self.user_file = workspace / "USER.md"
|
||||
self._dream_log_file = self.memory_dir / ".dream-log.md"
|
||||
self._cursor_file = self.memory_dir / ".cursor"
|
||||
self._dream_cursor_file = self.memory_dir / ".dream_cursor"
|
||||
self._git = GitStore(workspace, tracked_files=[
|
||||
"SOUL.md", "USER.md", "memory/MEMORY.md",
|
||||
])
|
||||
|
||||
@property
|
||||
def git(self) -> GitStore:
|
||||
return self._git
|
||||
|
||||
# -- generic helpers -----------------------------------------------------
|
||||
|
||||
@ -175,15 +182,6 @@ class MemoryStore:
|
||||
def set_last_dream_cursor(self, cursor: int) -> None:
|
||||
self._dream_cursor_file.write_text(str(cursor), encoding="utf-8")
|
||||
|
||||
# -- dream log -----------------------------------------------------------
|
||||
|
||||
def read_dream_log(self) -> str:
|
||||
return self.read_file(self._dream_log_file)
|
||||
|
||||
def append_dream_log(self, entry: str) -> None:
|
||||
with open(self._dream_log_file, "a", encoding="utf-8") as f:
|
||||
f.write(f"{entry.rstrip()}\n\n")
|
||||
|
||||
# -- message formatting utility ------------------------------------------
|
||||
|
||||
@staticmethod
|
||||
@ -569,14 +567,10 @@ class Dream:
|
||||
reason, new_cursor,
|
||||
)
|
||||
|
||||
# Write dream log
|
||||
ts = datetime.now().strftime("%Y-%m-%d %H:%M")
|
||||
if changelog:
|
||||
log_entry = f"## {ts}\n"
|
||||
for change in changelog:
|
||||
log_entry += f"- {change}\n"
|
||||
self.store.append_dream_log(log_entry)
|
||||
else:
|
||||
self.store.append_dream_log(f"## {ts}\nNo changes.\n")
|
||||
# Git auto-commit (only when there are actual changes)
|
||||
if changelog and self.store.git.is_initialized():
|
||||
sha = self.store.git.auto_commit(f"dream: {ts}, {len(changelog)} change(s)")
|
||||
if sha:
|
||||
logger.info("Dream commit: {}", sha)
|
||||
|
||||
return True
|
||||
|
||||
@ -96,23 +96,86 @@ async def cmd_dream(ctx: CommandContext) -> OutboundMessage:
|
||||
|
||||
|
||||
async def cmd_dream_log(ctx: CommandContext) -> OutboundMessage:
|
||||
"""Show the Dream consolidation log."""
|
||||
loop = ctx.loop
|
||||
store = loop.consolidator.store
|
||||
log = store.read_dream_log()
|
||||
if not log:
|
||||
# Check if Dream has ever processed anything
|
||||
"""Show what the last Dream changed.
|
||||
|
||||
Default: diff of the latest commit (HEAD~1 vs HEAD).
|
||||
With /dream-log <sha>: diff of that specific commit.
|
||||
"""
|
||||
store = ctx.loop.consolidator.store
|
||||
git = store.git
|
||||
|
||||
if not git.is_initialized():
|
||||
if store.get_last_dream_cursor() == 0:
|
||||
content = "Dream has not run yet."
|
||||
msg = "Dream has not run yet."
|
||||
else:
|
||||
content = "No dream log yet."
|
||||
msg = "Git not initialized for memory files."
|
||||
return OutboundMessage(
|
||||
channel=ctx.msg.channel, chat_id=ctx.msg.chat_id,
|
||||
content=msg, metadata={"render_as": "text"},
|
||||
)
|
||||
|
||||
args = ctx.args.strip()
|
||||
|
||||
if args:
|
||||
# Show diff of a specific commit
|
||||
sha = args.split()[0]
|
||||
result = git.show_commit_diff(sha)
|
||||
if not result:
|
||||
content = f"Commit `{sha}` not found."
|
||||
else:
|
||||
commit, diff = result
|
||||
content = commit.format(diff)
|
||||
else:
|
||||
content = f"## Dream Log\n\n{log}"
|
||||
# Default: show the latest commit's diff
|
||||
result = git.show_commit_diff(git.log(max_entries=1)[0].sha) if git.log(max_entries=1) else None
|
||||
if result:
|
||||
commit, diff = result
|
||||
content = commit.format(diff)
|
||||
else:
|
||||
content = "No commits yet."
|
||||
|
||||
return OutboundMessage(
|
||||
channel=ctx.msg.channel,
|
||||
chat_id=ctx.msg.chat_id,
|
||||
content=content,
|
||||
metadata={"render_as": "text"},
|
||||
channel=ctx.msg.channel, chat_id=ctx.msg.chat_id,
|
||||
content=content, metadata={"render_as": "text"},
|
||||
)
|
||||
|
||||
|
||||
async def cmd_dream_restore(ctx: CommandContext) -> OutboundMessage:
|
||||
"""Restore memory files from a previous dream commit.
|
||||
|
||||
Usage:
|
||||
/dream-restore — list recent commits
|
||||
/dream-restore <sha> — revert a specific commit
|
||||
"""
|
||||
store = ctx.loop.consolidator.store
|
||||
git = store.git
|
||||
if not git.is_initialized():
|
||||
return OutboundMessage(
|
||||
channel=ctx.msg.channel, chat_id=ctx.msg.chat_id,
|
||||
content="Git not initialized for memory files.",
|
||||
)
|
||||
|
||||
args = ctx.args.strip()
|
||||
if not args:
|
||||
# Show recent commits for the user to pick
|
||||
commits = git.log(max_entries=10)
|
||||
if not commits:
|
||||
content = "No commits found."
|
||||
else:
|
||||
lines = ["## Recent Dream Commits\n", "Use `/dream-restore <sha>` to revert a commit.\n"]
|
||||
for c in commits:
|
||||
lines.append(f"- `{c.sha}` {c.message.splitlines()[0]} ({c.timestamp})")
|
||||
content = "\n".join(lines)
|
||||
else:
|
||||
sha = args.split()[0]
|
||||
new_sha = git.revert(sha)
|
||||
if new_sha:
|
||||
content = f"Reverted commit `{sha}` → new commit `{new_sha}`."
|
||||
else:
|
||||
content = f"Failed to revert commit `{sha}`. Check if the SHA is correct."
|
||||
return OutboundMessage(
|
||||
channel=ctx.msg.channel, chat_id=ctx.msg.chat_id,
|
||||
content=content, metadata={"render_as": "text"},
|
||||
)
|
||||
|
||||
|
||||
@ -135,7 +198,8 @@ def build_help_text() -> str:
|
||||
"/restart — Restart the bot",
|
||||
"/status — Show bot status",
|
||||
"/dream — Manually trigger Dream consolidation",
|
||||
"/dream-log — Show Dream consolidation log",
|
||||
"/dream-log — Show what the last Dream changed",
|
||||
"/dream-restore — Revert memory to a previous state",
|
||||
"/help — Show available commands",
|
||||
]
|
||||
return "\n".join(lines)
|
||||
@ -150,4 +214,7 @@ def register_builtin_commands(router: CommandRouter) -> None:
|
||||
router.exact("/status", cmd_status)
|
||||
router.exact("/dream", cmd_dream)
|
||||
router.exact("/dream-log", cmd_dream_log)
|
||||
router.prefix("/dream-log ", cmd_dream_log)
|
||||
router.exact("/dream-restore", cmd_dream_restore)
|
||||
router.prefix("/dream-restore ", cmd_dream_restore)
|
||||
router.exact("/help", cmd_help)
|
||||
|
||||
@ -12,7 +12,6 @@ always: true
|
||||
- `USER.md` — User profile and preferences. **Managed by Dream.** Do NOT edit.
|
||||
- `memory/MEMORY.md` — Long-term facts (project context, important events). **Managed by Dream.** Do NOT edit.
|
||||
- `memory/history.jsonl` — append-only JSONL, not loaded into context. search with `jq`-style tools.
|
||||
- `memory/.dream-log.md` — Changelog of what Dream changed. View with `/dream-log`.
|
||||
|
||||
## Search Past Events
|
||||
|
||||
|
||||
@ -454,4 +454,15 @@ def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]
|
||||
from rich.console import Console
|
||||
for name in added:
|
||||
Console().print(f" [dim]Created {name}[/dim]")
|
||||
|
||||
# Initialize git for memory version control
|
||||
try:
|
||||
from nanobot.agent.git_store import GitStore
|
||||
gs = GitStore(workspace, tracked_files=[
|
||||
"SOUL.md", "USER.md", "memory/MEMORY.md",
|
||||
])
|
||||
gs.init()
|
||||
except Exception:
|
||||
logger.warning("Failed to initialize git store for {}", workspace)
|
||||
|
||||
return added
|
||||
|
||||
@ -48,6 +48,7 @@ dependencies = [
|
||||
"chardet>=3.0.2,<6.0.0",
|
||||
"openai>=2.8.0",
|
||||
"tiktoken>=0.12.0,<1.0.0",
|
||||
"dulwich>=0.22.0,<1.0.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
|
||||
234
tests/agent/test_git_store.py
Normal file
234
tests/agent/test_git_store.py
Normal file
@ -0,0 +1,234 @@
|
||||
"""Tests for GitStore — git-backed version control for memory files."""
|
||||
|
||||
import pytest
|
||||
from pathlib import Path
|
||||
|
||||
from nanobot.agent.git_store import GitStore, CommitInfo
|
||||
|
||||
|
||||
TRACKED = ["SOUL.md", "USER.md", "memory/MEMORY.md"]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def git(tmp_path):
|
||||
"""Uninitialized GitStore."""
|
||||
return GitStore(tmp_path, tracked_files=TRACKED)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def git_ready(git):
|
||||
"""Initialized GitStore with one initial commit."""
|
||||
git.init()
|
||||
return git
|
||||
|
||||
|
||||
class TestInit:
|
||||
def test_not_initialized_by_default(self, git, tmp_path):
|
||||
assert not git.is_initialized()
|
||||
assert not (tmp_path / ".git").is_dir()
|
||||
|
||||
def test_init_creates_git_dir(self, git, tmp_path):
|
||||
assert git.init()
|
||||
assert (tmp_path / ".git").is_dir()
|
||||
|
||||
def test_init_idempotent(self, git_ready):
|
||||
assert not git_ready.init()
|
||||
|
||||
def test_init_creates_gitignore(self, git_ready):
|
||||
gi = git_ready._workspace / ".gitignore"
|
||||
assert gi.exists()
|
||||
content = gi.read_text(encoding="utf-8")
|
||||
for f in TRACKED:
|
||||
assert f"!{f}" in content
|
||||
|
||||
def test_init_touches_tracked_files(self, git_ready):
|
||||
for f in TRACKED:
|
||||
assert (git_ready._workspace / f).exists()
|
||||
|
||||
def test_init_makes_initial_commit(self, git_ready):
|
||||
commits = git_ready.log()
|
||||
assert len(commits) == 1
|
||||
assert "init" in commits[0].message
|
||||
|
||||
|
||||
class TestBuildGitignore:
|
||||
def test_subdirectory_dirs(self, git):
|
||||
content = git._build_gitignore()
|
||||
assert "!memory/\n" in content
|
||||
for f in TRACKED:
|
||||
assert f"!{f}\n" in content
|
||||
assert content.startswith("/*\n")
|
||||
|
||||
def test_root_level_files_no_dir_entries(self, tmp_path):
|
||||
gs = GitStore(tmp_path, tracked_files=["a.md", "b.md"])
|
||||
content = gs._build_gitignore()
|
||||
assert "!a.md\n" in content
|
||||
assert "!b.md\n" in content
|
||||
dir_lines = [l for l in content.split("\n") if l.startswith("!") and l.endswith("/")]
|
||||
assert dir_lines == []
|
||||
|
||||
|
||||
class TestAutoCommit:
|
||||
def test_returns_none_when_not_initialized(self, git):
|
||||
assert git.auto_commit("test") is None
|
||||
|
||||
def test_commits_file_change(self, git_ready):
|
||||
(git_ready._workspace / "SOUL.md").write_text("updated", encoding="utf-8")
|
||||
sha = git_ready.auto_commit("update soul")
|
||||
assert sha is not None
|
||||
assert len(sha) == 8
|
||||
|
||||
def test_returns_none_when_no_changes(self, git_ready):
|
||||
assert git_ready.auto_commit("no change") is None
|
||||
|
||||
def test_commit_appears_in_log(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
(ws / "SOUL.md").write_text("v2", encoding="utf-8")
|
||||
sha = git_ready.auto_commit("update soul")
|
||||
commits = git_ready.log()
|
||||
assert len(commits) == 2
|
||||
assert commits[0].sha == sha
|
||||
|
||||
def test_does_not_create_empty_commits(self, git_ready):
|
||||
git_ready.auto_commit("nothing 1")
|
||||
git_ready.auto_commit("nothing 2")
|
||||
assert len(git_ready.log()) == 1 # only init commit
|
||||
|
||||
|
||||
class TestLog:
|
||||
def test_empty_when_not_initialized(self, git):
|
||||
assert git.log() == []
|
||||
|
||||
def test_newest_first(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
for i in range(3):
|
||||
(ws / "SOUL.md").write_text(f"v{i}", encoding="utf-8")
|
||||
git_ready.auto_commit(f"commit {i}")
|
||||
|
||||
commits = git_ready.log()
|
||||
assert len(commits) == 4 # init + 3
|
||||
assert "commit 2" in commits[0].message
|
||||
assert "init" in commits[-1].message
|
||||
|
||||
def test_max_entries(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
for i in range(10):
|
||||
(ws / "SOUL.md").write_text(f"v{i}", encoding="utf-8")
|
||||
git_ready.auto_commit(f"c{i}")
|
||||
assert len(git_ready.log(max_entries=3)) == 3
|
||||
|
||||
def test_commit_info_fields(self, git_ready):
|
||||
c = git_ready.log()[0]
|
||||
assert isinstance(c, CommitInfo)
|
||||
assert len(c.sha) == 8
|
||||
assert c.timestamp
|
||||
assert c.message
|
||||
|
||||
|
||||
class TestDiffCommits:
|
||||
def test_empty_when_not_initialized(self, git):
|
||||
assert git.diff_commits("a", "b") == ""
|
||||
|
||||
def test_diff_between_two_commits(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
(ws / "SOUL.md").write_text("original", encoding="utf-8")
|
||||
git_ready.auto_commit("v1")
|
||||
(ws / "SOUL.md").write_text("modified", encoding="utf-8")
|
||||
git_ready.auto_commit("v2")
|
||||
|
||||
commits = git_ready.log()
|
||||
diff = git_ready.diff_commits(commits[1].sha, commits[0].sha)
|
||||
assert "modified" in diff
|
||||
|
||||
def test_invalid_sha_returns_empty(self, git_ready):
|
||||
assert git_ready.diff_commits("deadbeef", "cafebabe") == ""
|
||||
|
||||
|
||||
class TestFindCommit:
|
||||
def test_finds_by_prefix(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
(ws / "SOUL.md").write_text("v2", encoding="utf-8")
|
||||
sha = git_ready.auto_commit("v2")
|
||||
found = git_ready.find_commit(sha[:4])
|
||||
assert found is not None
|
||||
assert found.sha == sha
|
||||
|
||||
def test_returns_none_for_unknown(self, git_ready):
|
||||
assert git_ready.find_commit("deadbeef") is None
|
||||
|
||||
|
||||
class TestShowCommitDiff:
|
||||
def test_returns_commit_with_diff(self, git_ready):
|
||||
ws = git_ready._workspace
|
||||
(ws / "SOUL.md").write_text("content", encoding="utf-8")
|
||||
sha = git_ready.auto_commit("add content")
|
||||
result = git_ready.show_commit_diff(sha)
|
||||
assert result is not None
|
||||
commit, diff = result
|
||||
assert commit.sha == sha
|
||||
assert "content" in diff
|
||||
|
||||
def test_first_commit_has_empty_diff(self, git_ready):
|
||||
init_sha = git_ready.log()[-1].sha
|
||||
result = git_ready.show_commit_diff(init_sha)
|
||||
assert result is not None
|
||||
_, diff = result
|
||||
assert diff == ""
|
||||
|
||||
def test_returns_none_for_unknown(self, git_ready):
|
||||
assert git_ready.show_commit_diff("deadbeef") is None
|
||||
|
||||
|
||||
class TestCommitInfoFormat:
|
||||
def test_format_with_diff(self):
|
||||
from nanobot.agent.git_store import CommitInfo
|
||||
c = CommitInfo(sha="abcd1234", message="test commit\nsecond line", timestamp="2026-04-02 12:00")
|
||||
result = c.format(diff="some diff")
|
||||
assert "test commit" in result
|
||||
assert "`abcd1234`" in result
|
||||
assert "some diff" in result
|
||||
|
||||
def test_format_without_diff(self):
|
||||
from nanobot.agent.git_store import CommitInfo
|
||||
c = CommitInfo(sha="abcd1234", message="test", timestamp="2026-04-02 12:00")
|
||||
result = c.format()
|
||||
assert "(no file changes)" in result
|
||||
|
||||
|
||||
class TestRevert:
|
||||
def test_returns_none_when_not_initialized(self, git):
|
||||
assert git.revert("abc") is None
|
||||
|
||||
def test_undoes_commit_changes(self, git_ready):
|
||||
"""revert(sha) should undo the given commit by restoring to its parent."""
|
||||
ws = git_ready._workspace
|
||||
(ws / "SOUL.md").write_text("v2 content", encoding="utf-8")
|
||||
git_ready.auto_commit("v2")
|
||||
|
||||
commits = git_ready.log()
|
||||
# commits[0] = v2 (HEAD), commits[1] = init
|
||||
# Revert v2 → restore to init's state (empty SOUL.md)
|
||||
new_sha = git_ready.revert(commits[0].sha)
|
||||
assert new_sha is not None
|
||||
assert (ws / "SOUL.md").read_text(encoding="utf-8") == ""
|
||||
|
||||
def test_root_commit_returns_none(self, git_ready):
|
||||
"""Cannot revert the root commit (no parent to restore to)."""
|
||||
commits = git_ready.log()
|
||||
assert len(commits) == 1
|
||||
assert git_ready.revert(commits[0].sha) is None
|
||||
|
||||
def test_invalid_sha_returns_none(self, git_ready):
|
||||
assert git_ready.revert("deadbeef") is None
|
||||
|
||||
|
||||
class TestMemoryStoreGitProperty:
|
||||
def test_git_property_exposes_gitstore(self, tmp_path):
|
||||
from nanobot.agent.memory import MemoryStore
|
||||
store = MemoryStore(tmp_path)
|
||||
assert isinstance(store.git, GitStore)
|
||||
|
||||
def test_git_property_is_same_object(self, tmp_path):
|
||||
from nanobot.agent.memory import MemoryStore
|
||||
store = MemoryStore(tmp_path)
|
||||
assert store.git is store._git
|
||||
@ -105,23 +105,6 @@ class TestDreamCursor:
|
||||
assert store2.get_last_dream_cursor() == 3
|
||||
|
||||
|
||||
class TestDreamLog:
|
||||
def test_read_dream_log_returns_empty_when_missing(self, store):
|
||||
assert store.read_dream_log() == ""
|
||||
|
||||
def test_append_dream_log(self, store):
|
||||
store.append_dream_log("## 2026-03-30\nProcessed entries #1-#5")
|
||||
log = store.read_dream_log()
|
||||
assert "Processed entries #1-#5" in log
|
||||
|
||||
def test_append_dream_log_is_additive(self, store):
|
||||
store.append_dream_log("first run")
|
||||
store.append_dream_log("second run")
|
||||
log = store.read_dream_log()
|
||||
assert "first run" in log
|
||||
assert "second run" in log
|
||||
|
||||
|
||||
class TestLegacyHistoryMigration:
|
||||
def test_read_unprocessed_history_handles_entries_without_cursor(self, store):
|
||||
"""JSONL entries with cursor=1 are correctly parsed and returned."""
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user